Search

• An edge detection algorithm for thermal infrared weak texture images. • Construct a high-quality thermal infrared image edge dataset RI-BSDS500 for training to improve the training convergence speed and generalization ability of the model. • Different thermal infrared image datasets are tested under different algorithms, and the results are analyzed from the perspectives of objective parameters and subjective effects, which proves that the proposed algorithm in this paper is more effective on thermal infrared images. In order to solve the problems such as difficulties in extracting image edge information caused by low contrast and blurred edges of thermal infrared images, a thermal infrared image edge detection algorithm PiDiNet-TIR constructed based on the PiDiNet model is proposed. On the basis of the visible light image dataset BSDS500, the visible light image is grayed out, noise is added, and contrast is reduced to construct the thermal infrared image edge dataset I R-BSDS500, which provides image data for model training and testing. Deeply study the theory of PiDiNet model, add rich convolution mechanism to its backbone network, improve the activation function, pooling layer and up-sampling module, study the SimAM attention mechanism and add it to the side network. Using the open-source thermal infrared image dataset and homemade thermal infrared images for testing, we compare and analyze the mean square error (MSE), structural similarity of image (SSIM), feature similarity of image (FSIM), and Frames Per Second (FPS)of different detection algorithms, such as HED, RCF, DexiNet, PiDiNet, and the algorithm proposed in this paper. The results of image evaluation parameters prove that the edge detection algorithm proposed in this paper has high feature extraction efficiency and feature expression ability, and the algorithm detection performance is higher than other algorithms. [ABSTRACT FROM AUTHOR]

• We proposed a delineating field parcel model (TSANet) based on satellite image time series. • TSANet learn the relevance of spatial-spectral-temporal feature representation. • TSANet is robust across space and time. • TSANet performs better than pervious methods. • The time series data from the main growing period has a greater impact. Satellite image time series (SITS), such as Sentinel-2 imagery, plays a crucial role in the delineation of agricultural fields by reducing the impacts of ambiguities due to the spatial arrangement of field boundaries. Existing delineate field parcel models rely extensively on spatial features derived from single-date imagery. However, several studies have exploited the potential of SITS to effectively tackle the complexities associated with the intrinsic consistency between agricultural fields and their boundaries. This paper proposes a novel Two-Stream Attention convolutional neural network (TSANet) to capture the subtle difference between agricultural fields from SITS. Specifically, a field temporal semantic stream is introduced to adaptively leverage the significance of spatial-spectral-temporal feature representation associated with the location of agricultural parcels, especially where transitions in crop types take place. Considering the consistency between field parcels and their boundaries, we developed a field boundary prediction stream to enhance the extraction of edge features, particularly for the extraction of small and irregular agricultural parcels. Moreover, a field parcel refining block is employed to further enhance the geometric accuracy of agricultural fields. We conducted experiments on Sentinel-2 images from the Netherlands. Results showed that our approach produced a better layout of agricultural fields, with an average F1-score of 0.91 than the existing 3D-UNet, U-TEA, and BiConvLSTM. In addition, through the analysis of both quantitative and qualitative results, the stronger robustness of the model compared to other algorithms has been verified by temporal transfer and large-scale spatial prediction. We compared the difference between SITS and the corresponding composite images, which further verified the influence of temporal variation on the proposed approach. This paper provides a general guide for delineating agricultural parcels using SITS. [ABSTRACT FROM AUTHOR]

Food safety is an important public health issue, and deep learning (DL) algorithms can provide powerful tools and methods for food safety and authenticity detection. Compared with chemometric algorithms and traditional machine learning algorithms, the performances of DL algorithms are improved in many aspects. By learning and analyzing a large amount of data, DL models can improve the efficiency and accuracy of food safety and authenticity detection, helping to ensure the public health and safety. This paper reviews some commonly used chemometric algorithms, traditional machine learning algorithms, and popular DL algorithms. Among them, special attentions are paid to convolutional neural network (CNN), fully convolutional network (FCN) and generative adversarial network (GAN). Moreover, the auxiliary effect of GAN on CNN is highlighted. Finally, this paper revisits recent applications of DL algorithms in the field of food safety and authenticity detection, and prospects the challenges and future directions of DL algorithms in this field. Although DL has made many achievements in the field of food safety and authenticity detection, there is still a great potential for development. For example, the data augmentation function of GAN can assist CNN to obtain more training samples, thus improving the recognition rate. In addition, multimodal neural network (MNN) or multimodal attention network (MAN) can be also used to achieve the fusion of data from different modalities to further improve the robustness and accuracy of DL algorithms. [Display omitted] • Some popular DL algorithms in food safety and authenticity detection are introduced. • The improvements of DL algorithms to chemometric and ML algorithms are summarized. • Recent applications of DL algorithms in food safety and authenticity detection are reviewed. • Future prospects of DL algorithms in food safety and authenticity detection are discussed. [ABSTRACT FROM AUTHOR]

Because the carbon load inside a diesel particulate filters (DPF) affects the DPF regeneration, and the carbon load recognition is significant for the particulate matter (PM) emission control. It is necessary to investigate an on-board DPF carbon load recognition method because the carbon load cannot be directly measured by sensors. Aiming to build a DPF carbon load prediction model adopting the deep learning method, this paper proposes a DPF carbon load identification model based on different experimental parameters using a layered one dimension convolutional neural network (1D-CNN) method. To improve data validity, this paper adopts two data-processing methods. The data pre-processing adopts data splicing method to complete the construction of the original sample set, and the data after-processing uses wavelet packet transform method to establish the feature sample sets. The model adopts the optimal feature dataset constructed by three input parameters, i.e., temperature difference, pressure difference, and exhaust mass flow, and has both high training accuracy and test accuracy above 90 %. The pressure difference is the most important influencing input parameter, and the three-parameter sample set (Δ T + Δ P + Q) has great recognition accuracy and good model stability with the high training accuracy and test accuracy as well as less iteration. • A heavy-duty diesel engine was tested under various conditions of carbon load inside DPF. • The data processing was done by two methods: data splicing and wavelet packet transform. • We proposed a DPF carbon load identification model based on a one-dimension CNN method. • The model adopts 3 parameters, and the 3-parameter sample set has optimal performance. • The 1D-CNN model has both high training accuracy and test accuracy above 90 %. [ABSTRACT FROM AUTHOR]

Groundwater level (GWL) prediction is important for ecological protection and resource utilization; it helps in formulating policies for artificial groundwater recharge, modifying the number of extraction wells, etc., and can support sustainable human development as well as inform water resource management decisions. However, climate change, anthropogenic impacts, and the complex coupling between surface water and groundwater increase the difficulty of predicting groundwater levels. The model proposed in this paper combines external data as well as multiple models. The method leverages long and short-term memory (LSTM) and convolutional neural network (CNN) models, combined with secondary modal decomposition and slime mould algorithm (SMA), together with an adaptive weight module (AWM). The study applies this method to predict GWL for three different hydrological conditions in China, specifically for the Jinan Baotu Spring, Heihu Spring, and Zhongtianshe watershed of Taihu Lake. A comparison of metrics such as mean absolute error and Nash efficiency coefficient for single and hybrid models shows that the model in this paper is more advantageous than the single model and other hybrid models. The interpretability of the model is enhanced by SHAP values that demonstrate the degree of contribution of the input variables. This paper uses SHAP analyses to identify the key drivers affecting groundwater levels. These factors must be detected in order to develop groundwater resource protection measures. [Display omitted] • Multivariate fusion data including hydrology and meteorology are used as model input. • A secondary modal decomposition module for historical groundwater level data was utilized. • The neural network hyperparameters are optimized using the slime mould algorithm. • Aggregate subsets of prediction with adaptive modules rather than linear summation. • The interpretable SHAP model measures the degree of influence of external variables. [ABSTRACT FROM AUTHOR]

Edge detection is of critical importance for middle-level and high-level tasks in computer vision. Existing edge detection methods usually use VGG16 as the encoding network and achieve exceptional performance through transfer learning, which has the characteristics of high parameters and high computational cost. Researchers have implemented edge detection by designing decoding networks. Unlike existing methods, this paper is inspired by the effective mechanisms of edge detection in the parallel pathway of biological vision and proposes a new lightweight encoding–decoding structure for edge detection networks, which we refer to as XYW-Net. In the encoding network, we drew inspiration from the receptive field properties of X-type cells, Y-type cells, and W-type cells involved in the parallel pathway, and developed more meticulous convolutional models. Based on the structure of the parallel pathway, the three cell modules are combined into a novel encoding network and excellent feature extraction performance is obtained. Within the decoding network, this paper draws inspiration from the feature integration ability of the inferotemporal cortex (IT) and introduces a novel feature integration module to constitute the decoding network. Experiments show that the proposed network in this paper obtains the Optimal Dataset Scale (ODS) = 0.812 on the BSDS500 dataset with only 0.79 M parameters. Additionally, the model has exhibited outstanding ODS performance on various publicly available edge detection datasets, including NYUD, BIPEDv1, and Multicue. Moreover, future research could concentrate on implementing more efficient antagonistic mechanisms and devising networks grounded in higher-level visual cortical mechanisms. This could further augment the performance and efficiency of edge detection networks. We encourage researchers to delve into these directions within the field. The codes are available at https://github.com/PXinTao/XYW-Net. [ABSTRACT FROM AUTHOR]

