Search

[Display omitted] • 3D-ACM involves two rounds of Hilbert transform and tensor product operations. • It significantly enhances the equivalent frequency points and sample numbers. • The R-squared values for PLS-LR, KNN, RF and CNN models approach or equal 1. • These supervised models are comparable to unsupervised models such as PCA-LR. We have developed a novel 3D asynchronous correlation method (3D-ACM) designed for the classification and identification of Chinese handmade paper samples using Raman spectra and machine learning. The 3D-ACM approach involves two rounds of tensor product and Hilbert transform operations. In the tensor product process, the outer product of the spectral data from different samples within the same category is computed, establishing inner connections among all samples within that category. The Hilbert transform introduces a 90-degree phase shift, resulting in a true three-dimensional spectral data structure. This expansion significantly increases the number of equivalent frequency points and samples within each category. This enhancement substantially boosts spectral resolution and reveals more hidden information within the spectral data. To maximize the potential of 3D-ACM, we employed six machine learning models: principal component analysis (PCA) with linear regression (LR), support vector machine (SVM) with LR, k-Nearest Neighbors (KNN), random forest (RF), and convolutional neural network (CNN). When applied to the 3D-ACM data preprocessing method, R-squared values of PLS-LR, KNN, RF and CNN supervised models, approached or equaled 1. This indicates exceptional performance comparable to unsupervised models like PCA. 3D-ACM stands as a versatile mathematical technique not confined to spectral data. It also eliminates the necessity for additional experimental setups or external control conditions, distinct from traditional two-dimensional correlation spectroscopy. Moreover, it preserves the original experimental data, setting it apart from conventional data preprocessing methods. This positions 3D-ACM as a promising tool for future material classification and identification in conjunction with machine learning. [ABSTRACT FROM AUTHOR]

Offshore wind-hydrogen systems operate in harsh marine environments for extended periods, posing risks of low accessibility and high failure rates. This paper proposes a data-driven fault detection framework for offshore wind-hydrogen systems, aiming to promptly detect potential faults based on the system's physical parameters. The research establishes a comprehensive model based on the operating principles of offshore wind-hydrogen systems. The study uses fault injection techniques to simulate common partial faults in offshore wind-hydrogen systems and collects relevant physical parameters (such as wind turbine power generation, energy storage battery charging/discharging current, and electrolyzer hydrogen production rate). A fault detection model was constructed using a combination of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) to enable precise detection of potential faults in the system. The established model provides theoretical support for designing, optimizing, and operating offshore wind-hydrogen systems, reducing reliance on actual experiments and lowering project risks and costs. Introducing artificial faults can evaluate the system's performance in different fault scenarios. This paper proposes a CNN-BiLSTM fault detection method that achieves automatic feature extraction and high-precision classification of time-series fault data, confirming the practicality and feasibility of offshore wind-hydrogen systems. This investigation realizes the integration of the offshore wind-hydrogen system model and deep learning, as well as a fully automated learning process from data to fault detection. By calculating and comparing results, it is verified that the framework has a high accuracy of 96.9%. This innovative research offers new methods and perspectives for enhancing the reliability and efficiency of fault detection in offshore wind-hydrogen systems. • A comprehensive multi-system simulation model for offshore wind-hydrogen systems is established. • Fault injection is employed to acquire data samples for offshore wind-hydrogen systems. • Utilizing the CNN-BiLSTM method, a high-accuracy deep learning fault detection model is crafted. • A simulation model-based data-driven deep learning framework for fault detection is devised in this study. [ABSTRACT FROM AUTHOR]

In order to accurately estimate the period of X-ray pulsars to improve navigation performance, this paper proposes a pulsar period estimation method based on photon energy using reverse Hilbert coding and double Convolutional Neural Networks (CNNs) discrimination. This method uses photon energy information to perform epoch folding. It converts one-dimensional contour information into two-dimensional image signals through reverse Hilbert curve and recognizes contour image features through CNN models to determine the optimal period. According to the simulation results, the period estimation accuracy of this method is 0.5350 ns, which is 65.71% higher than the χ 2 epoch folding method. The contour phase accuracy is 0.0004767, which is 41.93% higher than the χ 2 epoch folding method. At the same time, the observation time and noise interference that may affect the accuracy of period estimation are also quantitatively analyzed. In addition, in order to simulate real navigation scenarios, this paper also conducts dynamic period estimation experiments on PSR B0531+21 pulsar in a specific period of time. The method proposed in this paper has the advantages of high precision, fast calculation speed, strong anti-interference ability and accurate dynamic period estimation, which can significantly improve the navigation performance of X-ray pulsars. • The proposed period estimation method uses photon energy information for contour weighted folding. • The proposed method uses reverse Hilbert curve to convert one-dimensional contour information into two-dimensional image information. • Convolutional Neural Network models are used to optimize pulsar period estimation. [Display omitted] [ABSTRACT FROM AUTHOR]

Autonomous spacecraft relative navigation via monocular images became a hot topic in the past few years and, recently, received a further push thanks to the constantly growing field of artificial neural networks and the publication of several spaceborne image datasets. Despite the proliferation of spacecraft relative-state initialization algorithms developed, most architectures adopt computationally expensive solutions relying on convolutional neural networks (CNNs) that provide accurate output at the cost of a high computational burden that seems unfeasible for current spaceborne hardware. The paper addresses this issue by proposing a novel pose initialization algorithm based on lightweight CNNs. Inspired by previous state-of-the-art algorithms, the developed architecture leverages a fast and accurate target detection CNN followed by a line segment detection CNN capable of running with low inference time on mobile devices. The line segments and their junctions are grouped into complex geometrical groups, reducing the solution search space, and subsequently, they are adopted to extract the final pose estimate. As a main outcome, the analyses demonstrate that the lightweight architecture developed scores high accuracy in the pose estimation task, with a mean estimation error of less than 10 cm in translation and 2.5°in rotation. The baseline algorithm scores a mean SLAB error of 0.04552 with a standard deviation of 0.22972 in the test dataset. Detailed analyses demonstrate that the uncertainties on the overall pose score are driven mainly by errors in the relative attitude, which gives the highest contribution to the pose error metric adopted. The analyses on the error distributions point out that the uncertainties on the estimated relative position are higher in the camera boresight axis direction. Concerning the relative attitude, the algorithm proposed has higher uncertainties in estimating directions of the target x and y axes due to ambiguities related to the target geometry. Notably, the target detection CNN trained in this work outperforms the previous top scores in the benchmark dataset. The performances of the proposed algorithm have been investigated further by analyzing the effects on the accuracy due to the relative distance and the presence of background in the images. Lastly, the paper delves into the possibility of adopting a sub-portion of the 2D-to-3D match matrix made by the most complex perceptual groups identified that positively affects the overall run-time, pointing out the performances in terms of accuracy of the estimates and providing a comparison of both the baseline and the reduced match matrix versions against state-of-the-art algorithms concerning relative position and attitude errors and solution availability, highlighting the high accuracy and solution availability of the proposed architectures. • New relative pose initialization algorithm based on the detection of line segments. • Detailed literature review and description of available spaceborne image datasets. • Improvement of state of the art in spacecraft detection using lightweight CNN. • Assessment of accuracy of the proposed architecture and error sources analyses. • Proven feasibility of the approach via comparison with other architectures. [ABSTRACT FROM AUTHOR]

Cancer is a condition in which abnormal cells uncontrollably split and damage the body tissues. Hence, detecting cancer at an early stage is highly essential. Currently, medical images play an indispensable role in detecting various cancers; however, manual interpretation of these images by radiologists is observer-dependent, time-consuming, and tedious. An automatic decision-making process is thus an essential need for cancer detection and diagnosis. This paper presents a comprehensive survey on automated cancer detection in various human body organs, namely, the breast, lung, liver, prostate, brain, skin, and colon, using convolutional neural networks (CNN) and medical imaging techniques. It also includes a brief discussion about deep learning based on state-of-the-art cancer detection methods, their outcomes, and the possible medical imaging data used. Eventually, the description of the dataset used for cancer detection, the limitations of the existing solutions, future trends, and challenges in this domain are discussed. The utmost goal of this paper is to provide a piece of comprehensive and insightful information to researchers who have a keen interest in developing CNN-based models for cancer detection. [ABSTRACT FROM AUTHOR]

