Search

Unmanned aerial vehicles (UAVs), particularly quadrotors, have seen a surge in applications ranging from surveillance to delivery services. However, autonomous control remains a challenge due to the complexity of their dynamics and the need for real-time responsiveness. This paper addresses the significant problem of autonomous quadrotor control by introducing a novel learning method that integrates a deep neural network with advanced control techniques. Novelty of the work is distribution of different learning tasks in different layers of learning and combining the total learning system in a applicable UAV. The purpose is to enhance the quadrotor's ability to perform complex maneuvers autonomously, which is crucial for expanding its application scope. The proposed method begins with the acquisition of direction control using a fractional order proportional–integral–derivative (FOPID) controller. The learning parameters are refined through a fuzzy method, ensuring adaptability and precision. For the optimization of the FOPID parameters, we apply two stochastic algorithms: Genetic Algorithm and Particle Swarm Optimization, comparing their efficacy. Our approach successfully teaches the quadrotor to generate and control a flight path autonomously. The second stage of learning involves proximal policy optimization, enabling the execution of intricate maneuvers. The experimental setup includes a quadrotor on a test stand with three degrees of freedom, where we validate the method through rigorous simulation and physical tests. The results demonstrate that our method not only teaches the quadrotor complex maneuvers but also ensures robust and precise execution, marking a significant advancement in UAV control systems. The implications of this research extend to improving UAV reliability for critical applications, potentially transforming the landscape of autonomous aerial operations. [ABSTRACT FROM AUTHOR]

Fundus examination, conducted through the analysis of retinal images, plays a pivotal role in aiding the diagnosis of ophthalmic diseases. Currently, deep learning models have been widely applied to retinal image analysis, specifically retinal image segmentation, including vessels, optic cups, lesions, etc., yielding promising outcomes. Nonetheless, the performance of these deep learning models experiences substantial degradation due to the domain shift between the distribution of the training images and unseen test images. In this paper, we focus on the challenging single-domain generalization (SDG), which aims to learn a generalized model on only one source domain, with the expectation that it performs well on unseen test domains. Our work is motivated by the observation that the main differences in retinal images from different domains primarily reside in their color variations, rather than changes in the shapes of objects. To this end, we present random color transformation (RCT) for SDG. RCT performs random linear transformations to each color channel of the training image. Through this approach, RCT can generate training images with rich and vibrant color representations, while preserving the structural information of objects in the images. Experiments are conducted over optic cup segmentation, retinal vessel segmentation, and diabetic retinopathy multi-lesion segmentation tasks, involving eight publicly available datasets. Experimental results show that the proposed RCT outperforms comparison SDG methods, achieving improvements of 5.9%, 1.3% and 3.6% compared to the second-best method on the optic cup, vessel, and lesion segmentation tasks, respectively. The source code will be available at https://github.com/guomugong/RCT. [ABSTRACT FROM AUTHOR]

To increase the economic efficiency of utilizing wind turbines, an enhanced object detection model based on the small version of the fifth generation of the You Look Only Once algorithm (YOLOv5s) is proposed in this paper, which can effectively detect cracks on the surface of wind turbine blades using images captured by unmanned aerial vehicles. To improve the extraction of light-colored and low-definition images, Omni-Dimensional Dynamic Convolution (ODConv) and Dynamic Head Module components (DyHead) are introduced in the proposed method, while a lightweight Group Shuffle convolution (GSConv) module is utilized to accelerate the model inference speed without sacrificing detection performance. Furthermore, a semi-supervised learning strategy is developed to reduce human labors in annotating images. Extensive experiments demonstrate that the proposed model outperforms the original YOLOv5s in terms of both detection accuracy and inference speed. Besides, the proposed model has good performance against state-of-the-art methods. Furthermore, the experiments validate the efficacy of the proposed semi-supervised learning strategy. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) motor imagery (MI) signals have recently attracted much attention because of their potential to communicate with the surrounding environment in a specific way without the need for muscular and physical movement. Despite these advantages, these signals are difficult to detect due to their low signal to noise (SNR) rate and non-stationary and dynamic nature. Convolutional neural networks (CNN) can extract appropriate spatial and temporal features without the need for separate feature extraction and classification steps. Clean input data for CNN significantly improves its performance, but sometimes, common interference occurs between multi-channel signals. This challenge, along with the noisy EEG signals, degrades the performance of CNN networks. This paper presents a channel selection method based on convolutional neural networks to obviate these challenges. The proposed shallow convolutional neural network (SCNN) is designed with temporal convolution and pointwise convolution (using 1 × 1 convolution) to select the best channel with minimal computational load. Following the channel selection step, the multi-layer fusion CNN model was used to classify the signals. Choosing suitable and relevant EEG channels for motor imagery tasks makes it possible to create appropriate inputs for the classification model so that the model can be improved in the end. For High Gamma Dataset and Brian-Computer Interface (BCI) Competition IV-2a, the following accuracies were obtained: 81.15% and 72.01%, which are higher than when the other channel selections such as Mutual Information, Sequential Feature Forward Selection (SFFS) and wrapper methods are used. [ABSTRACT FROM AUTHOR]

This paper presents an improved version of the U-Net segmentation framework for medical image segmentation, called CHWS-UNet. To build the proposed framework CHWS-UNet, we first develop a novel lightweight channel attention module called LCAM, based on which we further propose the Channel-Height-Width-Spatial (CHWS) attention module for channel, height, width, and spatial dimension-level feature refinement. Our CHWS-UNet is constructed by integrating the proposed CHWS attention modules into the shortcut paths between the encoder and the decoder stem. To justify the effectiveness of the proposed modules and networks, we then carried out extensive experiments on four public medical image datasets, including BUSI, ISIC2017, ISIC2018, PH and a proprietary uterus lesion ultrasound dataset from Shenzhen Maternity and Child Healthcare Hospital. The results show that the proposed attention module can significantly improve the performance of baseline models, even on small medical image datasets, without introducing noticeable parameters and computational costs. Further, the proposed segmentation framework can achieve promising performance compared to edge-cutting frameworks. The code can be found at CHWS-UNet. • We proposed a lightweight channel attention module called LCAM. • We developed an enhanced attention module that performs better than existing ones. • We built a novel U-Net called CHWS-UNet achieving state-of-the-art performance. [Display omitted] [ABSTRACT FROM AUTHOR]

Rail surface defect detection is an essential part of railroad maintenance to prevent safety accidents. Recently, deep learning-based defect detection algorithms have shown impressive detection performance. However, the performance improvement from deep neural networks is based on a strong assumption that the training images have the same data distribution as the test images. This requirement is unrealistic in practical railroad surface defect detection. The appearance of rails varies significantly in different railroad sections due to changes in working conditions and maintenance status. In this paper, we propose a novel uncertainty-inspired unsupervised domain adaptation framework (UIUDA) to improve the generalization of deep learning models on data with distribution differences. Specifically, domain adversarial learning is used to align the feature distributions of training and test data. To mitigate the negative transfer caused by global alignment, we design a locally aligned domain adaptation strategy. In addition, self-training is introduced to refine the decision boundaries of the model in the test data. In this process, we propose an uncertainty-inspired evaluation method to remove noisy pseudo labels. We conducted domain adaptation experiments with RSDD and NEU-RSDD as the source domain and FRSD dataset as the target domain. The results show that UIUDA can effectively improve the generalization ability of the model, and the mIoU metric of defect segmentation is 80.17%. [ABSTRACT FROM AUTHOR]