The core of data series classification and clustering is how to evaluate the similarity between time series. However, for one-dimensional time series, the vast majority of similarity measurement methods currently relied on one-dimensional information. Although some classifications of time series were achieved by the images transformed from time series, they mostly relied on a single imaging mechanism (time domain or frequency domain). In order to give a new idea for time series similarity measurement, this paper proposed a similarity measurement method of time series based on the fused images. According to recurrence plots (RP) and wavelet scalogram (WS), the original time series was first transformed into images. Then, RP and WS were fused into an image. Next, the feature in the image was extracted by ResNet-18. Finally, the similarity of the time series can be obtained by the Euclidean distance between the features extracted by ResNet-18. The proposed method was verified by the time series from UCR Time Series Classification/Clustering Homepage. The results showed that the similarity measurement of time series can be effectively improved by fusing the images obtained by different imaging mechanisms in the time domain and frequency domain. • This paper proposes a new similarity measurement method for time series based on the image fusion of different forms. • The time domain and frequency domain information of time series are represented by recurrence plots and wavelet scalogram. • The characteristics of the image fused by recurrence plots and wavelet scalogram are extracted by Convolutional Neural Network to measure the similarity of time series. • 30 sets of time series show the validity and superiority of the proposed method. • The reasons for the effectiveness of the proposed method are analyzed in detail. [ABSTRACT FROM AUTHOR]

The fault management process is facilitated by equipping power distribution systems with automated devices, especially remote-controlled switches (RCSs). Although RCS plays a key role in improving the system's reliability, it imposes significant investment, installation, and maintenance costs. Hence, RCSs should be optimally located in distribution feeders for the highest profit. In previous works, reliability-oriented mathematical optimization models have been formulated to reach this goal. However, the number of test solutions exponentially grows with the problem size to find the globally optimal solution. This paper uses machine learning to propose a scalable and easy-to-implement model for optimal switch placement in real power distribution systems. At first, the features of candidate points for installing RCSs are introduced. Then, a learning model is applied to deeply explore the relationship between these features and optimal locations for installing RCSs. After training, the learning-based surrogate model directly determines the optimal RCS placement strategy in real power distribution systems by leveraging knowledge gained from past experiences. Simulation results demonstrate that the proposed surrogate model is approximately 29 times faster than the integer programming-based mathematical model, without a significant loss of accuracy, when implemented on a modified 11 kV network connected to Bus 4 of the Roy Billiton test system. This paper also employs explainable artificial intelligence (XAI) tools to select the most important features, where the Hamming loss is decreased by approximately 5%. [ABSTRACT FROM AUTHOR]

CAPTCHAs represent a vital technique for protecting the security of websites by differentiating between humans and bots. There have been many successful attacks against text and image CAPTCHAs, demonstrating that they are no longer secure, and blindly using methods to enhance CAPTCHAs robustness may reduce user-friendliness. Slider CAPTCHAs, which are based on behavioral verification, are being used on more and more websites as an alternative to text CAPTCHAs and image CAPTCHAs. However, despite the widespread use of slider CAPTCHAs, their security remains largely unknown. In this paper, we introduce a simple, efficient and generic approach for attacking five widely deployed slider CAPTCHAs, with success rates ranging from 87.5% to 100%. Experimental results proving that behavior-verification-based slider CAPTCHAs do not fully differentiate between humans and bots, especially with regard to mouse operation behavior. Simultaneously, this paper also discusses whether deep learning technology can further improve the security of slider CAPTCHAs by analyzing user behavior trajectories, hoping that our work can provide new inspiration for designers to design more effective CAPTCHAs. [Display omitted] • The first comprehensive cracking and security analysis of behavior-verification-based slider CAPTCHAs. • The method was verified on five mainstream websites, and the highest cracking success rate was 100%. • Through in-depth analysis, human operation and machine simulation were successfully identified with an accuracy rate of 98.06%. [ABSTRACT FROM AUTHOR]

• In this paper, we proposed a CNN-OAM mode classifier to detect OAM modes of distorted high-order (radial index p > 0) and zero-order (radial index p = 0) vortex beams. • The effect of propagation distance, atmospheric turbulence intensity and radial index on the detection accuracy of the CNN-OAM mode classifier was analyzed. • For 5AT (atmospheric turbulence)-mixed dataset, the CNN-OAM mode classifier has an average detection accuracy of 97.3%. • The CNN-OAM mode classifier used in this paper can offer a novel approach to the detection of high-order vortex beams. Vortex beams provide an innovative multiplexing mechanism for the field of optical communication due to its specific orthogonality. The precise and efficient detection of orbital angular momentum (OAM) modes carried by vortex beams is an essential technology for OAM multiplexing communication systems. An OAM mode classifier based on convolutional neural network (CNN) is proposed for the mode detection of distorted high-order vortex beams (radial index p > 0). The effect of different atmospheric turbulence (AT) intensities, radial indexes, and propagation distances on the detection accuracy of the OAM modes are investigated. The ability of the classifier models for generalization after training on both specific and mixed AT dataset is analyzed. The results show that the higher-order vortex beams have a greater detection accuracy in AT environments. For the high-order vortex beam carrying OAM modes, the CNN-OAM mode classifier has an average detection accuracy of 97.3% and can detect up to 30 OAM modes under any AT intensities ranging from 1 × 10−16 m−2/3 to 1 × 10−14 m−2/3 at a propagation distance of 1000 m. The great accuracy and extensive detection range of the CNN-OAM mode classifier proposed in this paper can offer a novel approach to the recognition and detection of high-order vortex beams. [ABSTRACT FROM AUTHOR]

With the rapid expansion of the electric vehicle market, the demand for lithium-ion batteries (LIBs) is exploding. The state of health (SOH) of LIBs is receiving more widespread attention, which is the key parameter for battery health management. This paper proposes a SOH estimation method for LIBs via feature optimization and convolutional neural network (CNN) to reduce the information redundancy of existing multiple features, aimed at leveraging multiple sources of features while optimizing their combination to minimize redundancy. Firstly, multiple features are extracted from different perspectives, including electrical, thermodynamic, and electrochemical properties, to comprehensively characterize the aging of batteries. Secondly, we construct a SOH estimator based on principal component analysis (PCA) with CNN (PCA-CNN). Finally, the dimension of features is optimized with a simulated annealing algorithm (SA) under the mean-variance objective function. Moreover, Comparative experiments are conducted on the Oxford dataset for validation. The results demonstrate the effectiveness of the proposed multi-feature description method in terms of accuracy and smoothness. Compared to traditional CNN methods and fixed-dimension PCA-CNN, this estimation approach significantly improves performance, showing more than 20% and 30% increases in the key metrics of MAE and RMSE, respectively. This study successfully optimized feature combinations to reduce redundancy within the feature set while enhancing the accuracy of SOH estimation. [ABSTRACT FROM AUTHOR]

Stable fault self-healing ensures the smooth operation of intelligent industrial manufacturing processes. However, current research, while capable of inferring fault propagation paths or individually controlling manufacturing processes, still faces some challenges and limitations in addressing issues within manufacturing processes. In particular, it is easy to overlook the impact of fault variables on normal causal relationships in the manufacturing process and how to achieve adaptive fault repair from the source of faults. The biological immune system possesses sensitive nodes and a neuro-endocrine-immune network with interconnected functionalities, bearing remarkable resemblance to the sensor arrays, information networks, and intelligent controller systems in modern self-healing control systems. These problem domains have significant practical implications in industrial manufacturing processes and urgently require new methods and technologies to address them. To address the issue of root cause fault self-healing in intelligent industrial manufacturing processes, this paper proposes an innovative method that utilizes root cause inference and bio-inspired heuristic reinforcement learning models to achieve fault self-healing in industrial processes. First, innovatively introduce the Variational Autoencoder (VAE) into the Time Convolutional Network (TCN) to construct the TCN-VAE network. By performing feature reconstruction, the network's feature extraction capability is enhanced, further exploring the relationships between latent variables, and consequently building a causal graph of faults. A multi-head attention mechanism is introduced into the network, and the inference process is quantitatively evaluated, thereby improving the generalization and accuracy of root cause inference. Root cause determination rules are established to identify the fundamental reasons for fault occurrence, ensuring self-healing from the source of faults. Next, we developed for the first time a fault self-healing model based on reinforcement learning, utilizing the immune repair process of effector T cells to characterize the fault self-healing process. It effectively adapts to eliminate various levels of faults based on the state transition process of antigens in T helper cells. Additionally, stability control analysis is performed on the proposed model. The average reward function curve and Sobol sensitivity index demonstrates the model's strong robustness in practical applications. The validation results from case studies on the Tennessee Eastman (TE) and Continuous Stirred Tank Reactor (CSTR) show that the average improvement in fault repair F1 score was 0.0941 and 0.105 respectively, and the fastest improvement in fault repair response time was 0.266s and 0.258s respectively. It was confirmed that the root cause inference and fault repair results align with the actual mechanisms of the manufacturing processes. The proposed method has been verified to achieve stable and accurate root cause fault repair in real-world intelligent industrial manufacturing systems, making a significant contribution to achieving stable and accurate root cause fault repair in intelligent industrial manufacturing systems. • TCN-VAE enables feature reconstruction and latent variable exploration for root cause reasoning. • Multi-head attention enhances generality and accuracy in root cause reasoning. • Effector T-cell immune-inspired RL adapts to eliminate faults effectively. • The fault self-healing model exhibits strong reliability and robustness. • Method validated on Tennessee Eastman and continuous stirred-tank reactor datasets. [ABSTRACT FROM AUTHOR]

