Search

This document discusses the recent advancements in decision support systems (DSSs) for disease detection and diagnosis. The combination of biomedical studies and information technology has led to the development of accessible and accurate solutions that can improve patient survival rates. The document highlights several research papers that cover a wide range of topics, including multiple sclerosis detection, neurodegenerative disease detection, breast lesion classification, COVID-19 mortality prediction, melanoma diagnosis, and prediction of second primary skin cancer. The adoption of efficient DSSs can aid clinical assessment, reduce misdiagnosis, and facilitate evidence-based decision-making. However, challenges such as validation, training, and user interface design need to be addressed for widespread application of DSSs in clinical practice. The document concludes by emphasizing the importance of future studies and developments in overcoming limitations and expanding the use of DSSs in different contexts. [Extracted from the article]

Video deepfake detection has emerged as a critical field within the broader domain of digital technologies driven by the rapid proliferation of AI-generated media and the increasing threat of its misuse for deception and misinformation. The integration of Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) has proven to be a promising approach for improving video deepfake detection, achieving near-perfect accuracy. CNNs enable the effective extraction of spatial features from video frames, such as facial textures and lighting, while LSTM analyses temporal patterns, detecting inconsistencies over time. This hybrid model enhances the ability to detect deepfakes by combining spatial and temporal analysis. However, the existing research lacks systematic evaluations that comprehensively assess their effectiveness and optimal configurations. Therefore, this paper provides a comprehensive review of video deepfake detection techniques utilising hybrid CNN-LSTM models. It systematically investigates state-of-the-art techniques, highlighting common feature extraction approaches and widely used datasets for training and testing. This paper also evaluates model performance across different datasets, identifies key factors influencing detection accuracy, and explores how CNN-LSTM models can be optimised. It also compares CNN-LSTM models with non-LSTM approaches, addresses implementation challenges, and proposes solutions for them. Lastly, open issues and future research directions of video deepfake detection using CNN-LSTM will be discussed. This paper provides valuable insights for researchers and cyber security professionals by reviewing CNN-LSTM models for video deepfake detection contributing to the advancement of robust and effective deepfake detection systems. [ABSTRACT FROM AUTHOR]

Featured Application: The model proposed in this paper can help stock investors to get high returns on newly listed stocks. Most previous stock investing methods were unable to predict newly listed stocks because they did not have historical data on newly listed stocks. In this paper, we use the Q-learning algorithm based on a convolutional neural network and add sentiment analysis to establish a prediction method for Chinese stock investment tasks. There are 118 companies that are ranked in the Chinese top 150 list for two consecutive years in both 2022 and 2023. We collected all comments under the stock bar of these 118 stocks for each day from 1 January 2022 to 1 July 2024, totaling nearly 10 million comments. There are 90 stocks left after the preprocessing of 118 stocks. We use these 90 stocks as the dataset. The stock's closing price, volume, and comment text data are fed together to the agent, and the trained agent outputs investment behaviors that maximize future returns. We apply the trained model to two test sets that are completely different from the training set and compare it to several other methods. Our proposed method called SADQN-S obtains results of 1.1229 and 1.1054 on the two test sets. SADQN-S obtained higher final total assets than the other methods on both test sets. This shows that our model can help stock investors earn high returns on newly listed stocks. [ABSTRACT FROM AUTHOR]

Every part of society relies on energy systems due to the growing population and the constant demand for energy. Because of the high energy demands of transportation, industry, and daily life, energy systems are crucial to every part of society. Electrical transmission lines are a crucial component of the electrical power system. Therefore, in order to determine the power system's protection plan and increase its reliability, it is critical to foresee and classify fault types. With this motivation, the main goal of this paper is to design a deep network model to classify faults in transmission lines based on real, generated, and publicly available datasets. A deep learning architecture that was based on a one-dimensional convolutional neural network (CNN) was utilized in this study. Accuracy, specificity, recall, precision, F1 score, ROC curves, and AUC were employed as performance criteria for the suggested model. Not only synthetic but also real data were used in this study. It has been seen that the created model can be used successfully for both real data and synthetic data. In order to measure the robustness of the network, it was tested with three different datasets consisting of real, generated, and publicly available datasets. In the paper, 1D CNN, one of the machine learning methods, was used on three different power systems, and it was observed that the machine learning method was successful in all three power systems. [ABSTRACT FROM AUTHOR]

The prediction of rock bursts is of paramount importance in ensuring the safety of coal mine production. In order to enhance the precision of rock burst prediction, this paper utilizes a working face of the Gengcun Coal Mine as a case study. The paper employs a three-year microseismic monitoring data set from the working face and employs a sensitivity analysis to identify three monitoring indicators with a higher correlation with rock bursts: daily total energy, daily maximum energy, and daily frequency. Three subsets are created from the 10-day monitoring data: daily frequency, daily maximum energy, and daily total energy. The impact risk score of the next day is assessed as the sample label by the expert assessment system. Sample input and sample label define the data set. The long short-term memory (LSTM) neural network is employed to extract the features of time series. The Bayesian optimization algorithm is introduced to optimize the model, and the Bayesian optimization–long short-term memory (BO-LSTM) combination model is established. The prediction effect of the BO-LSTM model is compared with that of the gated recurrent unit (GRU) and the convolutional neural network (1DCNN). The results demonstrate that the BO-LSTM combined model has a practical application value because the four evaluation indexes of the model are mean absolute error (MAE), mean absolute percentage error (MAPE), variance accounted for (VAF), and mean squared error (MSE) of 0.026272, 0.226405, 0.870296, and 0.001102, respectively. These values are better than those of the other two single models. The rock explosion prediction model can make use of the research findings as a guide. [ABSTRACT FROM AUTHOR]

Due to the high detection efficiency of the airborne time-domain electromagnetic method, it can quickly collect electromagnetic response data for large area-wide regions, but it also brings great challenges to the inversion interpretation of the data because there are numerous survey data that need to be inverted. Conventional optimal inversion and fast imaging methods still take a long time to obtain conductivity and depth information, which affect the efficiency of real-time data interpretation. In this paper, we present a deep learning inversion method that can be used to solve the fast inversion problem of airborne time-domain electromagnetic data; the method uses a one-dimensional convolutional neural network. The network structure consists of two parts containing different numbers of convolutional and pooling layers. The training sample dataset was generated via two ways of constructing geoelectric models through forward modelling. To check the effectiveness of our deep learning inversion strategy, we tested it on synthetic data and two types of survey data. The experimental results show that this inversion method is effective and that it can be applied to airborne time-domain electromagnetic data collected using different observation systems. The proposed inversion method can obtain better inversion results for both simple and complex stratigraphic structures and requires significantly less computation time compared to conventional optimal inversion methods. [ABSTRACT FROM AUTHOR]

