Search

Herein, the challenge of accurately classifying the manufacturing origin of printing paper, including continent, country, and specific product, was addressed. One-dimensional convolutional neural network (1D CNN) models trained on infrared (IR) spectrum data acquired from printing paper samples were used for the task. The preprocessing of the IR spectra through a second-derivative transformation and the restriction of the spectral range to 1800 to 1200 cm-1 improved the classification performance of the model. The outcomes were highly promising. Models trained on second-derivative IR spectra in the 1800 to 1200-cm-1 range exhibited perfect classification for the manufacturing continent and country, with an impressive F1 score of 0.980 for product classification. Notably, the developed 1D CNN model outperformed traditional machine learning classifiers, such as support vector machines and feed-forward neural networks. In addition, the application of data point attribution enhanced the transparency of the decision-making process of the model, offering insights into the spectral patterns that affect classification. This study makes a considerable contribution to printing paper classification, with potential implications for accurate origin identification in various fields. [ABSTRACT FROM AUTHOR]

The use of Artificial Intelligence (AI) to preserve and promote cultural heritage has experienced significant growth in recent years. Among the various areas of cultural heritage, numismatics have emerged as a particularly promising field where we can develop AI solutions. Numismatics refers to the study of coins, tokens, paper money, and medals, which play a critical role in understanding human history and culture. However, there are still limited resources available to help researchers and collectors in the identification of coins. This is due to the vast number of coins in circulation, which presents a significant challenge in developing smart tools for classification tasks. This paper aims to provide a contribution to this setting. In particular, we start by creating a new dataset called EURO-Coin, which consists of images showing the side of coins with reliefs and is designed to facilitate the training and testing of AI models for euro coin classification. Then, we propose two approaches that leverage Convolutional Neural Networks and self-attention layers to classify the country and value of the coins. In our experiments, we obtain an accuracy of 86.9% for country classification and an accuracy of 96.4% for value classification. Finally, we conduct an ablation study to evaluate the impact of the preprocessing activities and attention layers in our approaches. [ABSTRACT FROM AUTHOR]

Since deep low‐frequency tremors are considered to be associated with large earthquakes that occur adjacently on the same subducting plate interface, it is important to investigate tremors that occurred before the establishment of modern seismograph networks such as the High Sensitivity Seismograph Network (Hi‐net). We propose a deep‐learning solution to detect evidence of tremors in scanned images of paper seismogram records from over 50 years ago. In this study, we fine‐tuned a convolutional neural network (CNN) based on the Residual Network, which was pre‐trained using images of synthetic waveforms from our previous study, using a data set comprised of images generated from real seismic data recorded digitally by Hi‐net to facilitate a supervised analysis. The fine‐tuned CNN was able to predict the presence or absence of tremors in the Hi‐net images with an accuracy of 98.64%. Gradient‐weighted Class Activation Mapping heatmaps created to visualize model predictions indicated that the CNN's ability to detect tremors is not degraded by the presence of teleseisms. Once validated using the Hi‐net images, the CNN was applied to paper seismograms recorded from 1966 to 1977 at the Kumano observatory in southwest Japan, operated by Earthquake Research Institute, The University of Tokyo. The CNN showed potential for detecting tremors in scanned images of paper seismogram records from the past, facilitating downstream tasks such as the creation of new tremor catalogs. However, further training using an augmented data set to control for variables such as inconsistent plotting pen thickness is required to develop a universally applicable model. Plain Language Summary: In 2002, deep low‐frequency tremors, which periodically occur with much smaller amplitudes and longer durations than common earthquakes, were discovered owing to the establishment of dense seismic arrays in Japan. These tremors are considered to be associated with megathrust earthquakes because they occur in deeper regions of plate boundaries compared with common earthquakes. Investigating tremors that occurred before the establishment of dense seismic arrays is important since megathrust earthquakes recur on intervals of 100–200 years, and digital records from modern seismic arrays cover only a fraction of that time. In this study, we developed a convolutional neural network based on the Residual Network (ResNet) that extracts tremors from images of waveforms recorded more than 50 years ago, when seismometers drew waveforms directly on drum‐rolled paper using a pen. The proposed ResNet, which was trained on seismogram images generated from synthetic waveforms and real data recorded digitally by modern seismic arrays, was applied to scanned images of paper seismograms recorded from 1966 to 1977 at an observatory in southwest Japan. A list of tremors was successfully obtained; however, further training using data that accounts for variables such as inconsistent plotting pen thickness is required to develop a universally applicable model. Key Points: Convolutional neural network model for detection of deep low‐frequency tremors from seismogram images is proposedThe model trained with seismogram images converted from real seismic data successfully detects tremorsThe detection performances of the trained model for the paper records at the Kumano observatory in southwest Japan are discussed [ABSTRACT FROM AUTHOR]

This paper presents a convolutional neural network (CNN) to classify between the conventionally and organically cultivated Memecik varieties of green olives. The image forming method called the rising paper chromatography is utilized in preparing the images of Memecik varieties of green olives for CNN. In the rising chromatography method, 20, 30, and 40% sample concentrations were determined as the suitable concentrations for both organic and conventional olives. The concentrations of AgNO3 and FeSO4 were determined as 0.25, 0.5, 0.75 and 1% for both conventional and organic samples. The visual differences used for differentiation of different types of Memecik green olives are usually determined according to the regional color differences, the vivid color occurrence, the width and the frequency of bowl occurrence, the thin line, and the picks at drop zone by the expert assessors. The testing results in this study verified the effectiveness of the CNN methodology in differentiating between the organically and conventionally cultivated Memecik green olives. The newly designed neural network achieved 100% accuracy. Furthermore, this high accuracy achieved by CNN might suggest that it can be effectively used in place of the expert assessors. [ABSTRACT FROM AUTHOR]

BACKGROUND: With the continuous improvement and progress of artificial intelligence technology in the treatment of spinal deformity, a large number of studies have been invested in this field, but the main research status, hot spots and development trends are still unclear. OBJECTIVE: To visually analyze the literature related to artificial intelligence in the field of spinal deformities by using bibliometrics, identify the research hotspots and shortcomings in this field, and provide references for future research. METHODS: The core database of Web of Science was used to search the articles related to artificial intelligence in the field of spinal deformities published from inception to 2023. The data were visually analyzed by Citespace 5.6.R5 and VOSviewer 1.6.19. RESULTS AND CONCLUSION: (1) A total of 165 papers were included, and the number of papers published in this field showed a fluctuating upward trend. The author with the largest number of articles is Lafage V, and the country with the largest number of articles is China. (2) Keyword analysis results show that adolescent scoliosis, deep learning, classification, precision and robot are the main keywords. (3) The in-depth analysis results of co-cited and highly cited articles show that artificial intelligence has three hotspots in the field of spinal deformities, including the use of U-shaped architecture (a mature mode of deep learning convolutional neural networks) to automatically measure imaging parameters (Cobb angle and accurate segmentation of paraspinal muscles), multiview correlation network architecture (i.e., spine curvature assessment framework), and robot-guided spinal surgery. (4) In the field of artificial intelligence treatment of spinal malformations, the mechanism research such as genomics is very weak. In the future, unsupervised hierarchical clustering and other machine learning techniques can be used to study the basic mechanism of susceptibility genes in the field of spinal deformities by genome-wide association analysis and other genomics research methods. [ABSTRACT FROM AUTHOR]