Longitudinal impulse, as a common dynamic problem of heavy haul trains, could induce the lateral instability of the coupler and the separation of the locomotive and wagon connection and thus seriously hinder the train running safety. The coupler force undergoes complex changes during longitudinal impulse transmission and exhibits strong nonlinear characteristics, which poses significant challenges to the identification of the coupler force. To address these issues, this paper reports a novel quantitative method for the coupler force identification of heavy haul locomotives. Firstly, the moving average filtering method is used to preprocess the signal of longitudinal relative displacement between the coupler and carbody (LRDCC), and the approximate relative velocity (ARV) feature is also extracted from the preprocessed signal. Then, a Convolutional Neural Network (CNN) model is constructed to extract high-level features from LRDCC and ARV. The model with randomly initialized weight parameters does not require additional training and thus reduces the computational cost. Finally, an Extreme Learning Machine (ELM) is used as the regression layer to process the extracted high-level features and further improve the identification performance. Additionally, the dung beetle algorithm is used to obtain the optimal model parameters to improve the coupler force identification performance. Not only a dynamics simulation but a field test is carried out to show that the proposed method could accurately detect the coupler force of heavy haul locomotives. Furthermore, the proposed method shows promising prospects in replacing the traditional monitoring method under the actual long-term working conditions of trains. • An indirect measurement scheme is proposed for coupler force dynamic identification. • The proposed network model presents high identification Accuracy and efficiency. • Method showcases strong generalization under complex, long-term train operations. [ABSTRACT FROM AUTHOR]

Accurate positioning of curtain wall frames is crucial for the automated installation of curtain wall modules. However, the current robot-based installation methods overly depend on visual guidance from operators, resulting in high costs and limiting construction efficiency. The development of deep learning has introduced an image segmentation approach that offers a new solution for the visual positioning of curtain wall frames. This paper proposes a context collaboration pyramid network to automatically segment curtain wall frames by incorporating context interaction and channel guided pyramid structure. The model adopts an "encoder-decoder" architecture with a feature interaction block strategically inserted between the encoder and decoder. Specifically, the encoder utilizes the pyramid pooling Transformer as a backbone to extract multi-level features from original RGB images. The decoder employs a channel guided pyramid convolution module to integrate multi-scale features and achieve finer prediction. Meanwhile, a context interaction fusion module between the features of adjacent levels was designed carefully to enhance the collaboration of the architecture. In addition, a benchmark dataset for the curtain wall frame segmentation task, consisting of 1547 images, was established. The dataset incorporates challenging scenarios, including strong lights, low contrast, and cluttered backgrounds. This method is evaluated on the collected dataset, and achieves an impressive accuracy of 97.30% and an F1-Score of 88.95%, outperforming other segmentation networks. Overall, the proposed method can extract target information accurately and efficiently and provide critical visual guidance for the robot, so as to promote the automatic installation level of the curtain wall module. [ABSTRACT FROM AUTHOR]

Accurate positioning of curtain wall frames is crucial for the automated installation of curtain wall modules. However, the current robot-based installation methods overly depend on visual guidance from operators, resulting in high costs and limiting construction efficiency. The development of deep learning has introduced an image segmentation approach that offers a new solution for the visual positioning of curtain wall frames. This paper proposes a context collaboration pyramid network to automatically segment curtain wall frames by incorporating context interaction and channel guided pyramid structure. The model adopts an "encoder-decoder" architecture with a feature interaction block strategically inserted between the encoder and decoder. Specifically, the encoder utilizes the pyramid pooling Transformer as a backbone to extract multi-level features from original RGB images. The decoder employs a channel guided pyramid convolution module to integrate multi-scale features and achieve finer prediction. Meanwhile, a context interaction fusion module between the features of adjacent levels was designed carefully to enhance the collaboration of the architecture. In addition, a benchmark dataset for the curtain wall frame segmentation task, consisting of 1547 images, was established. The dataset incorporates challenging scenarios, including strong lights, low contrast, and cluttered backgrounds. This method is evaluated on the collected dataset, and achieves an impressive accuracy of 97.30% and an F1-Score of 88.95%, outperforming other segmentation networks. Overall, the proposed method can extract target information accurately and efficiently and provide critical visual guidance for the robot, so as to promote the automatic installation level of the curtain wall module. [ABSTRACT FROM AUTHOR]

Temporal knowledge graphs (TKGs) are still far from completeness although they have benefited many artificial intelligence applications successfully. To alleviate the incompleteness of TKGs, temporal knowledge graph completion (TKGC) aims to perform link prediction and reason new time-sensitive facts from existing facts. Among the various TKGC methods, temporal knowledge graph embedding (TKGE) methods represent entities, relations, and timestamps in low-dimensional spaces, which are known for their high reasoning performance and robust scalability. Some previous researches on TKGE aim to endow the embedding quadruple with the translational characteristic by modeling the global relationship in the embedding quadruple. However, the weights of same dimensional entries of the embedding quadruple are fixed and unique, which limits the ability to capture diverse global relationships. Besides, most TKGE models view timestamps as a kind of general feature and overlook their interrelations and correlations with the queries. Moreover, the distinct characteristics of an entity as the subject entity and the object entity of facts have not been fully leveraged. In this paper, we propose a query-aware embedding model based on the convolutional neural network (CNN) named ConvTKG to perform TKGE, thus tackling the TKGC task. We design a new temporal information encoder based on the Gated Recurrent Unit (GRU) and attention mechanism to learn the query-aware representation of temporal information. More importantly, we utilize a CNN-based decoder where multiple one-dimensional convolution kernels are operated on the matrix composed of entity embedding, relation embedding, and temporal representation to capture global relationships among them. In addition, we assign two independent vectors for each entity and take advantage of the inverse relation to allow them to be learned dependently. Experiments show that ConvTKG achieves better link prediction performance than previous state-of-the-art baseline methods for TKGC on three benchmark datasets: ICEWS14, ICEWS05-15, and GDELT. • We propose the first weight-adaptive TKGE model with translational characteristic. • We introduce a new query-aware timestamp encoding method for TKGC. • Two dependent embedding vectors for each entity capture its distinct semantics. • Experiments demonstrate the effectiveness of ConvTKG on three TKGC benchmarks. [ABSTRACT FROM AUTHOR]

• Four different types of melt pool signals are integrated and fused to enhance the signal-to-defect correlation. • A data partitioning method is proposed to reduce registration errors and facilitate the defect-related feature extraction. • The feature-level fusion obtains the optimal classification performance compared with the other two fusion strategies. • The proposed data fusion method outperforms the individual signal-based methods for quality classification. In situ monitoring technologies for additive manufacturing are severely affected by signal-to-defect spatial registration, and a single monitoring solution that captures a specific process signature cannot identify defects with sufficient accuracy in industrial applications. In this paper, a data partitioning method was proposed to reduce registration errors and facilitate the extraction of defect-related representative features from data segments. Then, three multi-signal fusion methods based on convolutional neural networks were established from feature-level fusion, decision-level fusion, and data-level fusion, which enhanced the signal-to-defect correlation by means of complementary sensor information. The results showed that the feature-level fusion obtained the optimal classification performance compared with the other two fusion strategies. Among them, the classification accuracies of 100-, 150-, 200-, 300-, 400-, and 500-μm defects reached 74.41%, 89.84%, 90.82%, 93.95%, 97.85%, and 98.83%, respectively. The proposed data fusion approach outperformed the individual signal-based models for quality classification. [ABSTRACT FROM AUTHOR]