The real-time monitoring and evaluation of water quality provides a scientific basis for water resource management and promotes regional sustainable development. This study established a database using Landsat-8 satellite data and water quality data from the Ningxia Yellow River basin in China, spanning 2021 to 2023, and this paper proposes a custom residual convolutional neural network model with a hybrid attention mechanism, referred to as PCWA-ResCNN. The accuracy of the model in predicting turbidity, permanganate, ammonia nitrogen, and dissolved oxygen concentration was more than 95%. Compared to convolutional neural networks and long short-term memory models, this model performed better in predicting water quality parameters with significantly improved prediction performance. In terms of spatial distribution, the pollution degree in the middle reaches of the basin is relatively serious. However, the overall water quality is good, being mainly Class I and Class II water quality. The hybrid model established in this paper can better capture the complex nonlinear relationship between the observed values and the surface water reflectance, showing strong robustness. This model can be used for the water quality monitoring of complex inland rivers and lakes, and it can also provide effective support for relevant government departments to formulate scientific and reasonable water quality management policies. [ABSTRACT FROM AUTHOR]

Featured Application: This work provides a systematic way to produce a defect-free atom array of neutral atom platforms for quantum information processing. This paper aims to present an approach to address the atom rearrangement problem by developing Convolutional Neural Network (CNN) models. These models predict the coordinates for atom movements while ensuring collision-free transitions and filling all vacancies in the target array. The process begins with designing a cost function for the assignment problem that incorporates constraints to prevent collisions and guarantee vacancy filling. We then build and train CNN models using datasets for three different grid sizes: 10 × 10 ,   13 × 13 ,   and   21 × 21 . Our models achieve high accuracy in predicting atom positions, with individual position accuracies of 99.63%, 98.93%, and 97.24%, respectively, for the aforementioned grid sizes. Despite limitations in training larger models due to hardware constraints, our approach demonstrates significant improvements in speed and accuracy. The final section of the paper presents detailed accuracy results and calculation times for each model, highlighting the potential of CNN-based methods in optimizing atom rearrangement processes. [ABSTRACT FROM AUTHOR]

Drone area coverage primarily involves using unmanned aerial vehicles (UAVs) for extensive monitoring, surveying, communication, and other tasks over specific regions. The significance and value of this technology are multifaceted. Firstly, UAVs can rapidly and efficiently reach remote or inaccessible areas to perform tasks such as terrain mapping, disaster monitoring, or search and rescue, significantly enhancing response speed and execution efficiency. Secondly, drone area coverage in agricultural monitoring, forestry conservation, and urban planning offers high-precision data support, aiding scientists and decision-makers in making more accurate judgments and decisions. Additionally, drones can serve as temporary communication base stations in areas with poor communication, ensuring the transfer of crucial information. Drone area coverage technology is vital in improving work efficiency, reducing costs, and strengthening decision support. This paper aims to solve the optimization problem of multi-UAV area coverage flight path planning to enhance system efficiency and task execution capability. For multi-center optimization problems, a region decomposition method based on the Voronoi graph is designed, transforming the multi-UAV area coverage issue into the single-UAV area coverage problem, greatly simplifying the complexity and computational process. For the single-UAV area coverage problem and its corresponding area, this paper contrives a convolutional neural network with the channel and spatial attention mechanism (CSAM) to enhance feature fusion capability, enabling the model to focus on core features for solving single-UAV path selection and ultimately generating the optimal path. Simulation results demonstrate that the proposed method achieves excellent performance. [ABSTRACT FROM AUTHOR]

The rapid advancement of autonomous vehicle technology has brought into focus the critical need for enhanced road safety systems, particularly in the areas of road damage detection and surface classification. This paper explores these two essential components, highlighting their importance in autonomous driving. In the domain of road damage detection, this study explores a range of deep learning methods, particularly focusing on one-stage and two-stage detectors. These methodologies, including notable ones like YOLO and SSD for one-stage detection and Faster R-CNN for two-stage detection, are critically analyzed for their efficacy in identifying various road damages under diverse conditions. The review provides insights into their comparative advantages, balancing between real-time processing and accuracy in damage localization. For road surface classification, the paper investigates the classification techniques based on both environmental conditions and material road composition. It highlights the role of different convolutional neural network architectures and innovations at the neural level in enhancing classification accuracy under varying road and weather conditions. The main finding of this work is that it offers a comprehensive overview of the current state of the art, showcasing significant strides in utilizing deep learning for road analysis in autonomous vehicle systems. The study concludes by underscoring the importance of continued research in these areas to further refine and improve the safety and efficiency of autonomous driving. [ABSTRACT FROM AUTHOR]

To solve the problem of the Morlet wavelet transform not satisfying wavelet admissibility conditions, which results in fuzzy and aliasing time–frequency image features, this paper proposes an improved Morlet wavelet. The scale parameter is the wavelet's dominant frequency parameter. It largely satisfies the admissibility conditions and effectively improves the fuzzy aliasing effect of time–frequency image features. To further improve feature learning, this paper proposes a combined Morlet wavelet and residual network. The experimental results show that the accuracy of the proposed method is 10%, 4.5%, and 3% higher than that of LeNets, CNNs, and ResNets under varying load and noise disturbance levels, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a transformative explainable convolutional neural network (CNN) framework for cataract detection, utilizing a hybrid deep learning model combining Siamese networks with VGG16. By leveraging a learning rate scheduler and Grad-CAM (Gradient-weighted Class Activation Mapping) for explainability, the proposed model not only achieves high accuracy in identifying cataract-infected images but also provides interpretable visual explanations of its predictions. Performance evaluation metrics such as accuracy, precision, recall, and F1 score demonstrate the model's robustness, with a perfect accuracy of 100%. Grad-CAM visualizations highlight the key image regions—primarily around the iris and pupil—that contribute most to the model's decision-making, making the system more transparent for clinical use. Additionally, novel statistical analysis methods, including saliency map evaluation metrics like AUC (Area Under the Curve) and the Pointing Game, were employed to quantify the quality of the model's explanations. These metrics enhance the interpretability of the model and support its practical applicability in medical image analysis. This approach advances the integration of deep learning with explainable AI, offering a robust, accurate, and interpretable solution for cataract detection with the potential for broader adoption in ocular disease diagnosis and medical decision support systems. [ABSTRACT FROM AUTHOR]

This paper introduces a novel deep learning model for ECG signal classification using feature fusion. The proposed methodology transforms the ECG time series into a spectrogram image using a short-time Fourier transform (STFT). This spectrogram is further processed to generate a histogram of oriented gradients (HOG) and local binary pattern (LBP) features. Three separate 2D convolutional neural networks (CNNs) then analyze these three image representations in parallel. To enhance performance, the extracted features are concatenated before feeding them into a gated recurrent unit (GRU) model. The proposed approach is extensively evaluated on two ECG datasets (MIT-BIH + BIDMC and MIT-BIH) with three and five classes, respectively. The experimental results demonstrate that the proposed approach achieves superior classification accuracy compared to existing algorithms in the literature. This suggests that the model has the potential to be a valuable tool for accurate ECG signal classification, aiding in the diagnosis and treatment of various cardiovascular disorders. [ABSTRACT FROM AUTHOR]