This paper introduces a damage diagnosis method based on the reassignment method and matching networks (MNs) to study the structural health monitoring of aerospace composite material components. This aims to facilitate the mapping of signal features to complex failure modes. We introduce a signal processing technique based on the reassignment method, employing a sliding analysis window to re‐estimate local instantaneous frequency and group delay. By utilizing the short‐time phase spectrum of the signal, we correct the nominal time and frequency coordinates of the spectrum data, aligning them more accurately with the true support region of the analyzed signal. Subsequently, this paper developed a deep matching network (DMN) damage diagnosis model based on MNs. This model utilizes a convolutional neural network (CNN) to extract damage‐related features from the signal and introduces the full context embedding (FCE) method to enhance the compatibility of sample embeddings. In this process, the embeddings of each sample in the training set should be mutually independent, while the embeddings of test samples should be regulated by the distribution of training set sample data. Ultimately, the damage category of test samples is determined based on cosine similarity. We validate our model using damage sample data collected from experiments and simulations conducted under varying components and operating conditions. Comparative assessments with five mainstream methods reveal an average accuracy exceeding 96%. This underscores the exceptional recognition accuracy and generalization performance of our proposed method in cross‐operating condition fault diagnosis experiments concerning aircraft composite material components. [ABSTRACT FROM AUTHOR]

Brain–computer interfacing (BCI) research, fueled by deep learning, integrates insights from diverse domains. A notable focus is on steady-state visual evoked potential (SSVEP) in BCI applications, requiring in-depth assessment through deep learning. EEG research frequently employs SSVEPs, which are regarded as normal brain responses to visual stimuli, particularly in investigations of visual perception and attention. This paper tries to give an in-depth analysis of the implications of deep learning for SSVEP-adapted BCI. A systematic search across four stable databases (Web of Science, PubMed, ScienceDirect, and IEEE) was developed to assemble a vast reservoir of relevant theoretical and scientific knowledge. A comprehensive search yielded 177 papers that appeared between 2010 and 2023. Thence a strict screening method from predetermined inclusion criteria finally generated 39 records. These selected works were the basis of the study, presenting alternate views, obstacles, limitations and interesting ideas. By providing a systematic presentation of the material, it has made a key scholarly contribution. It focuses on the technical aspects of SSVEP-based BCI, EEG technologies and complex applications of deep learning technology in these areas. The study delivers more penetrating reporting on the latest deep learning pattern recognition techniques than its predecessors, together with progress in data acquisition and recording means suitable for SSVEP-based BCI devices. Especially in the realms of deep learning technology orchestration, pattern recognition techniques, and EEG data collection, it has effectively closed four important research gaps. To increase the accessibility of this critical material, the results of the study take the form of easy-to-read tables just generated. Applying deep learning techniques in SSVEP-based BCI applications, as the research shows, also has its downsides. The study concludes that a radical framework will be presented which, includes intelligent decision-making tools for evaluation and benchmarking. Rather than just finding a comparable or similar analogy, this framework is intended to help guide future research and pragmatic applications, and to determine which SSVEP-based BCI applications have succeeded at responsibility for what they set out with. [ABSTRACT FROM AUTHOR]

Blockchain technology has unlocked the doors of building decentralized applications, where security plays a vital role. Any transaction ever created in a blockchain is recorded permanently. With the increasing usage of social media modalities today, many non-reputable sources create and publish fake and luring news. Due to the easy availability of the internet and excessive use of social media, fake news can spread like a flash. It causes the need to eliminate fake news posted on social media platforms. The main motive of the paper is to develop an ensemble model that assists in the automated identification of fake news. This paper addresses the identified gaps in detecting multi-modal fake news. We propose Fake News Network (FNNet) as a novel secure blockchain-based deep learning model to detect fake news. It uses blockchain and deep learning to assure data integrity and learn data representations, respectively. The proposed model consists of four layers: the node layer, the deep learning layer, the blockchain layer, and the network layer. This is an ensemble deep-learning model that leverages Bi-LSTM and CNN models, where the Bi-LSTM model captures the sequential data in both directions, and CNN captures the hidden features. We use Pheme, CrisisLexT6, and ISOT datasets to train the model. FNNet achieves an average accuracy of 86.93%, 92.22%, and 98.53% on Pheme, CrisisLexT9, and ISOT datasets, respectively. Our results show that the proposed model is robust and applicable to real-time datasets and social media networks to detect fake news effectively. [ABSTRACT FROM AUTHOR]

Face recognition (FR) uses a passive approach to person authentication that avoids face-to-face contact. Among different FR techniques, most FR approaches place little emphasis on reducing powerful cryptography and instead concentrate on increasing recognition rates. In this paper, we have proposed the Hidden Markov Model (HMM) and convolutional Neural Network (CNN) models for FR by using ORL and Yale datasets. Facial images from the given data sets are divided into 3 portions, 4 portions, 5 portions, and 6 portions corresponding to their respective HMM hidden states being used in the HMM model. Quantized levels of eigenvalues and eigenvector coefficients of overlapping blocks of facial images define the observation states of the HMM model. For image selection and rejection, a threshold is calculated using singular value decomposition (SVD). After training HMM on 3 states HMM, 4 states HMM, 5 states HMM, and 6 states HMM, the recognition accuracies are 96.5%, 98.5%, 98.5%, and 99.5%, respectively, on the ORL database and 90.6667%, 94.6667%, 94.6667%, and 94.6667% on the Yale database. The CNN model uses convolutional layers, a max-pooling layer, a flattening layer, a dense layer, and a dropout layer. Relu is used as the activation function in all layers except in the last layer, where softmax is used as the activation function. Cross entropy is used as a loss function, and we have used the Adam optimizer in our proposed algorithm. The proposed CNN model has given 100% training and testing accuracy on the ORL data set. While using the Yale data set, the CNN model has a training accuracy of 100% and a testing accuracy of 85.71%. In this paper, our proposed model showed that the HMM model is cost-effective with lesser accuracy, while the CNN model is more accurate as compared to HMM but has a higher computational cost. [ABSTRACT FROM AUTHOR]

In the last few years, the use of convolutional neural networks (CNNs) in intrusion detection domains has attracted more and more attention. However, their results in this domain have not lived up to expectations compared to the results obtained in other domains, such as image classification and video analysis. This is mainly due to the datasets used, which contain preprocessed features that are not compatible with convolutional neural networks, as they do not allow a full exploit of all the information embedded in the original network traffic. With the aim of overcoming these issues, we propose in this paper a new efficient convolutional neural network model for network intrusion detection based on raw traffic data (pcap files) rather than preprocessed data stored in CSV files. The novelty of this paper lies in the proposal of a new method for adapting the raw network traffic data to the most suitable format for CNN models, which allows us to fully exploit the strengths of CNNs in terms of pattern recognition and spatial analysis, leading to more accurate and effective results. Additionally, to further improve its detection performance, the structure and hyperparameters of our proposed CNN-based model are automatically adjusted using the self-adaptive differential evolution (SADE) metaheuristic, in which symmetry plays an essential role in balancing the different phases of the algorithm, so that each phase can contribute in an equal and efficient way to finding optimal solutions. This helps to make the overall performance more robust and efficient when solving optimization problems. The experimental results on three datasets, KDD-99, UNSW-NB15, and CIC-IDS2017, show a strong symmetry between the frequency values implemented in the images built for each network traffic and the different attack classes. This was confirmed by a good predictive accuracy that goes well beyond similar competing models in the literature. [ABSTRACT FROM AUTHOR]

