Search

Deep learning has become the main solution for face recognition applications due to its high accuracy and robustness. In recent years, a batch of research on lightweight convolutional neural networks (CNNs) has emerged, bringing new ideas to the economic application of face recognition systems. In this paper, a lightweight face recognition algorithm is proposed to reduce the number of parameters and calculations of the face feature extraction network. The most important part of our approach lies in designing a novel inverted residual shuffle unit (IR-Shuffle). After being trained by ArcFace loss on a GPU workstation, our model built on improved IR-Shuffle blocks of size 1.45 MB achieves an accuracy of 98.65%. In terms of running time, our model is 5 ms faster than the current fastest MobileFaceNet, with only about 0.5% drop in accuracy. The proposed algorithm is implemented and optimized on the Jetson Nano embedded platform, and accurate and real-time deployment of the face recognition system is realized. The system takes 37 ms to perform the complete face detection and recognition and is robust to complex backgrounds and ambient light changes. Experimental results show that our system is of practical application value. [ABSTRACT FROM AUTHOR]

The accuracy of insulators and their defect identification by UAVs (unmanned aerial vehicles) in transmission-line inspection needs to be further improved, and the model size of the detection algorithm is significantly reduced to make it more suitable for edge-end deployment. In this paper, the algorithm uses a lightweight GhostNet module to reconstruct the backbone feature extraction network of the YOLOv4 model and employs depthwise separable convolution in the feature fusion layer. The model is lighter on the premise of ensuring the effect of image information extraction. Meanwhile, the ECA-Net channel attention mechanism is embedded into the feature extraction layer and PANet (Path Aggregation Network) to improve the recognition accuracy of the model for small targets. The experimental results show that the size of the improved model is reduced from 244 MB to 42 MB, which is only 17.3% of the original model. At the same time, the mAp of the improved model is 0.77% higher than that of the original model, reaching 95.4%. Moreover, the mAP compared with YOLOv5-s and YOLOX-s, respectively, is improved by 1.98% and 1.29%. Finally, the improved model is deployed into Jetson Xavier NX and run at a speed of 8.8 FPS, which is 4.3 FPS faster than the original model. [ABSTRACT FROM AUTHOR]

The common spatial pattern (CSP) algorithm is efficient and accurate for channels selection and features extraction for electroencephalogram (EEG) signals classification. The CSP algorithm is usually applied on a subject-by-subject basis by measuring only intra-subject variations for selecting the most significant channels; we refer to this algorithm as CSP-based customized channels selection (CSP-CC). In practice, deploying the CSP-CC algorithm requires to set up a customized EEG device for each subject separately, which can be very costly. In this paper, we propose a new algorithm, called CSP-based unified channels (CSP-UC), for overcoming the aforementioned difficulties. The aim of the proposed algorithm is to extract unified channels that are valid for any subject; hence, one EEG device can be deployed for all subjects. Moreover, a methodology for developing both binary-class and ternary-class EEG signals classification models using either customized or unified channels is introduced. This methodology is applicable for both subject-by-subject and cross-subjects basis. In ternary-class classification models, the traditional "Max_Vote" method, used for voting the predicted class labels, has been modified to a more accurate method called "Max_Vote_then_Max_Probability." On a subject-by-subject basis, the experimental results on EEG-based driver's fatigue dataset have shown that the accuracy of the classification models that are based on the proposed CSP-UC algorithm is slightly lower than that of those based on the CSP-CC algorithm. Nevertheless, the former algorithm is more practical and cost-effective than the latter. But in cross-subjects, the classification models based on the CSP-UC algorithm outperform those based on the CSP-CC algorithm in both accuracy and the number of used channels. [ABSTRACT FROM AUTHOR]

In view of the fact that the aerial images of UAVs are usually taken from a top-down perspective, there are large changes in spatial resolution and small targets to be detected, and the detection method of natural scenes is not effective in detecting under the arbitrary arrangement of remote sensing image direction, which is difficult to apply to the detection demand scenario of road technology status assessment, this paper proposes a lightweight network architecture algorithm based on MobileNetv3-YOLOv5s (MR-YOLO). First, the MobileNetv3 structure is introduced to replace part of the backbone network of YOLOv5s for feature extraction so as to reduce the network model size and computation and improve the detection speed of the target; meanwhile, the CSPNet cross-stage local network is introduced to ensure the accuracy while reducing the computation. The focal loss function is improved to improve the localization accuracy while increasing the speed of the bounding box regression. Finally, by improving the YOLOv5 target detection network from the prior frame design and the bounding box regression formula, the rotation angle method is added to make it suitable for the detection demand scenario of road technology status assessment. After a large number of algorithm comparisons and data ablation experiments, the feasibility of the algorithm was verified on the Xinjiang Altay highway dataset, and the accuracy of the MR-YOLO algorithm was as high as 91.1%, the average accuracy was as high as 92.4%, and the detection speed reached 96.8 FPS. Compared with YOLOv5s, the p-value and mAP values of the proposed algorithm were effectively improved. It can be seen that the proposed algorithm improves the detection accuracy and detection speed while greatly reducing the number of model parameters and computation. [ABSTRACT FROM AUTHOR]

Registration between remote sensing images has been a research focus in the field of remote sensing image processing. Most of the existing image registration algorithms applied to feature point matching are derived from image feature extraction methods, such as scale-invariant feature transform (SIFT), speed-up robust features (SURF) and Siamese neural network. Such methods encounter difficulties in achieving accurate image registration where there is a large bias in the image features or no significant feature points. Aiming to solve this problem, this paper proposes an algorithm for multi-source image registration based on geographical location information (GLI). By calculating the geographic location information that corresponds to the pixel in the image, the ideal projected pixel position of the corresponding image is obtained using spatial coordinate transformation. Additionally, the corresponding relationship between the two images is calculated by combining multiple sets of registration points. The simulation experiment illustrates that, under selected common simulation parameters, the average value of the relative registration-point error between the two images is 12.64 pixels, and the registration accuracy of the corresponding ground registration point is higher than 6.5 m. In the registration experiment involving remote sensing images from different sources, the average registration pixel error of this algorithm is 20.92 pixels, and the registration error of the image center is 21.24 pixels. In comparison, the image center registration error given by the convolutional neural network (CNN) is 142.35 pixels after the registration error is manually eliminated. For the registration of homologous and featureless remote sensing images, the SIFT algorithm can only offer one set of registration points for the correct region, and the neural network cannot achieve accurate registration results. The registration accuracy of the presented algorithm is 7.2 pixels, corresponding to a ground registration accuracy of 4.32 m and achieving more accurate registration between featureless images. [ABSTRACT FROM AUTHOR]

In recommender systems, extracting higher order information about the graph using methods such as graph convolutional network alleviates the cold start problem. In order to fuse the deep feature extraction capability of neural network collaborative filtering on this basis, this paper proposed a two-channel collaborative filtering recommendation algorithm (GCNCF-2C) based on graph convolution. Firstly, it divided the recommendation problem into an upstream task and a downstream task. Secondly, to form a feature representation of nodes, in the upstream task, a pre-trained encoder extracted node features and higher-order features of the graph using a one-dimensional convolutional layer containing residuals and multiple graph convolutional layers in two independent channels. Finally, the decoder performed end-to-end training by node features for rating prediction. Experiments on the datasets MovieLens-100k and MovieLens-1M show that compared to the baseline models, the algorithm improves RMSE metrics by 1.72% and 1.76% on average and MAE metrics by 2.7% and 1.98% on average on the two datasets. Meanwhile, it improves RMSE metrics by 5.9% on average in the cold-start experiments based on users and projects, which shows overall performance. [ABSTRACT FROM AUTHOR]