Deep neural networks have achieved outstanding performance in computer vision tasks. Convolutional Neural Networks (CNNs) typically operate in the spatial domain with raw images, but in practice, images are usually stored and transmitted in their compressed representation where JPEG is one of the most widely used encoder. Also, these networks are computationally intensive and slow. This paper proposes performing the learning and inference processes in the compressed domain in order to reduce the computational complexity and improve the speed of popular CNNs. For this purpose, a novel graph-based frequency channel selection method is proposed to identify and select the most important frequency channels. The computational complexity is reduced by retaining the important frequency components and discarding the insignificant ones as well as eliminating the unnecessary layers of the network. Experimental results show that the modified ResNet-50 operating in the compressed domain is up to 70% faster than the spatial-based traditional ResNet-50 while resulting in similar classification accuracy. Moreover, this paper proposes a preprocessing step with partial encoding to improve the resilience to distortions caused by low-quality encoded images. Finally, we show that training a network with highly compressed data can achieve a good classification accuracy with up to 93% reduction in the storage requirements of the training data. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, robots are widely used in various fields, grasping detection has been the focus of intelligent robot research. A dual manipulator grasping detection model based on Markov decision process is proposed to realize the stable grasping with complex multiple objects in this paper. Based on the principle of Markov decision process, the cross entropy convolutional neural network and full convolutional neural network are used to parameterize the grasping detection model of dual manipulators which are two-finger manipulator and vacuum sucker manipulator for multi-objective unknown objects. The data set generated in the simulated environment is used to train the two grasping detection networks. By comparing the grasping quality of the detection network output the best grasping by the two grasping methods, the network with better detection effect corresponding to the two grasping methods of two-finger and vacuum sucker is determined, and the dual manipulator grasping detection model is constructed in this paper. Robot grasping experiments are carried out, and the experimental results show that the proposed dual manipulator grasping detection method achieves 90.6% success rate, which is much higher than the other groups of experiments. The feasibility and superiority of the dual manipulator grasping detection method based on Markov decision process are verified. [ABSTRACT FROM AUTHOR]

• AI improves infectious waste management. • Ensemble model exceeds 97.81% accuracy. • Reinforcement learning optimizes classification. • Geometric augmentation boosts model robustness. • Study addresses urgent urban waste challenges. This research paper focuses on effective infectious municipal waste management in urban settings, highlighting a dearth of dedicated research in this domain. Unlike general or specific waste types, infectious waste poses distinct health and environmental risks. Leveraging advanced artificial intelligence techniques, we prioritize infectious waste categorization and optimization, integrating metaheuristics into optimization methods to create a robust dual-ensemble framework. Our model, the "Enhanced Artificial Intelligence for Infectious Municipal Waste Classification System," combines ensemble image segmentation methods and diverse convolutional neural network models. Innovative geometric image augmentation enhances model robustness, diversifies training data, and improves accuracy across waste types. A pivotal aspect is the integration of a reinforcement learning-differential evolution algorithm as a decision fusion strategy, optimizing classification by harmonizing outputs from ensemble methods and convolutional neural network models. Computational results, using a newly collected dataset, demonstrate our model's accuracy exceeding 96.54% while using the existing solid waste dataset we achieve the accuracy of 97.81%, outperforming advanced approaches by margins ranging from 2.02% to 8.80%. This research significantly advances sustainable waste management, showcasing artificial intelligence's transformative potential in addressing intricate waste challenges. It establishes a foundational framework prioritizing efficiency, effectiveness, and sustainability for future waste management solutions. Acknowledging the importance of diverse datasets, customization for urban contexts, and practical integration into existing infrastructures, our work contributes to the broader discourse on the role of artificial intelligence in evolving waste management practices. [ABSTRACT FROM AUTHOR]

Energy hubs (EHs) represent a pivotal paradigm in achieving optimal resource utilization across various energy domains. This paper presents an advanced framework for the optimal management of a smart island, leveraging the synergies within the water-electricity nexus. By integrating diverse resources, including electricity, water, heat, and hydrogen, the proposed EH model aims to meet the multifaceted demands of consumers on the island. To enhance operational efficiency, this study delves into the nuanced impacts of key EH components, elucidating their roles in meeting demand profiles and minimizing operational costs. Formulated as a mixed integer linear programming (MILP) model, the EH optimization problem is addressed using the GAMS optimization tool. The overarching objective is to fulfill consumer demand while concurrently optimizing resource utilization, considering factors such as storage degradation costs and emissions from fossil-fuel-based units. In addition to strategic optimization, this study pioneers a novel approach to stochastic parameter forecasting, integrating convolutional neural networks (CNNs) and long-short-term memory networks (LSTMs). By harnessing the capabilities of these advanced forecasting techniques, the EH model can anticipate dynamic changes in demand patterns with heightened accuracy and precision. The empirical results underscore the transformative potential of the proposed EH framework, showcasing significant reductions—up to 30%—in emission costs. Moreover, the study underscores the pivotal role of EHs as enablers for scaling up renewable energy penetration, offering a robust foundation for sustainable energy transitions in island communities and beyond. Additionally, implementing a load-shifting demand response program can lower total costs by approximately $257 per day, offering significant savings for EHs over extended periods. [Display omitted] • Modeling a mixed integer linear programming for energy management of an energy hub. • Comprehensive study on hydrogen and electric storage systems. • Uncertainty modeling using convolutional and long short-term memory networks. • Modeling water–electricity nexus to meet water and electricity demand. [ABSTRACT FROM AUTHOR]

In this paper, we address the image denoising problem in presence of speckle degradation typically arising in ultra-sound images. Variational methods and Convolutional Neural Networks (CNNs) are considered well-established methods for specific noise types, such as Gaussian and Poisson noise. Nonetheless, the advances achieved by these two classes of strategies are limited when tackling the de-speckle problem. In fact, variational methods for speckle removal typically amounts to solve a non-convex functional with the related issues from the convergence viewpoint; on the other hand, the lack of large datasets of noise-free ultra-sound images has not allowed the extension of the state-of-the-art CNN denoiser methods to the case of speckle degradation. Here, we aim at combining the classical variational methods with the predictive properties of CNNs by considering a weighted total variation regularized model; the local weights are obtained as the output of a statistically inspired neural network that is trained on a small and composite dataset of natural and synthetic images. The resulting non-convex variational model, which is minimized by means of the Alternating Direction Method of Multipliers (ADMM) is proven to converge to a stationary point. Numerical tests show the effectiveness of our approach for the denoising of natural and satellite images. • An hybrid strategy for the despeckling problem combining convolutional neural networks and variational methods is proposed. • The proposed neural architecture is statistically-inspired and not requires the training on a large data-set of images. • A proof of convergence to a stationary point for the alternating direction method is given. [ABSTRACT FROM AUTHOR]

Timely and effective fault diagnosis is crucial to guarantee the reliability and durability of proton exchange membrane fuel cell (PEMFC). Segmented cell technology has been proven to be a powerful tool for exploring the internal characteristics of fuel cells, yet it is seldom applied for fault diagnosis. This paper proposes a data-driven fault diagnosis method that combines segmented cell and deep learning technology for PEMFC water management fault diagnosis. The dynamic characteristics of the current distribution of the fuel cell under different levels of faults are explored with segmented cell technology. A dual-input convolutional neural network is applied to combine current distribution data and sensor data for a more comprehensive system status for fault diagnosis. The results show that the model can efficiently identify flooding and drying faults with more than 98.5% accuracy, faster and more accurately than other algorithms. This work highlights the significance of segmented cell technology for the comprehension of water management inside PEMFC and provides a new concept for PEMFC fault diagnosis. [Display omitted] • The segmented cell technology is applied to investigate the current distribution during flooding and drying process. • A dual-input CNN is adopted to establish a fault diagnosis model for PEMFC water management. • The proposed method exhibits excellent diagnostic performance, with an accuracy rate of over 98.5%. [ABSTRACT FROM AUTHOR]