This paper proposes a novel drone detection method based on a convolutional neural network (CNN) utilizing range–Doppler map images from a frequency-modulated continuous-wave (FMCW) radar. The existing drone detection and identification techniques, which rely on the micro-Doppler signature (MDS), face challenges when a drone is small or located far away, leading to performance degradation due to signal attenuation and faint (MDS). In order to address these issues, this paper suggests a method where multiple time-series range–Doppler images from an FMCW radar are overlaid onto a single image and fed to a CNN. The experimental results, using actual data for three different drone sizes, show significant performance improvements in drone detection accuracy compared to conventional methods. [ABSTRACT FROM AUTHOR]

The fault diagnosis of rolling bearings is faced with the problem of a lack of fault data. Currently, fault diagnosis based on traditional convolutional neural networks decreases the diagnosis rate. In this paper, the developed adaptive residual shrinkage network model is combined with transfer learning to solve the above problems. The model is trained on the Case Western Reserve dataset, and then the trained model is migrated to a small-sample dataset with a scaled-down sample size and the Jiangnan University bearing dataset to conduct the experiments. The experimental results show that the proposed method can efficiently learn from small-sample datasets, improving the accuracy of the fault diagnosis of bearings under variable loads and variable speeds. The adaptive parameter-rectified linear unit is utilized to adapt the nonlinear transformation. When rolling bearings are in operation, noise production is inevitable. In this paper, soft thresholding and an attention mechanism are added to the model, which can effectively process vibration signals with strong noise. In this paper, the real noise is simulated by adding Gaussian white noise in migration task experiments on small-sample datasets. The experimental results show that the algorithm has noise resistance. [ABSTRACT FROM AUTHOR]

Forest fire is a severe natural disaster, which leads to the destruction of forest ecology. At present, fire detection technology represented by convolutional neural network is widely used in forest resource protection, which can realize rapid analysis. However, in forest flame and smoke detection tasks, due to continuous expansion of the target range, a better detection effect cannot be achieved. This paper proposes an improved YOLOX method for multi-scale forest fire detection. This method proposes a novel feature pyramid model to reduce the information loss of high-level forest fire feature maps and enhance the representation ability of feature pyramids. Moreover, the method applies a small object data augmentation strategy to enrich the forest fire dataset, making it more suitable for the actual forest fire scene. According to the experimental results, the mAP of the model proposed in this paper reaches 79.64%, which is about 4.89% higher than the baseline network YOLOX. The method improves the accuracy of forest fire detection, reduces false alarms, and is suitable for real scenarios of forest fires. [ABSTRACT FROM AUTHOR]

Due to the harsh working environments of certain bridges, the bridge structural health monitoring systems (SHMs) are prone to error warning because of anomaly data. Therefore, it is of great significance to accurately classify and locate the anomaly data for effectively addressing these issues. This paper proposes a method for classifying and locating anomaly data utilizing one-dimensional monitoring data based on convolutional neural networks. Compared to previous research reliant on visual features, the proposed method has lower computational costs. By incorporating the anomaly data localization network, manual localization operations for data restoration are replaced. The analysis in this paper is based on monitoring data from a large-span cable-stayed bridge, along with artificially generated anomaly data. The two neural network frameworks proposed in this paper are trained and validated, showcasing precise classification and localization of anomaly data. Furthermore, the paper discusses the impact of common errors in labeling data categories and locating training samples in practical operations. The results demonstrate that even in the presence of noticeable yet non-extreme labeling errors in the training set, the proposed method still achieves accurate classification and localization, highlighting its robustness. [ABSTRACT FROM AUTHOR]

Accurate power load forecasting can provide crucial insights for power system scheduling and energy planning. In this paper, to address the problem of low accuracy of power load prediction, we propose a method that combines secondary data cleaning and adaptive variational mode decomposition (VMD), convolutional neural networks (CNN), bi-directional long short-term memory (BILSTM), and adding attention mechanism (AM). The Inner Mongolia electricity load data were first cleaned use the K-means algorithm, and then further refined with the density-based spatial clustering of applications with the noise (DBSCAN) algorithm. Subsequently, the parameters of the VMD algorithm were optimized using a multi-strategy Cubic-T dung beetle optimization algorithm (CTDBO), after which the VMD algorithm was employed to decompose the twice-cleaned load sequences into a number of intrinsic mode functions (IMFs) with different frequencies. These IMFs were then used as inputs to the CNN-BILSTM-Attention model. In this model, a CNN is used for feature extraction, BILSTM for extracting information from the load sequence, and AM for assigning different weights to different features to optimize the prediction results. It is proved experimentally that the model proposed in this paper achieves the highest prediction accuracy and robustness compared to other models and exhibits high stability across different time periods. [ABSTRACT FROM AUTHOR]

Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model's performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model's mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems. [ABSTRACT FROM AUTHOR]

With the immense growth of the internet, sensitive, confidential, important corporate and individual data passing through the internet has grown rapidly. Due to the limitation of security systems, potential hackers and attackers have possessed vulnerabilities and attacks for intruding into the network to gain confidential and sensitive information to affect the performance of networks by breaching network confidentiality. Thereby, to counterfeit these attacks and abnormal behaviors, a network intrusion detection system (NIDS), acts as a crucial branch of cybersecurity for analysis and monitoring the network traffic regularly to report and detect abnormal and malicious activities in a network. Currently, various reviews and survey papers have covered various techniques for NIDS, out of which, mostly followed a non-systematic way of approach without an in-depth analysis of techniques and evaluation metrics used by deep learning(DL) based NIDS models. In addition, various reviews focused on machine learning (ML) and DL-based methodology, but with less emphasis on DL techniques (i.e. AE, CNN, DNN, DBN, RNN, and Hybrid DL) based classification. Thereby, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology was used to accomplish this work by providing a comprehensive and detailed overview of DL-based NIDS. Research papers for this work were collected from five well-known databases (ScienceDirect, IEEE, Hindawi, SpringerNature, and MDPI) which were cut among several reputable conference proceedings and reputable journals. Across the 750 articles identified in the literature, 72 research papers were finally marked and selected for synthesis and analysis to find the answers to research questions. In addition, we identified various potential research challenges in the current domain based on research findings. Lastly, to design an efficient NIDS, we concluded our study by identifying high-impact and promising future research areas in the NIDS domain. [ABSTRACT FROM AUTHOR]

As a vital component of mining hoisting equipment, mining wire rope (MWR) is critical in the operation of the mine. Once damaged, it is very easy to cause the loss of life and property. Therefore, it is meaningful to identify the damage to MWR, especially the weak damage identification. This paper proposes a method based on continuous wavelet transform (CWT) and convolutional neural network (CNN) model for MWR damage degree identification. Firstly, the MWR signals with different damage degrees were acquired. Secondly, CWT and data augmentation were performed on the original signals to obtain a time-frequency image dataset of MWR damage degree. Then, a deep learning (DL) model is built for identification and compared with traditional machine learning and some classical CNN models. The results show that the model proposed in this paper is better than the traditional machine learning models. It has the highest accuracy of 91.58% in MWR damage degree identification with classical CNN models. The method focuses on the weak damage of MWR and combines CWT with CNN model to meet the requirements of accuracy and efficiency, detecting the early damage as soon as possible and ensuring intelligent, safe and stable operation in the mining industry. [ABSTRACT FROM AUTHOR]