The failure of insulators may seriously threaten the safe operation of the power system, where the state detection of high-voltage insulators is a must for the normal and safe operation of the power system. Based on the data of insulators in aerial images, this work explored an enhanced particle swarm algorithm to optimize the parameters of the support vector machine. A support vector machine model was therefore established for the identification of the normal and defective states of the insulators. This methodology works with the structure minimization principle of SVM and the characteristics of particle swarm fast optimization. First, the aerial insulator image was segmented as a target by way of the seed region growth based on double-layer cascade morphological improvements, and then, HOG features plus GLCM features were extracted as sample data. Finally, an ameliorated PSO-SVM classifier was designed to realize insulator state identification. Comparisons were made between PSO-SVM and conventional machine learning algorithms, SVM and Random Forest, and an optimization algorithm, Gray Wolf Optimization Support Vector Machine (GWO-SVM), and advanced neural network CNN. The experimental results showed that the performance of the algorithm proposed in this paper touched the top level, where the recognition accuracy rate was 92.11%, the precision rate 90%, the recall rate 94.74%, and the F1-score 92.31%. [ABSTRACT FROM AUTHOR]

This paper proposes a data valuation algorithm for inertial measurement unit-based human activity recognition (IMU-based HAR) data based on meta reinforcement learning. Unlike previous studies that received feature-level input, the algorithm in this study added a feature extraction structure to the data valuation algorithm, and it can receive raw-level inputs and achieve excellent performance. As IMU-based HAR data are multivariate time-series data, the proposed algorithm incorporates an architecture capable of extracting both local and global features by inserting a transformer encoder after the one-dimensional convolutional neural network (1D-CNN) backbone in the data value estimator. In addition, the 1D-CNN-based stacking ensemble structure, which exhibits excellent efficiency and performance on IMU-based HAR data, is used as a predictor to supervise model training. The Berg balance scale (BBS) IMU-based HAR dataset and the public datasets, UCI-HAR, WISDM, and PAMAP2, are used for performance evaluation in this study. The valuation performance of the proposed algorithm is observed to be excellent on IMU-based HAR data. The rate of discovering corrupted data is higher than 96% on all datasets. In addition, classification performance is confirmed to be improved by the suppression of discovery of low-value data. [ABSTRACT FROM AUTHOR]

Indoor 3D positioning is useful in multistory buildings, such as shopping malls, libraries, and airports. This study focuses on indoor 3D positioning using wireless access points (AP) in an environment without adding additional hardware facilities in large-scale complex places. The integration of a deep learning algorithm into indoor 3D positioning is studied, and a 3D dynamic positioning model based on temporal fingerprints is proposed. In contrast to the traditional positioning models with a single input, the proposed method uses a sliding time window to build a temporal fingerprint chip as the input of the positioning model to provide abundant information for positioning. Temporal information can be used to distinguish locations with similar fingerprint vectors and to improve the accuracy and robustness of positioning. Moreover, deep learning has been applied for the automatic extraction of spatiotemporal features. A temporal convolutional network (TCN) feature extractor is proposed in this paper, which adopts a causal convolution mechanism, dilated convolution mechanism, and residual connection mechanism and is not limited by the size of the convolution kernel. It is capable of learning hidden information and spatiotemporal relationships from the input features and the extracted spatiotemporal features are connected with a deep neural network (DNN) regressor to fit the complex nonlinear mapping relationship between the features and position coordinates to estimate the 3D position coordinates of the target. Finally, an open-source public dataset was used to verify the performance of the localization algorithm. Experimental results demonstrated the effectiveness of the proposed positioning model and a comparison between the proposed model and existing models proved that the proposed model can provide more accurate three-dimensional position coordinates. [ABSTRACT FROM AUTHOR]

Most of the traditional image feature point extraction and matching methods are based on a series of light properties of images. These light properties easily conflict with the distinguishability of the image features. The traditional light imaging methods focus only on a fixed depth of the target scene, and subjects at other depths are often easily blurred. This makes the traditional image feature point extraction and matching methods suffer from a low accuracy and a poor robustness. Therefore, in this paper, a light field camera is used as a sensor to acquire image data and to generate a full-focus image with the help of the rich depth information inherent in the original image of the light field. The traditional ORB feature point extraction and matching algorithm is enhanced with the goal of improving the number and accuracy of the feature point extraction for the light field full-focus images. The results show that the improved ORB algorithm extracts not only most of the features in the target scene but also covers the edge part of the image to a greater extent and produces extracted feature points which are evenly distributed for the light field full-focus image. Moreover, the extracted feature points are not repeated in a large number in a certain part of the image, eliminating the aggregation phenomenon that exists in traditional ORB algorithms. [ABSTRACT FROM AUTHOR]

Aiming at the problem of motion blur in the inspection image of wind power generation equipment, an improved fast motion blur removal method based on deblurganv2 is proposed in this paper. Firstly, according to the characteristics of disparate local motion blur degrees and different global motion blur directions of the wind power inspection image, the real wind power fuzzy image data set is collected and produced. Secondly, according to the characteristics of the single background of the wind power inspection image and the requirements of fast and effective processing, the lightweight network Ghostnet is redesigned as the backbone network of the Deblurganv2 generator to reduce the number of network parameters and calculations. Finally, five SE channel attention mechanism layers are added to GhostNet to strengthen feature extraction, and the upsampling process is optimized through bilinear interpolation, to improve the deblurring performance of the wind power inspection image. The experimental results show that compared with other algorithms, the proposed algorithm has a higher peak signal‐to‐noise ratio and structural similarity, the network model parameters are compressed to 6.1 MB, and the reasoning speed is improved to 0.42 s. [ABSTRACT FROM AUTHOR]

The fruit quality and yield of sweet peppers can be effectively improved by accurately and efficiently controlling the growth conditions and taking timely corresponding measures to manage the planting process dynamically. The use of deep-learning-based image recognition technology to segment sweet pepper instances accurately is an important means of achieving the above goals. However, the accuracy of the existing instance segmentation algorithms is seriously affected by complex scenes such as changes in ambient light and shade, similarity between the pepper color and background, overlap, and leaf occlusion. Therefore, this paper proposes an instance segmentation algorithm that integrates the Swin Transformer attention mechanism into the backbone network of a Mask region-based convolutional neural network (Mask RCNN) to enhance the feature extraction ability of the algorithm. In addition, UNet3+ is used to improve the mask head and segmentation quality of the mask. The experimental results show that the proposed algorithm can effectively segment different categories of sweet peppers under conditions of extreme light, sweet pepper overlap, and leaf occlusion. The detection AP, AR, segmentation AP, and F1 score were 98.1%, 99.4%, 94.8%, and 98.8%, respectively. The average FPS value was 5, which can be satisfied with the requirement of dynamic monitoring of the growth status of sweet peppers. These findings provide important theoretical support for the intelligent management of greenhouse crops. [ABSTRACT FROM AUTHOR]

Identifying the abnormal samples from a data set and determining their type are two key tasks of anomaly detection. However, the existing anomaly detection algorithms are generally faced with the defects of weak generalization ability and insufficient interpretation, the core reason of which is that they cannot mine specific features for different abnormal types. In this paper, a new anomaly detection algorithm aiming at feature selection for different abnormal types is developed. Inspired by self-supervised learning, we take the stationarity of variance changes of abnormal score similarity as a pretext task and combine it with wrapped search method. Then, the features and the corresponding parameters for different abnormal types can be screened to apply to the downstream task of anomaly integration detection. To verify the efficiency of the new algorithm, we conduct two sets of experiments to compare the new algorithm with 11 classical anomaly detection and 3 clustering anomaly detection algorithms on the data sets WDBC, WPBC and Wilt from DAMI database with the evaluation measures P@n , Adj- P@n , AP, Adj-AP and AUC. The experiment results show that, both in the identification and classification on abnormal samples, all performance measures of the new algorithm are explicitly better than that of the contrastive algorithms. Also, we apply the new algorithm to the Chinese auto insurance market, and find that the results can help managers to identify the main patterns of fraudulent claims and to summarize the feature combinations of fraud behaviors. In general, the new algorithm developed in this paper has the following advantages compared with traditional algorithms: 1) It can directly capture abnormal features and realize effective recognition of abnormal types, which effectively bridge the gap between abnormal judgement and feature screening. 2) Automatic screening of abnormal features can be completed under the condition of self-updating learning optimal strategy. 3) Only a few features are extracted from all features to reveal the abnormal characteristics, which significantly improves the interpretability and generalization ability of the algorithm and its results. In a word, through the novel self-supervised design method, feature screening is skillfully integrated into the anomaly detection task, which may provide a new way for anomaly detection research. [ABSTRACT FROM AUTHOR]