This paper develops benchmark cases for low- and very-low-frequency passive acoustic source localization (ASL) using synthetic data. These cases can be potentially applied to the detection of turbulence-generated low-frequency acoustic emissions in the atmosphere. A deep learning approach is used as an alternative to conventional beamforming, which performs poorly under these conditions. The cases, which include two- and three-dimensional ASL, use a shallow and inexpensive convolutional neural network (CNN) with an appropriate input feature to optimize the source localization. CNNs are trained on a limited dataset to highlight the computational tractability and viability of the low-frequency ASL approach. Despite the modest training sets and computational expense, detection accuracies of at least 80% and far superior performance compared with beamforming are achieved—a result that can be improved with more data, training, and deeper networks. These benchmark cases offer well-defined and repeatable representative problems for comparison and further development of deep learning-based low-frequency ASL. [ABSTRACT FROM AUTHOR]

The steel manufacturing process is inherently continuous, meaning that if defects are not effectively detected in the initial stages, they may propagate through subsequent stages, resulting in high costs for corrections in the final product. Therefore, detecting surface defects and obtaining segmentation information is critical in the steel manufacturing industry to ensure product quality and enhance production efficiency. Specifically, segmentation information is essential for accurately understanding the shape and extent of defects, providing the necessary details for subsequent processes to address these defects. However, the time-consuming and costly process of generating segmentation annotations poses a significant barrier to practical industrial applications. This paper proposes a cost-efficient segmentation labeling framework that combines deep learning-based anomaly detection and label enhancement to address these challenges in the steel manufacturing process. Using ResNet-50, defects are classified, and faster region convolutional neural networks (faster R-CNNs) are employed to identify defect types and generate bounding boxes indicating the defect locations. Subsequently, recursive learning is performed using the GrabCut algorithm and the DeepLabv3+ model based on the generated bounding boxes, significantly reducing annotation costs by generating segmentation labels. The proposed framework effectively detects defects and accurately defines them, even in randomly collected images from the steel manufacturing process, contributing to both quality control and cost reduction. This study presents a novel approach for improving the quality of the steel manufacturing process and is expected to enhance overall efficiency in the steel manufacturing industry. [ABSTRACT FROM AUTHOR]

In the transition to fully automated driving, the interaction between drivers and vehicles is crucial as drivers' emotions directly influence their behavior, thereby impacting traffic safety. Currently, relying solely on a backbone based on a convolutional neural network (CNN) to extract single RGB modal facial features makes it difficult to capture enough semantic information. To address this issue, this paper proposes a Dual-branch Multimodal Fusion Network (DMFNet). DMFNet extracts semantic features from visible–infrared (RGB-IR) image pairs effectively capturing complementary information between two modalities and achieving a more accurate understanding of the drivers' emotional state at a global level. However, the accuracy of facial recognition is significantly affected by variations in the drivers' head posture and light environment. Thus, we further propose a U-Shape Reconstruction Network (URNet) to focus on enhancing and reconstructing the detailed features of RGB modes. Additionally, we design a Detail Enhancement Block (DEB) embedded in a U-shaped reconstruction network for high-frequency filtering. Compared with the original driver emotion recognition model, our method improved the accuracy by 18.77% on the DEFE++ dataset, proving the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Speech audiometry is a vital tool in assessing an individual's ability to perceive and comprehend speech, traditionally requiring specialized testing that can be time-consuming and resource -intensive. This paper approaches a novel use of deep learning to predict speech audiometry using pure-tone audiometry (PTA) data. By utilizing PTA data, which measure hearing sensitivity at specific frequencies, we aim to develop a model that can bypass the need for direct speech testing. This study investigates two neural network architectures: a multi-layer perceptron (MLP) and a one-dimensional convolutional neural network (1D-CNN). These models are trained to predict key speech audiometry outcomes, including speech recognition thresholds and speech discrimination scores. To evaluate the effectiveness of these models, we employed two key performance metrics: the coefficient of determination (R2) and mean absolute error (MAE). The MLP model demonstrated predictive solid power with an R2 score of 88.79% and an average MAE of 7.26, while the 1D-CNN model achieved a slightly higher level of accuracy with an MAE score of 88.35% and an MAE of 6.90. The superior performance of the 1D-CNN model suggests that it captures relevant features from PTA data more effectively than the MLP. These results show that both models hold promise for predicting speech audiometry, potentially simplifying the audiological evaluation process. This approach is applied in clinical settings for hearing loss assessment, the selection of hearing aids, and the development of personalized auditory rehabilitation programs. [ABSTRACT FROM AUTHOR]

Echocardiography (ECG) is a noninvasive technology that is widely used for recording heartbeats and diagnosing cardiac arrhythmias. However, interpreting ECG signals is challenging and may require substantial time from medical specialists. The evolution of technology and artificial intelligence has led to advances in the study and development of automatic arrhythmia classification systems to aid in medical diagnoses. Within this context, this paper introduces a framework for classifying cardiac arrhythmias on the basis of a multimodal convolutional neural network (CNN) with an adaptive attention mechanism. ECG signal segments are transformed into images via the Hilbert space-filling curve (HSFC) and recurrence plot (RP) techniques. The framework is developed and evaluated using the MIT-BIH public database in alignment with AAMI guidelines (ANSI/AAMI EC57). The evaluations accounted for interpatient and intrapatient paradigms, considering variations in the input structure related to the number of ECG leads (lead MLII and V1 + MLII). The results indicate that the framework is competitive with those in state-of-the-art studies, particularly for two ECG leads. The accuracy, precision, sensitivity, specificity and F1 score are 98.48%, 94.15%, 80.23%, 96.34% and 81.91%, respectively, for the interpatient paradigm and 99.70%, 98.01%, 97.26%, 99.28% and 97.64%, respectively, for the intrapatient paradigm. [ABSTRACT FROM AUTHOR]

This paper addresses the practical challenge of detecting tomato plant diseases using a hybrid lightweight model that combines a Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). Traditional image classification models demand substantial computational resources, limiting their practicality. This study aimed to develop a model that can be easily implemented on low-cost IoT devices while maintaining high accuracy with real-world images. The methodology leverages a CNN for extracting high-level image features and an RNN for capturing temporal relationships, thereby enhancing model performance. The proposed model incorporates a Closed-form Continuous-time Neural Network, a lightweight variant of liquid time-constant networks, and integrates Neural Circuit Policy to capture long-term dependencies in image patterns, reducing overfitting. Augmentation techniques such as random rotation and brightness adjustments were applied to the training data to improve generalization. The results demonstrate that the hybrid models outperform their single pre-trained CNN counterparts in both accuracy and computational cost, achieving a 97.15% accuracy on the test set with the proposed model, compared to around 94% for state-of-the-art pre-trained models. This study provides evidence of the effectiveness of hybrid CNN-RNN models in improving accuracy without increasing computational cost and highlights the potential of liquid neural networks in such applications. [ABSTRACT FROM AUTHOR]