Understanding road conditions is essential for implementing effective road safety measures and driving solutions. Road situations encompass the day-to-day conditions of roads, including the presence of vehicles and pedestrians. Surveillance cameras strategically placed along streets have been instrumental in monitoring road situations and providing valuable information on pedestrians, moving vehicles, and objects within road environments. However, these video data and information are stored in large volumes, making analysis tedious and time-consuming. Deep learning models are increasingly utilized to monitor vehicles and identify and evaluate road and driving comfort situations. However, the current neural network model requires the recognition of situations using time-series video data. In this paper, we introduced a multi-directional detection model for road situations to uphold high accuracy. Deep learning methods often integrate long short-term memory (LSTM) into long-term recurrent network architectures. This approach effectively combines recurrent neural networks to capture temporal dependencies and convolutional neural networks (CNNs) to extract features from extensive video data. In our proposed method, we form a multi-directional long-term recurrent convolutional network approach with two groups equipped with CNN and two layers of LSTM. Additionally, we compare road situation recognition using convolutional neural networks, long short-term networks, and long-term recurrent convolutional networks. The paper presents a method for detecting and recognizing multi-directional road contexts using a modified LRCN. After balancing the dataset through data augmentation, the number of video files increased, resulting in our model achieving 91% accuracy, a significant improvement from the original dataset. [ABSTRACT FROM AUTHOR]

The aim of image inpainting is to fill in damaged areas according to certain rules based on information about the adjacent positions of missing areas and the overall structure of the image, a technique that plays a key role in various tasks in computer vision. With the rapid development of deep learning, researchers have combined it with image inpainting and achieved excellent performance. To gain insight into the techniques involved, this paper summarizes the latest research advances in the field of image inpainting. Firstly, existing classical image inpainting methods are reviewed, and traditional image inpainting methods and their advantages and disadvantages are introduced. Secondly, three classical network models are outlined, and the image inpainting methods are classified into single-stage, multi-stage and a priori condition-guided approaches according to different network types and model structures. Representative algorithms among them are selected and their important technical improvement ideas are analyzed and summarized. Then, the common datasets commonly used in image inpainting tasks and the evaluation metrics used to evaluate inpainting results are introduced. The paper presents a comprehensive summary of the various algorithms in terms of network models and inpainting methods, and selects representative algorithms for quantitative and qualitative comparative analysis. Finally, the future development trends and research directions have prospected, and the current problems of image inpainting are summarized. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to improve the manufacturability of additive manufacturing (AM) for topology-optimized (TO) structures. Enhancement of manufacturability focuses on modifying geometric constraints and classifying the building orientation (BO) of AM parts to reduce stresses and support structures (SSs). To this end, artificial intelligence (AI) networks are being developed to automate design for additive manufacturing (DfAM). Design/methodology/approach: This study considers three geometric constraints for their correction by convolutional autoencoders (CAEs) and transfer learning (TL). Furthermore, BOs of AM parts are classified using generative adversarial (GAN) and classification networks to reduce the SS. To verify the results, finite element analysis (FEA) is performed to compare the stresses of modified components with the original ones. Moreover, one sample is produced by the laser-based powder bed fusion (LB-PBF) in the BO predicted by the AI to observe its SSs. Findings: CAE and TL resulted in promoting the manufacturability of TO components. FEA demonstrated that enhancing manufacturability leads to a 50% reduction in stresses. Additionally, training GAN and pre-training the ResNet-18 resulted in 80%, 95% and 96% accuracy for training, validation and testing. The production of a sample with LB-PBF demonstrated that the predicted BO by ResNet-18 does not require SSs. Originality/value: This paper provides an automatic platform for DfAM of TO parts. Consequently, complex TO parts can be designed most feasibly and manufactured by AM technologies with minimal material usage, residual stresses and distortions. [ABSTRACT FROM AUTHOR]

The precision of short-term photovoltaic power forecasts is of utmost importance for the planning and operation of the electrical grid system. To enhance the precision of short-term output power prediction in photovoltaic systems, this paper proposes a method integrating K-means clustering: an improved snake optimization algorithm with a convolutional neural network–bidirectional long short-term memory network to predict short-term photovoltaic power. Firstly, K-means clustering is utilized to categorize weather scenarios into three categories: sunny, cloudy, and rainy. The Pearson correlation coefficient method is then utilized to determine the inputs of the model. Secondly, the snake optimization algorithm is improved by introducing Tent chaotic mapping, lens imaging backward learning, and an optimal individual adaptive perturbation strategy to enhance its optimization ability. Then, the multi-strategy improved snake optimization algorithm is employed to optimize the parameters of the convolutional neural network–bidirectional long short-term memory network model, thereby augmenting the predictive precision of the model. Finally, the model established in this paper is utilized to forecast photovoltaic power in diverse weather scenarios. The simulation findings indicate that the regression coefficients of this method can reach 0.99216, 0.95772, and 0.93163 on sunny, cloudy, and rainy days, which has better prediction precision and adaptability under various weather conditions. [ABSTRACT FROM AUTHOR]

The traditional method for retrieving cloud optical thickness (COT) is carried out through a Look-Up Table (LUT). Researchers must make a series of idealized assumptions and conduct extensive observations and record features in this scenario, consuming considerable resources. The emergence of deep learning effectively addresses the shortcomings of the traditional approach. In this paper, we first propose a daytime (SOZA < 70°) COT retrieval algorithm based on FY-4A AGRI. We establish and train a Convolutional Neural Network (CNN) model for COT retrieval, CM4CR, with the CALIPSO's COT product spatially and temporally synchronized as the ground truth. Then, a deep learning method extended from video prediction models is adopted to predict COT values based on the retrieval results obtained from CM4CR. The COT prediction model (CPM) consists of an encoder, a predictor, and a decoder. On this basis, we further incorporated a time embedding module to enhance the model's ability to learn from irregular time intervals in the input COT sequence. During the training phase, we employed Charbonnier Loss and Edge Loss to enhance the model's capability to represent COT details. Experiments indicate that our CM4CR outperforms existing COT retrieval methods, with predictions showing better performance across several metrics than other benchmark prediction models. Additionally, this paper also investigates the impact of different lengths of COT input sequences and the time intervals between adjacent frames of COT on prediction performance. [ABSTRACT FROM AUTHOR]

This paper introduces a novel one-dimensional convolutional neural network that utilizes clinical data to accurately detect choledocholithiasis, where gallstones obstruct the common bile duct. Swift and precise detection of this condition is critical to preventing severe complications, such as biliary colic, jaundice, and pancreatitis. This cutting-edge model was rigorously compared with other machine learning methods commonly used in similar problems, such as logistic regression, linear discriminant analysis, and a state-of-the-art random forest, using a dataset derived from endoscopic retrograde cholangiopancreatography scans performed at Olive View–University of California, Los Angeles Medical Center. The one-dimensional convolutional neural network model demonstrated exceptional performance, achieving 90.77% accuracy and 92.86% specificity, with an area under the curve of 0.9270. While the paper acknowledges potential areas for improvement, it emphasizes the effectiveness of the one-dimensional convolutional neural network architecture. The results suggest that this one-dimensional convolutional neural network approach could serve as a plausible alternative to endoscopic retrograde cholangiopancreatography, considering its disadvantages, such as the need for specialized equipment and skilled personnel and the risk of postoperative complications. The potential of the one-dimensional convolutional neural network model to significantly advance the clinical diagnosis of this gallstone-related condition is notable, offering a less invasive, potentially safer, and more accessible alternative. [ABSTRACT FROM AUTHOR]

