Search

To explore whether the brain contains pattern differences in the rock–paper–scissors (RPS) imagery task, this paper attempts to classify this task using fNIRS and deep learning. In this study, we designed an RPS task with a total duration of 25 min and 40 s, and recruited 22 volunteers for the experiment. We used the fNIRS acquisition device (FOIRE-3000) to record the cerebral neural activities of these participants in the RPS task. The time series classification (TSC) algorithm was introduced into the time-domain fNIRS signal classification. Experiments show that CNN-based TSC methods can achieve 97% accuracy in RPS classification. CNN-based TSC method is suitable for the classification of fNIRS signals in RPS motor imagery tasks, and may find new application directions for the development of brain–computer interfaces (BCI).

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that make the digitization of documents viable. Since the advent of deep learning, deep learning-based object detection performance has improved many folds. This work outlines and summarizes the deep learning approaches for detecting graphical page objects in document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

High-precision and rapid detection of apparent defects in subway tunnel linings is crucial for ensuring the structural integrity of tunnels and the safety of train operations. However, current methods often do not adequately account for the spatial characteristics of these defects and perform poorly in detecting and extracting small-scale defects, which limits the accuracy of detection and geometric parameter extraction. To address these challenges, this paper proposes an efficient algorithm for detecting and extracting apparent defects in subway tunnels. Firstly, YOLOv8 was selected as the foundational architecture due to its comprehensive performance. The coordinate attention module and Bottleneck Transformer 3 were then integrated into the model’s backbone to enhance the focus on defect-prone areas and improve the learning of feature relationships between defects and other infrastructure. Subsequently, a high-resolution detection layer was added to the model’s head to further improve sensitivity to subtle defects. Additionally, a low-quality crack dataset was created using an open access dataset, and transfer learning combined with Real-ESRGAN was employed to enhance the detail and resolution of fine cracks. The results of the field experiments demonstrate that the proposed model significantly improves detection accuracy in high-incidence areas and for small-scale defects, achieving a mean average precision (mAP) of 87% in detecting cracks, leakage, exfoliation, and related infrastructure defects. Furthermore, the crack enhancement techniques substantially improve the representation of fine-crack details, increasing feature extraction accuracy by a factor of four. The findings of this paper could provide crucial technical support for the automated operation and maintenance of metro tunnels.

The current object detection algorithm based on CNN makes it difficult to effectively capture the characteristics of subtle defects in online industrial product packaging bags. These defects are often visually similar to the texture or background of normal product packaging bags, and the model cannot effectively distinguish them. In order to deal with these challenges, this paper optimizes and improves the network structure based on YOLOv8 to achieve accurate identification of defects. First, in order to solve the long-tail distribution problem of data, a fuzzy search data enhancement algorithm is introduced to effectively increase the number of samples. Secondly, a joint network of FasterNet and SPD-Conv is proposed to replace the original backbone network of YOLOv8, which effectively reduces the computing load and improves the accuracy of defect identification. In addition, in order to further improve the performance of multiscale feature fusion, a weighted bidirectional feature pyramid network (BiFPN) is introduced, which effectively enhances the model’s ability to detect defects at different scales through the fusion of deep information and shallow information. Finally, in order to reduce the sensitivity of the defect position deviation, the NWD loss function is used to optimize the positioning performance of the model better and reduce detection errors caused by position errors. Experimental results show that the FSNB_YOLOv8 model proposed in this paper can reach 98.8% mAP50 accuracy. This success not only verifies the effectiveness of the optimization and improvement of this article’s model but also provides an efficient and accurate solution for surface defect detection of industrial product packaging bags on artificial assembly systems.

There are numerous methods for detecting interturn faults (ITFs) in the field winding of synchronous machines (SMs). One effective approach is based on comparing theoretical and measured excitation currents. This method is unaffected by rotor temperature in static excitation SMs. However, this paper investigates the influence of rotor temperature in brushless synchronous machines (BSMs), where rotor temperature significantly impacts the exciter excitation current. Extensive experimental tests were conducted on a special BSM with measurable rotor temperature. Given the challenges of measuring rotor temperature in industrial machines, this paper explores the feasibility of using stator temperature in the exciter field current estimation model. The theoretical exciter field current is calculated using a deep neural network (DNN), which incorporates electrical brushless synchronous generator output values and stator temperature, and it is subsequently compared with the measured exciter field current. This method achieves an error rate below 0.5% under healthy conditions, demonstrating its potential for simple implementation in industrial BSMs for ITF detection.

Framing theory is a widely accepted theoretical framework in the field of news communication studies, frequently employed to analyze the content of news reports. This paper innovatively introduces framing theory into the text summarization task and proposes a news text summarization method based on framing theory to address the global context of rapidly increasing speed and scale of information dissemination. Traditional text summarization methods often overlook the implicit deep-level semantic content and situational frames in news texts, and the method proposed in this paper aims to fill this gap. Our deep learning-based news frame identification module can automatically identify frame elements in the text and predict the dominant frame of the text. The frame-aware summarization generation model (FrameSum) can incorporate the identified frame feature into the text representation and attention mechanism, ensuring that the generated summary focuses on the core content of the news report while maintaining high information coverage, readability, and objectivity. Through empirical studies on the standard CNN/Daily Mail dataset, we found that this method performs significantly better in improving summary quality and maintaining the accuracy of news facts.

In order to improve the precision of phase recognition and reduce the rate of misdetection, this paper applies the deep learning method to automatic phase recognition. In this paper, an automatic seismic phase recognition model based on the Bi-LSTM network is designed. To test the performance of this model, the STEAD dataset is used for training and testing, and this model is compared with the traditional STA/LTA and AIC methods. The experimental results show that, compared to STA/LTA and AIC methods, the Bi-LSTM network can reduce the misdetection rate by about 8–15%, and improve the RSEM; especially, the prediction error of S-wave is greatly reduced.

Text matching promotes the research and application of deep understanding of text information, and it provides the basis for information retrieval, recommendation systems and natural language processing by exploring the similar structures in text data. Owning to the outstanding performance and automatically extract text features for the target, the methods based-pre-training models gradually become the mainstream. However, such models usually suffer from the disadvantages of slow retrieval speed and low running efficiency. On the other hand, previous text matching algorithms have mainly focused on horizontal domain research, and there are relatively few vertical domain algorithms for agricultural text, which need to be further investigated. To address this issue, a second-order text matching algorithm has been developed. This paper first obtains a large amount of text about typical agricultural crops and constructs a database by using web crawlers and querying relevant textbooks, etc. Then BM25 algorithm is used to generate a candidate set and BERT model is used to filter the optimal match based on the candidate set. Experiments have shown that the Precision@1 of this second-order algorithm can reach 88.34% on the dataset constructed in this paper, and the average time to match a piece of text is only 2.02 s. Compared with BERT model and BM25 algorithm, there is an increase of 8.81% and 13.73% in Precision@1 respectively. In terms of the average time required for matching a text, it is 55.2 s faster than BERT model and only 2 s slower than BM25 algorithm. It can improve the efficiency and accuracy of agricultural information retrieval, agricultural decision support, agricultural market analysis, etc., and promote the sustainable development of agriculture.