Transmission line parameter identification plays a crucial role in power systems. However, existing methods for identifying transmission line parameters face several challenges: (1) when dealing with non-Euclidean data such as power grid data, a considerable amount of noise is introduced, (2) inability to treat the power grid as a global system, limiting calculations to individual transmission lines and overlooking inter-branch correlations, (3) high sensitivity to data contamination. To address these issues, this paper proposes a multi-task noisy graph attention network (MNGAN) for power grid parameter identification, which leverages the spatial structure of the power grid and considers the inter-branch correlations. By computing the homogeneity and average degree of the graph data, we introduce an adaptive attention mechanism to the model. This attention mechanism dynamically adjusts the model's focus on key information, mitigating the impact of data contamination and improving parameter identification accuracy. Additionally, to achieve simultaneous recognition of multiple branch parameters and enhance model training speed and accuracy, we incorporate a multi-task loss function based on homoscedastic uncertainty. Experimental results demonstrate the superiority of our proposed model over other machine learning and deep learning methods, providing more accurate predictions of branch parameters. [ABSTRACT FROM AUTHOR]

Sea–land segmentation is of great significance for autonomous coastline monitoring, which is fundamental research in the remote sensing community. Due to the diverse contents and easily confused sea–land boundaries contained in remote sensing images, it is always challenging to achieve precise sea–land segmentation for complex scenarios. Although existing deep learning-based methods have exhibited promising performance, excessive computational load and insufficient use of hierarchical features remain unresolved. In this paper, we contribute to addressing the problems by developing an efficient and lightweight convolutional neural network (CNN) termed E-Net. On the one hand, the proposed network adopts a novel E-shaped architecture that reforms the conventional U-codec structure to make full use of hierarchical features at different depths, so that the sea–land segmentation effect can be significantly improved without excessive computational load. On the other hand, a contextual aggregation attention mechanism (CA2M) is designed to further facilitate efficient aggregation and transmission of contextual information, so that the fuzzy and irregular sea–land boundaries can be accurately distinguished. Extensive experiments reveal that our approach not only produces superior sea–land segmentation effect but also demonstrates promising computational efficiency. Specifically, the proposed E-Net achieves state-of-the-art sea–land segmentation performance with 92.78% and 93.62% mean Intersection over Union (mIoU) on the SLSD and HRSC2016 datasets, respectively, while the frames per second (FPS) reaches 108.032 with as low as 52.287G floating point operations per second (FLOPs). [ABSTRACT FROM AUTHOR]

Electricity demand prediction is crucial to ensure the operational safety and cost-efficient operation of the power system. Electricity demand has predominantly been predicted deterministically, while uncertainty analysis has been usually overlooked. To address this research gap, an integrated Neural Facebook Prophet (NFBP) model and Gaussian Kernel Density Estimation (KDE) model is proposed in this paper, as a way to obtain point and interval predictions of electricity demand, quantifying this way the uncertainty in the predictions. First, historical lagged data, created by utilizing the Partial Auto-correlation Function and Mutual Information Test, is applied to train a prediction model based on NFBP, Deep Learning (DL) as well as Statistical Models. Second, the model Prediction Errors (PE) are derived from the difference between actual and predicted values. A splitting strategy based on the mean and standard deviation of PE is proposed. Finally, electricity demand prediction intervals are obtained by applying Gaussian KDE on split PE. To verify the effectiveness of the proposed model, simulation studies are carried out for three prediction horizons on freely available datasets for the Bulimba sub-station in Southeast Queensland, Australia. Compared with DL models (Long-Short Term Memory Network and Deep Neural Network), the Root Mean Square Error of the NFBP model was reduced by 6.1% and 11.3% for 0.5-hr ahead, 22.7% and 26.3% for 6-hr ahead, and 31.8% and 29.9% for daily prediction. In addition, the Prediction Interval normalized Interval width is smaller in magnitude for the proposed NFBP-KDE model compared to other DL and Statistical models. [Display omitted] • A novel method is proposed for interval prediction of electricity demand. • Kernel density estimation with Gaussian function is applied to obtain interval prediction based on point prediction error. • Parameter of KDE distribution is optimized by minimizing Mean Integrated Square Error. • Deterministic and probabilistic metrics verify the superiority of the proposed prediction model. [ABSTRACT FROM AUTHOR]

The minimization of milling wear from prolonged contact between a tool and a workpiece is crucial in modern manufacturing, where high precision, efficiency, and productivity are required. Therefore, many researchers have developed systems for monitoring milling wear in real-time. However, while the adoption of multiple sensor signals can enhance the training effectiveness of the model, the complex setup process, data extraction, and feature analysis make it challenging to practically apply it for wear monitoring on production lines. Therefore, this study integrates various machining parameters of machine tools and a single type of sensor signal to extract features related to tool wear. These features are utilized as training data for an artificial neural network (ANN) model. The paper proposes a tool wear prediction ANN model based on automatic hyperparameter tuning and transfer learning, incorporating the architecture of Inception, DenseNet, and Layer Normalization. The network structure enhances the training efficiency for target features by expanding and reusing features from a single sensor's data. The combination of automatic hyperparameter tuning with a general optimizer optimizes the ANN architecture to achieve the best tool wear prediction model. Lastly, the proposed model is compared with other models using metrics including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R 2) to evaluate the model performance. In the results, the proposed model shows the best performance among all the comparing models in all three metrics. The MAE is 0.03527, RMSE is 0.05135, and the R 2 is 0.9611. Compared to the common models such as Random Forest, the MAE and RMSE can be reduced by 43.2%, and 43.5% respectively, and a 9.5% R 2 performance increase. • The deep learning model is used for extended feature extraction for the proposed network for transfer learning. • This study proposes a fully connected layers structure which is similar to DenseNet with Layer Normalization at the end of each layer of dense connection. • The model optimization method is used to automatically adjust and optimize hyperparameters. • The experimental results show the proposed model which is capable of predicting tool wear in real-time by feeding the processing parameters has higher prediction accuracy than the other algorithms. [ABSTRACT FROM AUTHOR]

The efficient and safe production of machinery equipment relies on the health of its mechanical components, making prognostics and health management (PHM) a critical aspect of production processes. One key PHM measure is the remaining useful life (RUL), which estimates the expected lifespan of a component in a production line before requiring repair or replacement. However, state-of-the-art RUL prediction methods, including data-driven, model-based, and hybrid approaches, face limitations such as incomplete/imprecise physical models, uncertainties in degradation processes, and measurement data noise. To address these limitations, this paper proposes a novel hybrid RUL prediction framework that combines the strengths of data-based and model-driven approaches. The framework includes an exponential model to leverage physical knowledge and a multi-head attention transformer to extract information from data. An extended Kalman filter is used to estimate unknown degradation process parameters and provide physical model information for the prediction process. A regression token is introduced to efficiently fuse the deep learning model and the stochastic filtering method. Numerical tests using real-world rolling bearing degradation datasets demonstrate the superiority of the proposed method over competitive alternatives. [ABSTRACT FROM AUTHOR]

The detection of pomegranate fruitlets is of great significance for fruit thinning and yield estimation. However, the researches on the detection of pomegranate fruitlets are rarely considered in recent years. In addition, the immature fruit detection algorithms often have a large amount of calculation, which require high computing memory and computing resources of the equipment. Based on the mentioned issue, we propose a lightweight detection method based on the improved You Only Look Once Version 8(YOLOv8) to realize the automatic detection of pomegranate fruitlets (PG-YOLO). Firstly, the lightweight network Shufflenetv2 is used to reconstruct the backbone of YOLOv8s. Secondly, the Depthwise separable convolution is used to replace the standard convolution of Neck layer. Then, the multi-head self-attention (MHSA) is used to enhance the positioning ability and feature extraction ability of the model before the backbone network outputs features. Finally, the self-built pomegranate fruitlet dataset is used to train and test the PG-YOLO model. It is shown that, the Mean Average Precision(mAP) of pomegranate fruitlets detected by PG-YOLO model is 93.4%. The optimal weight size of PG-YOLO is only 2.2 Mb, which is 89.9% less than the original YOLOv8s. In addition, the detection speed of the PG-YOLO model is 74.1% higher than the original YOLOv8s. The results demonstrate that the study significantly reduces the complexity of the model and provides a research basis for further application in mobile devices. The self-built PG-YOLO-Dataset used in this paper has been published on github: https://github.com/LforikC/PG-YOLO-Dataset. [ABSTRACT FROM AUTHOR]