Radio frequency interference (RFI) significantly hampers the target detection performance of frequency-modulated continuous-wave radar. To address the problem and maintain the target echo signal, this paper proposes a priori assumption on the interference component nature in the radar received signal, as well as a method for interference estimation and mitigation via time–frequency analysis. The solution employs Fourier synchrosqueezed transform to implement the radar's beat signal transformation from time domain to time–frequency domain, thus converting the interference mitigation to the task of time–frequency distribution image restoration. The solution proposes the use of image processing based on the dual-tree complex wavelet transform and combines it with the spatial domain-based approach, thereby establishing a dual-domain fusion interference filter for time–frequency distribution images. This paper also presents a convolutional neural network model of structurally improved UNet++, which serves as the interference estimator. The proposed solution demonstrated its capability against various forms of RFI through the simulation experiment and showed a superior interference mitigation performance over other CNN model-based approaches. [ABSTRACT FROM AUTHOR]

The safety and robustness of convolutional neural networks (CNNs) have raised increasing concerns, especially in safety-critical areas, such as medical applications. Although CNNs are efficient in image classification, their predictions are often sensitive to minor, for human observers, invisible modifications of the image. Thus, a modified, corrupted image can be visually equal to the legitimate image for humans but fool the CNN and make a wrong prediction. Such modified images are called adversarial images throughout this paper. A popular method to generate adversarial images is backpropagating the loss gradient to modify the input image. Usually, only the direction of the gradient and a given step size were used to determine the perturbations (FGSM, fast gradient sign method), or the FGSM is applied multiple times to craft stronger perturbations that change the model classification (i-FGSM). On the contrary, if the step size is too large, the minimum perturbation of the image may be missed during the gradient search. To seek exact and minimal input images for a classification change, in this paper, we suggest starting the FGSM with a small step size and adapting the step size with iterations. A few decay algorithms were taken from the literature for comparison with a novel approach based on an index tracking the loss status. In total, three tracking functions were applied for comparison. The experiments show our loss adaptive decay algorithms could find adversaries with more than a 90% success rate while generating fewer perturbations to fool the CNNs. [ABSTRACT FROM AUTHOR]

The existing change detection methods are difficult to balance local features and global features, and the boundary between change objects and backgrounds is blurred, so this paper proposed a remote sensing image building change detection method based on local-global feature coupling and boundary guidance. In the encoding stage, the method adopted parallel convolutional neural network and Transformer to extract the local features and global representation of remote sensing images, respectively. At different scales, the local-global feature coupling module fused local features and global feature representation to enhance the expression ability of image features. In addition, it introduced the boundary guidance branch to obtain the prior boundary information of the change objects, so that its guide change map can highlight the structural characteristics of the building and promote the accurate boundary location. This paper conducted experiments on the LEVIR-CD and WHU datasets, resulting in F1-score of 91.25% and 91.27%, IoU of 83.90% and 83.95%, respectively. The experimental results show that the method has a great improvement in the detection accuracy and good generalization ability. [ABSTRACT FROM AUTHOR]

Satellite networking, as the future development direction of aero-space, requires high-precision autonomous fault diagnosis capability for a single satellite. In this paper, aiming at the characteristics of closed-loop fault propagation and high data dimensionality of spacecraft control system, neural network algorithms are conducted to study the fault diagnosis of spacecraft high-dimensional coupled data. Based on the ground test data of a certain spacecraft, this paper converts the high-dimensional sequence data into grayscale images, and then uses Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to diagnose them respectively. The effectiveness of the methods in this paper is illustrated by comparing and validating them with three non-image-based machine learning algorithms, namely, K-NearestNeighbor, Bayesian classifier, and K-NearestNeighbor based on Principal Component Analysis. [ABSTRACT FROM AUTHOR]

A pipeline is critical in conveying water, oil, gas, petrochemicals, and slurry. As the pipeline ages and corrodes, it becomes susceptible to deterioration, resulting in wastage and hazardous damages depending on the material it transports. To mitigate these risks, implementing a suitable monitoring system becomes essential, enabling the early identification of damage and minimizing waste and the potential for hazardous incidents. The pipeline monitoring system can be exterior, visual/biological, and computational. This paper surveys state-of-the-art approaches and also performs experimental analyses with a few methods in signal/data-driven approaches within computational methods. More precisely, signal processing-based leak localization methods, artificial intelligence-based leak detection methods, and combined approaches are given. This paper implements five signal processing-based methods and 17 artificial intelligence-based methods. This implementation helps to compare and understand the significance of appropriate noise removal and feature extraction. The data for this analysis is collected using acousto-optic sensors from an experimental setup. After implementation, the highest observed leak localization accuracy is 99.14% with the wavelet packet adaptive independent component analysis-based generalized cross correlation, and the highest leak detection accuracy is 98.32% with the one-dimensional convolutional neural network. [ABSTRACT FROM AUTHOR]

With the advent of intelligent manufacturing era, higher requirements are put forward for the fault diagnosis technology of machinery. The existing data‐driven approaches either rely on specialized empirical knowledge for feature analysis, or adopt single deep neural network topology structure for automatic feature extraction with compromise of certain information loss especially the time‐series information's sacrifice, which both eventually affect the diagnosis accuracy. To address the issue, this paper proposes a novel multi‐temporal correlation feature fusion net (MTCFF‐Net) for intelligent fault diagnosis, which can capture and retain time‐series fault feature information from different dimensions. MTCFF‐Net contains four sub‐networks, which are long and short‐term memory (LSTM) sub‐network, Gramian angular summation field (GASF)‐GhostNet sub‐network and Markov transition field (MTF)‐GhostNet sub‐network and feature fusion sub‐network. Features of different dimensional are extracted through parallel LSTM sub‐network, GASF‐GhostNet sub‐network and MTF‐GhostNet sub‐network, and then fused by feature fusion sub‐network for accurate fault diagnosis. Two fault diagnosis experimental studies on bearings are implemented to validate the effectiveness and generalization of the proposed MTCFF‐Net. Experimental results demonstrate that the proposed model is superior to other comparative approaches. [ABSTRACT FROM AUTHOR]

Automatically extracting roads from remote sensing images is increasingly important for autonomous driving and geographic information systems. However, due to factors such as ground objects blocking road boundaries and some roads being narrow and long in high-resolution remote sensing images, it is difficult for the current mainstream pixel-level extraction model to guarantee the continuity of roads and the smoothness of boundaries. To solve this problem, this paper designs a neural network Rse-net based on semantic segmentation, using a two-stream semantic segmentation network algorithm to make the network pay more attention to the boundary information of roads and narrow roads. This structure uses shape stream to process road boundary information (roads' shape stream), and processes it in parallel with classic stream. Use the Gated Shape CNN to connect the two streams of roads' shape stream and classic stream, and use the classical stream to optimize the boundary information in the shape stream. At the same time, a multi-scale convolutional attention mechanism is used between the decoder and the encoder to expand the receptive field through large-core attention, and obtain more semantic information without causing too much calculation. Finally, the effectiveness of the proposed network is verified by comparative experiments. [ABSTRACT FROM AUTHOR]

The efficient detection of leakages in water distribution networks (WDNs) is crucial to ensuring municipal water supply safety and improving urban operations. Traditionally, machine learning methods such as Convolutional Neural Networks (CNNs) and Autoencoders (AEs) have been used for leakage detection. However, these methods heavily rely on local pressure information and often fail to capture long-term dependencies in pressure series. In this paper, we propose a transformer-based model for detecting leakages in WDNs. The transformer incorporates an attention mechanism to learn data distributions and account for correlations between historical pressure data and data from the same time on different days, thereby emphasizing long-term dependencies in pressure series. Additionally, we apply pressure data normalization across each leakage scenario and concatenate position embeddings with pressure data in the transformer model to avoid feature misleading. The performance of the proposed method is evaluated by using detection accuracy and F1-score. The experimental studies conducted on simulated pressure datasets from three different WDNs demonstrate that the transformer-based model significantly outperforms traditional CNN methods. [ABSTRACT FROM AUTHOR]