The integration of edge computing with IoT (EC-IoT) systems provides significant improvements in addressing security and privacy challenges in IoT networks. This paper examines the combination of EC-IoT and artificial intelligence (AI), highlighting practical strategies to improve data and network security. The published literature has suggested decentralized and reliable trust measurement mechanisms and security frameworks designed explicitly for IoT-enabled systems. Therefore, this paper reviews the latest attack models threatening EC-IoT systems and their impacts on IoT networks. It also examines AI-based methods to counter these security threats and evaluates their effectiveness in real-world scenarios. Finally, this survey aims to guide future research by stressing the need for scalable, adaptable, and robust security solutions to address evolving threats in EC-IoT environments, focusing on the integration of AI to enhance the privacy, security, and efficiency of IoT systems while tackling the challenges of scalability and resource limitations.

Human action recognition has many application prospects in human-computer interactions, innovative furniture, healthcare, and other fields. The traditional human motion recognition methods have limitations in privacy protection, complex environments, and multi-person scenarios. Millimeter-wave radar has attracted attention due to its ultra-high resolution and all-weather operation. Many existing studies have discussed the application of millimeter-wave radar in single-person scenarios, but only some have addressed the problem of action recognition in multi-person scenarios. This paper uses a commercial millimeter-wave radar device for human action recognition in multi-person scenarios. In order to solve the problems of severe interference and complex target segmentation in multiplayer scenarios, we propose a filtering method based on millimeter-wave inter-frame differences to filter the collected human point cloud data. We then use the DBSCAN algorithm and the Hungarian algorithm to segment the target, and finally input the data into a neural network for classification. The classification accuracy of the system proposed in this paper reaches 92.2% in multi-person scenarios through experimental tests with the five actions we set.

When people tell lies, they often exhibit tension and emotional fluctuations, reflecting a complex psychological state. However, the scarcity of labeled data in datasets and the complexity of deception information pose significant challenges in extracting effective lie features, which severely restrict the accuracy of lie detection systems. To address this, this paper proposes a semi-supervised lie detection algorithm based on integrating multiple speech emotional features. Firstly, Long Short-Term Memory (LSTM) and Auto Encoder (AE) network process log Mel spectrogram features and acoustic statistical features, respectively, to capture the contextual links between similar features. Secondly, the joint attention model is used to learn the complementary relationship among different features to obtain feature representations with richer details. Lastly, the model combines the unsupervised loss Local Maximum Mean Discrepancy (LMMD) and supervised loss Jefferys multi-loss optimization to enhance the classification performance. Experimental results show that the algorithm proposed in this paper achieves better performance.

The accurate distribution of joints on the tunnel face is crucial for assessing the stability and safety of surrounding rock during tunnel construction. This paper introduces the Mask R-CNN image segmentation algorithm, a state-of-the-art deep learning model, to achieve efficient and accurate identification and extraction of joints on tunnel face images. First, digital images of tunnel faces were captured and stitched, resulting in 286 complete images suitable for analysis. Then, the joints on the tunnel face were extracted using traditional image processing algorithms, the commonly used U-net image segmentation model, and the Mask R-CNN image segmentation model introduced in this paper to address the lack of recognition accuracy. Finally, the extraction results obtained by the three methods were compared. The comparison results show that the joint extraction method based on the Mask R-CNN image segmentation deep learning model introduced in this paper achieved the best joint extraction effect with a Dice similarity coefficient of 87.48%, outperforming traditional methods and the U-net model, which scored 60.59% and 75.36%, respectively, realizing accurate and efficient acquisition of tunnel face rock joints. These findings suggest that the Mask R-CNN model can be effectively implemented in real-time monitoring systems for tunnel construction projects.

Rockburst is an extremely hazardous geological disaster. In order to accurately predict the hazardous degree of rockbursts, this paper proposes eight new classification models for predicting the intensity level of rockbursts based on intelligent optimisation algorithms and deep learning techniques and collects 287 sets of real rockburst data to form a sample database, in which six quantitative indicators are selected as feature parameters. In order to validate the effectiveness of the constructed eight machine learning prediction models, the study selected Accuracy, Precision, Recall and F1 Score to evaluate the prediction performance of each model. The results show that the NGO-CNN-BiGRU-Attention model has the best prediction performance, with an accuracy of 0.98. Subsequently, engineering validation of the model is carried out using eight sets of real rockburst data from Daxiangling Tunnel, and the results show that the model has a strong generalisation ability and can satisfy the relevant engineering applications. In addition, this paper also uses SHAP technology to quantify the impact of different factors on the rockburst intensity level and found that the elastic strain energy index and stress ratio have the greatest impact on the rockburst intensity level.

Weld stability is directly related to the safety and reliability of engineering, and continuous improvement of its detection technology has great research significance. This paper presents a novel method for weld stability detection based on color digital holography. A color digital holography optical path was designed to capture the holograms of welds under varying loads. Several common denoising algorithms were used to deal with speckle noise in the wrapped phase, among which the 4-f optical simulation integrated cycle-consistent generative adversarial network (4f-CycleGAN) denoising algorithm based on deep learning was more suitable for the color digital holographic detection system. The three-dimensional deformation fields of three samples (lap-jointed, butt-jointed, and defective butt-jointed aluminum alloy plates) under different loads were calculated. The center profile of the deformation field in the direction of load and holographic reconstruction images are used to determine the position of the weld. The coefficient of variation near the weld was used to evaluate the weld stability. The coefficient of variation for lap-jointed, butt-jointed and defective butt-jointed plates are 0.0335 (0.36, poor stability), respectively. The research results of this paper provide a new strategy for detecting weld stability.

Pandemics can result in large morbidity and mortality rates that can cause significant adverse effects on the social and economic situations of communities. Monitoring and predicting the spread of pandemics helps the concerned authorities manage the required resources, formulate preventive measures, and control the spread effectively. In the specific case of COVID-19, the UAE (United Arab Emirates) has undertaken many initiatives, such as surveillance and contact tracing by introducing mobile apps such as Al Hosn, containment of spread by limiting the gathering of people, online schooling and remote work, sanitation drives, and closure of public places. The aim of this paper is to predict the trends occurring in pandemic outbreak, with COVID-19 in the UAE being a specific case study to investigate. In this paper, a predictive modeling approach is proposed to predict the future number of cases based on the recorded history, taking into consideration the enforced policies and provided vaccinations. Machine learning models such as LASSO Regression and Exponential Smoothing, and deep learning models such as LSTM, LSTM-AE, and bi-directional LSTM-AE, are utilized. The dataset used is publicly available from the UAE government, Federal Competitiveness and Statistics Centre (FCSC) and consists of several attributes, such as the numbers of confirmed cases, recovered cases, deaths, tests, and vaccinations. An additional categorical attribute is manually added to the dataset describing whether an event has taken place, such as a national holiday or a sanitization drive, to study the effect of such events on the pandemic trends. Experimental results showed that the Univariate LSTM model with an input of a five-day history of Confirmed Cases achieved the best performance with an RMSE of 275.85, surpassing the current state of the art related to the UAE by over 30%. It was also found that the bi-directional LSTMs performed relatively well. The approach proposed in the paper can be applied to monitor similar infectious disease outbreaks and thus contribute to strengthening the authorities’ preparedness for future pandemics.