[Display omitted] • A feature extraction module is proposed to extract the geometric and semantic features of each point efficiently. Then, the attention mechanism is deployed to aggregate the learned features. • The proposed ResDLPS-Net is optimized by joint training of residual connections and dense convolutional connections. • Experiments demonstrate that ResDLPS-Net outperforms the state-of-the-art deep learning networks on the indoor dataset S3DIS and the outdoor large-scale dataset Toronto-3D. Significantly, the Mean Intersection over Union (mIoU) of ResDLPS-Net on the Toronto-3D dataset is 80.27%. Semantic segmentation methods based on three-dimensional (3D) point clouds are mostly limited to input point clouds that have been divided into blocks for training. This is mainly attributed to the requirement of constant trade-offs between computational resources and accuracy for directly processing large-scale point clouds. Specifically, the block dividing strategy will add the data preprocessing time to some extent and may disturb the complete geometry of the object. Therefore, this paper proposes a large-scale point cloud semantic segmentation network without block dividing operation, referred to as ResDLPS-Net. This network can take the complete point cloud of the whole large scene as input and process up to nearly a million points on one single GPU. In particular, a novel feature extraction module is designed to efficiently extract neighbor, geometric, and semantic features. The learned features are then aggregated through the attention mechanism to form local feature descriptors. In addition, the proposed ResDLPS-Net is jointly trained by residual connections and dense convolutional connections to optimize the feature aggregation operation. As a result, the ResDLPS-Net performs brilliantly on multiple objects, such as windows, road markings, fences, etc. For example, the Mean Intersection over Union (mIoU) of road markings on the Toronto-3D dataset is 37.76% higher than the state-of-the-art algorithm. Moreover, this paper outperforms most deep learning methods on three well-known benchmark datasets, including the indoor dataset S3DIS and the outdoor large-scale scene datasets Semantic3D and Toronto-3D. The proposed ResDLPS-Net achieves the best performance on the S3DIS dataset. The average accuracy (mA) and overall accuracy (OA) are 82.3% and 88.1%, respectively. Notably, the proposed ResDLPS-Net attains a mIoU of 80.27% on the Toronto-3D dataset, which is 6.00% higher than the best results published currently. [ABSTRACT FROM AUTHOR]

Taking Uyghur character recognition as an example, this paper use a method of image segmentation which combines traditional methods with CNN, and transforms and implements the Uyghur character on intelligent devices. Firstly, after analyzing the application of several general segmentation methods, this paper finds some shortcomings but also some ideas for Uighur segmentation. Then, starting from the characteristics of Uyghur language, such as structure, word formation and input habits, the author studies the idea of Uyghur adhesive language segmentation from the perspective of language characteristics, puts forward the basic algorithm of Uyghur symbol segmentation, and applies the Uyghur character adhesion segmentation based on minimum spanning tree and multi-queue primitive merging model to improve the segmentation efficiency. In addition, in order to solve the limitations of the traditional handwriting recognition framework of "preprocessing + feature extraction + classifier", this paper puts forward a new solution of Uyghur handwriting recognition technology combining prior domain knowledge with CNN, constructs a Uyghur handwriting recognition model on the basis of CNN and random elastic deformation, and also improves the recognition rate of the system by combining domain knowledge with CNN. According to the experimental results, we can conclude that the mixed method proposed in this paper can effectively break the technical bottleneck of traditional methods, thus improving the efficiency of segmentation and recognition. [ABSTRACT FROM AUTHOR]

Traditional text annotation-based video retrieval is done by manually labeling videos with text, which is inefficient and highly subjective and generally cannot accurately describe the meaning of videos. Traditional content-based video retrieval uses convolutional neural networks to extract the underlying feature information of images to build indexes and achieves similarity retrieval of video feature vectors according to certain similarity measure algorithms. In this paper, by studying the characteristics of sports videos, we propose the histogram difference method based on using transfer learning and the four-step method based on block matching for mutation detection and fading detection of video shots, respectively. By adaptive thresholding, regions with large frame difference changes are marked as candidate regions for shots, and then the shot boundaries are determined by mutation detection algorithm. Combined with the characteristics of sports video, this paper proposes a key frame extraction method based on clustering and optical flow analysis, and experimental comparison with the traditional clustering method. In addition, this paper proposes a key frame extraction algorithm based on clustering and optical flow analysis for key frame extraction of sports video. The algorithm effectively removes the redundant frames, and the extracted key frames are more representative. Through extensive experiments, the keyword fuzzy finding algorithm based on improved deep neural network and ontology semantic expansion proposed in this paper shows a more desirable retrieval performance, and it is feasible to use this method for video underlying feature extraction, annotation, and keyword finding, and one of the outstanding features of the algorithm is that it can quickly and effectively retrieve the desired video in a large number of Internet video resources, reducing the false detection rate and leakage rate while improving the fidelity, which basically meets people's daily needs. [ABSTRACT FROM AUTHOR]

Various UNet architecture-based image change detection algorithms promote the development of image change detection, but there are still some defects. First, under the encoder–decoder framework, the low-level features are extracted many times in multiple dimensions, which generates redundant information; second, the relationship between each feature layer is not modeled so sufficiently that it cannot produce the optimal feature differentiation representation. This paper proposes a remote image change detection algorithm based on the multi-feature self-attention fusion mechanism UNet network, abbreviated as MFSAF UNet (multi-feature self-attention fusion UNet). We attempt to add multi-feature self-attention mechanism between the encoder and decoder of UNet to obtain richer context dependence and overcome the two above-mentioned restrictions. Since the capacity of convolution-based UNet network is directly proportional to network depth, and a deeper convolutional network means more training parameters, so the convolution of each layer of UNet is replaced as a separated convolution, which makes the entire network to be lighter and the model's execution efficiency is slightly better than the traditional convolution operation. In addition to these, another innovation point of this paper is using preference to control loss function and meet the demands for different accuracies and recall rates. The simulation test results verify the validity and robustness of this approach. [ABSTRACT FROM AUTHOR]

Person re-identification is to recognize a pedestrian who has been observed at different places in monitoring system, which is done by computer automatically. Important practical significance can be found in this paper on improving the intelligence of monitoring system. There are two challenging problems needed to be solved for person re-identification, which is feature representation and matching. Designing a suitable feature representation method is both challenging and crucial. Ideally, the extracted features should be robust enough to cope with the various situations of the monitoring environment, such as posture difference, illumination changing, and shooting angle difference, etc. There are a lot of challenges for feature matching too, such as small sample size, inter-class confusion, and intra-class variation, etc. In order to meet these challenges, a new person re-identification scheme was put forward in this paper. The following three aspects would be used to describe it. First, an improved BOF feature extraction algorithm based on SURF was put forwarded, SURF algorithm extracts the preliminary feature descriptor and generates visual dictionary, so the influence factors such as illumination and scale invariants can be deal with. And then, covariance descriptor was adopted by the algorithm. It has high robustness, and matching accuracy can be improved too for the case of small sample. Finally, an effective classifier was designed by LIBSVM based on improved BOF algorithm, so the efficiency of the person re-identification algorithm can be improved. The proposed method was compared with the current mainstream algorithm through experiment, and it can be found through the experimental results that it is effective to solve the difficult problems for person re-identification. [ABSTRACT FROM AUTHOR]