The accurate extraction of buildings from remote sensing images is crucial in fields such as 3D urban planning, disaster detection, and military reconnaissance. In recent years, models based on Transformer have performed well in global information processing and contextual relationship modeling, but suffer from high computational costs and insufficient ability to capture local information. In contrast, convolutional neural networks (CNNs) are very effective in extracting local features, but have a limited ability to process global information. In this paper, an asymmetric network (CTANet), which combines the advantages of CNN and Transformer, is proposed to achieve efficient extraction of buildings. Specifically, CTANet employs ConvNeXt as an encoder to extract features and combines it with an efficient bilateral hybrid attention transformer (BHAFormer) which is designed as a decoder. The BHAFormer establishes global dependencies from both texture edge features and background information perspectives to extract buildings more accurately while maintaining a low computational cost. Additionally, the multiscale mixed attention mechanism module (MSM-AMM) is introduced to learn the multiscale semantic information and channel representations of the encoder features to reduce noise interference and compensate for the loss of information in the downsampling process. Experimental results show that the proposed model achieves the best F1-score (86.7%, 95.74%, and 90.52%) and IoU (76.52%, 91.84%, and 82.68%) compared to other state-of-the-art methods on the Massachusetts building dataset, the WHU building dataset, and the Inria aerial image labeling dataset. [ABSTRACT FROM AUTHOR]

Pansharpening refers to enhancing the spatial resolution of multispectral images through panchromatic images while preserving their spectral features. However, existing traditional methods or deep learning methods always have certain distortions in the spatial or spectral dimensions. This paper proposes a remote sensing spatial–spectral fusion method based on a multi-scale dual-stream convolutional neural network, which includes feature extraction, feature fusion, and image reconstruction modules for each scale. In terms of feature fusion, we propose a multi cascade module to better fuse image features. We also design a new loss function aim at enhancing the high degree of consistency between fused images and reference images in terms of spatial details and spectral information. To validate its effectiveness, we conduct thorough experimental analyses on two widely used remote sensing datasets: GeoEye-1 and Ikonos. Compared with the nine leading pansharpening techniques, the proposed method demonstrates superior performance in multiple key evaluation metrics. [ABSTRACT FROM AUTHOR]

Leather products are widely used across various fields permeating every aspect of daily life. However during the production of synthetic leather fabrics defects are inevitable directly affecting the quality and price of leather products. Early identification of these defects in the production process can prevent further production losses. Nevertheless the high local similarity of defects on leather fabric surfaces causes significant similarities between different types of defects leading to poor detection results. To address this issue the article proposed an end-to-end defect detection method for leather fabric surfaces achieving finer granularity in distinguishing leather defects. To address the high similarity between defect classes this paper introduced an adaptive convolutional attention ACA module. This module comprises channel attention and spatial attention integrating the channel and spatial attention information through a residual structure to generate more discriminative features. Two different-sized convolutional kernels in the spatial attention work in concert to effectively enhance the differences between defects focusing attention on target features and thus reducing the interference response to background information. To amplify the differences between leather fabric defect classes ACA was incorporated into the backbone network to enhance the semantic feature representation capabilities. This integration not only improves the network's ability to differentiate between defect types but also ensures more accurate detection outcomes. Then the article designed a feature pyramid network based on adaptive convolutional attention AC-FPN to improve multi-scale fusion. By leveraging the feature information enhanced by ACA the network enables the flow of information between different scales allowing for finer differentiation between defects and background. Such enhancement significantly improves the detection capability of defects at different scales achieving finer granularity in leather defect differentiation. The multi-scale fusion process ensures that defects of various sizes and shapes are accurately detected regardless of their scale contributing to a more robust detection system. Finally the traditional detection head was replaced with the side-aware boundary localization SABL detection head enabling precise localization of leather fabric defects. The SABL detection head is specifically designed to enhance the accuracy of defect localization by focusing on the boundaries of defects ensuring that even the smallest and most subtle defects are accurately identified and localized. This replacement is crucial for improving the overall precision of the defect detection system making it more reliable for practical applications in leather fabric production. The article validated the proposed method using a self-constructed leather fabric dataset and compared it with different methods. Experimental results demonstrate that the proposed method achieves better performance in distinguishing between different defect types with similar appearances. Compared to other methods this method exhibits superior detection accuracy across various defect types with AP AP50 and AP75 evaluation metrics reaching 83. 4 89. 7 and 85. 6 respectively. This provides a new perspective for automated surface defect detection of leather fabrics. The improved accuracy metrics indicate that the proposed method is highly effective in identifying and classifying defects with significant improvement over existing methods. The proposed defect detection method for leather fabrics demonstrates better performance compared to other methods offering new feasibility for defect detection. Despite the advantages mentioned above the use of a dataset primarily comprising grayscale images may reduce the ability to extract effective information for some colored leather defects. In future research color cameras can be used to capture images of leather defects and incorporate color information to distinguish some leather fabric surface defects. Additionally exploring advanced image processing techniques and integrating them with the current approach could further enhance the defect detection capabilities so as to make the system more versatile and applicable to a wider range of leather products. [ABSTRACT FROM AUTHOR]

This paper introduces a novel normalization operation, Channel Modulus Normalization (CMN), to enhance the image classification performance of traditional convolutional neural networks (CNNs) by leveraging latent feature characteristics across all levels. CMN is seamlessly integrated into existing CNN architectures without using additional trainable parameters. Following convolution operations at every level, CMN is applied to each feature map, utilizing a normalization adjustment factor to mitigate the influence of feature modulus length. This operation pays more attention to the change characteristics of the image details for classification. Experiments on six datasets such as CIFAR10, CIFAR100, FaceScrub, Tiny ImageNet, ImageNet (100), and ImageNet (1000), show that the channel modulus normalization operation can effectively improve the classification accuracy of the datasets above. Taking ResNet50 as an example, it is increased by 0.57%, 3.17%, 1.11%, 2.28%, 0.61% and 0.14% respectively. At the same time, the normalization operation will not increase the number of parameters of the model, and the convergence performance during training is better, which will only increase a small amount of calculation. The implementation code is available at . [ABSTRACT FROM AUTHOR]

Hyperspectral image classification (HSI) is a vital aspect of remote sensing technology. However, the high-dimensional nature of HSI and the continuous spectral bands significantly impact its classification performance. In this paper, we propose a classification method called MBSFC for HSI classification. MBSFC utilizes multi-branch and spectral feature conversion (SFC) techniques to eliminate redundant information and extract valuable features. Firstly, to preserve spectral-spatial information, the SFC block is introduced to eliminate redundant information through up-sampling. Subsequently, the feature maps from the SFC block and the spectral bands reduced by a factor of four are fed into three branches: the spectral branch, spatial-X branch, and spatial-Y branch. Each branch employs a 3D-CNN-based dense block and attention mechanism to extract useful features. Finally, the obtained features from the three branches are fused for HSI classification. To cater to different application scenarios, we divide MBSFC into three models with different network structures: MBSFC-s, MBSFC-m, and MBSFC-l. The MBSFC-l model, with a three-branch structure, achieves the best performance. The three models differ in the number of branches in the feature extraction. Experimental results on four publicly available hyperspectral datasets show that MBSFC achieves competitive results with small samples compared to other state-of-the-art methods. The code is available at https://github.com/TeresaTing/MBSFC. [ABSTRACT FROM AUTHOR]