Tomb murals are different from cave temple murals and temple murals, as they are underground cultural relics, their painting style is unique, solemn, and austere, and the performance image is characterised by simple colours, low contrast, and fewer survivors. During the digital restoration process, it is important to have sufficient reference samples to ensure the accuracy of the restoration. In addition, the style of mural paintings in the tombs varies greatly from other styles of murals and types of word paintings. Therefore, learning the unique artistic style of tomb murals, providing stylistically consistent training samples for digital restoration, and overcoming the problems of dim lighting and complex surface granularity of tomb murals are all necessary for research. This paper proposes a generative adversarial network algorithm that separates and fuses style features to enhance the generative network’s ability to acquire image information. The algorithm extracts underlying and surface style feature details of the image to be tested and conducts fusion generation experiments. The generative network’s parsing layer modifies the input noise tensor and optimises the corresponding weights to prevent misalignment between drawing lines and fresco cracks. Finally, to optimise the fresco generation effect, we add the corresponding loss function in the discriminator. The tomb murals dataset was established for experiments and tests, and quantitatively and qualitatively analysed with other style migration models, and SSIM, FID, LPIPS and NIQE were used as evaluation indexes. The results were 0.97, 269.579, 0.425 and 3.250, respectively, and the effect of style migration of this paper’s method was significantly higher than that of the control group model.

With the rapid development of digital core technology, the acquisition of high-resolution rock thin section images has become crucial. Due to the limitation of optical principles, thin section imaging involves a contradiction between resolution and field of view. In order to solve this problem, this paper proposes a lightweight, fully aggregated network with multi-branch structure for super resolution of rock thin section images. The experimental results on the rock thin section dataset demonstrate that the improved method, called OmniSR-M, achieves significant enhancement compared to the original OmniSR method and also surpasses other state-of-the-art methods. OmniSR-M effectively recovers image details while maintaining its lightweight nature. Specifically, OmniSR-M reduces the number of parameters by 26.56% and the computation by 27.66% compared to OmniSR. Moreover, this paper quantitatively analyzes both the facies porosity rate and grain size features in the application scenario. The results show that the images generated by OmniSR-M successfully recover key information about the rock thin section.

Evolutionary multi-objective clustering (EMOC) algorithms have gained popularity recently, as they can obtain a set of clustering solutions in a single run by optimizing multiple objectives. Particularly, in one type of EMOC algorithm, the number of clusters k is taken as one of the multiple objectives to obtain a set of clustering solutions with different k. However, the numbers of clusters k and other objectives are not always in conflict, so it is impossible to obtain the clustering solutions with all different k in a single run. Therefore, evolutionary multi-objective k-clustering (EMO-KC) has recently been proposed to ensure this conflict. However, EMO-KC could not obtain good clustering accuracy on high-dimensional datasets. Moreover, EMO-KC’s validity is not ensured as one of its objectives (SSDexp, which is transformed from the sum of squared distances (SSD)) could not be effectively optimized and it could not avoid invalid solutions in its initialization. In this paper, an improved evolutionary multi-objective clustering algorithm based on autoencoder (AE-IEMOKC) is proposed to improve the accuracy and ensure the validity of EMO-KC. The proposed AE-IEMOKC is established by combining an autoencoder with an improved version of EMO-KC (IEMO-KC) for better accuracy, where IEMO-KC is improved based on EMO-KC by proposing a scaling factor to help effectively optimize the objective of SSDexp and introducing a valid initialization to avoid the invalid solutions. Experimental results on several datasets demonstrate the accuracy and validity of AE-IEMOKC. The results of this paper may provide some useful information for other EMOC algorithms to improve accuracy and convergence.

This paper addresses the limitations of relying solely on facial expressions for emotion recognition by proposing an advanced approach that emphasizes continuous monitoring of electroencephalography (EEG) signals. Recognizing the potential for deception in facial expressions, our study leverages the growing interest in EEG signals, tapping into advancements in deep learning and machine learning. By optimizing the configuration of EEG electrodes, our approach enhances the accuracy of emotion classification systems, offering a streamlined solution. The proposed multi-input system refines EEG-based emotion recognition efficiency and integrates facial expression analysis to enhance overall system effectiveness. Through the application of brain heat map topographies and facial expression recognition, our system, employing just nine electrodes, outperforms basic emotion recognition setups. Experimental results validate that combining facial expression analysis with EEG signals provides a more comprehensive and accurate understanding of human emotions. This innovative approach holds significance across various sectors, including healthcare, psychology, and human–computer interaction. The paper introduces a novel multi-input system approach, collaboratively fusing two powerful deep learning algorithms: two Convolutional Neural Networks (CNNs). The proposed EEG-based CNN algorithm achieves an efficiency of 87.43%, rising to 91.21% when integrated with the DeepFace CNN. The seamless integration of facial expressions and brain topographies enables the system to efficiently harness abundant information from both modalities, ensuring a thorough comprehension of human emotions. By capitalizing on the combined advantages of analyzing facial expressions and EEG-derived brain topography, this avant-garde technique substantially improves both precision and efficiency in emotion recognition systems. This enhancement establishes a foundation for the introduction of innovative applications across a spectrum of fields.

With the advent of the era of big data and information technology, deep learning (DL) has become a hot trend in the research field of artificial intelligence (AI). The use of deep learning methods for parameter inversion, disease identification, detection, surrounding rock classification, disaster prediction, and other tunnel engineering problems has also become a new trend in recent years, both domestically and internationally. This paper briefly introduces the development process of deep learning. By reviewing a number of published papers on the application of deep learning in tunnel engineering over the past 20 years, this paper discusses the intelligent application of deep learning algorithms in tunnel engineering, including collapse risk assessment, water inrush prediction, crack identification, structural stability evaluation, and seepage erosion in mountain tunnels, urban subway tunnels, and subsea tunnels. Finally, it explores the future challenges and development prospects of deep learning in tunnel engineering.

High-quality agricultural multi-view stereo reconstruction technology is the key to precision and informatization in agriculture. Multi-view stereo reconstruction methods are an important part of 3D vision technology. In the multi-view stereo 3D reconstruction method based on deep learning, the effect of feature extraction directly affects the accuracy of reconstruction. Aiming at the actual problems in orchard fruit tree reconstruction, this paper designs an improved multi-view stereo structure based on the combination of remote sensing and artificial intelligence to realize the accurate reconstruction of jujube tree trunks. Firstly, an automatic key frame extraction method is proposed for the DSST target tracking algorithm to quickly recognize and extract high-quality data. Secondly, a composite U-Net feature extraction network is designed to enhance the reconstruction accuracy, while the DRE-Net feature extraction enhancement network improved by the parallel self-attention mechanism enhances the reconstruction completeness. Comparison tests show different levels of improvement on the Technical University of Denmark (DTU) dataset compared to other deep learning-based methods. Ablation test on the self-constructed dataset, the MVSNet + Co U-Net + DRE-Net_SA method proposed in this paper improves 20.4% in Accuracy, 12.8% in Completion, and 16.8% in Overall compared to the base model, which verifies the real effectiveness of the scheme.