The tolerance for different defects in the production process of fiberglass fabric varies. For acceptable defects, only relevant information needs to be recorded and printed, while for intolerable defects, the loom needs to be stopped promptly for handling. To address the issue of inefficient production of fiberglass fabric due to this situation, this paper proposes a task-modularized cascade network model for quality inspection of fiberglass fabric. The three stages cascaded detection network is composed of the improved MobilenetV3-small and the enhanced You Only Look Once v8 Nano (YOLOv8n). For MobilenetV3_small, the Squeeze- and-Excitation(SE) module in the Block layer with a 5 × 5 convolutional kernel is replaced with the Efficient Channel Attention (ECA) mechanism, enhancing channel information while making the model more lightweight. For YOLOv8n, a Global Attention Module (GAM) is added to the network, enhancing the ability to capture global information of input data, making the model more perceptual. Additionally, a Similarity Attention Module (SimAM) is added between the neck and head networks, enabling the network to better capture relevant information in the images, improving the quality of feature maps and enhancing network performance. Finally, a large number of defect images of fiberglass fabric were collected from an industrial site, and different datasets for the three stages were created. Numerous experiments were conducted, and when using all three stages for detection, the accuracy rate reaches 99.4%, with a parameter count of 16.8M and Frames Per Second (FPS) of 186. The cascade network has been successfully applied in the industrial field of fiberglass fabric and meets industrial production requirements. [ABSTRACT FROM AUTHOR]

Due to the increasing high penetration of Photovoltaic (PV), it brings great challenge for voltage control issue of distribution network. To address this problem, this paper presents an improved collaborative Multi-Agent Reinforcement Learning (MARL) approach for proactive voltage control, aimed at mitigating voltage violations and minimizing power losses. The self-attention mechanism is embedded into the multi-agent soft actor-critic (MASAC) algorithm to enhance the collaboration of multi-agent system, which can well improve the learning efficiency to ensure the voltage safety of Distribution Network. In addition, the proposed learning approach is implemented on IEEE 33-bus, 141-bus and 322-bus systems, and the simulation results reveal that the proposed approach can control the voltage into safety domain as well as reduce power losses. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification pertains to the task of assigning a single label to each pixel by analyzing its spectral–spatial characteristics. Convolutional Neural Networks (CNNs) have garnered significant attention on account of their remarkable performance in feature representation. However, these approaches possess a restricted capacity to acquire highly similar spectral features. Recently, Attention-based approaches have been devised as a means to surmount the limitations inherent in CNNs. In this paper, we address a novel architecture for spectral–spatial feature extraction and HSI classification. The framework efficiently amalgamates the robustness and efficacy of three modern backbone networks, i.e., Multiscale CNN, Squeeze and Excitation (SE), and Transformer named MSTSENet. Initially, the multiscale convolution module integrates three branches of 3D convolution layers, each employing distinct kernel sizes, facilitating multiscale and multi-resolution feature extraction. Subsequently, the SE module enhances the inter-channel relationship by adaptively recalibrating the feature weight. The strategic fusion of the SE module with multiscale CNN strengthens deep feature extraction while introducing a minimal increment in overall parameters. Lastly, the Transformer module orchestrates information aggregation across different spectral–spatial regions, accurately modeling long-range contextual dependencies and capturing dominant feature representations. To evaluate the model performance, comprehensive experiments have been carried out on widely used benchmark HSI datasets. The overall accuracy of 98.74%, 99.83%, and 99.98% is achieved over the Indian Pines, Pavia University, and Salinas Valley datasets, respectively. The code of this work will be accessible at https://github.com/irfan01000/MSTSENet. [ABSTRACT FROM AUTHOR]

Accurate typhoon intensity estimation is vital for timely risk warning and hazard assessment. The task is challenging since the subcategories of the typhoon have visually similar appearances. The local context extracted from the typhoon center region and the global context of cloud pattern is the most discriminative features for intensity estimation. However, the existing method does not utilize local and global contexts together. Furthermore, the interactions between local and global contexts remain unexplored. To make a better prediction, this paper proposes a local and global context attention mechanism-based fusion network that consists of a spatial attention fusion block and a channel attention fusion block. The channel attention fusion block infers an optimal channel fusion weight by exploiting the inter-channel relationship. The spatial fusion block learns the best inter-spatial relationship of features. Extensive experiments on DeepTi and TCIR benchmarks demonstrate the effectiveness of our method, and the proposed network achieves new state-of-the-art. The code is at https://github.com/chen-huanxin/RBCFN. • Local and global information fusion improve estimation accuracy. • A multi-level framework aggregates information from multiple areas. • Spatial and channel attention fusion improve feature representation ability. • Attention mechanism effectively fuses multi-modal information. [ABSTRACT FROM AUTHOR]

Deep learning has advanced the development of automated cervical cytology, yet limited studies have delved into methods for incorporating medical domain knowledge, and model interpretability has not been thoroughly investigated. To address this issue, this paper proposes a novel, explainable detection method for abnormal cervical cells, called dual-stream self-attention based feature fusion and origin grouping network (DSA-FFOGNet). To encourage the model to focus more on lesion cells and cell nuclei of diagnostic significance, the dual-stream self-attention (DSA) module is introduced to enhance the learning of lesion-specific features. In view of the complex background, cell dense distribution, cell overlap, or clumps existing in the actual cervical cytology images, multi-scale features are extracted and fused by using the path aggregation network (PAN) to enhance the feature representation ability. By integrating biomedical insights regarding cell provenance and formulating an origin grouping loss, DSA-FFOGNet adjusts the penalties for cervical cells originating from different groups, thereby enhancing the optimization of the model training process. To further improve the detection performance, the classification and localization tasks are decoupled via the use of double detection heads. Extensive experiments validate the robustness of the proposed DSA-FFOGNet. The visualization of class activation maps (CAMs) showcases the model's interpretability. The proposed approach advances the application and development of explainable artificial intelligence (XAI) models in cervical cytology and inspires further research in automated cervical cytology. [ABSTRACT FROM AUTHOR]

Derailments significantly harm railroads in terms of severity and fatality rates. Manually monitoring railway tracks is a tedious and often insufficient task to prevent derailment accidents. This necessitates the development of an automated monitoring system to oversee the condition of railway tracks. In the foreseeable future, Unmanned Aerial Vehicles (UAVs), artificial intelligence, and computer vision will play a crucial role in periodically assessing the railway environment to ensure passenger safety. This paper proposes a lightweight and efficient railroad semantic segmentation network (Lite-RSNet), which segments real-time aerial railroad images into rails, gauges, and backgrounds. The segmented regions then compute the distance between rails and obstacles, identifying potential derailment hazards in railroad applications. Lite-RSNet incorporates a multi-level feature fusion framework that includes a residual layer, a multi-head attention layer, a Concurrent Spatial and Channel Squeeze Excitation (CSSE) block, and a Convolutional Block Attention Module (CBAM). The designed approach enhances onboard processing efficiency by streamlining the model to use fewer parameters and reduce storage demands. Performance assessment of the model utilized the Rail Segmentation Dataset (RSD), which consists of high-resolution, low-altitude aerial photographs of Indian railroads. The Lite-RSNet model outperforms current leading methods, maintaining a lean structure with only 6 million parameters and achieving notable metrics of 0.971 for the Dice Coefficient (DC) and 0.947 for the Jaccard Index (JI) on the test dataset. Furthermore, distance estimation between an obstacle and rail has been implemented using image processing techniques as an additional work of this proposal to know about the caution of an obstacle. [ABSTRACT FROM AUTHOR]