Many major diseases of the retina often show symptoms of lesions in the fundus of the eye. The extraction of blood vessels from retinal fundus images is essential to assist doctors. Some of the existing methods do not fully extract the detailed features of retinal images or lose some information, making it difficult to accurately segment capillaries located at the edges of the images. In this paper, we propose a multi-scale retinal vessel segmentation network (SCIE_Net) based on skip connection information enhancement. Firstly, the network processes retinal images at multiple scales to achieve network capture of features at different scales. Secondly, the feature aggregation module is proposed to aggregate the rich information of the shallow network. Further, the skip connection information enhancement module is proposed to take into account the detailed features of the shallow layer and the advanced features of the deeper network to avoid the problem of incomplete information interaction between the layers of the network. Finally, SCIE_Net achieves better vessel segmentation performance and results on the publicly available retinal image standard datasets DRIVE, CHASE_DB1, and STARE. [ABSTRACT FROM AUTHOR]

In clinical practice, the morphology of the left atrial appendage (LAA) plays an important role in the selection of LAA closure devices for LAA closure procedures. The morphology determination is influenced by the segmentation results. The LAA occupies only a small part of the entire 3D medical image, and the segmentation results are more likely to be biased towards the background region, making the segmentation of the LAA challenging. In this paper, we propose a lightweight attention mechanism called fusion attention, which imitates human visual behavior. We process the 3D image of the LAA using a method that involves overview observation followed by detailed observation. In the overview observation stage, the image features are pooled along the three dimensions of length, width, and height. The obtained features from the three dimensions are then separately input into the spatial attention and channel attention modules to learn the regions of interest. In the detailed observation stage, the attention results from the previous stage are fused using element-wise multiplication and combined with the original feature map to enhance feature learning. The fusion attention mechanism was evaluated on a left atrial appendage dataset provided by Liaoning Provincial People's Hospital, resulting in an average Dice coefficient of 0.8855. The results indicate that the fusion attention mechanism achieves better segmentation results on 3D images compared to existing lightweight attention mechanisms. [ABSTRACT FROM AUTHOR]

In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained R P 2 of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (R P 2 = 0.85) compared to RF bands (R P 2 = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with R P 2 of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved R P 2 above 0.93 in individual years (R P 2 = 0.96 in 2021, R P 2 = 0.94 in 2021) and R P 2 in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation. • 3DCNN-LSTM method was proposed to extract spectral-spatial feature for LCC estimation. • 3DCNN reduced the interference of soil and crop difference. • 3DCNN-LSTM method can reduce the image segmentation procedure. • LSTM captured growth dynamics and improved robustness in multiple years and stages. [ABSTRACT FROM AUTHOR]

This paper investigates the nuanced characteristics of the spectral envelope attributes due to vocal-tract resonance structure and fine-level excitation source features within short-term Fourier transform (STFT) magnitude spectra for the assessment of dysarthria. The single-channel convolutional neural network (CNN) employing time-frequency representations such as STFT spectrogram (STFT-SPEC) and Mel-spectrogram (MEL-SPEC) does not ensure capture of the source and system information simultaneously due to the filtering operation using a fixed-size filter. Building upon this observation, this study first explores the significance of convolution filter size in the context of the CNN-based automated dysarthric assessment system. An approach is then introduced to effectively capture resonance structure and fine-level features through a multi-channel CNN. In the proposed approach, the STFT-SPEC is decomposed using a one-level discrete wavelet transform (DWT) to separate the slow-varying spectral structure and fine-level features. The resulting decomposed coefficients in four directions are taken as the inputs to multi-channel CNN to capture the source and system features by employing different sizes of convolution filters. The experimental results conducted on the UA-speech corpus validate the efficacy of the proposed approach utilizing multi-channel CNN. The proposed approach demonstrates the notable enhancement in accuracy and F1 score (60.86% and 48.52%) compared to a single-channel CNN using STFT-SPEC (46.45% and 40.97%), MEL-SPEC (48.86% and 38.20%), and MEL-SPEC appended with delta and delta-delta coefficients (52.40% and 42.84%) for assessment of dysarthria in a speaker-independent and text-independent mode. [ABSTRACT FROM AUTHOR]

Current research in deep learning, which is widely used in mineral prospectivity prediction, focuses on obtaining high-performance models to predict mineral resources. However, because the network structure and depth of different algorithms differ, there are some differences in the correlation between the spatial pattern of ore-generating geological big data and the spatial location of discovered ore deposits; this causes instability in the prediction. To solve this problem, this paper proposes the use of ensemble learning to synthesize convolutional neural network algorithms and self-attention mechanism algorithms for mineral prospectivity prediction. In this study, 14 factors related to gold mineralization were selected, 10 types of geochemical exploration data (Au, Ag, As, Cu, Pb, Zn, Hg, Sb, W, and Mo) and 4 geological factors (ductile shear zones, brittle fault zones, mineralization–alteration body zones, and metamorphic quartz sandstone zones). Six classical convolutional neural network models (MobileNet V2, ResNet 50, VGG 16, AlexNet, LeNet, and VIT) were used to extract the features of the metallogenic factors. After training, a network model with an accuracy over 94% was obtained. Then, the mineral prospectivity of an unknown area was predicted. The models were evaluated according to their accuracy. Using these results, ensemble learning was performed, areas with high potential were obtained, and the prospectivity prediction map was drawn. This map provides guidance for gold exploration in the Bawanggou mine area of the northern Hanyin gold orefield, South Qinling, China. This comprehensive method can effectively leverage the advantages of various models, fully extract the internal relationships of deep-level mineralization, and has extremely high extensibility. The calculated results can be made more scientific and stable by adding more mineralization factors and introducing an algorithm with the new structure in the future. [ABSTRACT FROM AUTHOR]

Current research in deep learning, which is widely used in mineral prospectivity prediction, focuses on obtaining high-performance models to predict mineral resources. However, because the network structure and depth of different algorithms differ, there are some differences in the correlation between the spatial pattern of ore-generating geological big data and the spatial location of discovered ore deposits; this causes instability in the prediction. To solve this problem, this paper proposes the use of ensemble learning to synthesize convolutional neural network algorithms and self-attention mechanism algorithms for mineral prospectivity prediction. In this study, 14 factors related to gold mineralization were selected, 10 types of geochemical exploration data (Au, Ag, As, Cu, Pb, Zn, Hg, Sb, W, and Mo) and 4 geological factors (ductile shear zones, brittle fault zones, mineralization–alteration body zones, and metamorphic quartz sandstone zones). Six classical convolutional neural network models (MobileNet V2, ResNet 50, VGG 16, AlexNet, LeNet, and VIT) were used to extract the features of the metallogenic factors. After training, a network model with an accuracy over 94% was obtained. Then, the mineral prospectivity of an unknown area was predicted. The models were evaluated according to their accuracy. Using these results, ensemble learning was performed, areas with high potential were obtained, and the prospectivity prediction map was drawn. This map provides guidance for gold exploration in the Bawanggou mine area of the northern Hanyin gold orefield, South Qinling, China. This comprehensive method can effectively leverage the advantages of various models, fully extract the internal relationships of deep-level mineralization, and has extremely high extensibility. The calculated results can be made more scientific and stable by adding more mineralization factors and introducing an algorithm with the new structure in the future. [ABSTRACT FROM AUTHOR]