A spectral power-based real-time BCI neuro-feedback (decision machine) system has been proposed in this paper. It is used to reflect the intended task of the movement imagination of hand movements. As a consequence of the cost-effective and greater temporal resolution, the proposed decision machine considered the electroencephalogram (EEG) signal. EEG data modeling is therefore an important step in seeking a rational solution for a specific application. The most potential temporal relative spectral power (TRSP) based feature extraction algorithm, and probabilistic Bayesian classifier has been used to model the EEG data for the reproduction of the thoughts. In this paper, the author has considered two channels of information for command generation. This paper also focuses on the maximization of information retrieval by analyzing incoming two channels' brain signals. This initiates to devise an appropriate reactive frequency band for each subject before applying the feature extraction algorithm. In this direction, this paper uses relative power spectral intensity (RPSI) for reactive frequency band estimation. The spectral power-based feature extraction method is responsible for the improvement of the accuracy, reducing the computational complexity, lowers the computational time, and improves the information transfer rate. The performance of the proposed BCI system shows better results compared to the different well established conventional EEG based BCI systems. The proposed real-time neuro-feedback system is a generalized BCI system that will be readily applicable for controlling any external devices. The proposed system shows 90.37% accuracy over the BCI Competition II dataset and 81% average accuracy with 64 ms computational time in the real-time application. [ABSTRACT FROM AUTHOR]

Absrtact: Background: Nowadays, numerical relays configured through power swing blocking function are vulnerable to faults with high impedance owing to nonlinearities present in the faulty path. Identification of symmetrical high impedance faults incepting during the power swing scenario is of prime importance for protection engineers to avoid cascade tripping. It is analyzed that the classical approaches for symmetrical fault detection during power swing can mal‐operate owing to high level of uncertainty arise during validation of high impedance fault, symmetrical faults and cross country faults during power swing with varied level of compensation which has been explored in this research. Aims: This paper presents an innovative scheme for series compensated line by utilizing the capability of Relevance Vector Machine (RVM) as a disturbance classifier taking into consideration of cross country faults, CT saturation; power swings prone to symmetrical faults along with high impedance faults in comparison with prevailing methods. Materials & Methods: In order to validate the proposed RVM based disturbance classifier algorithm, different kinds of faults and power swing situations have been applied in IEEE 9 bus test system using PSCAD/EMTDC software followed by validation in MATLAB. The features of sequence components of currents are estimated using Modified Full Cycle Discrete Fourier Transform (MFCDFT). The extracted features are used as control inputs to RVM for discernment among power swing and fault under the influence of wide range of system and fault dynamics. Results: The developed RVM based disturbance classifier scheme generates a tripping signal in the event of high impedance fault during power swing and remains stable during swing conditions. It can be used in conjunction with an adaptive numerical distance relaying scheme for realizing complete protection of the power grid for all zones of protection. A comparative analysis with an existing disturbance classifier algorithm indicates relative superiority with much improved fault classification accuracy. Discussion: In order to validate the proposed algorithm, different kinds of fault and power swing scenario are realized in IEEE 9 bus test system using PSCAD and current samples are acquired at sampling frequency of 4 kHz. The phasor estimation of sampled signals has been performed using MFCDFT which is used to derive feature vector extraction from symmetrical components. The extracted features are applied to RVM based fault classifier algorithm for classification of disturbance. The obtained results are also compared with existing schemes of protections. It has been proved that developed algorithm outperforms with much improved fault classification accuracy. Conclusion: This paper discovers relevance vector machine based adaptive learning approach for dynamic disturbance classification in complex power grid network. The developed algorithm has been validated on IEEE 9 bus test system modelled in PSCAD. The fault and system dynamics are varied over a wider range which includes variation in fault type, fault impedance, fault inception angle, power flow angle, fault location and degree of line compensation level. Moreover, the validation of scripted algorithm has been performed for very complex power grid scenarios like cross‐country faults, high impedance faults with varying degree of compensation, power swing and saturation of instrument transformers etc. The feature vectors are extracted using MFCDFT and applied to supervised RVM based disturbance classifier and outperforms with classification accuracy of 99.74% which indicates it's superiority over existing classifier approaches based on SVM & ANN. [ABSTRACT FROM AUTHOR]

Multi-scale image decomposition is crucial for image fusion, extracting prominent feature textures from infrared and visible light images to obtain clear fused images with more textures. This paper proposes a fusion method of infrared and visible light images based on spatial domain and image features to obtain high-resolution and texture-rich images. First, an efficient hierarchical image clustering algorithm based on superpixel fast pixel clustering directly performs multi-scale decomposition of each source image in the spatial domain and obtains high-frequency, medium-frequency, and low-frequency layers to extract the maximum and minimum values of each source image combined images. Then, using the attribute parameters of each layer as fusion weights, high-definition fusion images are through adaptive feature fusion. Besides, the proposed algorithm performs multi-scale decomposition of the image in the spatial frequency domain to solve the information loss problem caused by the conversion process between the spatial frequency and frequency domains in the traditional extraction of image features in the frequency domain. Eight image quality indicators are compared with other fusion algorithms. Experimental results show that this method outperforms other comparative methods in both subjective and objective measures. Furthermore, the algorithm has high definition and rich textures. [ABSTRACT FROM AUTHOR]

The image copy–move forgery can achieve the realistic effects without leaving any obvious manipulation traces because the copied source and pasted target belong to the homogenous sources. Image copy–move forgery detection (CMFD) is still a serious challenge issue for researchers, e.g. computational efficiency, occlusive (smoothing) object detection, and partial object detection, under various post-processing and geometrical transformations. This paper proposes a novel CMFD scheme using the characteristics of local descriptors. First, the proposed method deeply analyzes the structure and mines the inherent characteristics of the local descriptor (SURF) for feature extraction in the coarse and smooth regions. Subsequently, the proposed method takes the kernel features as coarse feature matching to decrease matching costs. Then, the found candidate keypoints with a relatively small quantity are used with complete features to perform fine keypoint matching for getting suspicious candidate keypoint pairs. Furthermore, based on the deep mining of the inherent local descriptor characteristics, the proposed method can indicate the forgery region localizations through keypoint pairs, even the forgeries suffering from various geometrical transformations. Then, the proposed method proposes adaptive dual-filtering algorithms of K -means relying on keypoint characteristics, and spatial distance for hierarchical progress of feature filtering. Finally, Delaunay Triangulation relies on the true-positive keypoint pairs to perform the forgery region matting effectively and efficiently. The experimental results demonstrate that the proposed method can achieve the best F1 scores compared to the state-of-the-art methods in most cases, especially in anti-scaling transformations. [ABSTRACT FROM AUTHOR]

The current ADMET classification methods have shortcomings in classifying the ADMET of compounds data with multiple characteristics and feature correlation. Moreover, the classification results of ADMET are not explainable. To solve these problems, this paper proposed a classification model based on capsule network（CapsMC). CapsMC model first proposed the Feature-to-Image algorithm. It used this algorithm to consider the correlation and dependence between features into the classification basis, and realized the multi-level extraction of features. Second, it explored the advanced application of capsule network, and designed a cognitive reasoning mechanism. It used this mechanism to carry out cognitive reasoning on features, and realized explainable classification of ADMET. Experimental results on five ADMET datasets show that CapsMC can achieve the explainable classification of ADMET well. [ABSTRACT FROM AUTHOR]