The large number of near-Earth asteroids (NEAs) has greatly impacted human space activities and Earth security. However, detecting NEAs in astronomical images with complex, varying backgrounds is still extremely challenging. In this paper, we propose a deep segmentation assisted asteroid tracking algorithm, termed DSAT, to construct a possible pipeline for faint NEA tracking in astronomical images. First, the single-frame object detection problem is converted to a segmentation problem, enabling robust extraction of faint potential moving objects. Then, a multiframe motion prior-based moving object tracking algorithm is proposed to find real NEAs. We further propose a distance tolerance criterion to help DSAT achieve effective tracking in practical situations when detection has partially failed. Finally, the pipeline is tested with both simulated and real astronomical images at different SNRs and in crowded fields. The results showed that our pipeline has the potential to detect and track faint NEAs in complex backgrounds. Our code is publicly available at https://github.com/zhenhongdu/DeepSegAsteroidTracker. [ABSTRACT FROM AUTHOR]

• Introduced the Siamese 4D-Alznet, which combines five distinct blocks of CNNs. • We proposed three custom TL models incorporating frozen and replacing layers. • Our methods prove 95.07% binary classification performance in terms of accuracy. • All techniques performed best for NC, EMCI, LMCI, and AD classification. Alzheimer's disease (AD) is the general form of dementia, leading to a progressive neurological disorder characterized by memory loss due to brain cell damage. Artificial Intelligence (AI) assists in the early identification and prediction of AD patients, determining future risks and benefits for radiologists and doctors to save time and cost. Since deep learning (DL) approaches work well with massive datasets and have recently become helpful for AD detection, there remains an area for improvement in automating detection performance. Present approaches somehow addressed the challenges of limited annotated data samples for binary classification. This contrasts with prior state-of-the-art techniques, which were constrained by their incapacity to capture abstract-level information. In this paper, we proposed a Siamese 4D-AlzNet model comprised of four parallel convolutional neural network (CNN) streams (Five CNN layer blocks) and customized transfer learning models (Frozen VGG-19, Frozen VGG-16, and customized AlexNet). Siamese 4D-AlzNet was vertically and horizontally stored, and the spatial features were passed to the final layer for classification. For experiments, T1-weighted MRI images comprised of four distinct subject classes, normal control (NC), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI), and AD, have been employed. Our proposed models achieved outstanding accuracy, with a remarkable 95.05% accuracy distinguishing between normal and AD subjects. The performance across remaining binary class pairs consistently exceeded 90%. We thoroughly compared our model with the latest methods using the same dataset as our reference. Our proposed model improved NC-AD and MCI-AD classification accuracy by 2% 7%. [ABSTRACT FROM AUTHOR]

Spatiotemporal fusion can provide remote sensing images with both high temporal and high spatial resolution for earth observation applications. Most of the state-of-the-art models require three or even five images as input, which may lead to difficulties in practical applications due to bad weather or data missing. In this paper, the enhanced cross-paired wavelet based spatiotemporal fusion networks (ECPW-STFN) are proposed to improve the accuracy and quality of the fusions with fewer remote sensing images as inputs. Wavelet transform is introduced into spatiotemporal image fusion to achieve separate training of the high and low frequency components of the image to better extract features of different levels. In addition, a compound loss function containing wavelet loss is proposed to facilitate the preservation of details. Also, an enhancement module with convolutional block attention is put forward to further refine the prediction quality. Experiments were conducted to compare the proposed ECPW-STFN with five state-of-the-art methods on the public CIA and Daxing datasets. The results show ECPW-STFN is better than GAN-STFM which also requires two images, and not inferior to the methods requiring at least three inputs, even exceeds the optimal MLFF-GAN in some cases, proving its great superiority and potential. The code will be available at https://github.com/lixinghua5540/ECPW-STFN. [ABSTRACT FROM AUTHOR]

The accumulation of lipid oxidation and biogenic amines is the primary cause of pork sausage spoilage during storage. Therefore, this study aimed to develop a colorimetric microfluidic paper analytical device (μPAD) that specifically responded to these two factors to evaluate sausage spoilage during storage. A dataset consisting of 4096 images of μPADs was collected, and a convolutional neural networks (CNN)-based classification model (Resnet50) was trained and tested with an accuracy, F1 score, and recall rate of 97.10%, 97.14%, and 99.17%, respectively. Additionally, the CNN-based model was integrated into a smartphone application with user-friendly interfaces catering to both professional and non-professional users. Furthermore, the classification method was validated by predicting the shelf life of sausages stored at different temperatures. Compared to conventional methods, this approach provided a cost-effective, rapid, and portable detection method for assessing pork sausage freshness while broadening the application of smartphone-based colorimetric μPADs in food safety and quality control. • A microfluidic paper-based analytical device (μPAD) was prepared. • A CNN model (Resnet50) was trained and embedded in a smartphone application. • TBARs and biogenic amines were colorimetric indicators of pork sausages' freshness. • The predictive model's accuracy was above 97% and validated by shelf-life. • The operation was low-cost and user-friendly. [ABSTRACT FROM AUTHOR]

Network pruning has attracted increasing attention recently for its capability of transferring large-scale neural networks (e.g., CNNs) into resource-constrained devices. Such a transfer is typically achieved by removing redundant network parameters while retaining its generalization performance in a static or dynamic manner. Concretely, static pruning usually maintains a larger and fit-to-all (samples) compressed network by removing the same channels for all samples, which cannot maximally excavate redundancy in the given network. In contrast, dynamic pruning can adaptively remove (more) different channels for different samples and obtain state-of-the-art performance along with a higher compression ratio. However, since the system has to preserve the complete network information for sample-specific pruning, the dynamic pruning methods are usually not memory-efficient. In this paper, our interest is to explore a static alternative, dubbed GlobalPru, from a different perspective by respecting the differences among data. Specifically, a novel channel attention-based learn-to-rank framework is proposed to learn a global ranking of channels with respect to network redundancy. In this method, each sample-wise (local) channel attention is forced to reach an agreement on the global ranking among different data. Hence, all samples can empirically share the same ranking of channels and make the pruning statically in practice. Extensive experiments on ImageNet, SVHN, and CIFAR-10/100 demonstrate that the proposed GlobalPru achieves superior performance than state-of-the-art static and dynamic pruning methods by significant margins. [ABSTRACT FROM AUTHOR]

Automated extraction of polygonal building contours from high-resolution remote sensing images is important for various applications. However, it remains a difficult task to achieve automated extraction of polygonal buildings at the level of human delineation due to diverse building structures and imperfect image conditions. In this paper, we propose Line2Poly, an end-to-end approach that uses feature lines as geometric primitives to achieve polygonal building extraction by recovering topological relationships among these lines within an individual building. To extract building feature lines with precision, we adopt a two-stage strategy that combines Convolutional Neural Network (CNN) and transformer architectures. A CNN-based module extracts preliminary feature lines, which serve as positional priors for initializing positional queries in the subsequent transformer-based module. For polygonal building contour reconstruction, we devise a learnable polygon topology reconstruction module that predicts adjacency relationships among discrete lines, and integrates lines into building polygons. The resultant building polygons, based on feature lines, exhibit inherent regularity that aligns with manual labeling standards. Extensive experiments on the Vectorizing World Buildings dataset, the WHU aerial building dataset and the WHU-Mix (vector) dataset validate Line2Poly's impressive performance in building feature line extraction and instance-level building detection. Moreover, Line2Poly's predictions exhibit the highest level of concurrence with manual delineations, with over 83% agreement on the WHU aerial building test set and 68.7/59.7% on the WHU-Mix (vector) test set I and II, respectively. [ABSTRACT FROM AUTHOR]