The detection and identification for aircraft icing and actuator/sensor fault has been a lasting topic in flight safety researches. The current algorithms are usually tailored for some specific cases (faults/icing locations, magnitude, etc.). Although the performance of the algorithm in the designated cases may be good, the transferring of it to other different cases is usually heavy as parameters tuning or even algorithm redesigning may be required. In this paper, the author advocates exploring a comprehensive scheme that balance both good performance and wide transferability for different cases. Referring to the current advances in other research communities, we follow the state-of-art Deep Learning (DL) and transfer learning (TL) concepts. A scheme for the icing/actuator fault detection using the DL technique is firstly constructed. The TL is then adopted to transfer this scheme to other different tasks, e.g. fault/icing identification, sensor fault detection. Test results show that the TL-enhanced DL scheme exhibits not only good performance for the designated detection task, but also reflects flexible transferability at low tuning efforts. Via this paper the author advocates furtherly exploring the potentials of the novel DL and TL technique as to advancing the researches/techniques in the flight dynamics and control realm. [ABSTRACT FROM AUTHOR]

Abstract Integrated modular avionics is one of the most advanced systems. Its performance deeply impacts on the working condition of aircraft. In order to enhance the safety and reliability of aircraft, the health state of the integrated modular avionics should be evaluated accurately. In this paper, a novel deep learning method is developed to evaluate the health state. Firstly, as one of the deep learning methods, stacked denoising autoencoders is used to extract the features from the raw data immediately to retain original information. Secondly, the extracted features are fed into the quantum neural network to classify the data set. The loss function of the quantum neural network is evolved to improve the classification performance. Experiments conducted on standard datasets show that the proposed method is more effective and robust than other four conventional algorithms. Finally, this paper builds an integrated modular avionics degradation model by the changing probability of the occurrence of soft faults in the whole life serves and the proposed method is applied to the health state evaluation. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of switch migration in software defined networking (SDN)/network function virtualization (NFV)-based fifth generation (5G) networks in which SDN controllers are deployed as virtualized network functions (VNFs). The problem of switch migration is how to properly transfer the traffic of some SDN switches to one or multiple other virtualized SDN controllers in order to cope with the traffic fluctuations and the changing network topology. The highly dynamic environment of 5G networks requires the simultaneous consideration of multiple conflicting objectives in this problem including controllers load-balancing and network stability. In this paper, this multi-objective problem is formulated as a mixed integer non-linear program (MINLP) which is computationally expensive to solve. Therefore, a mathematical-based solution method is first provided based on the successive convex approximation (SCA) technique for the single-objective problem in which preference parameters are given to describe associated importance of the objectives. Taking into account the time restrictions for practical developments, an extended deep learning (DL) approach is then proposed to produce multiple mappings over multiple objectives. The verification results show that the proposed multi-objective DL algorithm can generate high quality Pareto Fronts close to those of the state-of-the-art algorithms based on optimization with orders of magnitude speedup in the computational time. [ABSTRACT FROM AUTHOR]

Face recognition is a very active research topic due to the number of potential applications that use this technique and the number of challenges that still require efforts to solve them. However, new research problems arise when dealing with devices operating in real-time, and using a non-controlled image source such as surveillance cameras, due to the needs and context of end-use. A robust and efficient face recognition system is proposed in this paper to monitor unauthorized access to equipments in a room using a surveillance camera. The system is based on a person detection algorithm adapted to the context of use, a person tracking algorithm robust to occlusion, a face detection algorithm robust to orientation and scale, and a face recognition algorithm robust to illumination change. To enhance the efficiency of person identification, a novel strategy for estimating the confidence of face recognition is proposed in this paper. This is achieved by leveraging the general conditions of the image used for this purpose. This technique allows to increase the identification rate while minimizing the false alarm rate. An effort is also made to optimize the implementation of the developed algorithms to guarantee a real-time operation while keeping a very high efficiency. Also, the evaluations of the proposed algorithms on public and private data show an improvement of the accuracy on the whole context of use of the proposed system. Furthermore the evaluation of the system in general shows a high efficiency, 100% detection of unauthorized accesses and 0 false alarms. [ABSTRACT FROM AUTHOR]

The use of Unmanned Aerial Vehicles (UAVs) has become increasingly popular in recent years, leading to a surge in research on this topic that is widely represented in the literature. They would be examined in accordance with the requirements of the sensors they house, their operating limits, and the output information they give. Since perception, planning, localization, and control are the major tasks of UAVs, an outstanding problem solver "Deep learning" is recently used in these systems. It is ideally suited for UAV applications because of its great capacity for learning representations from the complicated data received in actual situations. This paper provides an extensive review and in-depth analysis of current advancements in UAVs that have applications with DNN, as well as a quick summary of research and development during the previous ten years. In terms of UAVs flight monitoring, remote sensing and vision capability, and energy modeling, this survey provides a roadmap for understanding the sequential development of sophisticated UAVs by reviewing 173 retrieved papers. For this purpose, first of all, the main titles of the studies carried out for UAV applications were gathered under a taxonomy, and then information about the studies carried out in recent years related to these main research fields was given. In the last part of the study, attention was drawn to the still challenging points, such as autonomous fault detection, path planning, and onboard event detection, which are anticipated to be the future trends involving UAV applications. • An up-to-date and comprehensive overview on UAV sensor applications with DNNs. • A taxonomy is given for the researchers to easily examine the studies. • To easily examine the data sets, information about them is summerized. • Information about DNNs architectures end evaluation method is given. • A total of 173 studies, with 117 articles, and 54 conferences proceedings are surveyed. [ABSTRACT FROM AUTHOR]

This paper proposes a alternate physics-informed neural network (PINN) with a two-stage training strategy to solve the thermoelastic coupling in the growth of Czochralski silicon single crystal. Particularly, neural networks with a two-stage training strategy are established for solving partial differential equations in the thermoelastic coupling model. At present, PINN still faces challenges in solving coupling models. Especially for the imbalance between and within equations in the coupling model. To solve this problem, this paper splits the model into two independent systems with their coupling term exchanged in the alternating iteration. Then, the imbalance inside a single solution of the coupling model is solved by the proposed two-stage training strategy, and the imbalance between solutions is avoided by alternative iterations. Experimental results show that the proposed alternate two-stage PINN (ATPINN) can accurately simulate the temperature and displacement in the thermoelastic coupling model. Compared with the finite element results, the error of temperature prediction and displacement prediction is acceptable. The numerical results demonstrate the feasibility and performance of the ATPINN. Furthermore, ATPINN can be extended to any type of coupling model, especially for coupling models with large differences in the magnitudes of the loss functions. The codes developed in this manuscript are publicy available at https://github.com/callmedrcom/ATPINN. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of an effective and robust fusion representation method for foreground moving object detection. Many fusion representation learning approaches pay attention to the similarity measurement between the fusion results and source images in texture details and pixel intensity, ignoring the harmful information, e.g., noise, blur, and extreme illumination. Therefore, the aggregated features of infrared and visible images will introduce much harmful information, affecting the model performance of downstream visual tasks. This paper tackles these problems by proposing a contrastive fusion representation learning method for the foreground moving object detection task, which consists of two major modules: the upstream fusion representation module (FRM) and the downstream foreground moving object detection module (FODM). Unlike the traditional fusion optimization mechanism, the former aims to extract valuable features and reject harmful features via the maximum mutual information theory. The latter is a siamese convolutional neural network to detect foreground moving objects by aggregating the time-sequence images generated by FRM. Experimental results and comparisons with the state-of-the-art on three public datasets (i.e., TNO, MF, and cross-modal FOD dataset of infrared and visible images), validate the effectiveness, robustness, and overall superiority of the proposed contrast fusion representation learning method. Concisely, our contrastive fusion representation learning has gained 53. 9 % , 43. 2 % , 46. 4 % , 52. 3 % , 2. 2 % , 87. 1 % , 3. 5 % on EI, SF, DF, AG, MI, and Nabf metrics compared with the best competitors. [ABSTRACT FROM AUTHOR]