In recent years, the Corona Virus Disease 2019 (Covid-19) epidemic has raged around the world, with more than 500 million people diagnosed. Relevant medical research and analysis results on Covid-19 indicate that wearing masks is an effective method to prevent and restrain virus transmission. Mask detection stations have been set up in hospitals, railway stations, schools, where there is large crowd flow, but results are not as good as expected. In order to ameliorate pandemic preventing and control measures, a mask wearing detection algorithm YOLOv3-M3 was designed and proposed in this paper. The algorithm can effectively detect people without mask, while consequently reminding them. Firstly, we substituted the feature extraction network of YOLOv3 with MobileNetv3, a lightweight convolutional neural network. Secondly, we utilized K-Means++ to substitute the original ground truth clustering algorithm to improve prediction precision. In addition, the bounding box regression loss function was revised as CIoU loss function. This loss function solves the issues of overlapping between the ground truth and the anchor box, which has increased the training speed. After experiments, the precision of YOLOv3 algorithm on mAP 0.5 and mAP 0.75 is 93.5% and 71.9%, respectively. Elevating 3.1% and 2.6%, respectively, higher than that of YOLOv3 algorithm, and it was superior to SSD, SSD Lite, YOLOv3-Tiny and other one-stage object detection algorithms. The detection speed can reach 13.6 frame/s, which has met the requirements of pandemic prevention and control in most places and can be deployed on terminal devices for object detection. [ABSTRACT FROM AUTHOR]

Since the onset of civilization, sketches have been used to portray our visual world, and they continue to do so in many different disciplines today. As in specific government agencies, establishing similarities between sketches is a crucial aspect of gathering forensic evidence in crimes, in addition to satisfying the user's subjective requirements in searching and browsing for specific sorts of images (i.e., clip art images), especially with the proliferation of smartphones with touchscreens. With such a kind of search, quickly and effectively drawing and retrieving sketches from databases can occasionally be challenging, when using keywords or categories. Drawing some simple forms and searching for the image in that way could be simpler in some situations than attempting to put the vision into words, which is not always possible. Modern techniques, such as Content-Based Image Retrieval (CBIR), may offer a more useful solution. The key engine of such techniques that poses various challenges might be dealt with using effective visual feature representation. Object edge feature detectors are commonly used to extract features from different image sorts. However, they are inconvenient as they consume time due to their complexity in computation. In addition, they are complicated to implement with real-time responses. Therefore, assessing and identifying alternative solutions from the vast array of methods is essential. Scale Invariant Feature Transform (SIFT) is a typical solution that has been used by most prevalent research studies. Even for learning-based methods, SIFT is frequently used for comparison and assessment. However, SIFT has several downsides. Hence, this research is directed to the utilization of handcrafted-feature-based Oriented FAST and Rotated BRIEF (ORB) to capture visual features of sketched images to overcome SIFT limitations on small datasets. However, handcrafted-feature-based algorithms are generally unsuitable for large-scale sets of images. Efficient sketched image retrieval is achieved based on content and separation of the features of the black line drawings from the background into precisely-defined variables. Each variable is encoded as a distinct dimension in this disentangled representation. For representation of sketched images, this paper presents a Sketch-Based Image Retrieval (SBIR) system, which uses the information-maximizing GAN (InfoGAN) model. The establishment of such a retrieval system is based on features acquired by the unsupervised learning InfoGAN model to satisfy users' expectations for large-scale datasets. The challenges with the matching and retrieval systems of such kinds of images develop when drawing clarity declines. Finally, the ORB-based matching system is introduced and compared to the SIFT-based system. Additionally, the InfoGAN-based system is compared with state-of-the-art solutions, including SIFT, ORB, and Convolutional Neural Network (CNN). [ABSTRACT FROM AUTHOR]

Traditional YOLOv4 object detection network is difficult to be applied to mobile embedded devices because it has some deficiencies such as complex structure and too many parameters. In this paper, the authors propose a lightweight object detection algorithm. Firstly, Mobienetv3 is used to replace the original feature extraction network, and the Mish function is used to be the activation function, which reduces the number of model parameters. Secondly, the dilated convolution is used to replace the maximum pooling operation in the original spatial pyramid pooling (SPP) structure. Then, a custom Dcn‐Dw structure is used to replace the convolution operation in the original PANet, which improves the accuracy of the model for irregular object detection and reduces the model size. Finally, a CBAM lightweight attention mechanism module is introduced in front of the YOLO Head, which further improves the model accuracy. An experiment on the VOC2007 dataset is carried out, and the results show that the mean average precision (mAP) is 80.3% and frames per second (FPS) is 15. At the expense of 3% accuracy, the detection speed is increased to two to three times, and the model size is reduced to one‐fifth of the original model. The lightweight object detection algorithm can suit for real‐time detection tasks on resource‐constrained embedded devices. [ABSTRACT FROM AUTHOR]

To address the problems of less semantic information and low measurement accuracy when the SSD (single shot multibox detector) algorithm detects small targets, an MPH-SSD (multiscale pyramid hybrid SSD) algorithm that integrates the attention mechanism and multiscale double pyramid feature enhancement is proposed in this paper. In this algorithm, firstly, the SSD algorithm is used to extract the feature map of small targets, and the shallow feature enhancement module is added to expand the receptive field of the shallow feature layer so as to enrich the semantic information in the feature layer for small targets and improve the expression ability of shallow features. The processed shallow feature layer and deep feature layer are fused at multiple scales, and the semantic information and location information are fused together to obtain a feature map with rich information. Secondly, the cascaded double pyramid structure is used to transfer from the deep layer to the shallow layer so that the context information between different feature layers can be effectively transferred and the feature information can be further strengthened. The hybrid attention mechanism can retain more context information in the network, adaptively adjust the feature map after addition and fusion, and reduce the background interference. The experimental analysis of MPH-SSD algorithm on Pascal VOC and MS COCO datasets shows that the map of this algorithm is 87.7% and 51.1%, respectively. The results show that the MPH-SSD algorithm can make better use of the feature information in the shallow feature layer in the process of small target detection and has better detection performance for small targets. [ABSTRACT FROM AUTHOR]

Object detection is a critical technology of environmental perception for autonomous driving vehicle. The Convolutional Neural Network has gradually become a powerful tool in the field of vehicle detection because of its powerful ability of feature extraction. In aiming to reach the balance between speed and accuracy of detection in complex traffic scenarios, this paper proposes an improved lightweight and high-performance vehicle–pedestrian detection algorithm based on the YOLOv4. Firstly, the backbone network CSPDarknet53 is replaced by MobileNetv2 to reduce the number of parameters and raise the capability of feature extraction. Secondly, the method of multi-scale feature fusion is used to realize the information interaction among different feature layers. Finally, a coordinate attention mechanism is added to focus on the region of interest in the image by way of weight adjustment. The experimental results show that this improved model has a great performance in vehicle–pedestrian detection in traffic scenarios. Experimental results on PASCAL VOC datasets show that the improved model's mAP is 85.79% and speed is 35FPS, which has an increase of 4.31% and 16.7% compared to YOLOv4. Furthermore, the improved YOLOv4 model maintains a great balance between detection accuracy and speed on different datasets, indicating that it can be applied to vehicle–pedestrian detection in traffic scenarios. [ABSTRACT FROM AUTHOR]

Deep learning-based target detection for optical remote sensing images is a significant research direction in the field of image processing. Different from natural images, remote sensing images are characterized by complex backgrounds, similarity of characteristics between various classes and diverse target scales. In this paper, we propose an adaptive multi-feature fusion YOLOv3 remote sensing small target detection algorithm to cope with these features. In the proposed algorithm, the shallow semantic information is extracted by the accessory feature extraction network, and fused with the deep features extracted by Darknet-53 down-sampling to enrich the semantic and spatial information of the feature layers on the auxiliary network. In addition, the shallow features are filtered using the adaptive feature selection module to refine the effective feature information. A cross-layer feature fusion module is proposed to fuse different feature layers to enhance the connection between the semantic information of feature contexts to obtain more information about the characteristics of small targets. To test the effectiveness of the proposed algorithm, it is validated on the Pascal voc2007 dataset. The experimental results show that the detection accuracy of the proposed algorithm could achieve 88.3%, and evidently superior to the original YOLOv3 algorithm. Finally, the proposed algorithm is applied to detect the small target in remote sensing images. The detection results show that compared with the original YOLOv3 algorithm, the mean average precision(mAP) of the proposed algorithm is improved by 2.6%, which can effectively detect more small targets and significantly improve the detection accuracy of small targets than other classical algorithms. [ABSTRACT FROM AUTHOR]