Regular patrol inspection of concrete dams can detect cracks at an early stage. However, conventional crack segmentation models based on deep learning (DL) are difficult to be deployed in resource-constrained mobile devices due to the large number of parameters. This paper describes a lightweight semantic segmentation model, termed as CrackTrNet, for images of concrete dam cracks. CrackTrNet is a hybrid U-shaped model based on convolutional neural network (CNN) and Vision Transformer. The CNN is adopted to extract low-level visual features and the Transformer focuses on learning the global contextual information. The results demonstrate that its segmentation accuracy can reach 97.60%, while the model size is only 34.86 MB, which is 66.12%–87.85% lower than that of current mainstream DL-based models. To make the model more practical, a crack inspection mobile application (APP) is developed using Android Studio. The integration of lightweight CrackTrNet and APP can effectively assist the intelligent inspection of dam cracks to ensure structural safety. • A lightweight hybrid network, CrackTrNet, is presented for semantic segmentation of dam cracks. • The integration of CNN and Transformer maximizes the preservation of global and local features. • Transfer learning and depthwise separable convolution are introduced to optimize the model size. • The mobile application is developed to assist patrol inspection of cracks in concrete dams. [ABSTRACT FROM AUTHOR]

This paper presents the first classical Convolutional Neural Network (CNN) that can be applied directly to data from unstructured finite element meshes or control volume grids. CNNs have been hugely influential in the areas of image classification and image compression, both of which typically deal with data on structured grids. Unstructured meshes are frequently used to solve partial differential equations and are particularly suitable for problems that require the mesh to conform to complex geometries or for problems that require variable mesh resolution. Central to our approach are space-filling curves, which traverse the nodes or cells of a mesh tracing out a path that is as short as possible (in terms of numbers of edges) and that visits each node or cell exactly once. The space-filling curves (SFCs) are used to find an ordering of the nodes or cells that can transform multi-dimensional solutions on unstructured meshes into a one-dimensional (1D) representation, to which 1D convolutional layers can then be applied. Although developed in two dimensions, the approach is applicable to higher dimensional problems. To demonstrate the approach, the network we choose is a convolutional autoencoder (CAE), although other types of CNN could be used. The approach is tested by applying CAEs to data sets that have been reordered with a space-filling curve. Sparse layers are used at the input and output of the autoencoder, and the use of multiple SFCs is explored. We compare the accuracy of the SFC-based CAE with that of a classical CAE applied to two idealised problems on structured meshes, and then apply the approach to solutions of flow past a cylinder obtained using the finite-element method and an unstructured mesh. • Use of space-filling curves (SFCs) to apply CNNs to data on unstructured meshes. • Introduction of multiple SFCs in order to improve the accuracy of the new CNNs. • Use of sparse smoothing layers at the input and output of the CNN to reduce noise. • Edge weights are included in a recurrent neural network to generate multiple SFCs. • Application to fluid flow data on an unstructured mesh. [ABSTRACT FROM AUTHOR]

This paper describes applications of two neural networks to improve drift chamber position measurements. One network calculates a data-driven estimate of the drift cell time-to-distance relationship that is conventionally estimated by a numerical calculation based on the anode and cathode wire geometry, wire potentials, and gas properties. The second network additionally uses the full digital waveform of the signal in the drift chamber, hence accessing information on the full ensemble of ionization clusters. This network uses more information than the conventional position estimate that relies exclusively on the arrival time of the first drift electron. In principle, this technique improves resolution even when multiple ionization clusters cannot be separated, in contrast with a cluster-counting technique. The performance of both networks when applied to MEG II drift chamber data is reported and compared to that of a conventional approach. [ABSTRACT FROM AUTHOR]

Date fruit (Phoenix dactylifera L.) is known for its diversity in terms of genotypes that differ in shape, color, texture, taste, and other physical and sensory attributes, in addition to biochemical compounds. This richness generates complex, long, and tedious work at the scale of farm as well as in handling, processing, and storage facilities to prepare standardized, and homogenous final products that deal with consumer preferences and needs. To alleviate this, an increased importance and particular trend were observed recently for the use of artificial intelligence (AI) techniques and computer vision technology since they are considered as accurate, objective, non-destructive, fast, and efficient emerging technologies. In this context, this manuscript provides comprehensive insights into key applications of AI techniques and computer vision technology, using different classification models and algorithms developed on the basis (for example) of neural network classifiers, such as convolutional and artificial neural network, on harvest and postharvest assessment of date fruit. Thus, the importance of date fruit dataset used in the AI domain was discussed with link to all accessible datasets in the field of date palm. In addition, available and relevant AI tools and approaches applied to the postharvest of date fruit from maturity distinguishing until storage through other key handling operations, sorting, grading, etc., were detailed in the five sections of this paper. In terms of conclusion, this review showed that these smart technologies can play a substantial role and offer new opportunities to improve the whole value chain of date palm sector. • Harvesting and post-harvest handling impact quality and storability of dates. • These operations are tedious and subjective leading to quantitative/qualitative losses. • Artificial intelligence (AI) techniques are emergent technologies that can reduce these losses. • AI techniques are more accurate, fast, non-destructive and objective. [ABSTRACT FROM AUTHOR]

This paper introduces AI-PotatoGuard, an artificial intelligence (AI) tool which enhances the management of diseases in potatoes through the use of generative models and convolutional neural networks (CNN). In contrast to traditional practices, AI-PotatoGuard is a tool which provides the ability to detect potatoes in the early stages of the disease and also precisely detects the area affected. Through AI-PotatoGuard, it was observed that the conventional approach of identifying the diseases have been surpassed with 95% success observed in terms of getting the detection perfectly right and 85% in terms of getting the detection right at a much earlier stage. Traditional practices lagged with 75% detection right observation and a mere 50% in terms of detecting the disease early on. While traditional methods applied chemicals 2–3 times in practice in an area, the monitoring with AI-PotatoGuard resulted in only 2 out of 6 times in the same area. Hence, efficient and sustainable agriculture is achieved using AI. [ABSTRACT FROM AUTHOR]

Fruit ripeness estimation models have for decades depended on spectral index features or colour-based features, such as mean, standard deviation, skewness, colour moments, and/or histograms for learning traits of fruit ripeness. Recently, few studies have explored the use of deep learning techniques to extract features from images of fruits with visible ripeness cues. However, the blackberry (Rubus fruticosus) fruit does not show obvious and reliable visible traits of ripeness when mature and therefore poses great difficulty to fruit pickers. The mature blackberry, to the human eye, is black before, during, and post-ripening. To address this problem, this paper proposes a novel multi-input convolutional neural network (CNN) ensemble classifier (MCE) for detecting subtle traits of ripeness in blackberry fruits. The multi-input CNN was created from a pre-trained visual geometry group 16-layer deep convolutional network (VGG16) model trained on the ImageNet dataset. The fully connected layers were optimized for learning traits of ripeness of mature blackberry fruits. The resulting model of about 600 K trainable parameters served as the base for building homogeneous ensemble learners t ensembled using the stack generalization ensemble (SGE) framework. The input to the network are images acquired with a stereo sensor using visible and near-infrared (Vis-NIR) spectral filters at wavelengths of 700 nm and 770 nm. Through experiments, the proposed model achieved 95.1 % accuracy on unseen sets and 90.2 % accuracy with in-field conditions. Further experiments reveal that machine sensory is highly and positively correlated to human sensory over blackberry fruit skin texture • Fruits that do not show obvious and reliable visible traits of ripeness when mature pose great difficulty in fruit ripeness estimation. • Hyperspectral imaging was investigated for evaluating blackberry fruit ripeness and determining the spectral wavelengths that optimally correspond to ripeness in mature blackberry fruit. • A novel multi-input convolutional neural network (CNN) ensemble classifier was proposed for detecting subtle traits of ripeness in images of blackberry fruits. • The proposed model with blackberry fruit images captured at spectral wavelengths of 700 nm and 770 nm achieved an 11.3 % and 16.2 % increase in test accuracies compared to the RGB-based model. • Bi-spectral imagery significantly improves the ripeness-sensing capabilities of deep learning techniques. • Machine sensory has a ripeness sensing capability that is highly and positively correlated to human sensory over blackberry fruit skin texture. [ABSTRACT FROM AUTHOR]

Implementing key engineering solutions to optimise the operation of energy industries requires daily electricity demand forecasting and including uncertainty, to promote markets insight analysis as part of their strategic planning, regulating and supplying electricity to consumers. This paper proposes hybrid artificial intelligence models combining convolutional neural networks (CNN) as a feature extraction algorithm with extreme learning machines (ELM) as a framework to predict electricity demand with confidence intervals generated by Kernel Density Estimation (KDE) approaches. In order to develop CELM-KDE model, time-lagged series of daily electricity demand with local climate variables based on the air temperature, atmospheric vapour pressure, evaporation, solar radiation, humidity and sea level pressures are used to train the proposed CELM-KDE hybrid model. In order to fully evaluate the newly developed model from a point-based, as well as a probabilistic prediction strategy, the observed and predicted electricity demand as well as the probability distribution of errors are analysed using KDE method that operates without prior data distribution assumptions. Based on observed and predicted electricity demand and the relevant probabilistic confidence intervals generated by the CELM-KDE model, the final results show that the proposed method attains significantly better probability interval predictions than traditionally-used point-based models. The proposed CELM-KDE model is demonstrated to be highly effective in providing a comprehensive coverage of predicted errors, as well as providing greater insights into the average bandwidth and detailed predicted electricity demand in the testing stage. The results also indicate that the proposed hybrid model is a reliable decision support tool to develop engineering solutions in area of energy modelling, monitoring and forecasting, which could potentially be useful to the industry policymakers. We show that the point-and probabilistic-based electricity demand predictive models can be employed as an effective tool to improve accuracy of forecasting and provision of insights for national electricity markets and key energy industry stakeholder application tools. [Display omitted] • A hybrid deep learning model for daily electricity demand prediction is proposed. • A Kernel Density Estimation is applied to derive probabilistic prediction intervals. • The algorithm quantifies uncertainties in point-based electricity demand predictions. • The proposed model outperforms deep learning models using statistical uncertainty indicators. [ABSTRACT FROM AUTHOR]