This work was conducted mainly to provide a healthy and safe monitoring system for the elderly living in the home environment. In this paper, two different target fall detection schemes are proposed based on whether the target is visible or not. When the target is visible, a vision-based fall detection algorithm is proposed, where an image of the target captured by a camera is transmitted to the improved You Only Look Once version 5s (YOLOv5s) model for posture detection. In contrast, when the target is invisible, a WiFi-based fall detection algorithm is proposed, where channel state information (CSI) signals are used to estimate the target's posture with an improved long short-term memory (LSTM) model. In the improved YOLOv5s model, adaptive picture scaling technology named Letterbox is used to maintain consistency in the aspect ratio of images in the dataset, and the weighted bidirectional feature pyramid (BiFPN) and the attention mechanisms of squeeze-and-excitation (SE) and coordinate attention (CA) modules are added to the Backbone network and Neck network, respectively. In the improved LSTM model, the Hampel filter is used to eliminate the noise from CSI signals and the convolutional neural network (CNN) model is combined with the LSTM to process the image made from CSI signals, and thus the object of the improved LSTM model at a point in time is the analysis of the amplitude of 90 CSI signals. The final monitoring result of the health status of the target is the result of combining the fall detection of the improved YOLOv5s and LSTM models with the physiological information of the target. Experimental results show the following: (1) the detection precision, recall rate, and average precision of the improved YOLOv5s model are increased by 7.2%, 9%, and 7.6%, respectively, compared with the original model, and there is almost no missed detection of the target; (2) the detection accuracy of the improved LSTM model is improved by 15.61%, 29.36%, and 52.39% compared with the original LSTM, CNN, and neural network (NN) models, respectively, while the convergence speed is improved by 90% compared with the original LSTM model; and (3) the proposed algorithm can meet the requirements of accurate, real-time, and stable applications of health monitoring. [ABSTRACT FROM AUTHOR]

The combination of few-shot learning and graph neural networks can effectively solve the issue of extracting more useful information from limited data. However, most graph-based few-shot models only consider the global feature information extracted by the backbone during the construction process, while ignoring the dependency information hidden within the features. Additionally, the essence of graph convolution is the filtering of graph signals, and the majority of graph-based few-shot models construct fixed, single-property filters to process these graph signals. Therefore, in this paper, we propose an Adaptive Filtering Graph Convolutional Neural Network (AFGN) for few-shot classification. AFGN explores the hidden dependency information within the features, providing a new approach for constructing graph tasks in few-shot scenarios. Furthermore, we design an adaptive filter for the graph convolution of AFGN, which can adaptively adjust its strategy for acquiring high and low-frequency information from graph signals based on different few-shot episodic tasks. We conducted experiments on three standard few-shot benchmarks, including image recognition and fine-grained categorization. The experimental results demonstrate that our AFGN performs better compared to other state-of-the-art models. [ABSTRACT FROM AUTHOR]

This paper is concerned with an end-to-end electrocardiogram (ECG) signal transformation from a continuous-wave (CW) radar signal using a specialized deep learning model. For this purpose, the presented deep learning model is designed using convolutional neural networks (CNNs) and bidirectional long short-term memory (Bi-LSTM) with a maximum-overlap discrete wavelet transform (MODWT) layer and an adaptive neuro-fuzzy network (ANFN) layer. The proposed method has the advantage of developing existing deep networks and machine learning to reconstruct signals through CW radars to acquire ECG biological information in a non-contact manner. The fully connected (FC) layer of the CNN is replaced by an ANFN layer suitable for resolving black boxes and handling complex nonlinear data. The MODWT layer is activated via discrete wavelet transform frequency decomposition with maximum-overlap to extract ECG-related frequency components from radar signals to generate essential information. In order to evaluate the performance of the proposed model, we use a dataset of clinically recorded vital signs with a synchronized reference sensor signal measured simultaneously. As a result of the experiment, the performance is evaluated by the mean squared error (MSE) between the measured and reconstructed ECG signals. The experimental results reveal that the proposed model shows good performance in comparison to the existing deep learning model. From the performance comparison, we confirm that the ANFN layer preserves the nonlinearity of information received from the model by replacing the fully connected layer used in the conventional deep learning model. [ABSTRACT FROM AUTHOR]

In recent years, deep learning (DL) has garnered significant attention for its successful applications across various domains in solving complex problems. This interest has spurred the development of numerous neural network architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and the more recently introduced Transformers. The choice of architecture depends on the data characteristics and the specific task at hand. In the 1D domain, one-dimensional CNNs (1D CNNs) are widely used, particularly for tasks involving the classification and recognition of 1D signals. While there are many applications of 1D CNNs in the literature, the technical details of their training are often not thoroughly explained, posing challenges for those developing new libraries in languages other than those supported by available open-source solutions. This paper offers a comprehensive, step-by-step tutorial on deriving feedforward and backpropagation equations for 1D CNNs, applicable to both regression and classification tasks. By linking neural networks with linear algebra, statistics, and optimization, this tutorial aims to clarify concepts related to 1D CNNs, making it a valuable resource for those interested in developing new libraries beyond existing ones. [ABSTRACT FROM AUTHOR]

After significant progress in stereo matching, the pursuit of robust and efficient ill-posed-region disparity refinement methods remains challenging. To further improve the performance of disparity refinement, in this paper, we propose the matchability and uncertainty-aware iterative disparity refinement neural network. Firstly, a new matchability and uncertainty decoder (MUD) is proposed to decode the matchability mask and disparity uncertainties, which are used to evaluate the reliability of feature matching and estimated disparity, thereby reducing the susceptibility to mismatched pixels. Then, based on the proposed MUD, we present two modules: the uncertainty-preferred disparity field initialization (UFI) and the masked hidden state global aggregation (MGA) modules. In the UFI, a multi-disparity window scan-and-select method is employed to provide a further initialized disparity field and more accurate initial disparity. In the MGA, the adaptive masked disparity field hidden state is globally aggregated to extend the propagation range per iteration, improving the refinement efficiency. Finally, the experimental results on public datasets show that the proposed model achieves a reduction up to 17.9% in disparity average error and 16.9% in occluded outlier proportion, respectively, demonstrating its more practical handling of ill-posed regions. [ABSTRACT FROM AUTHOR]