The state-of-the-art methods for cloud detection are dominated by deep convolutional neural networks (DCNNs). However, it is very expensive to train DCNNs for cloud detection and the trained DCNNs do not always perform well as expected. This paper proposes a shallow CNN (SCNN) by removing pooling/unpooling layers and normalization layers in DCNNs, retaining only three convolutional layers, and equipping them with 3 filters of 1 × 1 , 1 × 1 , 3 × 3 in spatial dimensions. It demonstrates that the three convolutional layers are sufficient for cloud detection. Since the label output by the SCNN for a pixel depends on a 3 × 3 patch around this pixel, the SCNN can be trained using some thousands 3 × 3 patches together with ground truth of their center pixels. It is very cheap to train a SCNN using some thousands 3 × 3 patches and to provide ground truth of their center pixels. Despite of its low cost, SCNN training is stabler than DCNN training, and the trained SCNN outperforms the representative state-of-the-art DCNNs for cloud detection. The same resolution of original image, feature maps and final label map assures that details are not lost as by pooling/unpooling in DCNNs. The border artifacts suffering from deep convolutional and pooling/unpooling layers are minimized by 3 convolutional layers with 1 × 1 , 1 × 1 , 3 × 3 filters. Incoherent patches suffering from patch-by-patch segmentation and batch normalization are eliminated by SCNN without normalization layers. Extensive experiments based on the L7 Irish, L8 Biome and GF1 WHU datasets are carried out to evaluate the proposed method and compare with state-of-the-art methods. The proposed SCNN promises to deal with images from any other sensors. The code and data will be open for further research. 1 1 https://github.com/dfchai/SCNN. [ABSTRACT FROM AUTHOR]

Hydrogen attack is the major failure cause of hydrogen equipment breakdown maintenance. Especially, common problems like cracks frequently occur but are challenging to find while operating, presenting an issue for safety and production. In the process of hydrogen damage evolution, a method for defect state recognition is proposed in this paper. Acoustic emission (AE) technology is used for inspecting the entire hydrogen charging process. The characteristic parameters including the counts and duration of the AE signals are first preprocessed, and the current damage states such as the dislocation propagation, and the occurrence of cracks are identified. Then, a deep learning convolutional neural network is used to create a hydrogen defect recognition (HDR) model with the input of a short-time Fourier transform for the feature vector extraction of various damage status AE signals. Finally, the hydrogen defect recognition experiment revealed that HDR is better in classification accuracy at 98.37% due to dislocation propagation and cracks identification. The study can provide an online damage recognition approach for damage state early warning and evaluation to guarantee hydrogen equipment safety operation. • Monitor the hydrogen damage process using acoustic emission detection technology. • Characteristics of the acoustic sources in hydrogen damage process are studied. • Neural network is used for hydrogen damage signal recognition and diagnosis. • STFT transform image is used as the neural network model input. [ABSTRACT FROM AUTHOR]

From the perspective of input features, information can be divided into independent information and correlation information. Current neural networks mainly concentrate on the capturing of correlation information through connection weight parameters supplemented by bias parameters. This paper introduces feature-wise scaling and shifting (FwSS) into neural networks for capturing independent information of features, and proposes a new neural network FwSSNet. In the network, a pair of scale and shift parameters is added before each input of each network layer, and bias is removed. The parameters are initialized as 1 and 0, respectively, and trained at separate learning rates, to guarantee the fully capturing of independence and correlation information. The learning rates of FwSS parameters depend on input data and the training speed ratios of adjacent FwSS and connection sublayers, meanwhile those of weight parameters remain unchanged as plain networks. Further, FwSS unifies the scaling and shifting operations in batch normalization (BN), and FwSSNet with BN is established through introducing a preprocessing layer. FwSS parameters except those in the last layer of the network can be simply trained at the same learning rate as weight parameters. Experiments show that FwSS is generally helpful in improving the generalization capability of both fully connected neural networks and deep convolutional neural networks, and FWSSNets achieve higher accuracies on UCI repository and CIFAR-10. [ABSTRACT FROM AUTHOR]

Brain–computer interfaces (BCIs) based on motor imagery (MI) enable the disabled to interact with the world through brain signals. To meet demands of real-time, stable, and diverse interactions, it is crucial to develop lightweight networks that can accurately and reliably decode multi-class MI tasks. In this paper, we introduce BrainGridNet, a convolutional neural network (CNN) framework that integrates two intersecting depthwise CNN branches with 3D electroencephalography (EEG) data to decode a five-class MI task. The BrainGridNet attains competitive results in both the time and frequency domains, with superior performance in the frequency domain. As a result, an accuracy of 80.26 percent and a kappa value of 0.753 are achieved by BrainGridNet, surpassing the state-of-the-art (SOTA) model. Additionally, BrainGridNet shows optimal computational efficiency, excels in decoding the most challenging subject, and maintains robust accuracy despite the random loss of 16 electrode signals. Finally, the visualizations demonstrate that BrainGridNet learns discriminative features and identifies critical brain regions and frequency bands corresponding to each MI class. The convergence of BrainGridNet's strong feature extraction capability, high decoding accuracy, steady decoding efficacy, and low computational costs renders it an appealing choice for facilitating the development of BCIs. [ABSTRACT FROM AUTHOR]

The complex flow of a supersonic jet (Mach number 2.4–2.5) around the blunt aerodynamic body (consisting of a cylinder with a diameter of 16 mm and a truncated cone) was studied using the high-speed shadowgraph technique and computer vision-based visual data processing. The problem considered is directly related to the rocket and space systems stages safe separation problem in a sufficiently dense atmosphere. For systems with a sequential arrangement of stages, their separation often occurs under the rocket engine jet action. The occurrence of lateral forces in violation of axial symmetry can lead to overturning of the discarded stage and undesirable interaction with the outgoing stage. The goals of the paper were to study the pulsation characteristics of the incoming supersonic jet streamlining the body, as well as the pulsations of the bow shock wave in both axisymmetric and asymmetric flows. The recording frame rate in the experiments was up to 775 000 fps. Computer vision and various machine learning approaches were used to process a large number of shadowgraph images. Canny edge detection and Hough transform, as well as a convolutional neural network (CNN) based on YOLOv2 architecture, were used to automatically track the position of the bow shock relative to the body. Jet sound generation was studied - the amplitude dependence on the distance from the nozzle and the evolution in time. The position of the bow shock relative to the streamlined body and flow pulsations over time were analyzed. Bow shock pulsation spectra at zero angle of attack were compared to those at a small angle of attack (α = 2.5°–3°). The power spectral density was also estimated. The slope of the spectra for the zero angle of attack case was found to be horizontal and the spectra for the small angle of attack case had a slope close to −5/3. The strongest of the measured bow shock frequencies were found to be close to those of the jet mixing layer pulsations. The hardware signal spectrum was also measured and this signal can be considered as noise. The described approach makes it possible to obtain the physical characteristics of the flow at any point of interest. It was also shown that the automation of flow visualization experiments using computer vision techniques allows to increase the speed of data processing and obtaining new physical information, which may be important for engineers developing aircraft and spacecraft technologies. • Supersonic jet flow around a blunt body was studied experimentally and also numerically. • Computer vision tools were applied to supersonic flow investigation. • Spectra of jet generated acoustic waves were determined. • Time dependent bow shock positions were automatically measured by the neural network. • Amplitudes of bow shock pulsations and flow fluctuations depend on the angle of the body relative to the jet direction. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks have been popularly applied in single-image deraining recently. Nevertheless, as the network becomes deeper, it is easy to cause training over-fitting and performance saturation, particularly in the case of insufficient training data. In this paper, we report the design of a new network, namely parallel deraining convolutional neural network (PARDNet), for single-image deraining. Specifically, PARDNet adopts two parallel residual sub-networks based on different receptive fields to extract more comprehensive characteristics of the rain streaks, as well as decrease the depth of the network. The hybrid dilated convolution is employed to enlarge the sub-network's receptive field to capture more context information. The efficient channel attention module is integrated into the proposed PARDNet to capture rain streaks more effectively and preserve more background details. Furthermore, to facilitate the network training, the residual learning is also fused into PARDNet in a holistic way. Extensive experiments on synthetic and real-world rainy image datasets demonstrate the superiority of PARDNet for single-image deraining. • We propose a new parallel deep network framework for single-image deraining. • The hybrid dilated convolution is employed to capture more useful context information. • The efficient channel attention is adopted to extract more rain streaks effectively. • The framework we developed achieves better deraining performance on three test datasets. [ABSTRACT FROM AUTHOR]