Facial expression recognition (FER) plays a crucial role in understanding human emotions and is becoming increasingly relevant in educational contexts, where personalized and empathetic interactions are essential. The problems with existing approaches are typically solved using a single deep learning method, which is not robust with complex datasets, such as FER data, which have a characteristic imbalance and multi-class labels. In this research paper, an innovative approach to FER using a homogeneous ensemble convolutional neural network, called HoE-CNN, is presented for future online learning education. This paper aims to transfer the knowledge of models and FER classification using ensembled homogeneous conventional neural network architectures. FER is challenging to research because there are many real-world applications to consider, such as adaptive user interfaces, games, education, and robot integration. HoE-CNN is used to improve the classification performance on an FER dataset, encompassing seven main multi-classes (Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral). The experiment shows that the proposed framework, which uses an ensemble of deep learning models, performs better than a single deep learning model. In summary, the proposed model will increase the efficiency of FER classification results and solve FER2013 at a accuracy of 75.51%, addressing both imbalanced datasets and multi-class classification to transfer the application of the model to online learning applications.

In this paper, first, we delved into the experiment by comparing various attention mechanisms in the semantic pixel-wise segmentation framework to perform frame-level transcription tasks. Second, the Viterbi algorithm was utilized by transferring the knowledge of the frame-level transcription model to obtain the vocal notes of Korean Pansori. We considered a semantic pixel-wise segmentation framework for frame-level transcription as the source task and a Viterbi algorithm-based Korean Pansori note-level transcription as the target task. The primary goal of this paper was to transcribe the vocal notes of Pansori music, a traditional Korean art form. To achieve this goal, the initial step involved conducting the experiments with the source task, where a trained model was employed for vocal melody extraction. To achieve the desired vocal note transcription for the target task, the Viterbi algorithm was utilized with the frame-level transcription model. By leveraging this approach, we sought to accurately transcribe the vocal notes present in Pansori performances. The effectiveness of our attention-based segmentation methods for frame-level transcription in the source task has been compared with various algorithms using the vocal melody task of the MedleyDB dataset, enabling us to measure the voicing recall, voicing false alarm, raw pitch accuracy, raw chroma accuracy, and overall accuracy. The results of our experiments highlight the significance of attention mechanisms for enhancing the performance of frame-level music transcription models. We also conducted a visual and subjective comparison to evaluate the results of the target task for vocal note transcription. Since there was no ground truth vocal note for Pansori, this analysis provides valuable insights into the preservation and appreciation of this culturally rich art form.

In the era of extensive data acquisition from manufacturing and transportation processes, the utilization of machine learning and deep learning techniques has emerged as a potent force for informed decision-making and optimized deliveries in contemporary urban landscapes. This study presents a novel approach grounded in deep learning, where product data are systematically gathered to construct a multilayer perceptron neural network model. This model proves instrumental in efficiently classifying product flows within the urban milieu. To validate its efficacy, machine learning classifiers are deployed, and their performance is juxtaposed with the neural network model. Addressing the critical question of the paper’s significance, our experimental evaluation unequivocally demonstrates the superior classification accuracy of the proposed multilayer perceptron model when compared to traditional machine learning models operating on the same product dataset. This advancement is not merely a theoretical achievement but translates into tangible improvements in last-mile delivery processes, marked by significant cost reduction and the mitigation of delays. The transformative potential of our approach is further underscored by the strategic application of a deep learning algorithm for optimization and illustrative purposes. This holistic methodology not only positions our work as a noteworthy contribution to the realm of product classification but also establishes a concrete pathway for enhancing the sustainability and efficiency of urban logistics. This paper, thus, goes beyond the conventional application of machine learning models, offering a paradigm shift in the intersection of deep learning, urban logistics, and sustainable development.

The paper introduces an approach for detecting brain aneurysms, a critical medical condition, by utilizing a combination of 3D convolutional neural networks (3DCNNs) and Convolutional Long Short-Term Memory (ConvLSTM). Brain aneurysms pose a significant health risk, and early detection is vital for effective treatment. Traditional methods for aneurysm detection often rely on complex and time-consuming procedures. A radiologist specialist annotates each aneurysm and supports our work with true-ground annotations. From the annotated data, we extract images to train proposed neural networks. The paper experiments with two different types of networks, specifically focusing on 2D convolutional neural networks (2DCNNs), 3D convolutional neural networks (3DCNNs), and Convolutional Long Short-Term Memory (ConvLSTM). Our goal is to create a virtual assistant to improve the search for aneurysm locations, with the aim of further realizing the virtual assistant. Subsequently, a radiologist specialist will confirm or reject the presence of an aneurysm, leading to a reduction in the time spent on the searching process and revealing hidden aneurysms. Our experimental results demonstrate the superior performance of the proposed approach compared to existing methods, showcasing its potential as a valuable tool in clinical settings for early and accurate brain aneurysm detection. This innovative fusion of 3DCNN and LSTM (3DCNN-ConvLSTM) techniques not only improves diagnostic precision but also holds promise for advancing the field of medical image analysis, particularly in the domain of neurovascular diseases. Overall, our research underscores the potential of neural networks for the machine detection of brain aneurysms.

Intelligent gangue sorting with high precision is of vital importance for improving coal quality. To tackle the challenges associated with coal gangue target detection, including algorithm performance imbalance and hardware deployment difficulties, in this paper, an intelligent gangue separation system that adopts the elevated YOLO-v5 algorithm and dual-energy X-rays is proposed. Firstly, images of dual-energy X-ray transmission coal gangue mixture under the actual operation of a coal mine were collected, and datasets for training and validation were self-constructed. Then, in the YOLOv5 backbone network, the EfficientNetv2 was used to replace the original cross stage partial darknet (CSPDarknet) to achieve the lightweight of the backbone network; in the neck, a light path aggregation network (LPAN) was designed based on PAN, and a convolutional block attention module (CBAM) was integrated into the BottleneckCSP of the feature fusion block to raise the feature acquisition capability of the network and maximize the learning effect. Subsequently, to accelerate the rate of convergence, an efficient intersection over union (EIOU) was used instead of the complete intersection over union (CIOU) loss function. Finally, to address the problem of low resolution of small targets leading to missed detection, an L2 detection head was introduced to the head section to improve the multi-scale target detection performance of the algorithm. The experimental results indicate that in comparison with YOLOv5-S, the same version of the algorithm proposed in this paper increases by 19.2% and 32.4% on mAP @.5 and mAP @.5:.95, respectively. The number of parameters decline by 51.5%, and the calculation complexity declines by 14.7%. The algorithm suggested in this article offers new ideas for the design of identification algorithms for coal gangue sorting systems, which is expected to save energy and reduce consumption, reduce labor, improve efficiency, and be more friendly to the embedded platform.