Alternating current optimal power flow (OPF) analysis is critical for efficient and reliable operation of power systems. For large systems or repetitive computations, the traditional methods such as the direct and gradient methods, or non-traditional methods, such as the genetic algorithm and simulating annealing, are time-consuming and unsuitable for real-time computing. The work in this paper proposes a novel framework to obtain the optimal solution of power flow in real-time using a combination of convolutional neural networks and a self-attention mechanism. All parameters of the power networks are rearranged in an image-like shape of a multi-channel image where each channel is a two-dimensional matrix. The proposed approach is adaptive with every input size of power systems as well as frequent variations of network topologies without intervention to the framework core. The encompassment of all power system contexts in which all parameters of internal elements, generation costs, and topology information are included, contributes to the higher accuracy of inference compared to other current machine-learning-based OPF-solving methods. Besides, the proposed framework established on ubiquitous platforms is effortlessly integrated into current infrastructures of power systems, and the great efficiency along with the computation speed may serve as a critical point for practical implications, such as enabling faster decision-making during real-time operations, predicting system contingencies, and remedial actions based on an offline pre-trained model. This supervised learning process is applied to the dataset of four case studies of meshed power systems: the IEEE 5-bus system (IEEE-5), the IEEE 30-bus system (IEEE-30), the IEEE 39-bus system (IEEE-39), and the IEEE 57-bus system (IEEE-57) to prove the efficacy of the proposed method. • Developing a novel approach to solve the OPF problems in real-time. • Wrap power system characteristics under a mold of an image-like shape. • Overcome the outburst of trainable parameters when training with large-scale systems. • Do not require looking up a new set of hyperparameters or re-coding a framework. • All time-consuming computations are shifted to the offline training process. [ABSTRACT FROM AUTHOR]

Image guided depth completion aims to predict a dense depth map from sparse depth measurements and the corresponding single color image. However, most state-of-the-art methods only rely on convolutional neural network (CNN) or transformer. In this paper, we propose a transformer-CNN parallel network (TCPNet) to integrate the advantages of CNN in local detail recovery and transformer in long-range semantic modeling. Specifically, our CNN branch adopts dense connection to strengthen feature propagation. Since the common transformer computes self-attention based on all the tokens in the window, no matter if they are relevant or not, this will inevitably introduce interferences and noises. To improve the self-attention accuracy, we propose a correlation-based transformer to only allow nearest neighbor tokens to participate in the self-attention computation. We also design a multi-scale conditional random field (CRF) module to implement multi-scale high-dimensional filtering for depth refinement. The comprehensive experimental results on KITTI and NYUv2 demonstrate that our method outperforms the state-of-the-art methods. • We propose a transformer-CNN parallel network by exploiting local details and global contexts. • We design a correlation-based transformer branch to compute attention only with the top-k relevant tokens. • We propose a multi-scale conditional random field module by adaptively assembling multiple dilated CRF for depth refinement. [ABSTRACT FROM AUTHOR]

This paper investigates the application of physics-informed neural networks (PINNs) to solve free-surface flow problems governed by the 2D shallow water equations (SWEs). Two types of PINNs are developed and analyzed: a physics-informed fully connected neural network (PIFCN) and a physics-informed convolutional neural network (PICN). The PINNs eliminate the need for labeled data for training by employing the SWEs, initial and boundary conditions as components of the loss function to be minimized. Results from a set of idealized and real-world tests showed that the prediction accuracy and computation time (i.e., training time) of both PINNs may be less affected by the resolution of the domain discretization when compared against solutions by a Finite Volume (FV) model. Overall, the PICN shows a better trade-off between computational speed and accuracy than the PIFCN. Also, our results for the idealized problems indicated that PINNs can provide more than 5 times higher prediction accuracy than the FV model, while the FV simulation with coarse resolution (e.g., 10 m) can provide sub-centimeter accurate (RMSE) solutions at least one order of magnitude faster than the PINNs. Results from a river flood simulation showed that PINNs delivered better speed-accuracy trade-off than the FV model in terms of predicting the water depth, while FV models outperformed the PINNs for predictions of total flow discharge. [Display omitted] • Physics-informed neural networks are developed to solve the Shallow Water Equations. • Proposed networks can be trained without any labeled data. • These networks offer alternatives to established numerical solvers. • Convolutional neural network outperformed fully connected neural network. [ABSTRACT FROM AUTHOR]

• Based on the theory of multi-granularity cognitive computation, we propose a diagnostic architecture for short-circuit faults in converter. This architecture is capable of adapting to noisy environments and exhibits high diagnostic performance. • We validate the diagnostic capability of our model on both bearing fault dataset and simulated power supply fault dataset. A unit simulation model constructed using simulink is utilized to simulate fault occurrences and generate fault data. • By combining the simulated small-sample power supply fault dataset, we investigated the data augmentation strategy based on ACGAN and conducted an analysis of the quality of the generated samples. Furthermore, we experimentally verified the performance improvement of MGDCNN with the augmented dataset. The power supply system of a tokamak device is a crucial subsystem responsible for providing the magnetic field for plasma confinement. The timely application of fault diagnosis techniques to identify abnormal states of the power supply is of crucial importance for the safe and efficient operation of tokamak devices. Intelligent diagnostic methods based on Convolutional Neural Networks (CNN) are widely employed nowadays. However, within the operational environment of the device, there exist multiple physical field couplings, and inevitable noise will impact the data. Moreover, the measurement equipment exhibits instability, resulting in limited availability of data that meets the required criteria. To address these issues, this paper investigates a fault diagnosis approach utilizing an Auxiliary Classifier Generative Adversarial Network (ACGAN) for data augmentation, and proposes a Multi-Granularity Denoising CNN (MGDCNN) that accounts for noise interference, enabling diagnosis of faults at different granularities. In our approach, we first construct a multi-granularity structure of the data based on prior knowledge. Then, a hierarchical structure corresponding to the multi-granularity data and robust to noise is built by introducing an embedded Discrete Wavelet Transform (DWT) into the one-dimensional (1-D) CNN. Finally, the natural stratification of the network is combined with individual granularity branches for fault diagnosis. Experimental results on simulated datasets and public benchmark datasets demonstrate that the proposed model achieves a diagnostic accuracy of 98.81 % for short-circuit faults in power supply converter at the finest granularity. Even with noisy data, the model maintains a diagnostic accuracy of approximately 97 %, indicating superior noise resistance performance in the inference process of the MGDCNN network. [ABSTRACT FROM AUTHOR]

• A novel methodology integrating percussion and CNN model is established to detect concrete voids. • The CNN model trained by both CWT and MFCC show satisfying categorizing performances. • The methodology proves its good noise-immune capacity in processing percussion sound signals. • The superiority of the proposed method is well demonstrated by comparison with ML methods. As a fundamental construction material, concrete commonly encounter void defects, which could significantly impair the integrity of concrete members and seriously weaken their load-bearing capacity. Worse still, void defects typically exist inside concrete members, making it difficult to detect them in real time. Therefore, conducting regular inspections for internal void defects of concrete structures is of great importance to maintain structural health. This paper investigates an integrated method to detect concrete voids based on percussion approach and a convolutional neural network (CNN). Firstly, percussion-induced sound signals were collected from 18 concrete specimens with different precast void defects. Each specimen was tapped 100 times, for a total of 1,800 percussion-induced acoustic signals. Subsequently, continuous wavelet transform (CWT) and Mel frequency cepstral coefficient (MFCC) were introduced to convert the collected acoustic signals into two types of images. The converted images were divided into testing and training datasets according to the ratio of 1:3, and 600 images were input to the CNN as the test dataset and 1200 images as the training dataset. The CNN was then trained and verified by the joint input of CWT and MFCC images to perform concrete voids classification. The result shows that the proposed method presents a satisfying classification accuracy of 100 %. Next, percussion tests under 5 levels of noisy environments were conducted, and the results prove the remarkable anti-noise performance of the methodology by achieving 88.12 % accuracy even at the strongest signal-to-noise ratio of 0 dB. Finally, the superiority of the proposed method was further demonstrated through the accuracy comparison with machine learning (ML) methods, with the accuracy consistently outperforming over 25 %. In conclusion, the proposed method has a great potential for future in-situ applications in concrete void detection. [ABSTRACT FROM AUTHOR]