• The deep learning model can better extract the deeper features of the multi-point deformation sequence. • MVMD algorithm reduces the complexity of multi-point displacement sequence. • The model considers the spatiotemporal characteristics of dam deformation, the prediction accuracy is obviously improved. It is difficult for single measuring point model to synchronously characterize the spatial correlation of deformation sequence of concrete dam and the similarity of displacements of different measuring points. Considering the limitation of conventional model in dealing with spatial-temporal data structure, In this study, a deep learning technique for multi-point and multi-output deformation prediction of concrete dams is proposed, which is based on Multivariate Variational Mode Decomposition (MVMD) and three-dimensional convolutional neural network (3D-CNN) combined model. Firstly, the multi-point sequence is decomposed into several relatively stable sub-sequences with different frequency scales by MVMD, which reduces the complexity of the multi-point displacement sequence. Then, In order to enhance the model 's ability to fit the time and spatial features of the sequence, the 3D-CNN model is used to predict the decomposed components and reconstruct the displacement data of the measuring points. This study focuses on the principle, process and calculation steps of the proposed model, and verifies the proposed model through the deformation data of three typical measuring points. The test results show that the prediction model proposed in this paper is an effective method for dam deformation prediction. [ABSTRACT FROM AUTHOR]

In recent years, many image denoising methods have been proposed based on convolutional neural networks (CNNs). While these methods have shown continuous performance improvement by introducing various mechanisms and structures, their computational cost tends to become increasingly expensive, owing to the resulting complex network architectures. This paper aims at winning the trade-off between computational efficiency and denoising performance for CNN-based image denoisers. Towards this end, we draw inspirations from traditional variational models with wavelet analysis operators for CNN architecture design. A model-inspired CNN is proposed with four key modules: iterative encoding-decoding units inspired by the iterative denoising process, directional convolutions inspired by the separable wavelet filters, inception modules inspired by the multi-scale analysis of wavelets, and stage-wise connections inspired by the adding noise back operation. In experiments, our CNN shows high computational efficiency in both training and test, with competitive results to state-of-the-art approaches. • A neural network inspired by the key ingredients of wavelet analysis model. • A sequential encoding-decoding network for image denoising. • A deep image denoiser well balancing effectiveness and computational efficiency. [ABSTRACT FROM AUTHOR]

The remarkable performance of Convolutional Neural Networks (CNNs) has increased their use in real-time systems and devices with limited resources. Hence, compacting these networks while preserving accuracy has become necessary, leading to multiple compression methods. However, the majority require intensive iterative procedures and do not delve into the influence of the used data. To overcome these issues, this paper presents several contributions, framed in the context of e x plainable Artificial Intelligence (xAI): (a) two filter pruning methods for CNNs, which remove the less significant convolutional kernels; (b) a fine-tuning strategy to recover generalization; (c) a layer pruning approach for U-Net; and (d) an explanation of the relationship between performance and the used data. Filter and feature maps information are used in the pruning process: Principal Component Analysis (PCA) is combined with a next-convolution influence-metric, while the latter and the mean standard deviation are used in an importance score distribution-based method. The developed strategies are generic, and therefore applicable to different models. Experiments demonstrating their effectiveness are conducted over distinct CNNs and datasets, focusing mainly on semantic segmentation (using U-Net, DeepLabv3+, SegNet, and VGG-16 as highly representative models). Pruned U-Net on agricultural benchmarks achieves 98.7% parameters and 97.5% FLOPs drop, with a 0.35% gain in accuracy. DeepLabv3+ and SegNet on CamVid reach 46.5% and 72.4% parameters reduction and a 51.9% and 83.6% FLOPs drop respectively, with almost no decrease in accuracy. VGG-16 on CIFAR-10 obtains up to 86.5% parameter and 82.2% FLOPs decrease with a 0.78% accuracy gain. • New filter pruning and fine-tuning strategies for segmentation and classification. • Novel layer pruning method for U-Net, a relevant semantic segmentation model. • Performing a detailed pruning survey on encoder–decoder and classification models. • Significant reduction in parameters and FLOPs maintaining networks efficiency. • Analyzing the dependence of the pruned models performance on the used dataset. [ABSTRACT FROM AUTHOR]

The effective use of temporal relationships while extracting fertile spatial features is the key to video action understanding. Video action understanding is a challenging visual task because it generally necessitates not only the features of individual key frames but also the contextual understanding of the entire video and the relationships among key frames. Temporal relationships pose a challenge to video action understanding. However, existing 3D convolutional neural network approaches are limited, with a great deal of redundant spatial and temporal information. In this paper, we present a novel two-stream approach that incorporates Spatial Residual Attention and Temporal Markov (SRATM) to learn complementary features to achieve stronger video action understanding performance. Specifically, the proposed SRATM consists of spatial residual attention and temporal Markov. Firstly, the spatial residual attention network captures effective spatial feature representation. Further, the temporal Markov network enhances the model by learning the temporal relationships via conducting probabilistic logic calculation among frames in a video. Finally, we conduct extensive experiments on four video action datasets, namely, Something-Something-V1, Something-Something-V2, Diving48, and Mini-Kinetics, show that the proposed SRATM method achieves competitive results. [ABSTRACT FROM AUTHOR]

Recently, video-based action recognition methods using convolutional neural networks (CNNs) achieve remarkable recognition performance. However, there is still lack of understanding about the generalization mechanism of action recognition models. In this paper, we suggest that action recognition models rely on the motion information less than expected, and thus they are robust to randomization of frame orders. Furthermore, we find that motion monotonicity remaining after randomization also contributes to such robustness. Based on this observation, we develop a novel defense method using temporal shuffling of input videos against adversarial attacks for action recognition models. Another observation enabling our defense method is that adversarial perturbations on videos are sensitive to temporal destruction. To the best of our knowledge, this is the first attempt to design a defense method without additional training for 3D CNN-based video action recognition models. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) target classification methods based on convolutional neural networks have attracted wide attention recently. Typically, these methods necessitate a substantial quantity of labeled data to train the deep model, which is an obstacle for SAR target classification since annotating SAR images is costly and time-consuming. Generating large-scale labeled data in simulation to train the deep model is a feasible alternative. However, cross-domain recognition is challenging due to significant differences in distribution between simulated and real domains. In this paper, we propose an unsupervised domain adaptation method for SAR target classification by aligning the distribution between the simulated and unlabeled real domains. Specifically, we encode the dependencies across different granularity perspectives including domain-, and class-levels simultaneously to align two domains finely. On the one hand, a gradient-weighted adversarial alignment method is proposed to align the global distributions at the domain-level. On the other hand, a novel class-level alignment method based on the prototypical network is proposed to align the finer class structure. Technically, we respectively model the cross-domain prototype-prototype relations and cross-domain prototype-instance relations with contrastive learning to achieve intra-class prototype compact as well as inter-class prototype separation among cross-domain categories, where the prototypes of the real domain are learned with pseudo labels. To improve the quality of pseudo-labels, a pseudo-label filtering strategy combined with the attribute scattering center is further designed. The experiments on two simulation-to-reality datasets indicate that the proposed method outperforms state-of-the-art unsupervised domain adaptive methods, such as pixelfeat (+4.45% and +7.6% in accuracy on SAMPLE and S2M datasets respectively). Code and data will be available in https://github.com/YuShi1213/Sim2Real-Unsupervised-SAR-Target-Classification. [ABSTRACT FROM AUTHOR]