Academic researchers publish their work in various formats, such as papers, patents, and research reports, on different academic sites. When searching for a particular researcher’s work, it can be challenging to pinpoint the right individual, especially when there are multiple researchers with the same name. In order to handle this issue, we propose a name disambiguation scheme for researchers with the same name based on heterogeneous academic sites. The proposed scheme collects and integrates research results from these varied academic sites, focusing on attributes crucial for disambiguation. It then employs clustering techniques to identify individuals who share the same name. Additionally, we implement the proposed rule-based algorithm name disambiguation method and the existing deep learning-based identification method. This approach allows for the selection of the most accurate disambiguation scheme, taking into account the metadata available in the academic sites, using a multi-classifier approach. We consider various researchers’ achievements and metadata of articles registered in various academic search sites. The proposed scheme showed an exceptionally high F1-measure value of 0.99. In this paper, we propose a multi-classifier that executes the most appropriate disambiguation scheme depending on the inputted metadata. The proposed multi-classifier shows the high F1-measure value of 0.67.

Identifying individual pigs is crucial for efficient breeding, health management, and disease control in modern farming. Traditional animal face identification methods are labor-intensive and prone to inaccuracies, while existing CNN-based pig face recognition models often struggle with high computational demands, large sizes, and reliance on extensive labeled data, which limit their practical application. This paper addresses these challenges by proposing a novel, decoupled approach to pig face recognition that separates detection from identification. This strategy employs a detection model as a pre-processing step, significantly reducing the need for extensive re-annotation for new datasets. Additionally, the paper introduces a method that integrates offline knowledge distillation with a lightweight pig face recognition model, aiming to build an efficient and embedding-friendly system. To achieve these objectives, the study constructs a small-scale, high-quality pig face detection dataset consisting of 1500 annotated images from a selection of 20 pigs. An independent detection model, trained on this dataset, then autonomously generates a large-scale pig face recognition dataset with 56 pig classes. In the face recognition stage, a robust teacher model guides the student model through a distillation process informed by a knowledge distillation loss, enabling the student model to learn relational features from the teacher. Experimental results confirm the high accuracy of the pig face detection model on the small-scale detection dataset and the ability to generate a large-scale dataset for pig face recognition on unlabeled data. The recognition experiments further verify that the distilled lightweight model outperforms its non-distilled counterparts and approaches the performance of the teacher model. This scalable, cost-effective solution shows significant promise for broader computer vision applications beyond agriculture.

As cloud computing rises in popularity across diverse industries, the necessity to compare and select the most appropriate cloud provider for specific use cases becomes imperative. This research conducts an in-depth comparative analysis of two prominent cloud platforms, Microsoft Azure and Amazon Web Services (AWS), with a specific focus on their suitability for deploying object-detection algorithms. The analysis covers both quantitative metrics—encompassing upload and download times, throughput, and inference time—and qualitative assessments like cost effectiveness, machine learning resource availability, deployment ease, and service-level agreement (SLA). Through the deployment of the YOLOv8 object-detection model, this study measures these metrics on both platforms, providing empirical evidence for platform evaluation. Furthermore, this research examines general platform availability and information accessibility to highlight differences in qualitative aspects. This paper concludes that Azure excels in download time (average 0.49 s/MB), inference time (average 0.60 s/MB), and throughput (1145.78 MB/s), and AWS excels in upload time (average 1.84 s/MB), cost effectiveness, ease of deployment, a wider ML service catalog, and superior SLA. However, the decision between either platform is based on the importance of their performance based on business-specific requirements. Hence, this paper ends by presenting a comprehensive comparison based on business-specific requirements, aiding stakeholders in making informed decisions when selecting a cloud platform for their machine learning projects.

Machine learning-based malware (malicious software) detection methods have a wide range of real-world applications. However, these types of approaches suffer from the fatal problem of “model aging”, in which the validity of the model decreases rapidly as the malware continues to evolve and variants emerge continuously. The model aging problem is usually solved by model retraining, which relies on lots of labeled samples obtained at great expense. To address this challenge, this paper proposes a semi-supervised continuous learning malware detection model based on Transformer. Firstly, this model improves the lifelong semi-supervised mixture algorithm to dynamically adjust the weighted combination of new sample sequences and historical ones to solve the imbalance problem. Secondly, the Learning with Local and Global Consistency algorithm is used to iteratively compute similarity scores for the unlabeled samples in the mixed samples to obtain pseudo-labels. Lastly, the Multilayer Perceptron is applied for malware classification. To validate the effectiveness of the model, this paper conducts experiments on the CICMalDroid2020 dataset. The experimental results show that the proposed model performs better than existing deep learning detection models. The F1 score has an average improvement of 1.27% compared to other models when conducting binary classification. And, after inputting hybrid samples, including historical data and new data, four times, the F1 score is still 1.96% higher than other models.

Music transcription is the process of transforming recorded sound of musical performances into symbolic representations such as sheet music or MIDI files. Extensive research and development have been carried out in the field of music transcription and technology. This comprehensive review paper surveys the diverse methodologies, techniques, and advancements that have shaped the landscape of music transcription. The paper outlines the significance of music transcription in preserving, analyzing, and disseminating musical compositions across various genres and cultures. It also provides a historical perspective by tracing the evolution of music transcription from traditional manual methods to modern automated approaches. It also highlights the challenges in transcription posed by complex singing techniques, variations in instrumentation, ambiguity in pitch, tempo changes, rhythm, and dynamics. The review also categorizes four different types of transcription techniques, frame-level, note-level, stream-level, and notation-level, discussing their strengths and limitations. It also encompasses the various research domains of music transcription from general melody extraction to vocal melody, note-level monophonic to polyphonic vocal transcription, single-instrument to multi-instrument transcription, and multi-pitch estimation. The survey further covers a broad spectrum of music transcription applications in music production and creation. It also reviews state-of-the-art open-source as well as commercial music transcription tools for pitch estimation, onset and offset detection, general melody detection, and vocal melody detection. In addition, it also encompasses the currently available python libraries that can be used for music transcription. Furthermore, the review highlights the various open-source benchmark datasets for different areas of music transcription. It also provides a wide range of references supporting the historical context, theoretical frameworks, and foundational concepts to help readers understand the background of music transcription and the context of our paper.

Recently, the spread of fake images on social media platforms has become a significant concern for individuals, organizations, and governments. These images are often created using sophisticated techniques to spread misinformation, influence public opinion, and threaten national security. This paper begins by defining fake images and their potential impact on society, including the spread of misinformation and the erosion of trust in digital media. This paper also examines the different types of fake images and their challenges for detection. We then review the recent approaches proposed for detecting fake images, including digital forensics, machine learning, and deep learning. These approaches are evaluated in terms of their strengths and limitations, highlighting the need for further research. This paper also highlights the need for multimodal approaches that combine multiple sources of information, such as text, images, and videos. Furthermore, we present an overview of existing datasets, evaluation metrics, and benchmarking tools for fake image detection. This paper concludes by discussing future directions for fake image detection research, such as developing more robust and explainable methods, cross-modal fake detection, and the integration of social context. It also emphasizes the need for interdisciplinary research that combines computer science, digital forensics, and cognitive psychology experts to tackle the complex problem of fake images. This survey paper will be a valuable resource for researchers and practitioners working on fake image detection on social media platforms.