Chlorophyll-a (Chl-a) concentration plays a crucial role in monitoring marine phytoplankton, holding significant implications for marine ecosystems and human livelihoods. Remote sensing serves as a valuable method for directly estimating Chl-a concentration and facilitating marine monitoring activities. In order to accurately estimate Chl-a concentration and effectively monitor the marine ecological environment of the Taiwan Strait, this paper introduces a novel neural network model called Convolutional Neural Network with Dual Attention Mechanism Optimization (CNN-CBAM). Additionally, the spectral bands derived from MODIS 500 m imagery are subjected to various processing techniques to generate four distinct sets of feature data. These datasets are subsequently merged with in-situ measurements of Chl-a concentration obtained from buoy stations. Given the limited availability of buoy stations, the temporal continuity of data is leveraged to overcome the spatial distribution constraints. This enables the estimation of Chl-a concentration at various time intervals within the research area of the Taiwan Strait. To evaluate the performance of the model, metrics such as root mean square error (RMSE), mean absolute percentage error (MAPE), and R2 are employed. The results demonstrate that the CNN-CBAM model, utilizing MODIS temporal data, effectively retrieves Chl-a concentration in the research area of the Taiwan Strait with high accuracy. For the CNN-CBAM model, the RMSE is 0.34 μg L−1, MAPE is 22%, and R2 is 0.86. In comparison, the traditional empirical model using the Band Ratio (BR) model has an RMSE of 0.61 μg L−1, MAPE of 57%, and R2 of 0.31. The results indicate that the CNN-CBAM model has improved R2 by 0.55 compared to the traditional BR model. Additionally, the RMSE and MAPE have decreased by 0.27 μg L−1 and 35%, respectively. The superiority of the CNN-CBAM model over the traditional BR model is evident, showcasing a substantial enhancement in the accuracy of Chl-a concentration retrieval. Given the challenges posed by the intricate and ever-changing marine environment, particularly the scarcity of in-situ buoy stations, this study offers a practical solution for monitoring Chl-a concentration. It establishes a framework for leveraging satellite-based multispectral sensors to enable large-scale and multi-temporal remote sensing retrieval of Chl-a concentration in the research area of the Taiwan Strait. • The CNN-CBAM model demonstrates exceptional performance in estimating Chl-a concentration. • The CNN-CBAM model excels in mining non-linear data compared to traditional empirical models. • CNN-CBAM outperforms other machine learning models in extracting high-dimensional feature data. • The incorporation of the CBAM module enhances the performance of the CNN model. [ABSTRACT FROM AUTHOR]

[Display omitted] • A new algorithm to generate distinctive and similar microstructures for FRP RVEs. • A CNN for accurate properties prediction by learning random microstructures. • An MCM segregating microstructural and material effects on RVE effective properties. • Rapid prediction integrating CNN and MCM for random RVEs with various materials. Despite recent advancements in using machine learning (ML) techniques to establish the microstructure-property linkage for composites' representative volume elements (RVEs), challenges persist in effectively characterising the effect of microstructural randomness on material properties. This complexity arises from the difficulty of expressing randomness as definitive variables and its intertwined relations with other factors, such as material constituents. Such complexities result in limitations in generalising ML models across different material constituents. Conventional solutions to these challenges usually necessitate large datasets, which require considerable computational resources, for an accurate and generalisable ML models to be trained. This paper presents an innovative approach to tackling these challenges by integrating a high-accuracy convolutional neural network (CNN) with a novel microstructure-factored constitutive model (MCM). The MCM, rooted from classic empirical constitutive modelling, effectively segregates the microstructural and constituting material effects, extending the generalisability and thus significantly enhancing the efficacy of the CNN. This new approach enabled a CNN trained on the transverse stress-strain curves of one set of material constituents (CF/PEEK at 270 °C) to be generalised for the rapid prediction of various sets of material constituents at different temperatures, unseen by the CNN during training, with an average mean absolute percentage error around 3 %. [ABSTRACT FROM AUTHOR]

[Display omitted] • A public perovskite labeling dataset is provided. • The MatBERT-CNN-CRF model was constructed. • The F1 score of the new model has improved to 90.8% Due to the significant increase in publications in the field of materials science, there has been a bottleneck in organizing material science knowledge and discovering new materials. The number of literature in the emerging field of perovskite materials has grown to a massive scale. It is necessary to compile information on the structure, properties, synthesis methods, characterization techniques, and applications of perovskite materials. To address this issue, we employed named entity recognition, a natural language processing technique, to extract important entities from perovskite material texts. In this paper, we propose a method based on convolutional neural networks (CNN) and MatBERT. Firstly, we utilized MatBERT, which has been pre-trained on a large amount of material science text, to generate contextualized word embeddings. Next, we extracted feature information using a CNN model. Finally, a conditional random field (CRF) layer was used for decoding sequences in addition to calculating the training and validation loss. Experimental results demonstrated that the performance of our model on perovskite material dataset was improved by 1 %∼6% compared with BERT, SciBERT and MatBERT models. Through this model, we extracted the entities of 2389 abstracts to obtain knowledge of perovskite materials. [ABSTRACT FROM AUTHOR]

With the rapid advancement of multimedia technologies, there is a growing demand for reliable methods to verify image integrity. Camera model identification, a passive approach aiming to determine the specific capturing device model, has garnered considerable attention in the field of source camera forensics. In this paper, we first propose a novel patch selection method that enhances the diversity of training data by utilizing the uniform local binary pattern operator to reveal spatial textual information. Secondly, we introduce a complex dual-path enhanced ConvNeXt network for camera model identification, effectively leveraging the multi-frequency information present in the image. Notably, our network demonstrates the ability to learn camera model-related features without relying on a residual prediction module. Finally, extensive experimental results on both Dresden and Vision datasets shown that the proposed network outperforms several state-of-the-art methods in both teams of identification accuracy and computational efficiency. • Proposing a patch selection method of the uniform local binary pattern operator. • Introducing a dual-path enhanced ConvNeXt network for camera model identification. • Obtaining robust results on the Dresden and Vision datasets. [ABSTRACT FROM AUTHOR]

Thunderstorms can be a large source of disruption for European air-traffic management causing a chaotic state of operation within the airspace system. In current practice, air-traffic managers are provided with imprecise forecasts which limit their ability to plan strategically. As a result, weather mitigation is performed using tactical measures with a time horizon of three hours. Increasing the lead time of thunderstorm predictions to the day before operations could help air-traffic managers plan around weather and improve the efficiency of air-traffic-management operations. Emerging techniques based on machine learning have provided promising results, partly attributed to reduced human bias and improved capacity in predicting thunderstorms purely from numerical weather prediction data. In this paper, we expand on our previous work on thunderstorm forecasting, by applying convolutional neural networks (CNNs) to exploit the spatial characteristics embedded in the weather data. The learning task of predicting convection is formulated as a binary-classification problem based on satellite data. The performance of multiple CNN-based architectures, including a fully-convolutional neural network (FCN), a CNN-based encoder–decoder, a U-Net, and a pyramid-scene parsing network (PSPNet) are compared against a multi-layer-perceptron (MLP) network. Our work indicates that CNN-based architectures improve the performance of point-prediction models, with a fully-convolutional neural-network architecture having the best performance. Results show that CNN-based architectures can be used to increase the prediction lead time of thunderstorms. Lastly, a case study illustrating the applications of convection-prediction models in an air-traffic-management setting is presented. • CNNs are applied to numerical weather prediction data to predict thunderstorms. • CNNs outperform MLP architectures in the task of predicting thunderstorms. • ML-based weather forecasts allow for better planning of air traffic operations. [ABSTRACT FROM AUTHOR]

The brain development during the perinatal period is characterized by rapid changes in both structure and function, which have significant impact on the cognitive and behavioral abilities later in life. Accurate assessment of brain age is a crucial indicator for brain development maturity and can help predict the risk of neonatal pathology. However, evaluating neonatal brains using magnetic resonance imaging (MRI) is challenging due to its complexity, multi-dimension, and noise with subtle alterations. In this paper, we propose a multi-modal deep learning framework based on transformers for precise post-menstrual age (PMA) estimation and brain development analysis using T2-weighted structural MRI (T2-sMRI) and diffusion MRI (dMRI) data. First, we build a two-stream dense network to learn modality-specific features from T2-sMRI and dMRI of brain individually. Then, a transformer module based on self-attention mechanism integrates these features for PMA prediction and preterm/term classification. Finally, saliency maps on brain templates are used to enhance the interpretability of results. Our method is evaluated on the multi-modal MRI dataset of the developing Human Connectome Project (dHCP), which contains 592 neonates, including 478 term-born and 114 preterm-born subjects. The results demonstrate that our method achieves a 0.5-week mean absolute error (MAE) in PMA estimation for term-born subjects. Notably, preterm-born subjects exhibit delayed brain development, worsening with increasing prematurity. Our method also achieves 95% accuracy in classification of term-born and preterm-born subjects, revealing significant group differences. [Display omitted] • Multi-modal framework based on transformers for gestational age estimation. • Two-stream dense network to learn modality-specific features from neuroimaging data. • Achieve a mean absolute error of 0.5 weeks in gestational age estimation. • Accurately classify preterm-born and term-born subjects and identify differences. [ABSTRACT FROM AUTHOR]