• A novel general cascaded convolutional neural network (CNN) reading method for pointer reading is presented. • Proposes PMA method, which can increase the data samples significantly without introducing redundant background information. • Proposes ADFPN for feature fusion, learns branch importance, performs fusion at various levels. Enhances fusion efficiency. • Construct a dataset for pointer meter readings that contains images of common pointer meters in substations. Pointer meters continue to serve as the primary monitoring instruments within substations. To solve the issue of poor model accuracy and low reading accuracy when reading multiple types of pointer meters, this paper proposes a universal cascaded convolutional neural network for accurate reading of various types of pointer instruments. The proposed detection method consists of two stages: instrument digital positioning and instrument pointer fitting. In the digital(figure of a number) positioning stage, an instrument data augmentation method for "large background and small target" is proposed to improve the model's sensitivity to digital position and reduce the interference of redundant background information to the model. In addition, an adaptive feature fusion pyramid structure is proposed for more effective feature fusion and enhanced fuzzy small target recognition. Compared with the baseline model, the method introduced in this study realizes a 0.47 % improvement in target detection accuracy. In our proposed dataset, the average recognition accuracy for the digital position location phase is 98.65 %,the average reading errors in square instruments, circular instruments, and instruments with uneven scales are 0.76 %, 0.73 %, and 0.67 % respectively. The proposed universal detection method in this paper achieves ultra-high precision and can be applied to reading pointer instruments of different types and scales. Compared with existing pointer meter reading methods, the proposed detection method showcases superior simplicity and effectiveness. Furthermore, it showcases a reduced measurement error, thereby bolstering its practical utility in industrial contexts. [ABSTRACT FROM AUTHOR]

Intrusion Detection System (IDS) can ensure the network security by identifying network intrusions according to the abnormal traffic data. However, the intrusion detection data has the problem of high dimensionality and changes with network and attack environments, which leads to the poor performance and poor portability of intrusion detection algorithms. Therefore, this paper proposes an intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network. Firstly, a feature selection method based on symmetric uncertainty and approximate Markov blanket is proposed, which fully considers the correlation and redundancy of features, and also the correlation between combined features and the class label, so as to reduce the data dimensionality. Secondly, the CNN-LSTM classifier fused with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is used to extract the spatial features and temporal features to improve the classification performance. Finally, the Particle Swarm Optimization (PSO) algorithm is improved and used to automatically optimize the hyperparameters of the classifier, so that the classifier can be applied to different intrusion detection datasets with better generalization ability and portability. Experiments have verified the effectiveness and superiority of the proposed algorithm on multiple evaluation indicators. • An effective algorithm for intrusion detection is proposed in this paper. • Feature selection is based on symmetric uncertainty and approximate Markov blanket. • A fusion neural network is constructed to extract the spatial and temporal features. • The PSO algorithm is improved to automatically optimize the hyperparameters. [ABSTRACT FROM AUTHOR]

This paper presents a formal verification guided approach for a principled design and implementation of robust and resilient learning-enabled systems. We focus on learning-enabled state estimation systems (LE-SESs), which have been widely used in robotics applications to determine the current state (e.g., location, speed, direction, etc.) of a complex system. The LE-SESs are networked systems, composed of a set of connected components including: Bayes filters for state estimation, and neural networks for processing sensory input. We study LE-SESs from the perspective of formal verification, which determines the satisfiabilty of a system model against the specified properties. Over LE-SESs, we investigate two key properties – robustness and resilience – and provide their formal definitions. To enable formal verification, we reduce the LE-SESs to a novel class of labelled transition systems, named {PO}2-LTS in the paper, and formally express the properties as constrained optimisation objectives. We prove that the verification problems are NP-complete. Based on {PO}2-LTS and the optimisation objectives, practical verification algorithms are developed to check the satisfiability of the properties on the LE-SESs. As a major case study, we interrogate a real-world dynamic tracking system which uses a single Kalman Filter (KF) – a special case of Bayes filter – to localise and track a ground vehicle. Its perception system, based on convolutional neural networks, processes a high-resolution Wide Area Motion Imagery (WAMI) data stream. Experimental results show that our algorithms can not only verify the properties of the WAMI tracking system but also provide representative examples, the latter of which inspired us to take an enhanced LE-SESs design where runtime monitors or joint-KFs are required. Experimental results confirm the improvement in the robustness of the enhanced design. [ABSTRACT FROM AUTHOR]

[Display omitted] • Integrating deep learning with 2DCOS for wheat flour spectral classification. • The improved EfficientNet model achieved 100% accuracy in wheat flour identification. • Comparison of deep learning and machine learning methods in spectral analysis. • Transforms spectra into images, applicable beyond wheat flour. Wheat flour is a ubiquitous food ingredient, yet discerning its various types can prove challenging. A practical approach for identifying wheat flour types involves analyzing one-dimensional near-infrared spectroscopy (NIRS) data. This paper introduces an innovative method for wheat flour recognition, combining deep learning (DL) with Two-dimensional correlation spectrum (2DCOS). In this investigation, 316 samples from four distinct types of wheat flour were collected using a near-infrared (NIR) spectrometer, and the raw spectra of each sample underwent preprocessing employing diverse methods. The discrete generalized 2DCOS algorithm was applied to generate 3792 2DCOS images from the preprocessed spectral data. We trained a deep learning model tailored for flour 2DCOS images – EfficientNet. Ultimately, this DL model achieved 100% accuracy in identifying wheat flour within the test set. The findings demonstrate the viability of directly transforming spectra into two-dimensional images for species recognition using 2DCOS and DL. Compared to the traditional stoichiometric method Partial Least Squares Discriminant Analysis (PLS_DA), machine learning methods Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), and deep learning methods one-dimensional convolutional neural network (1DCNN) and residual neural network (ResNet), the model proposed in this paper is better suited for wheat flour identification, boasting the highest accuracy. This study offers a fresh perspective on wheat flour type identification and successfully integrates the latest advancements in deep learning with 2DCOS for spectral type identification. Furthermore, this approach can be extended to the spectral identification of other products, presenting a novel avenue for future research in the field. [ABSTRACT FROM AUTHOR]

Remote sensing scene (RSS) image classification plays a vital role in various fields such as urban planning and environmental protection. However, due to higher inter-class similarity and intra-class variability, achieving accurate classification for RSS images poses a considerable challenge for current convolutional neural networks (CNNs)-based and visual transformer (ViT)-based methods. To address these issues, this paper proposes a novel dual-encoding method named master–slave encoding network (MSE-Net) from two perspectives of feature extraction and fusion. The master encoder, based on ViT, extracts higher-level semantic features, while the slave encoder, based on CNN, captures relative lower-level spatial structure information. Secondly, to integrate feature information from the two encoders effectively, this paper further develop two fusion strategies. The first strategy involves the auxiliary enhancement units (AEUs), which eliminates semantic divergence between the two encoders, enhances spatial context awareness of the slave encoder and promotes effective feature learning. The interactive perception unit (IPU), as the second strategy, facilitates interaction and integration of the two encoders' representations to extract more discriminative feature information. In addition, we conducted comparative experiments on four widely-used RSS datasets, including RSSCN7, SIRI-WHU, the aerial image dataset (AID) and NWPU-RESISC45 (NWPU45), to verify the effectiveness of MSE-Net. The experimental results demonstrate that MSE-Net achieved state-of-the-art (SOTA) performance across all the datasets. [Display omitted] [ABSTRACT FROM AUTHOR]