To overcome the deficiencies in segmenting hot spots from thermal infrared images, such as difficulty extracting the edge features, low accuracy, and a high missed detection rate, an improved Mask R-CNN photovoltaic hot spot thermal image segmentation algorithm has been proposed in this paper. Firstly, the edge image features of hot spots were extracted based on residual neural networks. Secondly, by combining the feature pyramid structure, an edge-guided feature pyramid structure was designed, and the hot spot edge features were injected into a Mask R-CNN network. Thirdly, an infrared spatial attention module was introduced into the Mask R-CNN network when feature extraction and the infrared features of the detected hot spots were enhanced. Fourthly, the size ratio of the candidate frames was adjusted self-adaptively according to the structural characteristics of the aspect ratio of the hot spots. Finally, the validation experiments were conducted, and the results demonstrated that the hot spot contours of thermal infrared images were enhanced through the algorithm proposed in this paper, and the segmentation accuracy was significantly improved.

With the development of the Internet, there has been a significant increase in various types of textual information. However, when people engage in the composition of formal texts, they often incorporate their colloquial habits, which can diminish the professionalism and formality of the text. Existing research on Chinese texts primarily focuses on correcting misspelt characters that are visually or phonetically similar, as well as obvious grammatical errors, such as redundancy, omissions, and incorrect word order. However, there is limited research addressing the correction of text that exhibits colloquial expressions without apparent grammatical errors or misspelt characters. This article proposes a novel technique that utilizes deep learning methods to directly transform colloquial textual expressions into formal written expressions. Firstly, a parallel corpus dataset of written and spoken language is constructed using a back-translation strategy. Then, an end-to-end learning mechanism based on neural machine translation is employed, with colloquial text as the source language and written text as the target language. This allows the model to directly transform the colloquial text into text with a formal style. Finally, an evaluation of the proposed approach is conducted using the bilingual evaluation understudy (BLEU) and manual assessment techniques. The experimental results demonstrate that the technology proposed in this paper performs well in the task of de-colloquialization in Chinese texts. The contribution of this paper lies in proposing an automated method for collecting a substitute for manually annotated parallel corpora of spoken and written language, which significantly saves time and reduces the manual cost of constructing the dataset. Furthermore, the application of end-to-end learning techniques from neural machine translation to the task of de-colloquialization allows the trained model to directly generate written language flexibly based on the input of spoken language. This presents a novel solution for the task of the de-colloquialization of Chinese text.

Vehicular edge computing (VEC) is essential in vehicle applications such as traffic control and in-vehicle services. In the task offloading process of VEC, predictive-mode transmission based on deep learning is constrained by limited computational resources. Furthermore, the accuracy of deep learning algorithms in VEC is compromised due to the lack of edge computing features in algorithms. To solve these problems, this paper proposes a task offloading optimization approach that enables edge servers to store deep learning models. Moreover, this paper proposes the LTransformer, a transformer-based framework that incorporates edge computing features. The framework consists of pre-training, an input module, an encoding–decoding module, and an output module. Compared with four sequential deep learning methods, namely a Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), a Gated Recurrent Unit (GRU), and the Transformer, the LTransformer achieves the highest accuracy, reaching 80.1% on the real dataset. In addition, the LTransformer achieves 0.008 s when predicting a single trajectory, fully satisfying the fundamental requirements of real-time prediction and enabling task offloading optimization.

Properly managed urban household waste landfills play a crucial role in achieving sustainable development and ecological civilization. This paper proposes an innovative design method that aims to overcome the limitations and extensive challenges of traditional urban domestic waste landfill design by combining aerial image segmentation with ecological restoration theory. We suggest an enhanced SEVnet, a combination of the basic vnet network and the sequence-and-excitation module, for precise and efficient garbage dump identification. Through this module, the network can independently analyze the significance of each feature channel and provide weights, leading to enhanced image detail recovery and more precise segmentation. We implemented the proposed SEVnet model based on an aerial photography database of urban garbage dumps. Following precise urban garbage disposal site division, we adopt ecological restoration theory to achieve sustainable design. This article presents the Saihanba area in China as a case study, collects pertinent data, and conducts image segmentation and GIS-assisted analysis. This paper examines the landscape application and design of the landfill site based on an analysis and planning of land use in its vicinity. The intervention of landscape ecology imbues the landfill site with new functions. We propose comprehensive planning and landscape restoration design measures from four perspectives, encompassing disadvantages, threats, opportunities, and strengths, using SWOT analysis to better integrate the Hebei Saihanba landfill site with the surrounding environment. This paper introduces a groundbreaking design scheme for a landfill that aligns with the principles of current green and sustainable development.

Gravitational wave research presents a range of intriguing challenges, each of which has driven significant progress in the field. Key research problems include glitch classification, glitch cancellation, gravitational wave denoising, binary black hole signal detection, gravitational wave bursts, and minor issues that contribute to the overall understanding of gravitational wave phenomena. This paper explores the applications of artificial intelligence, deep learning, and machine learning techniques in addressing these challenges. The main goal of the paper is to provide an effective view of AI and deep learning usage for gravitational wave analysis. Thanks to the advancements in artificial intelligence and machine learning techniques, aided by GPUs and specialized software frameworks, these techniques have played a key role over the last decade in the identification, classification, and cancellation of gravitational wave signals, as presented in our results. This paper provides a comprehensive exploration of the adoption rate of these techniques, with reference to the software and hardware involved, their effectiveness, and potential limitations, offering insights into the advancements in the analysis of gravitational wave data.

Point cloud learning has recently gained strong attention due to its applications in various fields, like computer vision, robotics, and autonomous driving. Point cloud semantic segmentation (PCSS) enables the automatic extraction of semantic information from 3D point cloud data, which makes it a desirable task for construction-related applications as well. Yet, only a limited number of publications have applied deep-learning-based methods to address point cloud understanding for civil engineering problems, and there is still a lack of comprehensive reviews and evaluations of PCSS methods tailored to such use cases. This paper aims to address this gap by providing a survey of recent advances in deep-learning-based PCSS methods and relating them to the challenges of the construction industry. We introduce its significance for the industry and provide a comprehensive look-up table of publicly available datasets for point cloud understanding, with evaluations based on data scene type, sensors, and point features. We address the problem of class imbalance in 3D data for machine learning, provide a compendium of commonly used evaluation metrics for PCSS, and summarize the most significant deep learning methods developed for PCSS. Finally, we discuss the advantages and disadvantages of the methods for specific industry challenges. Our contribution, to the best of our knowledge, is the first survey paper that comprehensively covers deep-learning-based methods for semantic segmentation tasks tailored to construction applications. This paper serves as a useful reference for prospective research and practitioners seeking to develop more accurate and efficient PCSS methods.

In recent years, deep learning methods have been used with increasing frequency to solve architectural design problems. This paper aims to study the spatial functional layout of deep learning-assisted generation subway stations. Using the PointNet++ model, the subway station point cloud data are trained and then collected and processed by the author. After training and verification, the following conclusions are obtained: (1) the feasibility of spatial deep learning for construction based on PointNet++ in the form of point cloud data is verified; (2) the effectiveness of PointNet++ for the semantic segmentation and prediction of metro station point cloud information is verified; and (3) the results show that the overall 9:1 training prediction data have 60% + MIOU and 75% + accuracy for 9:1 training prediction data in the space of 20 × 20 × 20 and a block_size of 10.0. This paper combines the deep learning of 3D point cloud data with architectural design, breaking through the original status quo of two-dimensional images as research objects. From the dataset level, the limitation that research objects such as 2D images cannot accurately describe 3D space is avoided, and more intuitive and diverse design aids are provided for architects.