Feature extraction is the key to the fault detection of rotating machinery based on vibration signals, and the quality of the features influences the reliability of the detection. This paper develops a fault feature extraction method of rotating machinery based on optimized resonance-based sparse signal decomposition and refined composite multiscale fluctuation dispersion entropy. First, resonance-based sparse signal decomposition is used to decompose the vibration signals adaptively. In order to obtain the resonance-based sparse signal decomposition algorithm with optimal performance, the marine predator algorithm is used for the parameters optimization with correlation kurtosis as the fitness function. Subsequently, based on the refined composite coarse-grained process and fluctuation dispersion entropy, a refined composite multiscale fluctuation dispersion entropy is developed, enabling a more accurate and comprehensive measure of the complexity of time series. Then, all feature matrices are input to the support matrix machine for fault identification. Experiments are conducted using two typical rotating machinery datasets for the validity of the proposed method, and comparisons are made with other methods. The results show that the proposed scheme outperforms other comparative methods regarding classification accuracy and stability. In addition, the proposed scheme can obtain relatively reliable classification results even when the data volume is small and the background noise is significant, demonstrating the scheme's potential for application in practical engineering. [ABSTRACT FROM AUTHOR]

A human contact network (HCN) consists of individuals moving around and interacting with each other. In HCN, it is essential to detect malicious users who break the data delivery through terminating the data delivery or tampering with the data. Since malicious users will pay more but gain less when breaking the data delivery of opportunistic contacts, we focus on the non-opportunistic contacts that occur more frequently and stably. It is observed that people contact with each other more frequently if they have more social features in common. In this paper, we build up topology structure for HCN based on social features, and propose a graph theoretical comparison detection model to perform malicious users detection. Then we present an adaptive detection scheme based on Hamiltonian cycle decomposition. Also, we define comparison-0-string and comparison-1-string to improve the detection efficiency. Moreover, we perform scenario simulations on real data to realize the detected process of malicious users. Experiments show that, when the number of malicious users is bounded by the dimension of HCN, our scheme has a detection rate of 100% with both false positive rate and false negative rate being 0%, and the running cost is also very low when compared to baseline approaches. When the number of malicious users exceeds the bound, the detection rate of our scheme decreases slowly, while the false positive rate and false negative rate increase slowly, but they are still better than the baseline approaches. [ABSTRACT FROM AUTHOR]

The task of ship target detection based on remote sensing images has attracted more and more attention because of its important value in civil and military fields. To solve the problem of low accuracy in ship target detection in optical remote sensing ship images due to complex scenes and large-target-scale differences, an improved R3Det algorithm is proposed in this paper. On the basis of R3Det, a feature pyramid network (FPN) structure is replaced by a search architecture-based feature pyramid network (NAS FPN) so that the network can adaptively learn and select the feature combination update and enrich the multiscale feature information. After the feature extraction network, a shallow feature is added to the context information enhancement (COT) module to supplement the small target semantic information. An efficient channel attention (ECA) module is added to make the network gather in the target area. The improved algorithm is applied to the ship data in the remote sensing image data set FAIR1M. The effectiveness of the improved model in a complex environment and for small target detection is verified through comparison experiments with R3Det and other models. [ABSTRACT FROM AUTHOR]

At present, deep learning has been widely used in SAR ship target detection, but the accurate and real-time detection of multi-scale targets still faces tough challenges. CNN-based SAR ship detectors are challenged to meet real-time requirements because of a large number of parameters. In this paper, we propose a lightweight, single-stage SAR ship target detection model called YOLO-based lightweight multi-scale ship detector (LMSD-YOLO), with better multi-scale adaptation capabilities. The proposed LMSD-YOLO consists of depthwise separable convolution, batch normalization and activate or not (ACON) activation function (DBA) module, Mobilenet with stem block (S-Mobilenet) backbone module, depthwise adaptively spatial feature fusion (DSASFF) neck module and SCYLLA-IoU (SIoU) loss function. Firstly, the DBA module is proposed as a general lightweight convolution unit to construct the whole lightweight model. Secondly, the improved S-Mobilenet module is designed as the backbone feature extraction network to enhance feature extraction ability without adding additional calculations. Then, the DSASFF module is proposed to achieve adaptive fusion of multi-scale features with fewer parameters. Finally, the SIoU is used as the loss function to accelerate model convergence and improve detection accuracy. The effectiveness of the LMSD-YOLO is validated on the SSDD, HRSID and GFSDD datasets, respectively, and the experimental results show that our proposed model has a smaller model volume and higher detection accuracy, and can accurately detect multi-scale targets in more complex scenes. The model volume of LMSD-YOLO is only 7.6MB (52.77% of model size of YOLOv5s), the detection speed on the NVIDIA AGX Xavier development board reached 68.3 FPS (32.7 FPS higher than YOLOv5s detector), indicating that the LMSD-YOLO can be easily deployed to the mobile platform for real-time application. [ABSTRACT FROM AUTHOR]

In the large data environment, there are many problems in the parallel deep convolution neural network（DCNN） algorithm, such as excessive data redundancy, slow convolution layer operation and poor convergence of loss function. This paper proposed a parallel deep convolution neural network optimization algorithm based on the Im2 col method. First, the algorithm proposed a parallel feature extraction strategy based on Marr-Hildreth operator to extract target features from data as input of convolution neural network, which can effectively avoid the problem of excessive data redundancy. Secondly, the algorithm designed a parallel model training strategy based on the Im2 col method. The redundant convolution kernel is removed by designing the Mahalanobis distance center value, and the convolution layer operation speed is improved by combining the MapReduce and Im2 col methods. Finally, the algorithm proposed an improved small-batch gradient descent strategy, which eliminates the effect of abnormal data on the batch gradient and solves the problem of poor convergence of the loss function. The experimental results show that IA-PDCNNOA algorithm performs well in deep convolution neural network calculation under large data environment and is suitable for parallel DCNN model training of large datasets. [ABSTRACT FROM AUTHOR]

The main intention of this paper is to develop a new intelligent framework for web page classification and re-ranking. The two main phases of the proposed model are (a) classification, and (b) re-ranking-based retrieval. In the classification phase, pre-processing is initially performed, which follows the steps like HTML (Hyper Text Markup Language) tag removal, punctuation marks removal, stop words removal, and stemming. After pre-processing, word to vector formation is done and then, feature extraction is performed by Principle Component Analysis (PCA). From this, optimal feature selection is accomplished, which is the important process for the accurate classification of web pages. Web pages contain several features, which reduces the classification accuracy. Here, the adoption of a new meta-heuristic algorithm termed Opposition based-Tunicate Swarm Algorithm (O-TSA) is employed to perform the optimal feature selection. Finally, the selected features are subjected to the Enhanced Convolutional-Recurrent Neural Network (E-CRNN) for accurate web page classification with enhancement based on O-TSA. The outcome of this phase is the categorization of different web page classes. In the second phase, the re-ranking is involved utilizing the O-TSA, which derives the objective function based on similarity function (correlation) for URL matching, which results in optimal re-ranking of web pages for retrieval. Thus, the proposed method yields better classification and re-ranking performance and reduce space requirements and search time in the web documents compared with the existing methods. [ABSTRACT FROM AUTHOR]