Advanced video codecs such as High Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC) are vital for streaming high-quality online video content, as they compress and transmit data efficiently. However, these codecs can occasionally degrade video quality by adding undesirable artifacts such as blockiness, blurriness, and ringing, which can detract from the viewer's experience. To ensure a seamless and engaging video experience, it is essential to remove these artifacts, which improves viewer comfort and engagement. In this paper, we propose a deep feature fusion based convolutional neural network (CNN) architecture (VVC-PPFF) for post-processing approach to further enhance the performance of VVC. The proposed network, VVC-PPFF, harnesses the power of CNNs to enhance decoded frames, significantly improving the coding efficiency of the state-of-the-art VVC video coding standard. By combining deep features from early and later convolution layers, the network learns to extract both low-level and high-level features, resulting in more generalized outputs that adapt to different quantization parameter (QP) values. The proposed VVC-PPFF network achieves outstanding performance, with Bjøntegaard Delta Rate (BD-Rate) improvements of 5.81% and 6.98% for luma components in random access (RA) and low-delay (LD) configurations, respectively, while also boosting peak signal-to-noise ratio (PSNR). [ABSTRACT FROM AUTHOR]

This paper utilizes prevalent deep learning techniques, such as Convolutional Neural Networks (CNNs) and Residual Neural Networks (ResNets), along with the well-established machine learning technique, Random Forest, to efficiently distinguish between common lithologies including coal, sandstone, limestone, and others. This approach is highly significant for resource extraction—such as coal, oil, natural gas, and groundwater—by streamlining the process and minimizing the need for the time-consuming manual interpretation of geophysical logging data. The natural gamma ray, density, and resistivity log data were collected from 22 wells in the mountainous region of Southern Sichuan, China, yielding approximately 70,000 samples for developing lithofacies prediction models. All the models achieved around 80% accuracy in classifying carbonaceous lithologies and up to 88% accuracy in predicting other lithologies. The trained models were applied to the logging data in the validation dataset, and the outputs were validated against geological core data, showing overall consistency, although variations in the classification results were observed across different wells. These findings suggest that deep learning techniques have the potential to develop a general model for effectively handling lithology classification with well logging data. [ABSTRACT FROM AUTHOR]

Ischemic stroke lesion segmentation in MRI images represents significant challenges, particularly due to class imbalance between foreground and background pixels. Several approaches have been developed to achieve higher F1-Scores in stroke lesion segmentation under this challenge. These strategies include convolutional neural networks (CNN) and models that represent a large number of parameters, which can only be trained on specialized computational architectures that are explicitly oriented to data processing. This paper proposes a lightweight model based on the U-Net architecture that handles an attention module and the Generalized Dice Focal loss function to enhance the segmentation accuracy in the class imbalance environment, characteristic of stroke lesions in MRI images. This study also analyzes the segmentation performance according to the pixel size of stroke lesions, giving insights into the loss function behavior using the public ISLES 2015 and ISLES 2022 MRI datasets. The proposed model can effectively segment small stroke lesions with F1-Scores over 0.7, particularly in FLAIR, DWI, and T2 sequences. Furthermore, the model shows reasonable convergence with their 7.9 million parameters at 200 epochs, making it suitable for practical implementation on mid and high-end general-purpose graphic processing units. [ABSTRACT FROM AUTHOR]

With the rapid increase in the number of drivers, traffic accidents due to driver distraction is a major threat around the world. In this paper, we present a novel long-term recurrent convolutional network (LRCN) model for real-time driver activity recognition during both day- and nighttime conditions. Unlike existing works that use static input images and rely on major pre-processing measures, we employ a TimeDistributed convolutional neural network (TimeDis-CNN) layer to process a sequential input to learn the spatial and temporal information of the driver activity without requiring any major pre-processing effort. A pre-trained (CNN) layer is applied for robust initialization and extraction of the primary spatial features of the sequential image inputs. Then, a long short-term memory (LSTM) network is employed to recognize and synthesize the dynamical long-range temporal information of the driver's activity. The proposed system is capable of detecting nine types of driver activities: driving, drinking, texting, smoking, talking, controlling, looking outside, head nodding, and fainting. For evaluation, we utilized a real vehicle environment and collected data from 35 participants, where 14 of the drivers were in real driving scenarios and the remaining in non-driving conditions. The proposed model achieved accuracies of 88.7% and 92.4% for the daytime and nighttime datasets, respectively. Moreover, the binary classifier's accuracy in determining whether the driver is non-distracted or in a distracted state was 93.9% and 99.2% for the daytime and nighttime datasets, respectively. In addition, we deployed the proposed model on a Jetson Xavier embedded board and verified its effectiveness by conducting real-time predictions. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) signals are a measure minute electrical signals generated during the cardiac cycle, a biometric signal that occurs during vital human activity. ECG signals are susceptible to various types of noise depending on the data acquisition conditions, with factors such as sensor placement and the physiological and mental states of the subject contributing to the diverse shapes of these signals. When the data are acquired in a single session, the environmental variables are relatively similar, resulting in similar ECG signals; however, in subsequent sessions, even for the same person, changes in the environmental variables can alter the signal shape. This phenomenon poses challenges for person identification using ECG signals acquired on different days. To improve the performance of individual identification, even when ECG data is acquired on different days, this paper proposes an ensemble deep neural network for person identification by comparing and analyzing the ECG recognition performance under various conditions. The proposed ensemble deep neural network comprises three streams that incorporate two well-known pretrained models. Each network receives the time-frequency representation of ECG signals as input, and a stream reuses the same network structure under different learning conditions with or without data augmentation. The proposed ensemble deep neural network was validated on the Physikalisch-Technische Bundesanstalt dataset, and the results confirmed a 3.39% improvement in accuracy compared to existing methods. [ABSTRACT FROM AUTHOR]

The convolutional neural network (CNN) has been widely applied in medical image segmentation due to its outstanding nonlinear expression ability. However, applications of CNN are often limited by the receptive field, preventing it from modeling global dependencies. The recently proposed transformer architecture, which uses a self-attention mechanism to model global context relationships, has achieved promising results. Swin-Unet is a Unet-like simple transformer semantic segmentation network that combines the dominant feature of both the transformer and Unet. Even so, Swin-Unet has some limitations, such as only learning single-scale contextual features, and it lacks inductive bias and effective multi-scale feature selection for processing local information. To solve these problems, the Residual Local induction bias-Unet (RL-Unet) algorithm is proposed in this paper. First, the algorithm introduces a local induction bias module into the RLSwin-Transformer module and changes the multi-layer perceptron (MLP) into a residual multi-layer perceptron (Res-MLP) module to model local and remote dependencies more effectively and reduce feature loss. Second, a new densely connected double up-sampling module is designed, which can further integrate multi-scale features and improve the segmentation accuracy of the target region. Third, a novel loss function is proposed that can significantly enhance the performance of multiple scales segmentation and the segmentation results for small targets. Finally, experiments were conducted using four datasets: Synapse, BraTS2021, ACDC, and BUSI. The results show that the performance of RL-Unet is better than that of Unet, Swin-Unet, R2U-Net, Attention-Unet, and other algorithms. Compared with them, RL-Unet produces significantly a lower Hausdorff Distance at 95% threshold (HD95) and comparable Dice Similarity Coefficient (DSC) results. Additionally, it exhibits higher accuracy in segmenting small targets. [ABSTRACT FROM AUTHOR]