Detecting defects in industrial products is one of the most widespread applications of industrial automation. Various product defects, large similarities, and drastic changes in scale in industrial scenarios pose challenges to existing industrial inspection networks. This paper proposes a deep learning-based industrial defect detection method (IDD-Net) to address the above challenges. Specifically, IDD-Net has three distinct features. First, for the defects of diversity and similarity (rolled-in_scale, crazing in steel defects), IDD-Net designed a novel local–global backbone feature network (LGB-Net). Second, IDD-Net proposes a novel Three-Layer Feature Aggregation network (TFLA-Net) to solve the problem of drastic scale changes. TFLA-Net adopts a novel three-layer descending method to aggregate semantic and fine-grained features effectively. At the same time, the dense connection of adjacent nodes of TFLA-Net ensures the efficient fusion of features of different scales in the network. In particular, this paper proposes a novel IoU loss (Defect-IoU loss) for the problem of object loss deviation at different scales. The novelty of Defect-IoU Loss is that the loss value is scaled by the difference in the area of different scale objects, which is more conducive to the balance of multi-scale object loss. The experimental results show that the calculation amount of IDD-Net is only 24.9 Gflops, and the mAP@.5 of 79.66%, 99.5%, and 95.9% in the steel defect, aluminium defect, and PCB defect datasets were respectively obtained, surpassing all comparison models. In addition, the test in the actual industrial scene also demonstrates the feasibility of the application of IDD-Net. [ABSTRACT FROM AUTHOR]

Safety and passengers' comfort affect directly the reliability and availability of trains. Therefore, appropriate monitoring of the variables influencing those two concepts is mandatory for good operation and maintenance costs reduction. Moreover, operators and rail manufacturers are evolving to a condition-based maintenance strategy (CBM). For this purpose, machine learning is being used to predict early main component's failures, avoiding a loss of reliability or availability during commercial operation. From the passengers' point of view, punctuality and comfortability are two of the most relevant factors when evaluating a railway transport service. Comfort is mainly based on the availability of all services in the train, but it is also related to the accelerations received through the car body to the passengers. More precisely, the lateral car body acceleration (Ayc variable in this paper) is a key variable related to comfort perception and it is therefore important to be monitored and controlled. Rolling, suspension, and damping elements must be kept in perfect conditions during operation to achieve a smooth train movement. In this paper, an optimized model based on Long Short Term Memory networks (LSTM) is designed and trained to predict lateral car body accelerations using only the train accelerometers and with no additional sensoring for this specific experiment. This model will be compared with artificial neural networks (ANN) models to evaluate the relevance of time dependency for this purpose. The optimal time frame to group data is a key characteristic of the neural network training process and is also determined in this paper. The model is trained with data corresponding to the correct dynamic behavior of the train. To test the reliability of this method, a real case of excessive train movement is tested. In these situations, an alert could be sent to the operator or the maintainer for a not-programmed maintenance inspection at the depot (predictive maintenance), avoiding future passenger complaints for the loss of comfort or, in extreme cases, speed limitations due to safety reasons for excessive accelerations. The main contributions of this work are the following: - A LSTM-based neural network, predicting lateral car body accelerations achieving better results than a plain ANN for this dataset: 0.0335 m/s2 MAE and a 12% gain on extreme axles. - An optimization of the time frame to group the measurements in this algorithm that is considering as an input the time variable: 5 s. - A real use case of the model in which monitoring the deviation would have helped to take an early maintenance adjustment on the suspension or damping elements to prevent the loss of comfort. - The p-value used to reduce the uncertainty of the results obtained in the real use case is reaching over 0.95 in the coaches with good dynamic behavior and less than 0.15 in the coaches where a dynamic problem related to comfort loss is detected. [ABSTRACT FROM AUTHOR]

Artificial intelligence research in the area of computer vision teaches machines to comprehend and interpret visual data. Machines can properly recognize and classify items using digital images captured by cameras and videos, deep learning models, and then respond to what they observe. Similarly, artificial intelligence has also been able to learn complex images captured by Synthetic Aperture Radar (SAR) that are widely used for various purposes but still leave room for improvements. Researchers have proposed numerous approaches in this field, from SAR target detection to SAR target recognition. This paper presents a survey on the different techniques and architectures proposed in the literature for various SAR image applications. The paper covers a survey on target detection models and target recognition models and their respective workflow to analyze the techniques involved and the performances of these models. This paper makes novel discussions, comparisons, and observations. It highlights the advantages and disadvantages of different approaches to give researchers the idea of how each technique can influence the performance for adoption in the future. The potential future directions along with hybrid models on each processing method are also highlighted based on the study. • State-of-the-art techniques on SAR image processing comprising detection and recognition are discussed. • The different architectures and parameter settings of each technique are also examined. • The significant advantages and disadvantages of the existing techniques are also discussed to give researchers insights into each method. • Necessary observations on each processing technique are discussed based on the study. • Future approaches to improving the existing techniques for performance enhancement are also highlighted, along with a few potential models. [ABSTRACT FROM AUTHOR]

Photoresist coating is a key procedure in semiconductor wafer surface processing, and bubbles in a photoresist dropper usually affect the uniformity of photoresist film, which seriously reduces the etching quality of semiconductor wafer surface. However, the problems of blurred edges of photoresist bubbles and complex corrugations in photoresist itself make the automatic detection of photoresist bubbles very challenging. To overcome this problem, a high-precision photoresist bubble detection method based on deep learning is proposed in this paper. First, aiming at the problem that the photoresist bubble samples are extremely lacking and cannot meet the requirement of deep learning model training, this paper proposes a sample automatic generator bubbleGAN based on the adversarial generative network, so as to effectively increase the number of photoresist bubble samples with better diversity of the target to be detected, thus improving the performance of the detection model; Second, aiming at the challenges of target detection caused by the blurred edges of photoresist bubbles and the complex ripples of photoresist itself, this paper proposes a novel bubble detection method mYOLO. Based on the recently developed high-performance target detection method YOLOX, we optimize its structure and activation function to reduce the difficulty of model training, solve the dead zone problem of activation function, and improve the accuracy of model detection. The experimental results on the dataset collected by the actual rotary coating machine prove the effectiveness of the proposed algorithm. In addition, we further compare the impact of different manual data augmentation methods on the detection model. [ABSTRACT FROM AUTHOR]