User authentication has become necessary in different life domains. Traditional authentication methods like personal information numbers (PINs), password ID cards, and tokens are vulnerable to attacks. For secure authentication, methods like biometrics have been developed in the past. Biometric information is hard to lose, forget, duplicate, or share because it is a part of the human body. Many authentication methods focused on electrocardiogram (ECG) signals have achieved great success. In this paper, we have developed cardiac biometrics for human identification using a deep learning (DL) approach. Cardiac biometric systems rely on cardiac signals that are captured using the electrocardiogram (ECG), photoplethysmogram (PPG), and phonocardiogram (PCG). This study utilizes the ECG as a biometric modality because ECG signals are a superior choice for accurate, secure, and reliable biometric-based human identification systems, setting them apart from PPG and PCG approaches. To get better performance in terms of accuracy and computational time, we have developed an ensemble approach based on VGG16 pre-trained transfer learning (TL) and Long Short-Term Memory (LSTM) architectures to optimize features. To develop this authentication system, we have fine-tuned this ensemble network. In the first phase, we preprocessed the ECG biosignal to remove noise. In the second phase, we converted the 1-D ECG signals into a 2-D spectrogram image using a transformation phase. Next, the feature extraction step is performed on spectrogram images using the proposed ensemble DL technique, and finally, those features are identified by the boosting machine learning classifier to recognize humans. Several experiments were performed on the selected dataset, and on average, the proposed system achieved 98.7% accuracy, 98.01% precision, 97.1% recall, and 0.98 AUC. In this paper, we have compared the developed approach with state-of-the-art biometric authentication systems. The experimental results demonstrate that our proposed system outperformed the human recognition competition.

To improve the accuracy of material identification under low contrast conditions, this paper proposes an improved YOLOv4-tiny target detection method based on an adaptive self-order piecewise enhancement and multiscale feature optimization. The model first constructs an adaptive self-rank piecewise enhancement algorithm to enhance low-contrast images and then considers the fast detection ability of the YOLOv4-tiny network. To make the detection network have a higher accuracy, this paper adds an SE channel attention mechanism and an SPP module to this lightweight backbone network to increase the receptive field of the model and enrich the expression ability of the feature map. The network can pay more attention to salient information, suppress edge information, and effectively improve the training accuracy of the model. At the same time, to better fuse the features of different scales, the FPN multiscale feature fusion structure is redesigned to strengthen the fusion of semantic information at all levels of the network, enhance the ability of network feature extraction, and improve the overall detection accuracy of the model. The experimental results show that compared with the mainstream network framework, the improved YOLOv4-tiny network in this paper effectively improves the running speed and target detection accuracy of the model, and its mAP index reaches 98.85%, achieving better detection results.

In China, table tennis has always been one of the most popular sports, with small field restrictions and it is simple and fun to play. But what is unknown is that with China’s major table tennis events thriving, the psychological pressure of table tennis players’ training is also increasing. However, the existing training methods obviously do not pay enough attention to psychological training, and there is no complete system for psychological training. Although the current dynamic heart rate measurement method can play a certain role in the detection, there is still the disadvantage of low detection accuracy. The heart rate is an important sign of life, and the monitoring of the heart rate of table tennis players should be strengthened, reflecting the functional state of the athletes’ heart, and facilitating the more intuitive adjustment of the psychological training method of athletes. The heart rate measurement method based on face recognition contains a plate content that is rich. Through deep learning face recognition, the heart rate measurement method has high calculation efficiency, can effectively eliminate the influence of other external environmental factors, can use video recording, and can use face recognition and physiological parameters’ quantification to monitor athletes’ heart rate changes in real time; the visible artificial intelligence auxiliary diagnosis potential is huge. To this end, this paper aims to provide effective suggestions for the psychological training of table tennis players with deep learning as the technical support. In response to this, the aim of this paper was to design a deep learning-based face recognition heart rate measurement method that judges the psychological fluctuations of athletes through changes in heart rate. We conducted a questionnaire survey with the table tennis players of the Hunan team as the object of investigation, so as to understand the source of the psychological pressure of athletes and make reasonable suggestions. The experimental results of this paper show that the heart rate error of the video heart rate measurement algorithm is within 3% in the calm state and within 4% in the post-exercise state. This can effectively measure psychological fluctuations, and through investigation and research, it can provide an effective method for the psychological training of table tennis players.

The accuracy of solar energy forecasting is critical for power system planning, management, and operation in the global electric energy grid. Therefore, it is crucial to ensure a constant and sustainable power supply to consumers. However, existing statistical and machine learning algorithms are not reliable for forecasting due to the sporadic nature of solar energy data. Several factors influence the performance of solar irradiance, such as forecasting horizon, weather classification, and performance evaluation metrics. Therefore, we provide a review paper on deep learning-based solar irradiance forecasting models. These models include Long Short-Term Memory (LTSM), Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Generative Adversarial Networks (GAN), Attention Mechanism (AM), and other existing hybrid models. Based on our analysis, deep learning models perform better than conventional models in solar forecasting applications, especially in combination with some techniques that enhance the extraction of features. Furthermore, the use of data augmentation techniques to improve deep learning performance is useful, especially for deep networks. Thus, this paper is expected to provide a baseline analysis for future researchers to select the most appropriate approaches for photovoltaic power forecasting, wind power forecasting, and electricity consumption forecasting in the medium term and long term.

Accurate segmentation of skin lesions is still a challenging task for automatic diagnostic systems because of the significant shape variations and blurred boundaries of the lesions. This paper proposes a multi-scale convolutional neural network, REDAUNet, based on UNet3+ to enhance network performance for practical applications in skin segmentation. First, the network employs a new encoder module composed of four feature extraction layers through two cross-residual (CR) units. This configuration allows the module to extract deep semantic information while avoiding gradient vanishing problems. Subsequently, a lightweight and efficient channel attention (ECA) module is introduced during the encoder’s feature extraction stage. The attention module assigns suitable weights to channels through attention learning and effectively captures inter-channel interaction information. Finally, the densely connected atrous spatial pyramid pooling module (DenseASPP) module is inserted between the encoder and decoder paths. This module integrates dense connections and ASPP, as well as multi-scale information fusion, to recognize lesions of varying sizes. The experimental studies in this paper were constructed on two public skin lesion datasets, namely, ISIC-2018 and ISIC-2017. The experimental results show that our model is more accurate in segmenting lesions of different shapes and achieves state-of-the-art performance in segmentation. In comparison to UNet3+, the proposed REDAUNet model shows improvements of 2.01%, 4.33%, and 2.68% in Dice, Spec, and mIoU metrics, respectively. These results suggest that REDAUNet is well-suited for skin lesion segmentation and can be effectively employed in computer-aided systems.