In order to solve the problem in which structurally incoherent low-rank non-negative matrix decomposition (SILR-NMF) algorithms only consider the non-negativity of the data and do not consider the manifold distribution of high-dimensional space data, a new structurally incoherent low rank two-dimensional local discriminant graph embedding (SILR-2DLDGE) is proposed in this paper. The algorithm consists of the following three parts. Firstly, it is vital to keep the intrinsic relationship between data points. By the token, we introduced the graph embedding (GE) framework to preserve locality information. Secondly, the algorithm alleviates the impact of noise and corruption uses the L1 norm as a constraint by low-rank learning. Finally, the algorithm improves the discriminant ability by encrypting the structurally incoherent parts of the data. In the meantime, we capture the theoretical basis of the algorithm and analyze the computational cost and convergence. The experimental results and discussions on several image databases show that the proposed algorithm is more effective than the SILR-NMF algorithm. [ABSTRACT FROM AUTHOR]

The advancement in technology is taking place with an accelerating pace across the globe. With the increasing expansion and technological advancement, a vast volume of text data are generated everyday, in the form of social media platform, websites, company data, healthcare data, and news. Indeed, it is a difficult task to extract intriguing patterns from the text data, such as opinions, summaries, and facts, having varying length. Because of the problems of the length of text data and the difficulty of feature value extraction in news, this paper proposes a news text classification method based on the combination of deep learning (DL) algorithms. In order to classify the text data, the earlier approaches use a single word vector to express text information and only the information of the relationship between words were considered, but the relationship between words and categories was ignored which indeed is an important factor for the classification of news text. This paper follows the idea of a customized algorithm which is the combination of DL algorithms such as CNN, LSTM, and MLP and proposes a customized DCLSTM-MLP model for the classification of news text data. The proposed model is expressed in parallel with word vector and word dispersion. The relationship among words is represented by the word vector as an input of the CNN module, and the relationship between words and categories is represented by a discrete vector as an input of the MLP module in order to realize comprehensive learning of spatial feature information, time-series feature information, and relationship between words and categories of news text. To check the stability and performance of the proposed method, multiple experiments were performed. The experimental results showed that the proposed method solves the problems of text length, difficulty of feature extraction in the news text, and classification of news text in an effective way and attained better accuracy, recall rate, and comprehensive value as compared to the other models. [ABSTRACT FROM AUTHOR]

Aiming at the local fault diagnosis of planetary gearbox gears, a feature extraction method based on improved dynamic time warping (IDTW) is proposed. As a calibration matching algorithm, the dynamic time warping method can detect the differences between a set of time-domain signals. This paper applies the method to fault diagnosis. The method is simpler and more intuitive than feature extraction methods in the frequency domain and the time-frequency domain, avoiding their limitations and disadvantages. Due to the shortcomings of complex calculation, singularity and poor robustness, the paper proposes an improved method. Finally, the method is verified by envelope spectral feature analysis and the local fault diagnosis of gears is realised. [ABSTRACT FROM AUTHOR]

Degradation state identification for hydraulic pumps is crucial to ensure system performance. As an important step, feature extraction has always been challenging. The non-stationary and non-Gaussian characteristics of the vibration signal are likely to weaken the performance of traditional features. In this paper, an efficient feature extraction algorithm named multi-scale ternary dynamic analysis (MTDA) is proposed. MTDA reconstructs the phase space based on the given signal and converts each embedding vector into a ternary pattern independently, which enhances its capacity of describing the details of non-stationary signals. State entropy (SE) and state transition entropy (STE) are calculated to estimate the dynamical changes and complexity of each signal sample. The excellent performance of SE and STE in detecting frequency changes, amplitude changes, and the development process of fault is verified with the use of four simulated signals. The proposed multi-scale analysis enables them to provide a more precise estimation of entropy. Furthermore, support vector machine (SVM) and nondominated sorting genetic algorithm II (NSGA-II) are introduced to conduct feature selection and state identification. NSGA-II and SVM can conduct the joint optimization of these two goals. The details of the method proposed in this paper are tested using simulated signals and experimental data, and some studies related to the fault diagnosis of rotating machinery are compared with our method. All the results show that our proposed method has better performance, which obtains higher recognition accuracy and lower feature set dimension. [ABSTRACT FROM AUTHOR]

The psychological health of a person plays an important role in their daily life activities. The paper addresses depression issues with the machine learning model using facial expressions of the patient. Some research has already been done on visual based on depression detection methods, but those are illumination variant. The paper uses feature extraction using LBP (Local Binary Pattern) descriptor, which is illumination invariant. The Viola-Jones algorithm is used for face detection and SVM (support vector machine) is considered for classification along with the LBP descriptor to make a complete model for depression level detection. The proposed method captures frontal face from the videos of subjects and their facial features are extracted from each frame. Subsequently, the facial features are analyzed to detect depression levels with the post-processing model. The performance of the proposed system is evaluated using machine learning algorithms in MATLAB. For the real-time system design, it is necessary to test it on the hardware platform. The LBP descriptor has been implemented on FPGA using Xilinx VIVADO 16.4. The results of the proposed method show satisfactory performance and accuracy for depression detection comparison with similar previous work. [ABSTRACT FROM AUTHOR]

In practical applications of the motor imagery-based brain–computer interface (BCI) system, the differences in electroencephalogram (EEG) signal manifestation and corresponding rhythm ranges in different individuals pose a significant challenge. The corresponding EEG features in different frequency bands differ; therefore, personalized screening must be conducted to obtain information that is conducive to the classification of EEG signals for different motor imageries. Also, in current BCI system, to obtain more information, multi-channel electrodes are often used to collect EEG signals, but also increasing the complexity of calculation. In this paper, a personalized feature extraction method based on filter bank and elastic net and a personalized channel selection based on Deep Belief Network to obtain a classification accuracy similar to or even higher than using all channels is proposed. Compared with the typically used feature extraction and classification algorithms, this method obtains higher calculation rates and recognition accuracy and provides a theoretical reference for the practical application of BCI systems. The shortcomings of the common spatial pattern (CSP) algorithm are addressed. The major contribution of this paper is the flexible screening of feature vectors and channels containing more classification information based on individual differences, thereby preventing the manual adjustment of specific frequency ranges in traditional CSP for performing feature extraction and avoiding inputting all channels. In the case study, the highest test accuracy reaches 86.94%. [ABSTRACT FROM AUTHOR]

Road damage detection is an important task to ensure road safety and realize the timely repair of road damage. The previous manual detection methods are low in efficiency and high in cost. To solve this problem, an improved YOLOv5 road damage detection algorithm, MN-YOLOv5, was proposed. We optimized the YOLOv5s model and chose a new backbone feature extraction network MobileNetV3 to replace the basic network of YOLOv5, which greatly reduced the number of parameters and GFLOPs of the model, and reduced the size of the model. At the same time, the coordinate attention lightweight attention module is introduced to help the network locate the target more accurately and improve the target detection accuracy. The KMeans clustering algorithm is used to filter the prior frame to make it more suitable for the dataset and to improve the detection accuracy. To improve the generalization ability of the model, a label smoothing algorithm is introduced. In addition, the structure reparameterization method is used to accelerate model reasoning. The experimental results show that the improved YOLOv5 model proposed in this paper can effectively identify pavement cracks. Compared with the original model, the mAP increased by 2.5%, the F1 score increased by 2.6%, and the model volume was smaller than that of YOLOv5. 1.62 times, the parameter was reduced by 1.66 times, and the GFLOPs were reduced by 1.69 times. This method can provide a reference for the automatic detection method of pavement cracks. [ABSTRACT FROM AUTHOR]