In recent studies, deep learning methodologies have shown significant promise in crack detection. However, their practical implementation faces challenges due to the intricate diversity of structural surfaces and the inherent narrowness of cracks. To mitigate these problems, this paper introduces SegFormer, an efficient semantic segmentation model with hierarchical Transformer, for crack detection on concrete and asphalt surfaces in multiple scenarios. The combination of Cross-Entropy (CE) and Dice loss functions is employed to enhance the detection of fine cracks. Additionally, the paper presents an evaluation framework and discusses metrics for assessing crack segmentation results to provide a more precise and comprehensive analysis of model performance. Experimental results indicate that SegFormer outperforms Convolutional Neural Networks (CNNs) such as FCN, U-Net, and DeepLabV3 utilizing different backbones. Notably, the integration of multiple loss functions contributes to a more stable training process, expedites convergence, and yields enhanced results compared to models utilizing individual loss functions. • SegFormer is introduced for fine crack detection in various scenarios. • The combination of CE and Dice loss functions enhances crack detection. • A comprehensive model evaluation framework is presented. • Metrics for fine crack segmentation assessment are discussed. [ABSTRACT FROM AUTHOR]

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

In personal identity recognition systems, detecting a person's age, gender, and language using voice signal characteristics is a crucial issue, especially because of the importance of security considerations. Age, gender, and language classification problems are important in signal processing because they are used to analyze and understand human behavior, interactions, and preferences. This can be especially useful in the fields of human-computer interaction, psychology, and social science research. In this paper, a new system for detecting a speaker's age, gender, and language based on deep learning models is presented. Deep learning models have shown great efficacy in various fields of signal processing. For this paper, a range of deep models were tested, including convolutional neural networks (CNNs), recurrent neural network (RNN), and a fine-tuning ResNet34 architecture. Additionally, techniques such as transfer learning were applied to improve the efficiency of the proposed system. The input voice signals are preprocessed by applying the spectro-temporal transform to obtain additional features that can be fed to the ResNet34 model, which is designed specifically for the task of voice signal processing. The dataset used in this paper was sourced from the Mozilla common voice initiative, which is dedicated to advancing speech recognition and language identification technologies. The performance of the proposed algorithm was evaluated in the presence of Gaussian noise to determine its robustness. The experimental results demonstrated that the proposed algorithm significantly outperformed basic algorithms and other deep neural networks in terms of age and gender recognition from voice signals. [ABSTRACT FROM AUTHOR]

Training all-optical neural networks in itself remains an unresolved problem, and the challenges compound when the problem is turned into the hardware implementations. In this paper, we propose a nonlinear activation function based on optical bistability within a micro-ring resonator (MRR), achieving threshold control without external modulation. Furthermore, a convolutional neural network similar to the Le-Net-5 architecture is designed, in which all nonlinear activation functions are composed of optical bistable hysteresis loop. The numerical simulation results demonstrate that the recognition rate on the Fashion-MNIST dataset can achieve 91.3%, which means that the optical neuromorphic computation can be implemented by utilizing the nonlinear optical effects themselves in the all-optical hardware. Such a scheme promises access to the all-optical neural network training in the optical hardware environment compared to numerical activation functions. • This paper proposed a nonlinear activation function based on optical bistability within a micro-ring resonator (MRR), achieving threshold control without external modulation. Furthermore, a convolutional neural network similar to the Le-Net-5 architecture is designed, in which all nonlinear activation functions are composed of optical bistable hysteresis loops. The numerical simulation results demonstrate that the recognition rate on the Fashion-MNIST dataset can achieve 91.3%, which means that the optical neuromorphic computation can be implemented by utilizing the nonlinear optical effects themselves in the all-optical hardware. [ABSTRACT FROM AUTHOR]

• A sparse sensor array was used for passive impact monitoring of large fuselage panels. • Fuzzy genetic algorithm provides adaptive adjustment ability and improves the localization accuracy of the algorithm under different structural conditions. • The impact force is reconstructed by GRU unit with attention mechanism. • Transfer learning is adopted to reduce the cost of training and improve the precision of training. During aircraft operations, the impact events experienced by the aircraft may cause damage to the structure, thus posing a safety hazard. Therefore, an accurate determination of where the impact occurred and the time history of the impact force can provide an important basis for assessing the condition of the aircraft. However, modern aircraft structures are often large and complex, and relying on dense arrays of sensors for monitoring adds additional weight to the aircraft and reduces the economics of aircraft operation. This paper proposes a region-to-point monitoring strategy. First, a Convolutional Neural Network (CNN) model with region localization capability is trained using the sparse sensor array acquisition data. Then, the weighted center algorithm is used to determine the specific location where the impact occurs, in which the added fuzzy genetic algorithm can provide the ability to adjust weights to improve localization accuracy adaptively. As for the impact force prediction, this paper adopts a model based on a Convolutional Neural Network-Gated Recurrent Unit combined with a Squeeze-Excitation attention mechanism (CNN-GRU-SE), which is capable of predicting the impact force occurring in the flat plate and reinforced structure region of the aircraft under different energy conditions. Finally, the impact of incorporating a transfer learning approach on model performance and training cost is investigated for fuselage regions with different structures. [ABSTRACT FROM AUTHOR]

• The improved VMD and DWT are combined to denoise and reconstruct the signal under strong noise without a reference. • The selection of wavelet function and transform level in DWT is optimized by Shannon entropy to denoise the signal without a reference. • The RAPID and the CNN are used to achieve spatial localization and visualization of the composite delamination. In this paper, a damage spatial imaging approach based on novel signal extraction is suggested to reconstruct the Lamb wave response signal under strong noise and realize the spatial localization of damage. First, the Variable Mode Decomposition (VMD) parameters are optimized by the improved Grey Wolf optimization method (IGWO) to decompose the response signal. To rebuild the response signal, the correlation coefficient is used to choose the optimal modal component and the residual. To give the best wavelet function and transform level for adaptive denoising of the reconstructed signal without a reference signal, an enhanced Discrete Wavelet Transform (DWT) based on Shannon entropy is proposed. To achieve damage localization imaging, a damage spatial localization model is built utilizing a reconstruction algorithm for probabilistic inspection of damage (RAPID) approach and a convolutional neural network (CNN). The suggested method may successfully increase the signal-to-noise ratio (SNR) of the reconstructed response signal and lower the error of spatial localization under strong noise through experiments. The spatial localization of composite damage using Lamb wave under strong noise is expanded in this paper. [ABSTRACT FROM AUTHOR]

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

Soybean is a critical source of food, protein, and oil, and thus has received extensive research aimed at enhancing their yield, refining cultivation practices, and advancing soybean breeding techniques. Within this context, soybean pod counting plays an essential role in understanding and optimizing production. Despite recent advancements, the development of a robust pod-counting algorithm capable of performing effectively in real-field conditions remains a significant challenge. This paper presents a pioneering work of accurate soybean pod counting utilizing unmanned aerial vehicle (UAV) images captured from actual soybean fields in Michigan, USA. Specifically, this paper presents SoybeanNet, a novel point-based counting network that harnesses powerful transformer backbones for simultaneous soybean pod counting and localization with high accuracy. In addition, a new dataset of UAV-acquired images for soybean pod counting was created and open-sourced, consisting of 113 drone images with more than 260k manually annotated soybean pods. The images are taken from an altitude of approximately 13 ft, with angles between 53 and 58 degrees, under natural lighting conditions. Through comprehensive evaluations, SoybeanNet demonstrates superior performance over five state-of-the-art approaches when tested on the collected images. Remarkably, SoybeanNet achieves a counting accuracy of 84.51% when tested on the testing dataset, attesting to its efficacy in real-world scenarios. The publication also provides both the source code and the labeled soybean dataset, offering a valuable resource for future research endeavors in soybean pod counting and related fields. • Created and open-sourced the 1st UAV-acquired image dataset for soybean pod counting. • Pioneered the first study on precise soybean pod counting utilizing UAV images. • Demonstrated SoybeanNet's superiority over 5 state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