Food security is a widely discussed topic globally. The key to ensuring the safety of food storage is to control temperature and humidity, with ventilation being an effective and fast method for temperature and humidity control. This paper proposes a new approach called “grain condition multimodal” based on the theory of computer multimodality. Under changing external environments, grain conditions can be classified according to different ventilation modes, including cooling ventilation, dehumidification ventilation, anti-condensation ventilation, heat dissipation ventilation, and quality adjustment ventilation. Studying intelligent ventilation decisions helps achieve grain temperature balance, prevent moisture condensation, control grain heating, reduce grain moisture, and create a low-temperature environment to improve grain storage performance. Combining deep learning models with data such as grain stack temperature and humidity can significantly improve the accuracy of ventilation decisions. This paper proposes a neural network model based on residual networks and self-attention mechanisms that performs better than basic models such as LSTM (Long Short-Term Memory), CNN (Convolutional Neural Network), GRU (Gated Recurrent Unit), and ResNet (Residual Network). The model’s accuracy, precision, recall, and F1 scores are 94.38%, 94.92%, 98.94%, and 96.89%, respectively.

At CRYPTO 2019, Gohr proposed the neural differential distinguisher using the residual network structure in convolutional neural networks on round-reduced Speck32/64. In this paper, we construct a 7-round differential neural distinguisher for Speck32/64, which results in better than Gohr’s work. The details are as follows. Firstly, a new data format (C_r,C_r′,d_l,Cl,Cr,Cl′,Cr′) is proposed for the input data of the differential neural distinguisher, which can help the distinguisher to identify the features of the previous round of ciphertexts in the Speck algorithm. Secondly, this paper modifies the convolution layer of the residual block in the residual network, inspired by the Inception module in GoogLeNet. For Speck32/64, the experiments show that the accuracy of the 7-round differential neural distinguisher is 97.13%, which is better than the accuracy of Gohr’s distinguisher of 9.1% and also higher than the currently known accuracy of 89.63%. The experiments also show that the data format and neural network in this paper can improve the accuracy of the distinguisher by 2.38% and 2.1%, respectively. Finally, to demonstrate the effectiveness of the distinguisher in this paper, a key recovery attack is performed on 8-rounds of Speck32/64. The results show that the success rate of recovering the correct key is 92%, with no more than two incorrect bits. Finally, this paper briefly discussed the effect of the number of ciphertext pairs in a sample on the training results of the differential neural distinguisher. When the total number of ciphertext pairs is kept constant, the accuracy of the distinguisher increases with s, but it also leads to the occurrence of overfitting.

Cracks are a common type of road distress. However, the traditional manual and vehicle-borne methods of detecting road cracks are inefficient, with a high rate of missed inspections. The development of unmanned aerial vehicles (UAVs) and deep learning has led to their use in crack detection and classification becoming an increasingly popular topic. In this paper, an aerial drone is used to efficiently and safely collect road data. However, this also brings many challenges. For example, flying too high or too fast may produce poor quality images, with unclear cracks that may be ignored or misjudged as other features and increased environmental noise that may make it difficult to distinguish between cracks and other noise features. To address the above challenges, this paper proposes the CrackNet model and CrackClassification algorithm. The CrackNet network is an encoder–decoder architecture. Low- and high-level semantic information are combined through the skip feature fusion layers between the encoder and decoder to enhance the model’s expression and ability to recover image details. Additionally, the MHDC module at the bottom of the network can significantly increase the receptive field without reducing the feature map resolution. The MHSA module can simultaneously capture features from multiple subspaces. The average precision (AP) scores of the CrackNet network on three datasets, namely UAVRoadCrack, CRKWH100, and CrackLS315, were 0.665, 0.942, and 0.895, respectively. In addition, values of the other two evaluation metrics, ODS and OIS, were the highest among the compared methods. Meanwhile, the proposed CrackClassification algorithm in this paper achieves 85% classification accuracy for transverse and longitudinal cracks and 78% classification accuracy for block cracks and reticulated cracks. Overall, the CrackNet algorithm provides a new baseline model for crack detection in UAV remote sensing image scenes. The CrackClassification algorithm provides a new approach for batch classification of highway cracks. The detection and classification algorithm proposed in this paper were applied to 108 km of road sections.

Sleep, as the basis for regular body functioning, can affect human health. Poor sleep conditions can lead to various physical ailments, such as poor immunity, memory loss, slow cognitive development, and cardiovascular diseases. Along the increasing stress in society comes with a growing surge in conditions associated with sleep disorders. Studies have shown that sleep stages are essential for the body’s memory, immune system, and brain functioning. Therefore, automatic sleep stage classification is of great medical practice importance as a basis for monitoring sleep conditions. Although previous research into the classification of sleep stages has been promising, several challenges remain to be addressed: (1) The EEG signal is a non-smooth signal with harrowing feature extraction and high requirements for model accuracy. (2) Some existing network models suffer from overfitting and gradient descent. (3) Correlation between long time sequences is challenging to capture. This paper proposes NAMRTNet, a deep model architecture based on the original single-channel EEG signal to address these challenges. The model uses a modified ResNet network to extract features from sub-epochs of individual epochs, a lightweight attention mechanism normalization-based attention module (NAM) to suppress insignificant features, and a temporal convolutional network (TCN) network to capture dependencies between features of long time series. The recognition rate of 20-fold cross-validation with the NAMRTNet model for Fpz-cz channel data in the public sleep dataset Sleep-EDF was 86.2%. The experimental results demonstrate the network’s superiority in this paper, surpassing some state-of-the-art techniques in different evaluation metrics. Furthermore, the total time to train the network was 5.1 h, which was much less than the training time of other models.

Human activity recognition (HAR) is an important research area with a wide range of application scenarios, such as smart homes, healthcare, abnormal behavior detection, etc. Wearable sensors, computer vision, radar, and other technologies are commonly used to detect human activity. However, they are severely limited by issues such as cost, lighting, context, and privacy. Therefore, this paper explores a high-performance method of using channel state information (CSI) to identify human activities, which is a deep learning-based spatial module-temporal convolutional network (SM-TCNNET) model. The model consists of a spatial feature extraction module and a temporal convolutional network (TCN) that can extract the spatiotemporal features in CSI signals well. In this paper, extensive experiments are conducted on the self-picked dataset and the public dataset (StanWiFi), and the results show that the accuracy reaches 99.93% and 99.80%, respectively. Compared with the existing methods, the recognition accuracy of the SM-TCNNET model proposed in this paper is improved by 1.8%.

Image matting is a fundamental technique used to extract a fine foreground image from a given image by estimating the opacity values of each pixel. It is one of the key techniques in image processing and has a wide range of applications in practical scenarios, such as in image and video editing. Deep learning has demonstrated outstanding performance in various image processing tasks, making it a popular research topic. In recent years, image matting methods based on deep learning have gained significant attention due to their superior performance. Therefore, this article presents a comprehensive overview of the deep learning-based image matting algorithms that have been proposed in recent years. This paper initially introduces frequently used datasets and their production methods, along with the basic principles of traditional image matting techniques. We then analyze deep learning-based matting algorithms in detail and introduce commonly used image matting evaluation metrics. Additionally, this paper discusses the application scenarios of image matting, conducts experiments to illustrate the limitations of current image matting methods, and outlines potential future research directions in this field. Overall, this paper can serve as a valuable reference for researchers that are interested in image matting.