Indoor occupancy detection (IOD) via Wi-Fi sensing capitalizes on the varying patterns in CSI (Channel State Information) to estimate the number of people in a given area. However, the precision of such systems heavily depends on the quality of the CSI data, which can be degraded by noise and environmental factors. To address this issue, In this paper, we present a CSI preprocessing method to improve the accuracy of IOD systems using Wi-Fi sensing. Unlike existing preprocessing methods that use computationally complex signal processing or statistical techniques, we expand the dimension of CSI amplitude data into a three-channel vector through nonlinear transformation to amplify subtle differences between CSI data belonging to a different number of people. By drawing clearer boundaries between CSI data distributions belonging to a different number of people in a monitored area, our method improves the people-counting accuracy of a Wi-Fi sensing system. To ensure temporal consistency and improve data quality, we discretize the CSI measurements based on their transmission periods and aggregate consecutive measurements over a given time interval. These samples are then fed into a Convolutional Neural Network (CNN) specifically trained for the IOD task. Experimental results in diverse real-world scenarios verify that compared to the traditional methods, the enhanced feature representation capability of our approach leads to more accurate and robust sensing outcomes even in the most resource-constrained environment, where a commercial off-the-shelf CSI capture machine with only one antenna is used when a Wi-Fi sender with one transmit antenna sends packets periodically to the channel with the smallest Wi-Fi channel bandwidth. [ABSTRACT FROM AUTHOR]

Conducting the remaining useful life (RUL) prediction for an aircraft engines is of significant importance in enhancing aircraft operation safety and formulating reasonable maintenance plans. Addressing the issue of low prediction model accuracy due to traditional neural networks' inability to fully extract key features, this paper proposes an engine RUL prediction model based on the adaptive moment estimation (Adam) optimized self-attention mechanism–temporal convolutional network (SAM-TCN) neural network. Firstly, the raw data monitored by sensors are normalized, and RUL labels are set. A sliding window is utilized for overlapping sampling of the data, capturing more temporal features while eliminating data dimensionality. Secondly, the SAM-TCN neural network prediction model is constructed. The temporal convolutional network (TCN) neural network is used to capture the temporal dependency between data, solving the mapping relationship of engine degradation characteristics. A self-attention mechanism (SAM) is employed to adaptively assign different weight contributions to different input features. In the experiments, the root mean square error (RMSE) values on four datasets are 11.50, 16.45, 11.62, and 15.47 respectively. These values indicate further reduction in errors compared to methods reported in other literature. Finally, the SAM-TCN prediction model is optimized using the Adam optimizer to improve the training effectiveness and convergence speed of the model. Experimental results demonstrate that the proposed method can effectively learn feature data, with prediction accuracy superior to other models. [ABSTRACT FROM AUTHOR]

Artificial intelligence technologies based on deep convolutional neural networks and large language models have made significant breakthroughs in many tasks, such as image recognition, target detection, semantic segmentation, and natural language processing, but also face a conflict between the high computational capacity of the algorithms and limited deployment resources. Quantization, which converts floating-point neural networks into low-bit-width integer networks, is an important and essential technique for efficient deployment and cost reduction in edge computing. This paper analyzes various existing quantization methods, showcases the deployment accuracy of advanced techniques, and discusses the future challenges and trends in this domain. [ABSTRACT FROM AUTHOR]

With the proliferation of the Internet, network complexities for both commercial and state organizations have significantly increased, leading to more sophisticated and harder-to-detect network attacks. This evolution poses substantial challenges for intrusion detection systems, threatening the cybersecurity of organizations and national infrastructure alike. Although numerous deep learning techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph neural networks (GNNs) have been applied to detect various network attacks, they face limitations due to the lack of standardized input data, affecting model accuracy and performance. This paper proposes a novel preprocessing method for flow data from network intrusion detection systems (NIDSs), enhancing the efficacy of a graph neural network model in malicious flow detection. Our approach initializes graph nodes with data derived from flow features and constructs graph edges through the analysis of IP relationships within the system. Additionally, we propose a new graph model based on the combination of the graph neural network (GCN) model and SAGEConv, a variant of the GraphSAGE model. The proposed model leverages the strengths while addressing the limitations encountered by the previous models. Evaluations on two IDS datasets, CICIDS-2017 and UNSW-NB15, demonstrate that our model outperforms existing methods, offering a significant advancement in the detection of network threats. This work not only addresses a critical gap in the standardization of input data for deep learning models in cybersecurity but also proposes a scalable solution for improving the intrusion detection accuracy. [ABSTRACT FROM AUTHOR]

Network-security situation prediction is a crucial aspect in the field of network security. It is primarily achieved through monitoring network behavior and identifying potential threats to prevent and respond to network attacks. In order to enhance the accuracy of situation prediction, this paper proposes a method that combines a convolutional neural network (CNN) and a gated recurrent unit (GRU), while also incorporating an attention mechanism. The model can simultaneously handle the spatial and temporal features of network behavior and optimize the weight allocation of features through the attention mechanism. Firstly, the CNN's powerful feature extraction ability is utilized to extract the spatial features of the network behavior. Secondly, time-series features of network behavior are processed through the GRU layer. Finally, to enhance the model's performance further, we introduce attention mechanisms, which can dynamically adjust the importance of different features based on the current context information; this enables the model to focus more on critical information for accurate predictions. The experimental results show that the network-security situation prediction method, which combines a CNN and a GRU and introduces an attention mechanism, performs well in terms of the fitting effect and can effectively enhance the accuracy of situation prediction. [ABSTRACT FROM AUTHOR]

Facial expression recognition has wide application prospects in many occasions. Due to the complexity and variability of facial expressions, facial expression recognition has become a very challenging research topic. This paper proposes a Vision Transformer expression recognition method based on hybrid local attention (HLA-ViT). The network adopts a dual-stream structure. One stream extracts the hybrid local features and the other stream extracts the global contextual features. These two streams constitute a global–local fusion attention. The hybrid local attention module is proposed to enhance the network's robustness to face occlusion and head pose variations. The convolutional neural network is combined with the hybrid local attention module to obtain feature maps with local prominent information. Robust features are then captured by the ViT from the global perspective of the visual sequence context. Finally, the decision-level fusion mechanism fuses the expression features with local prominent information, adding complementary information to enhance the network's recognition performance and robustness against interference factors such as occlusion and head posture changes in natural scenes. Extensive experiments demonstrate that our HLA-ViT network achieves an excellent performance with 90.45% on RAF-DB, 90.13% on FERPlus, and 65.07% on AffectNet. [ABSTRACT FROM AUTHOR]