Link prediction is a fundamental problem in complex network analysis, aimed at predicting missing or forthcoming connections. Recent research investigates the potential of Nonnegative Matrix Factorization (NMF) models in reconstructing sparse networks and using deep NMF to uncover the hierarchical structure. Deep models have demonstrated remarkable performance in various domains, but they are susceptible to overfitting, especially on the limited training data. This paper proposes a novel Link Prediction using Adversarial Deep NMF (LPADNMF) to enhance the generalization of network reconstruction in sparse graphs. The main contribution is the introduction of an adversarial training that incorporates a bounded attack on the input, leveraging the L 2 , 1 norm to generate diverse perturbations. This adversarial training aims to improve the model's robustness and prevent overfitting, particularly in scenarios with limited training data. Additionally, the proposed method incorporates first and second-order affinities as input to capture higher-order dependencies and encourage the extraction of informative features from the network structure. To further mitigate overfitting, a smooth L 2 regularization is applied to the model parameters. To optimize the proposed model effectively, we utilize a majorization-minimization algorithm that efficiently updates the perturbation and latent factors in an iterative manner. Our findings demonstrate that the proposed model not only has the ability to uncover and learn complex structures but also possesses generalization capabilities. This method demonstrates superior performance compared to state-of-the-art methods across eight networks. In comparison to the best-performing approach, LPADNMF exhibited improvements of 2.36% in AUC, 4.67% in Precision, 2.21% in Recall, and 3.73% in F-Measure. [ABSTRACT FROM AUTHOR]

It is necessary to efficiently and accurately predict the dynamic behavior of the train-track system subjected to massive random track geometric excitations for system evaluation and maintenance. This paper proposed an engineering practical approach for the train-track system behavior prediction by integrating the deep learning surrogate model-based long-short term memory (LSTM) and physical model of the train-ballasted track interaction (TBTI) system, and then the generalized probability density evolution method (GPDEM) is introduced to achieve the probabilistic assessment of the TBTI system under limited track irregularities, where the track irregularity probability model (TIPM) coupled with generalized-F discrepancy points sets is employed to compress the track irregularity sets to reduce the number of system responses (as training target) but without loss of the responses completeness, therefore, it can promote the efficiency and accuracy of training model. The prediction performance of the surrogate model is illustrated by comparing the time-frequency domain information, mean and standard deviation of the responses obtained by the physical model and surrogate model. The results indicated the proposed method can accurately predict the system response, especially the low and medium frequency response below 50 Hz, and improve the efficiency of stochastic analysis for the TBTI system by approximately 20 times. Furthermore, the applicability of the proposed method is further examined by investigating the influence of probability levels of track irregularity and train speeds on train performance. Its extended model is also implemented to predict the response of systems induced by any measured track irregularity in real-time, which promotes the generalization capability of the proposed surrogate model. [ABSTRACT FROM AUTHOR]

This paper presents a novel deep learning approach for reconstruction of local through-the-thickness fiber orientation distribution (FOD) in discontinuous long-fiber, prepreg-platelet molded composites (PPMC). The thermal-residual strains on composite surfaces are used as inputs to train a fully convolutional neural network, named U-Net, to predict spatially varying, local FOD. High fidelity synthetic data was generated via computational simulation of PPMC with stochastic material orientation state and was used for training the deep learning model. The proposed U-Net model allowed for rapid recognition of PPMC morphology by solving the inverse structural mechanics problem of determining the average fiber orientation through the composite thickness based on the provided surface strain measurements. Upon training and validation, the U-Net deep learning model was deployed to rapidly predict complex distributions of the local through-the-thickness FOD in PPMC. [ABSTRACT FROM AUTHOR]

Due to the inevitable light absorption and scattering, underwater images always suffer from severe quality degradation, leading to significant performance decline for various maritime engineering-related applications. In recent years, deep neural networks (DNNs) have been proven to achieve high-quality enhancement of underwater images, which aims to extract and learn abstract features to exhibit superior performance. However, existing solutions often stack multilayer processing units to enrich features, which not only significantly burdens computational load but also encounters difficulties in fully utilizing and interacting between features at different depths. To address the above problems, this paper presents a cost-effective underwater image enhancement network via cascaded feature extraction, termed CFENet. Specifically, we develop a cost-effective cascaded structure for sufficient feature extraction and multiscale establishment of pixel-level long-range dependencies. In addition, we construct a dual-branch structure for effective feature fusion, so that the detailed texture and semantic information in the image can be simultaneously enhanced. Extensive experiments reveal the superiority of our proposed CFENet in both underwater image enhancement effects and computational complexity. Sufficient ablation study is conducted to demonstrate the effectiveness of each component in the network. [ABSTRACT FROM AUTHOR]

Deep learning has made significant advancements in shadow removal. However, current methods primarily focus on local operations, leading to artifacts around shadow boundaries and inconsistent lighting between shadow and non-shadow regions. To address this issue, a global context aware dual channel pyramid model is proposed for robust image shadow removal in this paper. The model leverages a multi-scale channel attention framework based on transformers to capture global information. It consists of a shadow detection module and a dual-channel shadow interaction module to utilize non-shadow regions in aiding shadow restoration. Additionally, Winograd-based separable convolution attention shadow interaction attention is proposed to effectively expand the perceptual field and facilitate comprehensive utilization of contextual relevance between shadow and non-shadow regions. Extensive experiments are conducted on several popular public datasets such as ISTD, SRD and ISTD + to evaluate the effectiveness of our model. [ABSTRACT FROM AUTHOR]

The digitization of engineering drawings is crucial for efficient reuse, distribution, and archiving. Existing computer vision approaches for digitizing engineering drawings typically assume the input drawings have high quality. However, in reality, engineering drawings are often blurred and distorted due to improper scanning, storage, and transmission, which may jeopardize the effectiveness of existing approaches. This paper focuses on restoring and recognizing low-quality engineering drawings, where an end-to-end framework is proposed to improve the quality of the drawings and identify the graphical symbols on them. The framework uses K-means clustering to classify different engineering drawing patches into simple and complex texture patches based on their gray level co-occurrence matrix statistics. Computer vision operations and a modified Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) model are then used to improve the quality of the two types of patches, respectively. A modified Faster Region-based Convolutional Neural Network (Faster R-CNN) model is used to recognize the quality-enhanced graphical symbols. Additionally, a multi-stage task-driven collaborative learning strategy is proposed to train the modified ESRGAN and Faster R-CNN models to improve the resolution of engineering drawings in the direction that facilitates graphical symbol recognition, rather than human visual perception. A synthetic data generation method is also proposed to construct quality-degraded samples for training the framework. Experiments on real-world electrical diagrams show that the proposed framework achieves an accuracy of 98.98% and a recall of 99.33%, demonstrating its superiority over previous approaches. Moreover, the framework is integrated into a widely-used power system software application to showcase its practicality. The reference codes and data can be found at https://github.com/Lattle-y/AI-recognition-for-lq-ed.git Future work will focus on improving the generalizability of the proposed framework to different quality degradation scenarios and extrapolating the application to different engineering domains. [ABSTRACT FROM AUTHOR]

The significant gap between the assumed and actual degradation model will undoubtedly lead to a serious performance decrease for deep learning based image super-resolution (SR) methods. To solve this shortcoming, this paper presents an enhanced blind image super-resolution (EBSR) network based on unsupervised degradation representation learning. The proposed EBSR mainly is made up of two branching subnetworks. The first subnetwork is a residual-based degradation encoder, which is responsible to learn a high-dimensional abstract degradation representation vector from the input low-resolution (LR) image patches using contrast learning. Another branch is the degradation-aware fusion SR (DAFSR) network that completes the image SR task with the aid of the degradation representation vector learned by the encoder. To obtain an improved SR performance under various degradation settings, the degradation-aware fusion block (DAFB), the core block of DAFSR, has been elaborated, which embeds the degradation model information learned by the encoder into every layer of the network. Additionally, a shallow feature extraction block (SFEB) is constructed for DAFSR to extract global information from the LR image. The proposed EBSR can flexibly adapt to various degradation models. Extensive experimental results on synthetic datasets and real images show that the proposed EBSR is able to achieve a leading reconstruction performance over other blind SR algorithms. • A boosted degradation representation learning is proposed for blind image SR. • A new degradation encoder is designed using residual connection. • A degradation-aware fusion block is designed to obtain improved SR performance. • A shallow feature extraction block is adopted to extract global informative features. [ABSTRACT FROM AUTHOR]