[Display omitted] • A fast accurate non-destructive quantitative analysis method of blended fabrics has been developed successfully using NIR and CNN-LSTM. • The CNN network structure in this paper is designed to adapt to a small sample regression. • The CNN-LSTM network designed in this paper can more accurately analyze the cotton content of cotton-polyester blended fabrics than PLS, CNN, and LSTM. • This CNN-LSTM method can accurately predict the cotton content of cotton-polyester blended fabrics with only simple MSC preprocessing. Accurate and rapid quantitative analysis of fiber content is important for blended fabric quality control and supervision. In this paper, a deep learning method based on an improved hybrid network of convolutional neural network (CNN) and long short-term memory (LSTM) to fast and accurate determine cotton content of cotton-polyester blended fabrics using near-infrared (NIR) spectroscopy. The cotton-polyester blended fabric samples were partitioned into training set, validation set and testing set in the ratio of 6:2:2 to develop the quantitative model of cotton content of blended fabric. Firstly, a one-dimensional CNN architecture is designed and modeled to obtain the CNN parameters and to evaluate the spectral preprocessing methods. Then, the CNN structure is modified and improved using LSTM to obtain a CNN-LSTM structure. The root mean square error (RMSE) of the validation set obtained by CNN model is 0.83%, which is 34.03% lower than that of the traditional partial least squares (PLS) model, and the RMSE of the testing set obtained by CNN model is 0.88%, which is 25.88% lower than that of the PLS model. The RMSE of the validation set obtained by CNN-LSTM model is 0.65%, which is 47.85% lower than that of the PLS model, and the RMSE of the testing set obtained by CNN-LSTM model is 0.75%, which is 36.57% lower than that of the PLS model. Compared with PLS and CNN models, the CNN-LSTM model can more accurately analyze the cotton content proportion of cotton-polyester blended fabrics, which provides a new fast and non-invasive method for the quantitative detection of fabrics. [ABSTRACT FROM AUTHOR]

Geological reports house a wealth of geological domain knowledge and expert experience knowledge, and the efficient extraction of geological entity relations from these texts holds great significance in constructing a geological knowledge graph. To address challenges such as overlapping entity relations, data imbalance, and the limited incorporation of contextual features in existing deep learning-based entity relation extraction methods, this paper proposes a relational graph convolutional network pointer model based on the pre-trained model of Robustly Optimize Bidirectional Encoder Representation from Transformers Pre-training Approach (RoBERTa). Specifically, our approach tackles the issue of overlapping entity relationships by identifying the primary entity and the subordinate entity associated with a specific relationship. Additionally, by incorporating a relationship graph convolutional network, we can capture multiple relationships among entities. Moreover, we leverage the Biaffine layer to accurately handle entity annotation boundaries, thereby enhancing the precision of entity classification. To address the issue of imbalanced data, we adopt the Focal Loss function during experiments. Furthermore, we construct a geological entity relation dataset comprising 24 types of relationships, which is generated by collecting seven regional geological reports and employing semi-automatic annotation techniques. Finally, the proposed algorithm was tested and comparison with several baseline models, the results demonstrate the superior performance of the proposed model in this paper. • In this paper, a geological entity relationship dataset is constructed. • In this paper, we propose a convolutional pointer network model for relational maps based on the pre-trained RoBERTa model and validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

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

• The initial measurement point is optimized, and the wavelet packet decomposition method is used to decompose and reconstruct the original measurement signal to realize the preprocessing of the data. Its main contributions include removing the DC component of the signal and reducing the non-stationarity and inconsistency of the sampled signal. • In view of the mode aliasing phenomenon caused by using EMD mode to analyze the signal, this paper uses VMD self-use segmentation technology to realize the adaptive segmentation of each component in the signal field, which effectively avoids the mode aliasing phenomenon, has stronger robustness, and effectively reduces the endpoint effect. At the same time, aiming at the problem that the grayscale map is not enough to visually express the deep features in the process of signal conversion to a grayscale map, this paper uses an SDPI diagram to display signal characteristics, and uses information entropy (IE) to select the optimal component after VMD decomposition to enhance the characteristics of symmetry point mode image (SDPI), and finally fuses the signal corresponding to the optimal component to generate a snowflake map, so as to display the changes between different vibration states simply, clearly and intuitively, and enhance the recognition ability of the image, and the image accuracy of the method is higher than the traditional sample accuracy. • Aiming at the phenomenon that the traditional SoftMax classification ability in convolutional neural network is not high, firstly, the convolutional neural network optimization is realized by adjusting the parameters of the CNN model, adding regularization, adjusting the hyperparameters, etc., and at the same time, the combined model combining SVM and CNN is used to replace the SoftMax classifier with the SVM classifier, and the results show that the method can improve the classification ability of images. • To verify the effectiveness and superiority of the proposed method, the proposed method is compared with the 1DCNN method, grey image-CNN method, SDPI-CNN, SDPI-SVM, and other methods, and the comparative results show that the model has good predictive performance and generalization ability, and verifies that the proposed signal picture establishment method and network improvement optimization model method are feasible for lead screw fault classification. The failure of the ball screw in the machine tool presents various types and complex coupling characteristics, which pose challenges in extracting fault features from vibration signals and lead to decreased accuracy in fault diagnosis classification. To tackle this issue, an improved intelligent fault diagnosis method based on enhanced CNN is proposed by optimizing the variational mode decomposition and symmetrized dot pattern image features. Initially, VMD is employed to decompose the preprocessed signals, incorporating information entropy for selecting decomposition layers to enhance accuracy. Different image features are generated using SDPI, and differential information is introduced to enhance feature expressive capability through fusion. Subsequently, considering the limited classification ability of traditional SoftMax classifiers in CNNs, SVM is integrated for classification purposes to optimize convolutional neural networks' structure and improve their classification performance. Finally, the proposed method was ultimately validated by means of comparative analysis of screw vibration signals, thereby affirming its exceptional accuracy in fault diagnosis and classification. [ABSTRACT FROM AUTHOR]

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

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

• Proposing a method to calculate the adjacency matrix of the relational graph of aspect words and a method to calculate the adjacency matrix of a syntactic dependency graph. • Proposesing a multiple ASGCN model architectures, and designing an experiment to compare the sentiment classification performance of these architectures. • Experimental results show that the proposed model can percept the semantic relationships. Aspect-level sentiment analysis aims to identify the sentiment polarity of aspect words in sentences. The existing research methods only focus on the grammatical dependencies between words, ignoring the semantic connections between aspect words and the dependency types between words, which limits the performance of the aspect-level sentiment analysis model. Therefore, this paper proposes an aspect-sentence Graph Convolutional Networks model (ASGCN) to perceive more comprehensive semantic information. Specifically, the model consists of sentence-focused GCN (SentenceGCN) and aspects-focused GCN (AspectsGCN) sub models. In the SentenceGCN model, this paper proposes a method to calculate the adjacency matrix (A s) of syntactic dependency graph, which uses the position encoding mechanism and pays attention to the influence of different dependency types on semantics, so that SentenceGCN can capture the semantic information of the whole sentence more comprehensively. In the AspectsGCN model, this paper also proposes a method to calculate the adjacency matrix (A a) of aspect words, which models the relational graph as fully connected and gives weight to the edges between aspect words according to the position, so that the AspectsGCN can pay attention to the semantic relation between different aspect words in the sentence. The proposed model outperforms all baseline models with 86.34 % accuracy and 79.96 F1 score, which indicates that there are more advantages in perceiving semantic information in ASGCN. [ABSTRACT FROM AUTHOR]