Solar radiation is an essential meteorological parameter for building energy efficiency analysis, and the quality of the data directly affects the analysis results. This paper investigates the estimation of hourly solar radiation based on the generation of the typical meteorological year(TMY) using various real meteorological parameters and limited solar radiation data. The focus of this paper is to use two types of neural network algorithms to improve the estimation accuracy and applicability, and to solve the problem of hourly solar radiation data acquisition in non-radiation areas. First, select two city station data and use three methods to generate TMY. Then, two neural network models, BP Neural Network (BP)，Convolutional Neural Network (CNN) are used to estimate the hourly solar radiation data and verify the results. Finally, by constructing a photovoltaic-integrated office building model, the accuracy of the hourly solar radiation estimation model is verified using energy consumption simulation and photovoltaic (PV) power generation simulation. The results show that this paper can well solve the problem of limited radiation data, which provides a new idea for the study of building energy efficiency in areas where radiation data is missing. • Multiple neural network is used to estimate the generation of solar radiation data using other meteorological parameters. • An advanced neural network is used to provide an effective TMY generation method in missing hourly solar radiation data. • The accuracy of the experimental results is verified by energy consumption simulation and photovoltaic power generation. [ABSTRACT FROM AUTHOR]

Pavement crack detection continues to be a stubborn problem given the interference of various factors in the actual pavement and the complex topological structure of asphalt pavement. Among all the obstacles, the bottleneck of pavement crack detection lies in the difficulty of segmenting the cracks in the pavement images whose edges are blurred. This paper proposes a multi-scale context feature and cross-attention based on convolutional neural network for accurate and robust pavement crack segmentation. The multi-scale context feature module is built in different deep networks to extract rich crack feature information. Subsequently, in order to effectively promote the seamless integration of features at different levels, we deploy cross-attention modules to each branch. After that, we add deep supervision to each branch to accelerate training. Finally, we integrate the outputs of each branch to obtain the final output diagram. The comparative experiments on various pavement datasets show that the method has better robustness. At the same time, this paper designs a complete system of pavement crack detection (PCD) and develops corresponding engineering application software. The PCD system can record the real-time pavement image data to the edge server, and the client can also monitor the real-time pavement images from the edge server through the HTTP protocol. • A multi-scale context feature module is built in the deep layer for robustly describing the size of the cracks. • The cross-attention module enables each pixel to select individual contextual information from multi-layer features. • In-depth supervision is added to each branch to accelerate the optimization of the network model. • An intelligent detection application software is designed and integrated with multiple modules. [ABSTRACT FROM AUTHOR]

The sales of new energy vehicles (NEVs) and the construction of charging infrastructure promote and constrain each other. It is crucial for the development of the new energy vehicle industry to understand the gap clearly and accurately between the supply and demand of NEV charging infrastructure. In this paper, a neural network combined model based on convolutional neural network (CNN) and long and short-term memory (LSTM) is introduced for accurate prediction of NEVS sales and charging infrastructure ownership. Compared with other traditional and combined models, the CNN-LSTM combined model performs best in multiple evaluation metrics while using less computing power. The RMSE, MAE, MAPE, and R2 of the CNN-LSTM combined model were 52.80, 42.67, 17 %, and 0.78, respectively. Accordingly, it is sufficient to demonstrate the excellent prediction performance of the CNN-LSTM combined model constructed in this paper. The forecast results show that in 2025, the ratio of NEVs to public charging piles will rise to 10.2:1 and the ratio to private charging piles will fall to 2.5:1. The overall ratio shows a downward trend and is expected to reach 2:1. There is a gap in the demand for NEV charging infrastructure. Finally, this paper makes suggestions for narrowing the gap between the supply and demand of NEV charging infrastructure and the sustainable development of the NEV industry. [ABSTRACT FROM AUTHOR]

• LPSF module is designed to improve the gas features. • Collaborative attention is proposed for local and global gas features. • The feature compensation mechanism of CNN and Transformer is designed. • PSCFormer is proposed for gas recognition. Based on their powerful feature extraction capability, a convolutional neural network (CNN) has been gradually applied to gas identification in the electronic nose (e-nose) system. The responses of different intensities in the e-nose system are significantly correlated, and CNN extracts the local gas features by convolution while ignoring their global correlation. Transformer combines different responses and obtains the correlation between global features by self-attention. This paper proposes a lightweight hybrid network called Peak Search-based Convolutional Transformers (PSCFormer). First, combining the data characteristics of gas information, the Local Peak Search and Feature Fusion (LPSF) module is proposed to focus on the key gas features. Second, Transformer Encoder (TE) is proposed to obtain the global correlation between global features, and the parallel Convolution Encoder (CE) is proposed to capture the local dependence. Finally, a reasonable feature complementation mechanism is presented, and the preference of TE is alleviated for the slow-down response while solving the receptive field limitation of CE. This paper has evaluated three different datasets to validate the effectiveness of PSCFormer, all of which show stable and excellent performance with a good tradeoff between efficiency and complexity. The results prove that PSCFormer is an efficient and lightweight gas identification network, which provides a method to promote the engineering application of the e-nose system. [ABSTRACT FROM AUTHOR]

• A multiple sub-holograms optimization method for holographic near-eye display is proposed. • The principle of the holographic viewing-window is specifically analyzed. • A phase-only hologram optimization method of 3D multiplane image by the CNN is proposed. • Natural motion parallax and enough movement range for the eye pupil are achieved. A multiple sub-holograms optimization method for holographic near-eye display (NED) based on holographic viewing-window (HVW) is proposed. The HVW is a hologram generated by the point source method (PSM) with the spatial frequency constraint, and the complete reconstructed images can be observed through it. In this paper, the HVW is a phase-only hologram (POH) of a three dimensional (3D) multiplane image and it is split into multiple sub-holograms that are optimized simultaneously for pupil movement by the convolutional neural network (CNN), where each optimized constant phase (OCP) is added to the wavefront of corresponding point source. Both the simulation and the experimental results show that the quality of the reconstructed image corresponding to each sub-hologram has significantly improved, especially compared with the random constant phase (RCP) method. Moreover, we establish a holographic NED system with a 4f system to pan the optimized POH to the pupil plane to generate the HVW, and then a camera with an additional aperture is used to capture the reconstructed images corresponding to each sub-hologram. In this paper, the high-quality 3D multiplane images with natural motion parallax can be observed through an 8.64 mm×8.64 mm HVW with nine sub-holograms. [ABSTRACT FROM AUTHOR]

[Display omitted] • The first time using CBAM-CNN to predict particle size distribution during fluidized bed granulation. • The CBAM-CNN model was optimized by introducing Bayesian optimization and C-Mixup algorithms. • The performance of CBAM-CNN was compared to other classic models. • The modeling convenience of CBAM-CNN was evaluated. Monitoring the particle size distribution (PSD) is crucial for controlling product quality during fluidized bed granulation. This paper proposed a rapid analytical method that quantifies the D10, D50, and D90 values using a Convolutional Block Attention Module-Convolutional Neural Network (CBAM-CNN) framework tailored for deep learning with near-infrared (NIR) spectroscopy. This innovative framework, which fuses CBAM with CNN, excels at extracting intricate features while prioritizing crucial ones, thereby facilitating the creation of a robust multi-output regression model. To expand the training dataset, we incorporated the C-Mixup algorithm, ensuring that the deep learning model was trained comprehensively. Additionally, the Bayesian optimization algorithm was introduced to optimize the hyperparameters, improving the prediction performance of the deep learning model. Compared with the commonly used Partial Least Squares (PLS), Support Vector Machine (SVM), and Artificial Neural Network (ANN) models, the CBAM-CNN model yielded higher prediction accuracy. Furthermore, the CBAM-CNN model avoided spectral preprocessing, preserved the spectral information to the maximum extent, and returned multiple predicted values at one time without degrading the prediction accuracy. Therefore, the CBAM-CNN model showed better prediction performance and modeling convenience for analyzing PSD values in fluidized bed granulation. [ABSTRACT FROM AUTHOR]