At present, the UAV (Unmanned Aerial Vehicle) has been widely used both in civilian and military fields. Most of the current object detection algorithms used to detect UAVs require more parameters, and it is difficult to achieve real-time performance. In order to solve this problem while ensuring a high accuracy rate, we further lighten the model and reduce the number of parameters of the model. This paper proposes an accurate and lightweight UAV detection model based on YOLOv4. To verify the effectiveness of this model, we made a UAV dataset, which contains four types of UAVs and 20,365 images. Through comparative experiments and optimization of existing deep learning and object detection algorithms, we found a lightweight model to achieve an efficient and accurate rapid detection of UAVs. First, from the comparison of the one-stage method and the two-stage method, it is concluded that the one-stage method has better real-time performance and considerable accuracy in detecting UAVs. Then, we further compared the one-stage methods. In particular, for YOLOv4, we replaced MobileNet with its backbone network, modified the feature extraction network, and replaced standard convolution with depth-wise separable convolution, which greatly reduced the parameters and realized 82 FPS and 93.52% mAP while ensuring high accuracy and taking into account the real-time performance. [ABSTRACT FROM AUTHOR]

Based on the problem of insufficient accuracy of the original tiny YOLOv3 algorithm for object detection in a lawn environment, an Optimized tiny YOLOv3 algorithm with less computation and higher accuracy is proposed. Three reasons affect the accuracy of the original tiny YOLOv3 algorithm for detecting objects in a lawn environment. First, the backbone of the original algorithm is composed of a stack of a single convolutional layer and a max-pooling layer, which results in insufficient ability to extract feature information of objects. An enhancement module is proposed to enhance the feature extraction capability of the shallow layers of the network. Second, the information of the shallow convolutional layers of the backbone is not fully used, which results in insufficient detection capability for small objects. Third, the deep part of the backbone uses a convolutional layer with an excessive number of channels, which results in a large amount of computation. A multi-resolution fusion module is proposed to enhance the information interaction capability of the deep and shallow layers of the network, and reduce the computation. To verify the accuracy of this Optimized tiny YOLOv3 algorithm, the algorithm was tested on the dataset containing trunk, spherical tree and person, and compared with the current research. The results show that the algorithm proposed in this paper improves the detection accuracy while reducing the calculation. [ABSTRACT FROM AUTHOR]

In view of the large amount of vehicle detection model parameters and missing detection of small targets and occluded targets. This paper presents a vehicle detection algorithm based on lightweight MobileVit. Firstly, in the data preprocessing stage, the method used GridMask image enhancement to improve the performance of occluded target detection; Secondly, the method used MobileVit network as the backbone feature extraction network of the model to fully extract the feature information and make the model lightweight; Finally, in the prediction layer network, the method used multiscale vehicle detection and recognition based on PANet network to improve the detection performance of the model for small targets. The experimental results show that the average detection accuracy of this algorithm is 98.24%, the detection speed is 58 ms per picture, and the model size is 136 MB, compared with the comparison algorithm, the comprehensive performance is better. [ABSTRACT FROM AUTHOR]

In the synthetic aperture radar (SAR) ship image, the target size is small and dense, the background is complex and changeable, the ship target is difficult to distinguish from the surrounding background, and there are many ship-like targets in the image. This makes it difficult for deep-learning-based target detection algorithms to obtain effective feature information, resulting in missed and false detection. The effective expression of the feature information of the target to be detected is the key to the target detection algorithm. How to improve the clear expression of image feature information in the network has always been a difficult point. Aiming at the above problems, this paper proposes a new target detection algorithm, the feature information efficient representation network (FIERNet). The algorithm can extract better feature details, enhance network feature fusion and information expression, and improve model detection capabilities. First, the convolution transformer feature extraction (CTFE) module is proposed, and a convolution transformer feature extraction network (CTFENet) is built with this module as a feature extraction block. The network enables the model to obtain more accurate and comprehensive feature information, weakens the interference of invalid information, and improves the overall performance of the network. Second, a new effective feature information fusion (EFIF) module is proposed to enhance the transfer and fusion of the main information of feature maps. Finally, a new frame-decoding formula is proposed to further improve the coincidence between the predicted frame and the target frame and obtain more accurate picture information. Experiments show that the method achieves 94.14% and 92.01% mean precision (mAP) on SSDD and SAR-ship datasets, and it works well on large-scale SAR ship images. In addition, FIERNet greatly reduces the occurrence of missed detection and false detection in SAR ship detection. Compared to other state-of-the-art object detection algorithms, FIERNet outperforms them on various performance metrics on SAR images. [ABSTRACT FROM AUTHOR]

Faces are widely used in information recognition and other fields. Due to the openness of the Internet, ensuring that face information is not stolen by criminals is a hot issue. The traditional encryption method only encrypts the whole area of the image and ignores some features of the face. This paper proposes a double-encrypted face image encryption algorithm. The contour features of the face are extracted, followed by two rounds of encryption. The first round of encryption algorithm encrypts the identified face image, and the second round of encryption algorithm encrypts the entire image. The encryption algorithm used is scrambling and diffusion at the same time, and the keystream of the cryptosystem is generated by 2D SF-SIMM. The design structure of this cryptosystem increases security, and the attacker needs to crack two rounds of the algorithm to get the original face image. [ABSTRACT FROM AUTHOR]

Motion blur can easily affect the quality of images. For example, Quick Response (QR) code is hard to be identified with severe motion blur caused by camera shaking or object moving. In this paper, a motion blur QR code identification algorithm based on feature extraction and improved adaptive thresholding is proposed. First, this work designs a feature extraction framework using a deep convolutional network for motion deblurring. The framework consists of a basic end-to-end network for feature extraction, an encoder-decoder structure for increasing training feasibility and several ResBlocks for producing large receptive fields. Then an improved adaptive thresholding method is used to avoid influence caused by uneven illumination. Finally, the proposed algorithm is compared with several recent methods on a dataset including QR code images influenced by both motion blur and uneven illumination. Experimental results demonstrate that the processing time and identification accuracy of the proposed algorithm are improved in executing motion blur QR code identification missions compared with other competing methods. [ABSTRACT FROM AUTHOR]

The purpose of aspect-level sentiment analysis is to determine the sentiment of specific aspect words in a sentence . In recent years, many methods have adopted syntactic dependency tree combined with graph convolutional network modeling. But the use of syntactic dependency structures is too direct and ignores the noise effect that accompanies the spanning tree, which limits the use of syntactic relations. This paper proposed an emotional classification model ( PCB-GCN) with progressive enhancement combined with a bidirectional graph convolution module. Firstly, it designed a progressive enhancement algorithm to obtain richer syntactic relations, used Bi-LSTM to extract semantics, and used bidirectional graph convolution module for feature extraction for syntactic graph structures in different directions. Finally, it combined the syntactic features and context semantics through a collaborative network, combined them for the final classification. The model has been tested on multiple public data sets, and all have achieved better results than the current baseline model. [ABSTRACT FROM AUTHOR]

A binocular camera composed of colour and depth cameras is an accurate and inexpensive tool for recognising fruit trees to plan spraying paths. For this purpose, however, the accurate visual registration of the depth and colour cameras is a problem that must be solved. This paper proposes a local feature point extraction (LFPE) algorithm for depth-colour image registration, which automatically extracts the feature points of local regions in the colour and depth images for registration. First, the binarised colour and depth images are divided into local regions after edge extraction, and the regions in which the edge features match at several pixels between images are selected. Then, these regions are again divided into smaller regions to detect local extrema of the pixels as feature points. Finally, the matching feature points are calculated based on the Euclidean distance and are used to optimise the affine transformation matrix. To verify the accuracy and effectiveness of the algorithm, it is compared with the FAST, SURF and BRISK algorithms. The experimental results show that the accuracy of the proposed LFPE algorithm is 1.6 times that of BRISK, 3.5 times that of FAST and 40.1 times that of SURF. Therefore, it is more suitable for registration between depth and colour images. • Proposed a depth-colour image registration method for orchard precision spraying. • A local feature point extraction (LFPE) algorithm is proposed to match images. • The registration accuracy of LFPE is much better than other similar algorithms. [ABSTRACT FROM AUTHOR]