Object detection is one of the most important domains in computer vision tasks, which is an important branch of artificial intelligence. It aims at finding and locating the accurate position of objects in given pictures or videos. With the development of deep learning techniques, more powerful and robust algorithms have emerged to deal with multi-scale, high-level features to overcome the limitations of traditional pipeline of object detectors. The popularity of transformer framework enables larger capacity datasets by processing self-attention mechanism, and the object detection methods have evolved into a new era. This paper first reviews traditional object detection pipeline and brief history of deep learning, afterwards it focuses on the classification of deep learning-based object detection methods covering Convolution Neural Network based and transformer-based methods. Commonly used datasets and metrics are also covered in the next part. The Convolution Neural Network based methods mainly contain two-stage and one-stage detectors, Convolution Neural Network is the underlying structure of these methods convolutional stages are fundamental parts. Transformer-based models convert traditional object detection issues into end-to-end detection, which is widely used in dealing with images. Finally, the promising future of object detection areas are listed to show guidance on future work. [Display omitted] [ABSTRACT FROM AUTHOR]

Image steganography is a technique of hiding secret information inside another image, so that the secret is not visible to human eyes and can be recovered when needed. Most of the existing image steganography methods have low hiding robustness when the container images affected by distortion. Such as Gaussian noise and lossy compression. This paper proposed a practical robust invertible network for image steganography (PRIS) to improve the robustness of image steganography, it based on invertible neural networks, and put two enhance modules before and after the extraction process with a 3-step training strategy. Moreover, rounding error is considered which is always ignored by existing methods, but actually it is unavoidable in practical. A gradient approximate function (GAF) is also proposed to overcome the undifferentiable issue of rounding distortion. Experimental results show that our method outperforms the state-of-the-art robust image steganography method in both robustness and practicability, achieved an average Peak Signal to Noise Ratio value of 34.28/32.96 on container/secret pairs under 5 different attacks. Codes are available at https://github.com/yanghangAI/PRIS , demonstration of our model in practical at http://yanghang.site/hide/. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the semi-supervised person re-identification (Re-ID) task. Under the semi-supervised setting, only a subset of individuals in large-scale datasets need to be labeled for training to reduce the manual annotation cost. To enhance recognition performance under this setting, we propose a novel three-stage, two-branch semi-supervised Re-ID framework. Within this framework, we implement a progressive training process that integrates three methods for training unlabeled data: identification learning based on the pseudo-label estimation technique, metric learning based on mining positive or negative pairwise relationships between samples, and feature consistency learning between views generated through various data augmentations. To make full use of the unlabeled data, the above three methods are gradually added in each training stage, and the defects of these methods are avoided. Moreover, to further improve the reliability of training samples, we design two modules for selecting reliable samples to determine which method to adopt for each unlabeled sample to reduce model performance deterioration due to incorrect pseudo-labels or incorrect sample pairs. Our framework can be combined with existing supervised methods and has less performance cost. Moreover, different components in our proposed framework can be used as plug-ins to integrate into existing semi-supervised Re-ID methods and improve their performance. Extensive experiments were conducted on two public Re-ID benchmarks that demonstrate the effectiveness of our proposed framework. [ABSTRACT FROM AUTHOR]

The existing deep learning-based image dehazing algorithms commonly employ an encoder–decoder structure to learn a direct mapping from hazy images to haze-free images. However, these state-of-the-art methods often fail to consider the varying contents of hazy images across different scenes, resulting in unsatisfactory dehazing outcomes. To address this issue, this paper attempts to integrate a novel instance-aware subnet into the classic encoder–decoder structure in order to achieve a clear separation between figure and background, conducting the selective incorporation of instance features into the dehazing network. Specifically, we introduce a novel architecture called the hybrid residual attention network, which is capable of separately extracting full-image features and instance-level features. This architecture incorporates attention mechanisms and a multi-scale dilated convolution structure, enabling adaptive perception of haze density in different scenes. Additionally, we introduce a global feature fusion subnet that employs a pixel attention structure to fuse features from the entire image and multiple individual instances, thus being aware of instance features. Compared to existing methods, our approach offers a major advantage in accurately estimating the haze density of individual instances, reducing color distortion, and mitigating noise amplification in the output images. Experimental results demonstrate that our method outperforms existing methods across different evaluation metrics and testing benchmarks. Therefore, we believe that our method will serve as a valuable addition to the current collection of artificial intelligence models and will benefit engineering applications in video surveillance and high-level computer vision tasks. [ABSTRACT FROM AUTHOR]

Accurate stock movement prediction is essential to profit from the stock market. However, this task is challenging due to the complexity and non-stationary nature of the market. Deep learning methods have obtained more attention and success in mining price movement patterns.However, some limitations affect their performances. In general, the stock market is ever-changing, and many factors affect stock movement, so capturing the stock movement patterns is hard without enough prior information. To tackle it, we consider employing economic facts to help improve the deep learning method. In this paper, we propose a novel Hierarchical Deep learning Model that fuses Economic Facts (HDMEF) to predict stock movement from the micro to the macro tiers: the individual, industry, and whole market tiers. Specifically, we present three well-designed modules to separately model them based on the Capital Asset Pricing Model (CAPM), the herding effects, and the holiday effects in the stock market. Experiments on the A-share CSI300 and CSI500 indexes demonstrate that our proposed method performs best on all test phases compared with previous competitive baselines, even an absolute improvement of 2%–3% on some test phases where all the baselines act poor, proving our method is more efficient and robust in different market conditions. In addition, we do an ablation study to analyze the role of various economic effects used in our model, and the results prove that each module is helpful for prediction. [ABSTRACT FROM AUTHOR]

In this paper, we propose the use of deep learning-based image super-resolution to accelerate structural topology optimization. Topology optimization suffers from iterative computation and a time cost that increases with the number of elements. Recently, there have been attempts to accelerate topology optimization using deep learning-based models, but they often do not address a wide range of physical conditions or require extensive training data. This highlights the need for an approach that can effectively solve different problem conditions with less training data. Our approach first starts topology optimization at a low resolution to quickly obtain an optimized structure. It is converted to the structure at a higher resolution by using an image super-resolution model. Then, the final structure is obtained by performing topology optimization at this high resolution by using the converted structure as the starting configuration. The super-resolution model learns how to transform low-resolution structural features into high-resolution ones regardless of optimization conditions. As a result, it can be applied to any problems different from the problem used to generate the data for training the model. The proposed approach's excellent acceleration and generalization performance is demonstrated for three representative problems in structural topology optimization with a small number of training datasets. Furthermore, it has been shown to be effective in the deck arch bridge problem and the natural frequency maximization problem. Finally, the proposed approach is also found to be effective on the three-dimensional cantilever beam problem. [ABSTRACT FROM AUTHOR]

As the important decomposition components of insulating gas sulfur hexafluoride, the accurate quantification of SO 2 , CS 2 and H 2 S is important to determine the type and severity of internal faults in the insulating equipment. In this paper, a method combining symmetry dot pattern and deep learning is proposed for quantitative detection of multi-component gas mixtures on the ultraviolet absorption spectroscopy platform. The method is based on symmetry dot pattern analysis to fuse the local ultraviolet spectral information which is useful for identifying trace gas mixtures with overlapping absorption peaks. A deep network based on transfer learning is established to recognize the symmetry dot pattern diagrams, achieving feature representation from different scales. The outstanding performance of this method is demonstrated and compared to the existing models by receiver operating characteristic curve. Experimental results on the platform show that the proposed method can quantitatively detect the concentrations of SO 2 , H 2 S and CS 2 ternary gas mixture online. [ABSTRACT FROM AUTHOR]