Fractal dimension (FD), as an important parameter for the surface morphology of mechanical machining, can be used to analyze the friction characteristics of contacting surfaces. The accurate and rapid measurement of the FD is of significant importance. To this end, this paper presents a novel approach based on a convolutional neural network (3D-CNN) for the recognition of three-dimensional FDs on machined surfaces. We construct a dataset of anisotropic rough surfaces with different FDs using the Weierstrass–Mandelbrot (WM) fractal function and use a one-factor experimental design to analyze the influence of network parameters (network depth, filter size, filter quantity) on the accuracy of FD identification, finding the optimal combination of neural network parameters. By comparing our 3D-CNN method with three other methods (differential box-counting (DBC), triangular prism surface area (TPSA), and fractal Brownian motion (FBM)), we validated the effectiveness of our proposed method. The experimental results show that the average absolute percentage error of FD calculated by the 3D-CNN method can be controlled within 2%, and the method exhibits small errors throughout the full dynamic range of FDs. We also apply the proposed method to calculate the FD of the vertical milling surface and compare the results with the TPSA and FBM methods. The results show that the FD obtained by our method is close to the other two methods, and can be used to calculate the FD of three-dimensional surface profiles, thereby providing a new approach for the dynamic modeling and parameter identification of contact surfaces. [ABSTRACT FROM AUTHOR]

The advent of satellite-borne machine learning hardware accelerators has enabled the onboard processing of payload data using machine learning techniques such as convolutional neural networks (CNNs). A notable example is using a CNN to detect the presence of clouds in the multispectral data captured on Earth observation (EO) missions, whereby only clear sky data are downlinked to conserve bandwidth. However, prior to deployment, new missions that employ new sensors will not have enough representative datasets to train a CNN model, while a model trained solely on data from previous missions will underperform when deployed to process the data on the new missions. This underperformance stems from the domain gap, i.e., differences in the underlying distributions of the data generated by the different sensors in previous and future missions. In this paper, we address the domain gap problem in the context of onboard multispectral cloud detection. Our main contributions lie in formulating new domain adaptation tasks that are motivated by a concrete EO mission, developing a novel algorithm for bandwidth-efficient supervised domain adaptation, and demonstrating test-time adaptation algorithms on space deployable neural network accelerators. Our contributions enable minimal data transmission to be invoked (e.g., only 1% of the weights in ResNet50) to achieve domain adaptation, thereby allowing more sophisticated CNN models to be deployed and updated on satellites without being hampered by domain gap and bandwidth limitations. [ABSTRACT FROM AUTHOR]

In order to achieve impact load localization of complex structures such as ships, this paper proposes a multi-scale feature fusion convolutional neural network (MSFF-CNN) method for impact load localization. An end-to-end machine learning model is used, where the raw vibration signals of impact loads are directly fed into the network model to avoid the process of feature extraction. Automatic feature learning and feature concatenation of the signal are achieved through four independent convolutional layers, each using a different size of convolutional kernel. Data normalization and L2 regularization techniques are introduced to enhance the data and prevent overfitting. Classification and localization of impact loads are accomplished using a softmax classification layer. Validation experiments are carried out using a ship's stern compartment model. Our results show that the classification and localization accuracy of the impact load sample group of MSFF-CNN reaches 94.29% compared with a traditional CNN. The method further improves the ability of the network to extract state features, takes local perception and global vision into account, effectively improves the classification ability of the model, and has good prospects for engineering applications. [ABSTRACT FROM AUTHOR]

In this article, a deep neural network (DNN)-based underwater acoustic (UA) communication receiver is proposed. Conventional orthogonal frequency-division multiplexing (OFDM) receivers perform channel estimation using linear interpolation. However, due to the significant delay spread in multipath UA channels, the frequency response often exhibits strong non-linearity between pilot subcarriers. Since the channel delay profile is generally unknown, this non-linearity cannot be modeled precisely. A neural network (NN)-based receiver effectively tackles this challenge by learning and compensating for the non-linearity through NN training. The performance of the DNN-based UA communication receiver was tested recently in river trials in Western Australia. The results obtained from the trials prove that the DNN-based receiver performs better than the conventional least-squares (LS) estimator-based receiver. This paper suggests that UA communication using DNN receivers holds great potential for revolutionizing underwater communication systems, enabling higher data rates, improved reliability, and enhanced adaptability to changing underwater conditions. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is the second most common movement disorder in the world. It is characterized by motor and non-motor symptoms that have a profound impact on the independence and quality of life of people affected by the disease, which increases caregivers' burdens. The use of the quantitative gait data of people with PD and deep learning (DL) approaches based on gait are emerging as increasingly promising methods to support and aid clinical decision making, with the aim of providing a quantitative and objective diagnosis, as well as an additional tool for disease monitoring. This will allow for the early detection of the disease, assessment of progression, and implementation of therapeutic interventions. In this paper, the authors provide a systematic review of emerging DL techniques recently proposed for the analysis of PD by using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Scopus, PubMed, and Web of Science databases were searched across an interval of six years (between 2018, when the first article was published, and 2023). A total of 25 articles were included in this review, which reports studies on the movement analysis of PD patients using both wearable and non-wearable sensors. Additionally, these studies employed DL networks for classification, diagnosis, and monitoring purposes. The authors demonstrate that there is a wide employment in the field of PD of convolutional neural networks for analyzing signals from wearable sensors and pose estimation networks for motion analysis from videos. In addition, the authors discuss current difficulties and highlight future solutions for PD monitoring and disease progression. [ABSTRACT FROM AUTHOR]

Recommender systems have been a kind of powerful tool to improve e-commerce benefits. Existing recommender systems mostly employ explicit features of products, such as description and attributes. However, visual characteristics contain fruitful implicit and intuitive information, and are always ignored by existing works. To deal with this issue, this paper proposes a novel intelligent recommender system via visual Transformer (ViT) model and convolutional neural network (CNN) structure. First, the ViT part is utilized to extract visual feature representation. By learning the visual similarity among products, it is expected to obtain a better scene understanding. Then, an improved CNN part is utilized to extract hidden association information from historical behaviors of users. It is expected to better perceive user preference and purchasing characteristics. The combination of two parts constructs the proposed recommender system. Finally, we make performance evaluation for the proposal on real-world e-commerce dataset. The results indicate that the proposal exhibits high recommendation accuracy and efficiency. Compared with other typical algorithms, our proposal can better understand product images and user behaviors, providing more personalized recommendation results. [ABSTRACT FROM AUTHOR]

Advancements in Machine Learning (ML) and Computer Vision have led to notable improvements in the detection of breast cancer. However, the accuracy of the classifier is limited due to imbalanced datasets that cause overfitting. Thus, additional images are needed to improve the classifier's performance. Generative Adversarial Networks (GAN) are used for image augmentation. Still, its limitations, such as the random use of different types of GAN, can lead to a too-good discriminator, causing generator training to fail due to vanishing gradients. Therefore, selecting the appropriate GAN model for the given scenario is crucial for optimal performance. This paper proposes a novel Smart Generative Adversarial Network (Smart GAN) architecture to develop an efficient and computational classification model for a limited imbalanced dataset. Smart GAN uses a three-fold approach. Different types of GAN augment the dataset in the first phase of experimental work, and their evaluation metrics are calculated. In the second phase, the metric scores are used as rewards for the Reinforcement learning model (Q-learning approach). The best augmentation is chosen based on the best Q-values for each metric score. It compares three different Convolutional Neural Networks (CNN) and selects the best-suited network to classify the augmented datasets. The proposed Smart GAN architecture outperforms other existing approaches by giving a better accuracy of 89.62% and 89.91% on Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) augmented datasets, respectively, representing an approximately 10% increment in detection rate compared to non-augmented datasets. [ABSTRACT FROM AUTHOR]