Estimating the total wind power output from the meteorological information at a province level (called Provincial Regional Wind Power Conversion Model, PRWPCM) plays vital and fundamental roles in energy modeling community and regional wind power forecasting. How to construct a reliable PRWPCM is a real challenge, since PRWPCM involves a large number of widely distributed wind turbines, massive meteorological data across the whole province, and complex nonlinear correlations. This paper proposes a lightweight PRWPCM by integrating Geographic Information System (GIS) analysis technology and Convolutional Neural Network (CNN). First, we conduct the land suitability analysis for wind turbine sites through the multi-criteria GIS layer overlay method to make the provincial wind turbine land suitability map (WTLSM) with scored divisions from the least suitable to the most suitable areas. On this basis, a new fusion mechanism for geographic and meteorological information is proposed, through which the raw meteorological data matrix can be reconstructed to filter and amplify the meteorological information that is more relevant to the total wind power output of the province, and avoid the time-consuming and labor-intensive data collection and processing, large-size model construction and validation. Second, a CNN-based regression architecture is designed to further capture the mapping relationship between the reconstructed meteorological data and total wind power output of the province; each type of meteorological factor is considered as an input channel and the attention modules are introduced to adaptively enhance useful channels and suppress less useful ones. Numerical experiments based on the wind power operation data of Yunnan Province, China, are conducted to validate the superiority of the proposed PRWPCM via benchmarking against 13 classical methods. • Mapping relationship between wind power output and meteorological information at a province level is recognized by integrating GIS and CNN. • A new fusion mechanism for geographic and meteorological information is proposed to achieve lightweight modeling. • Comparative experimental studies are conducted in Yunnan province, China. [ABSTRACT FROM AUTHOR]

Automatic modulation recognition (AMR) has garnered significant attention in both civilian and military domains, with applications ranging from spectrum sensing and cognitive radio (CR) to the deterrence of adversary communication. Index modulation (IM) represents an innovative digital modulation technique that exploits the indices of parameters of communication systems to transmit extra information bits. This paper aims to examine the performance of a convolutional neural network (CNN)-based AMR across various IM systems, including spatial modulation (SM), quadrature spatial modulation (QSM), and generalized spatial modulation (GSM) with eight digital modulation schemes. In this study, we leverage confusion matrices, receiver operating characteristic (ROC) curves, and F1 scores to illustrate the recognition model's outputs. • Modulation recognition models exploit deep learning algorithms effectively. • Index modulation is a novel technique for conveying additional information. • Three datasets are created for the recognition of eight digital modulation schemes. • Three modulation recognition scenarios analyze the system's performance. • Quadrature amplitude modulation types are more robust than phase shift keying types. [ABSTRACT FROM AUTHOR]

In the construction of intelligent transportation systems, short-term traffic flow prediction is of great significance for the advancement of traffic network management. But due to the presence of many complex factors in both spatial and temporal domains, it remains a complex and challenging task. Existing literature usually employs the convolutional neural network (CNN)-based methods in capturing spatiotemporal correlations. These CNN-based methods often use a single-channel data structure to represent different periodic patterns, which makes the model susceptible to over-parameterization when capturing periodic dependencies and prone to information loss after convolution. To overcome these limitations, this paper presents a hybrid deep learning method for short-term traffic flow prediction. In this method, a video-shaped multi-channel data structure is designed to represent different periodic patterns more efficiently. Next, a new mixed-pointwise convolution is introduced for capturing periodic dependencies without the negative impacts mentioned above. Lastly, an improved channel attention mechanism is proposed to learn channel inter-dependencies with controllable parameter usage. The proposed method is lightweight, yet highly effective. Compared to the state-of-the-art baseline method, it reduces the root mean squared error by up to 6.7% on the PeMSD4 dataset and 13.3% on the PeMSD7 dataset, while also achieving substantial improvement in two additional metrics, exhibiting strong robustness and great scalability across various settings. [ABSTRACT FROM AUTHOR]

Accurate fault identification provides an important basis for well location deployment, oil and gas resource development. However, obtaining a large number of fault samples through manual labeling or interpretation is difficult. Conventional convolutional neural networks have certain challenges in finely characterizing low-order faults and fault continuity. This paper studies a 3D intelligent fault identification method that integrates deep learning with attention mechanism. Based on 3D-UNet network, the method constructs a dual attention fault identification model with an encoder-decoder structure, which focuses on enhancing low-order fault information and extracting key features. An adaptive hybrid loss function is proposed to address the imbalance problem of fault proportions in seismic amplitude data. The function introduces an adjustment coefficient to adaptively enhance the attention to high-order or low-order faults according to the actual situation of the fault, improving the accuracy and continuity of fault identification. Furthermore, a model re-training learning optimization method is presented to capture the missed fault information in the first training and repair the connectivity of low-order faults. Applying this method to the synthetic data set, the accuracy can be improved to 0.9732, and the loss can be converged to 0.0982. The results of shale reservoirs in the North Sea Basin and Kerry-3D indicate that the method can reduce the situation of fault missing and misidentification, effectively improve fault identification accuracy, and enhance low-order fault identification by obtaining more contextual fault features. • A seismic fault image segmentation network is developed with attention mechanism. • Construct an adaptive hybrid loss function to solve the problem of data imbalance. • A method retraining learning that integrates theory and predictive data is proposed. [ABSTRACT FROM AUTHOR]

[Display omitted] • Accurate classification of different tree species and conspecifics in hickory forests. • Captured UAV hyperspectral images from two hickory bases. • Comparing the classification performance of hyperspectral and RGB images, with hyperspectral images achieving superior accuracy in tree species classification. • Introduced the 3D-2DCNN-CA method and validated it on two datasets. • Combining 3D-CNN, 2D-CNN, and channel attention mechanism yields the best results. Hickory trees possess substantial economic, nutritional, and ecological value, and they play a pivotal role in both human societies and natural ecosystems. To maximize benefits, many bases have adopted a composite planting strategy. Effective and timely monitoring of hickory forest species information is crucial for precise management and conservation. In this study, a low-altitude unmanned aerial vehicle (UAV) was employed to capture RGB and hyperspectral data from the canopy of two hickory bases. A hybrid convolutional neural network structure was then utilized to classify different tree species and congeneric hickory species. By introducing a channel attention module to refine the features of hyperspectral images, classification stability was enhanced. The experimental results demonstrate that hyperspectral images yield superior classification performance in hickory species identification compared to RGB images, particularly in classifying highly homogeneous tree species. The 3D-2DCNN-CA proposed in this paper demonstrated the best performance in classifying hickory species compared to other classification methods. In the classification of different tree species, the accuracy for a single hickory reached 99.38%, and in the classification of the same hickory species, it achieved an accuracy of 93.97%. Furthermore, this method also achieved significant classification results at the single-tree scale. These results indicate that the method can realize fine-scale monitoring of hickory forests and provide substantial support for forest land management and expert guidance on planting distribution. [ABSTRACT FROM AUTHOR]

The detection and classification of concrete damage is essential for maintaining good infrastructure condition. Traditional semantic segmentation methods often can not provide accurate crack boundary information, which limits the further location and measurement analysis. In this study, the case segmentation method is used to solve the shortcomings of the previous detection methods and achieve more accurate crack identification results. This paper presents an improved YOLOv7 network design scheme. The network includes three different custom modules that can optimize the algorithm to solve missing feature problems, small recognition frames, and gradient problems, thereby improving accuracy. In addition, data sets with different sizes, exposures and noise are used to train the network, which expands the prediction range of the network and enhances the stability of the network. The experimental results show that compared with YOLOv7, YOLOv5, SOLOv2, Cascade Mask R-CNN, Condinst, Sparseinst, mAP is significantly improved. Thus, the proposed network algorithm has high practical engineering value. • Crack morphology detection and category classification are achieved using instance segmentation. • Two innovative modules and a unique connection are developed. • A dataset for crack with high exposure, darkness, and noise is constructed. • The model achieves mAP of 72.2% and 87.9% on public and self-built datasets. [ABSTRACT FROM AUTHOR]

Data-driven fault diagnosis has become a hot topic of research in recent years, due to its wide applicability, high accuracy, and ease of modeling. In data-driven fault diagnosis, feature extraction is usually performed through a combination of one-dimensional time domain or frequency domain analysis methods. However, the constraints of data format and diagnostic methods give rise to three primary issues: inadequate utilization, expression, and mining of fault features, thereby impeding the broader application of data-driven methods. This paper presents a fault diagnosis framework that integrates cross-domain fusion images and a lightweight feature-enhanced network to address these issues. We leverage the temporal and frequency features of raw time series data, transforming them into images. This approach not only offers a greater amount of fault information but also highlights the inherent features more prominently. In terms of diagnosis methods, a novel feature-enhanced network model is proposed. This model takes images generated by a cross-domain image fusion module as inputs and then goes through a customized feature extraction module, a feature fusion module, a feature enhancement module, and a classification module to achieve high-precision and fast fault diagnosis. The effectiveness of this framework is validated on two publicly available datasets. The results show that the average accuracy of this fault diagnosis framework can reach 100%, surpassing the findings of existing research. The experiments on noise resistance further showcase the superiority of the proposed framework. It is expected that the framework presented in this study will provide a new perspective and direction for fault diagnosis. • Propose an innovative framework for precise fault diagnosis. • CFI images can translate fault information into texture and color features. • Differences between different faults can be better highlighted through CFI images. • Demonstrate the superiority of the framework through two distinct case studies. [ABSTRACT FROM AUTHOR]