Executing various production tasks is critical to the safe operation and efficient production of industrial processes. As one of them, the detection task of key quality variables directly affects the operation optimization and decision-making of industrial processes, but it is severely limited by the harsh environment and detection instruments. Therefore, the real-time prediction task of key quality variables becomes the basis for optimal control of industrial processes. To address this issue, this paper proposes a task-oriented deep learning framework based on a target-related transformer (TR-Former) network for industrial quality prediction tasks. Specifically, a new target-related self-attention (TR-SA) mechanism is developed to guide feature learning by adding attention scores between task-related target variables and other variables. As a result, the learned features in this instance will be guaranteed to be relevant to the target variable and useful for the quality prediction task. Moreover, the long-range dynamics of industrial process data can also be captured, which can further improve the prediction performance of the model. Finally, extensive experiments were conducted on two industrial processes to validate the superiority of the proposed method in terms of quality prediction tasks. The experimental results demonstrate that the proposed TR-Former method exhibits an improvement ranging from 3% to 13% in the mean absolute error indicator compared to the traditional transformer and other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recently, research based on the camouflaged object detection (COD) task has achieved great progress, while the collaborative camouflaged object detection (CoCOD) task is still lacking. Our research focuses on the simultaneous detection and localization of the collaborative camouflaged objects, i.e., CoCOD task. We use the cooperative information between a single image and a group of camouflage images to discover cooperative camouflaged objects effectively. In this paper, we propose a collaborative cross-scale feature learning network (CCNet). Our model is characterized by two innovative constructions: We proposed an edge augmentation module (EAM), which effectively extracts edge information of the camouflaged object and integrates it with the collaborative information employed in auxiliary supervision. In addition, we design a group decoder module (GDM) to extract and merge co-camouflage information. Extensive experiments on CoCOD8K datasets demonstrate that our CCNet significantly outperforms the existing 13 state-of-the-art COD and 6 state-of-the-art collaborative salient object detection (CoSOD) methods under six widely used evaluation metrics. The code will be available at: https://github.com/zc199823/CCNet--CoCOD. [ABSTRACT FROM AUTHOR]

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

The harmful utilization of DeepFake technology poses a significant threat to public welfare, precipitating a crisis in public opinion. Existing detection methodologies, predominantly relying on convolutional neural networks and deep learning paradigms, focus on achieving high in-domain recognition accuracy amidst many forgery techniques. However, overseeing the intricate interplay between textures and artifacts results in compromised performance across diverse forgery scenarios. This paper introduces a groundbreaking framework, denoted as Texture and Artifact Detector (TAD), to mitigate the challenge posed by the limited generalization ability stemming from the mutual neglect of textures and artifacts. Specifically, our approach delves into the similarities among disparate forged datasets, discerning synthetic content based on the consistency of textures and the presence of artifacts. Furthermore, we use a model ensemble learning strategy to judiciously aggregate texture disparities and artifact patterns inherent in various forgery types, thereby enabling the model's generalization ability. Our comprehensive experimental analysis, encompassing extensive intra-dataset and cross-dataset validations along with evaluations on both video sequences and individual frames, confirms the effectiveness of TAD. The results from four benchmark datasets highlight the significant impact of the synergistic consideration of texture and artifact information, leading to a marked improvement in detection capabilities. • We build an artifact and texture inconsistency detector for deepfake detection. • Texture coherence is analyzed via a novel mask extraction method and an autoencoder. • The use of an ensemble training strategy improved the ability to generalize. • Extensive experiments verified the effectiveness of the model we built. [ABSTRACT FROM AUTHOR]

Cortical neural connectivity exhibits a small-world (SW) network topology. However, its role in neural information processing remains unclear. In this study, we investigate the learning performance of a Deep Echo State Network (DeepESN) that incorporates the Newman-Watts-Strogatz (NWS) graph topology as a reservoir. The short path length of the SW topology allows input information to reach output nodes faster, and the clustered arrangement of this topology can expand the range of the echo state property. Additionally, in this paper, we seek to identify the best set of these key factors, such as the spectral radius of the reservoir's weight matrix and the hyperparameters neighbors' and probabilities. We evaluate the NWS-DeepESNs on four Speech Emotion Recognition (SER) tasks, which are RAVDESS, Emo-db, SAVEE, and TESS databases. By examining the NWS-DeepESN's performance on SER tasks, we aim to determine the role of the NWS graph topology in enhancing neural information processing. The obtained results exhibited significant improvements in recognition accuracies (weighted and unweighted) with (76.45%, 75.79%), (87.89%, 87.14%), (99%, 98.62%), and (63%, 62.24%), respectively, for RAVDESS, Emo-db, SAVEE, and TESS databases. The proposed approach improves emotion recognition capabilities and yields more accurate results compared to existing state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Semantic segmentation is a well-studied topic and one of the most challenging tasks in computer vision applications, such as autonomous driving. Deep learning approaches based on convolutional neural networks (CNN) have demonstrated exceptional success on this task in recent years. Despite this success, existing approaches are plagued by higher-order inconsistencies between the ground truth images and the ones predicted by the segmentation model. This paper proposes a novel post-processing scheme based on adversarial learning to counter these inconsistencies. Such a scheme can be combined with a variety of existing CNN-based semantic segmentation networks to improve their segmentation performances. The proposed scheme is a Two-Stream Conditional Generative Adversarial Network (TScGAN), with one stream having initial semantic segmentation masks predicted by an existing CNN, while the other stream utilizes scene images to retain high-level information under a supervised residual network structure. In addition, TScGAN incorporates a novel dynamic weighting mechanism, which leads to significant and consistent gains in segmentation performance. Several comparative tests on public benchmark driving databases, including Cityscapes, Mapillary, and Berkeley DeepDrive100K, demonstrate the effectiveness of the proposed method when used with state-of-the-art CNN-based semantic segmentation models. Furthermore, the ablation experiment proved the structural rationality of our two-stream structure. The code for TScGAN could be found at https://github.com/epan-utbm/TScGAN-for-Improving-Semantic-Predictions • Explores various post-processing techniques for enhancing semantic segmentation. • Novel Two-Stream Conditional GAN enhances urban drive scene segmentation. • Enhances feature extraction by implementing dynamic weighting within streams. • Evaluates the model against existing semantic segmentation methodologies. • Tests on Cityscapes, Mapillary, BDD100K reveal major IoU gains with proposed model. [ABSTRACT FROM AUTHOR]

The image noise generated by the welding process, such as arc light, splash, and smoke, brings significant challenges for the laser vision sensor-based welding robot to locate the weld seam and accurately conduct automatic welding. Currently, deep learning-based approaches surpass traditional methods in flexibility and robustness. However, their significant computational cost leads to a mismatch with the real-time requirement of automated welding. In this paper, we propose an efficient hybrid architecture of Convolutional Neural Network (CNN) and transformer, referred to as Dynamic Squeeze Network (DSNet), for real-time weld seam segmentation. More precisely, a lightweight segmentation framework is developed to fully leverage the advantages of the transformer structure without significantly increasing computational overhead. In this respect, an efficient encoder, which aims to increase its features diversity, has been designed and resulted in substantial improvement of encoding performance. Moreover, we propose a plug-and-play lightweight attention module that generates more effective attention weights by exploiting statistical information of weld seam data and introducing linear priors. Extensive experiments on weld seam images using NVIDIA GTX 1050Ti show that our approach reduces the number of parameters by 54x, decreases computational complexity by 34x, and improves inference speed by 33x compared to the baseline method TransUNet. DSNet achieves superior accuracy (78.01% IoU, 87.64% Dice) and speed performance (100 FPS) with lower model complexity and computational burden than most state-of-the-art methods. The code is available at https://github.com/hackerschen/DSNet. [ABSTRACT FROM AUTHOR]