Detecting instruments in a music signal is often used in database indexing, song annotation, and creating applications for musicians and music producers. Therefore, effective methods that automatically solve this issue need to be created. In this paper, the mentioned task is solved using mel-frequency cepstral coefficients (MFCC) and various architectures of artificial neural networks. The authors' contribution to the development of automatic instrument detection covers the methods used, particularly the neural network architectures and the voting committees created. All these methods were evaluated, and the results are presented and discussed in the paper. The proposed automatic instrument detection methods show that the best classification quality was obtained for an extensive model, which is the so-called committee of voting classifiers. [ABSTRACT FROM AUTHOR]

The vibration signals collected by acceleration sensors are interspersed with noise interference, which increases the difficulty of fault diagnosis for rolling bearings. For this reason, a rolling bearing fault diagnosis method based on complete ensemble empirical model decomposition with adaptive noise (CEEMDAN) and improved convolutional neural network (CNN) is proposed. Firstly, the original vibration signal is decomposed into a series of intrinsic modal function (IMF) components using the CEEMDAN algorithm, the components are filtered according to the correlation coefficients and the signals are reconstructed. Secondly, the reconstructed signals are converted into a two-dimensional grey-scale map and input into a convolutional neural network to extract the features. Lastly, the features are inputted into a support vector machine (SVM) with the optimised parameters of the grey wolf optimiser (GWO) to perform the identification and classification. The experimental results show that the rolling bearing fault diagnosis method based on CEEMDAN and CNN-SVM proposed in this paper can significantly reduce the noise interference, and its average fault diagnosis accuracy is as high as 99.25%. Therefore, it is feasible to apply it in the field of rolling bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

Facial expression recognition plays an increasingly important role in daily life, and it is used in several areas of human–computer interaction, such as robotics, assisted driving, and intelligent tutoring systems. However, the current mainstream methods are based on the whole face, and do not consider the existence of expression asymmetry between the left and right half-face. Hence, the accuracy of facial expression recognition needs to be improved. In this paper, we propose a half-face self-attention weighted approach called HSAW. Using statistical analysis and computer vision techniques, we found that the left half-face contains richer expression features than the right half-face. Specifically, we employed a self-attention mechanism to assign different weights to the left and right halves of the face. These weights are combined with convolutional neural network features for improved facial expression recognition. Furthermore, to attack the presence of uncertain categories in the dataset, we introduce adaptive re-labeling module, which can improve the recognition accuracy. Extensive experiments conducted on the FER2013 and RAF datasets have verified the effectiveness of the proposed method, which utilizes fewer parameters. [ABSTRACT FROM AUTHOR]

This paper presents a novel use of a bio-inspired retina model as a scene preprocessing stage for the recognition of letters and numbers on Chilean vehicle license plates. The goal is to improve the effectiveness and ease of pattern recognition. Inspired by the responses of mammalian retinas, this retinal model reproduces both the natural adjustment of contrast and the enhancement of object contours by parvocellular cells. Among other contributions, this paper provides an in-depth exploration of the architecture, advantages, and limitations of the model; investigates the tuning parameters of the model; and evaluates its performance when integrating a convolutional neural network and a spiking neural network into an optical character recognition (OCR) algorithm, using 40 different genuine license plate images as a case study and for testing. The results obtained demonstrate the reduction of error rates in character recognition based on convolutional neural networks (CNNs), spiking neural networks (SNNs), and OCR. It is concluded that this bio-inspired retina model offers a wide spectrum of potential applications to further explore, including motion detection, pattern recognition, and improvement of dynamic range in images, among others. [ABSTRACT FROM AUTHOR]

Automatic Container Code Recognition (ACCR) is critical for enhancing the efficiency of container terminals. However, existing ACCR methods frequently fail to achieve satisfactory performance in complex environments at port gates. In this paper, we propose an approach for accurate, fast, and compact container code recognition by utilizing YOLOv4 for container region localization and Deeplabv3+ for character recognition. To enhance the recognition speed and accuracy of YOLOv4 and Deeplabv3+, and to facilitate their deployment at gate entrances, we introduce several improvements. First, we optimize the feature-extraction process of YOLOv4 and Deeplabv3+ to reduce their computational complexity. Second, we enhance the multi-scale recognition and loss functions of YOLOv4 to improve the accuracy and speed of container region localization. Furthermore, we adjust the dilated convolution rates of the ASPP module in Deeplabv3+. Finally, we replace two upsampling structures in the decoder of Deeplabv3+ with transposed convolution upsampling and sub-pixel convolution upsampling. Experimental results on our custom dataset demonstrate that our proposed method, C-YOLOv4, achieves a container region localization accuracy of 99.76% at a speed of 56.7 frames per second (FPS), while C-Deeplabv3+ achieves an average pixel classification accuracy (MPA) of 99.88% and an FPS of 11.4. The overall recognition success rate and recognition speed of our approach are 99.51% and 2.3 ms per frame, respectively. Moreover, C-YOLOv4 and C-Deeplabv3+ outperform existing methods in complex scenarios. [ABSTRACT FROM AUTHOR]

As an advanced detection technique, electrical resistive tomography (ERT) has been applied to detect the solid–liquid two-phase flow velocity based on available ERT measurements. The flow velocity computation by ERT must depend on the relative algorithms, including both the cross-correlation (CC) principle and convolutional neural networks (CNNs). However, these two types of algorithms have poor accuracy and generalization under complex measuring conditions and various flow patterns. To address this issue, in this paper, a hybrid network is proposed that combines a CNN with a reproducing kernel-based support vector machine (RKSVM) technique. The features hidden in ERT measurements are extracted using the CNN, and then the flow velocity is computed by the RKSVM in a high-dimensional feature space. According to the ERT measurements in an actual experimental platform, the results show that the hybrid network has higher accuracy and generalization ability for flow velocity computation compared with the existing CC, RKSVM, and CNN methods. [ABSTRACT FROM AUTHOR]

Existing deep learning-based seismic signal denoising methods primarily operate in the time domain. Those methods are ineffective when noise overlaps with the seismic signal in the time domain. Time–frequency domain-based deep learning methods are relatively rare and usually employ single loss function, resulting in suboptimal performance on low SNR signals and potential damage to P wave. This paper proposes a method based on generative adversarial networks (GANs). Compared to convolutional neural networks, the discriminator in GANs helps retain more true signal details by judging denoising performance. Additionally, an attention mechanism is introduced to fully extract signal features, and a perceptual loss is employed to evaluate the difference between the denoised result and the target's high-level features. Experimental results show that this method can effectively improve SNR and ensure that the denoised result is close to the true signal. Furthermore, by comparing DeepDenoiser and ARDU, it is proven that the proposed method achieves better denoising performance, especially for low SNR signals, while causing less damage to the seismic signals. [ABSTRACT FROM AUTHOR]

This study compares the performance of graph convolutional neural network (GCN) models with conventional natural language processing (NLP) models for classifying scientific literature related to radio frequency electromagnetic field (RF-EMF). Specifically, the study examines two GCN models: BertGCN and the citation-based GCN. The study concludes that the model achieves consistently good performance when the input text is long enough, based on the attention mechanism of BERT. When the input sequence is short, the composition parameter  λ , which combines output values of the two subnetworks of BertGCN, plays a crucial role in achieving high classification accuracy. As the value of  λ  increases, the classification accuracy also increases. The study also proposes and tests a simplified variant of BertGCN, revealing performance differences among the models under two different data conditions by the existence of keywords. This study has two main contributions: (1) the implementation and testing of a variant of BertGCN and citation-based GCN for document classification tasks related to radio frequency electromagnetic fields publications, and (2) the confirmation of the impact of model conditions, such as the existence of keywords and input sequence length, in the original BertGCN. Although this study focused on a specific domain, our approaches have broader implications that extend beyond scientific publications to general text classification. [ABSTRACT FROM AUTHOR]

This document is the closing editorial for a special issue of the journal Applied Sciences on computer vision and pattern recognition based on deep learning. The issue includes 31 papers covering various topics such as image and video processing, object detection, object and scene recognition, visual application technologies, classification, segmentation, compression, and more. Each paper explores different methods and techniques to improve the performance and accuracy of deep learning models in these areas. The document provides a brief summary of each paper, highlighting their contributions and findings. [Extracted from the article]

Monitoring the condition of the grinding wheel in real-time during the grinding process is crucial as it directly impacts the precision and quality of the workpiece. Deep learning technology plays a vital role in analyzing the changes in sensor signals and identifying grinding wheel wear during the grinding process. Therefore, this paper innovatively proposes a grinding wheel wear recognition method based on Variational Mode Decomposition (VMD) denoising and Aquila Optimizer—Convolutional Neural Network—Long Short-Term Memory (AO-CNN-LSTM). The paper utilizes Acoustic Emission (AE) signals generated during grinding to identify the condition of the grinding wheel. To address noise interference, the study introduces the VMD algorithm for denoising the sample dataset, enhancing the effectiveness of neural network training. Subsequently, the dataset is fed into the designed Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM) structure with AO-optimized parameters. Experimental results demonstrate that this method achieves high accuracy and performance. [ABSTRACT FROM AUTHOR]

Current research on scene text recognition primarily focuses on languages with abundant linguistic resources, such as English and Chinese. In contrast, there is relatively limited research dedicated to low-resource languages. Advanced methods for scene text recognition often employ Transformer-based architectures. However, the performance of Transformer architectures is suboptimal when dealing with low-resource datasets. This paper proposes a Collaborative Encoding Method for Scene Text Recognition in the low-resource Uyghur language. The encoding framework comprises three main modules: the Filter module, the Dual-Branch Feature Extraction module, and the Dynamic Fusion module. The Filter module, consisting of a series of upsampling and downsampling operations, performs coarse-grained filtering on input images to reduce the impact of scene noise on the model, thereby obtaining more accurate feature information. The Dual-Branch Feature Extraction module adopts a parallel structure combining Transformer encoding and Convolutional Neural Network (CNN) encoding to capture local and global information. The Dynamic Fusion module employs an attention mechanism to dynamically merge the feature information obtained from the Transformer and CNN branches. To address the scarcity of real data for natural scene Uyghur text recognition, this paper conducted two rounds of data augmentation on a dataset of 7267 real images, resulting in 254,345 and 3,052,140 scene images, respectively. This process partially mitigated the issue of insufficient Uyghur language data, making low-resource scene text recognition research feasible. Experimental results demonstrate that the proposed collaborative encoding approach achieves outstanding performance. Compared to baseline methods, our collaborative encoding approach improves accuracy by 14.1%. [ABSTRACT FROM AUTHOR]

Long Short-Term Memory (LSTM)-Based Dog Activity Detection Using Accelerometer and Gyroscope. The third paper, authored by Jeong et al. [[14]], introduced a fall detection system that combines a simple threshold method (STM) and LSTM, creating the STM-LSTM-based fall detection system. With rapid advancements in artificial intelligence (AI), the Internet of Things (IOTs), and communication networks, the future of information and communication engineering (ICE) promises remarkable opportunities and challenges. 10.3390/app12199801 18 Zhang M., Wang C., Zhu W., Shen Y. An Intelligent DOA Estimation Error Calibration Method Based on Transfer Learning. [Extracted from the article]

In the rapidly evolving field of cybersecurity, the integration of multi-source, heterogeneous, and fragmented data into a coherent knowledge graph has garnered considerable attention. Such a graph elucidates semantic interconnections, thereby facilitating sophisticated analytical decision support. Central to the construction of a cybersecurity knowledge graph is Named Entity Recognition (NER), a critical technology that converts unstructured text into structured data. The efficacy of NER is pivotal, as it directly influences the integrity of the knowledge graph. The task of NER in cybersecurity, particularly within the Chinese linguistic context, presents distinct challenges. Chinese text lacks explicit space delimiters and features complex contextual dependencies, exacerbating the difficulty in discerning and categorizing named entities. These linguistic characteristics contribute to errors in word segmentation and semantic ambiguities, impeding NER accuracy. This paper introduces a novel NER methodology tailored for the Chinese cybersecurity corpus, termed CSBERT-IDCNN-BiLSTM-CRF. This approach harnesses Iterative Dilated Convolutional Neural Networks (IDCNN) for extracting local features, and Bi-directional Long Short-Term Memory networks (BiLSTM) for contextual understanding. It incorporates CSBERT, a pre-trained model adept at processing few-shot data, to derive input feature representations. The process culminates with Conditional Random Fields (CRF) for precise sequence labeling. To compensate for the scarcity of publicly accessible Chinese cybersecurity datasets, this paper synthesizes a bespoke dataset, authenticated by data from the China National Vulnerability Database, processed via the YEDDA annotation tool. Empirical analysis affirms that the proposed CSBERT-IDCNN-BiLSTM-CRF model surpasses existing Chinese NER frameworks, with an F1-score of 87.30% and a precision rate of 85.89%. This marks a significant advancement in the accurate identification of cybersecurity entities in Chinese text, reflecting the model's robust capability to address the unique challenges presented by the language's structural intricacies. [ABSTRACT FROM AUTHOR]

We present in this paper the state of the art and an analysis of recent research work and achievements performed in the domain of AI-based and vision-based systems for helping blind and visually impaired people (BVIP). We start by highlighting the recent and tremendous importance that AI has acquired following the use of convolutional neural networks (CNN) and their ability to solve image classification tasks efficiently. After that, we also note that VIP have high expectations about AI-based systems as a possible way to ease the perception of their environment and to improve their everyday life. Then, we set the scope of our survey: we concentrate our investigations on the use of CNN or related methods in a vision-based system for helping BVIP. We analyze the existing surveys, and we study the current work (a selection of 30 case studies) using several dimensions such as acquired data, learned models, and human–computer interfaces. We compare the different approaches, and conclude by analyzing future trends in this domain. [ABSTRACT FROM AUTHOR]