Search

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

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]

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]

The performance of object detection networks is often limited by the depth of the feature extraction network. Increasing network parameters may yield limited improvements in the detection system's performance. Additional careful designs of network details are necessary, but they can significantly increase training difficulty. This paper introduces a novel object detection method that utilizes generative adversarial training. Our approach focuses on minimizing the EM distance (Wasserstein distance) of the feature distribution as the primary training objective. We enhance the image features so that training of GAN (Generative Adversarial Networks) yields a feature distribution that exceeds that of the original dataset, obtaining a better feature extraction network. A new loss function is also added to the adversarial training process to ensure stable improvement of the detector. A comparative experiment conducted with the original CenterNet network on MS COCO (Microsoft Common Objects in COntext) 2017 reveals that the generative adversarial training method significantly improves the average precision for most of the examined backbone networks. Among the four backbone networks employed in the experiments, the mean improvement in network AP (Average Precision) values ranged from 0.3 to 0.9, demonstrating their success with minimal training efforts. Moreover, none of the four backbone networks experienced an increase in network parameters during inference. Experimental results indicate that the proposed architecture effectively enhances the network's feature extraction capability without compromising speed during inference. [ABSTRACT FROM AUTHOR]

Feature extraction is one of the fundamental problems in pattern recognition research. For image recognition, extracting effective image features is the key to accomplish the recognition task. In this paper, a partial differential equations-based multi-rank two-dimensional canonical correlation analysis (PDEs-MR2DC2A) is proposed for multi-view feature extraction and pattern classification. Unlike most of the previous researches on multi-view algorithms that work directly on the original 2D representation, in our approach, we first utilize the evolution process of PDEs to extract the feature matrix of per-view. In addition, we employ multi-rank left and right projecting matrices to maximize the correlation. The computational complexity of PDEs-MR2DC2A is also analyzed. To evaluate the effectiveness of the proposed algorithm, we conducted a series of performance comparisons with some existing methods on several popular datasets. The experimental results showed that our proposed algorithm performed very well on these datasets and outperformed the existing related methods on some metrics. • A novel multi-rank multi-view algorithm based on PDEs is proposed. • This approach can extract rotation and translation invariant features. • Numerous experimental results demonstrate the effectiveness of our proposed method. [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]

With the increasing maturity of convolution neural network (CNN) technology, the image super-resolution reconstruction (SR) method based on CNN is booming and has achieved many remarkable results. Undoubtedly, SR has become the mainstream direction of image reconstruction technology. However, most of the existing SR methods improve the reconstruction performance by increasing the depth of networks, which also increases the number of parameters, number of network computations, and difficulty of training network. To solve the performance complexity dilemma in SR, this paper proposes a network called a multi-scale dense recursive fusion network (MSDRFN). The network is composed of three parts: initial feature extraction module, multi-scale dense fusion group module and recursive reconstruction module. In detail, rough features are first extracted through a shallow feature extraction module, and then are inputted into multi-scale dense fusion blocks (MSDFBs) group. Each MSDFB makes full use of image features in convolution kernels of different sizes to obtain different hierarchical features, and further these output features are inputted into the channel attention mechanism to learn their corresponding weights. All MSDFBs outputs will be restored to high resolution images via the recursive reconstruction module. In addition, the network supplements the information loss with residual learning, which is embodied in one long-jump connection and several short-jump connections. The proposed network is mainly trained in the Pytorch deep learning framework. In comparison experiments on benchmark datasets, the proposed method outperformed the most advanced convolutional methods. [ABSTRACT FROM AUTHOR]

• We focused on deep learning (DL), PAD and multimodal finger vein recognition. • DL, PAD and multimodal approaches are comprehensively studied. • A comparative study is presented for reviewed paper based on performance. • Existing challenges, problems in DL, PAD and multimodal approaches are discussed. • Prospect for future work in this area for stable finger vein recognition system. Finger vein recognition biometric trait is a significant biometric modality that is considered more secure, reliable, and emerging. This article presents a review to focus on the recent research landscape in biometric finger vein recognition systems. This article focuses on manuscripts related to keywords 'Finger Vein Authentication System', 'Anti-spoofing or Presentation Attack Detection', 'Multimodal Biometric Finger Vein Authentication' and their variations in four main digital research libraries such as IEEE Xplore, Springer, ACM, and Science Direct. The final set of articles is divided into three main categories: Deep Learning (DL) based finger vein recognition, Presentation Attack Detection (PAD), and Multimodal-based finger vein authentication system. Deep learning-based finger vein recognition techniques are further sub-divided into pre-processing (Quality assessment and enhancement) based, feature extraction based, and feature extraction and recognition based schemes. Presentation attack detection methods are sub-divided into software-based and hardware-based approaches. Multimodal-based finger vein biometric system is sub-categorized into feature level fusion, matching level fusion, and hybrid fusion methods. The authors have studied the problem of the recent algorithm and their solution related to finger vein biometric system from the recent literature. Performance analysis and selected the best promising research work from the mentioned studies are also presented. Finally, open challenges, opportunities, and suggested solutions related to deep learning, PAD, and Multimodal based finger vein recognition systems have been discussed in the discussion section. This work would be helpful to the developers, company users, researchers, and readers to get insight into the importance of such technology and the recent problem faced by finger vein authentication technology with respect to deep learning and multimodal systems. [ABSTRACT FROM AUTHOR]

The mortality rate due to cardiac abnormalities is enormous, making the development of wearables to monitor functioning of the heart of paramount importance. In this paper, wepresent a resource efficient and low power architecture using Integer Haar Wavelet Transform for the complete delineation of ECG signal. The novelty of the algorithm lies in the use of single scale wavelet coefficients to delineate P-QRS-T features making it computationally simple. The proposed architecture is implemented using Xilinx FPGA ZedBoard Zynq™ − 7000 platform, and utilises only 4.38% of the available resources. It is synthesised using 180 nm CMOS technology consuming 0.88 μ W power, making it area as well as power-efficient for the wearable IoT healthcare devices. • Extracting features of ECG (P-QRS-T) using single scale wavelet coefficients. • Integer Haar wavelet is utilised to avoid floating point arithmetic reducing computational complexity. • Architecture developed operates in low power and utilise minimum hardware resources. • Architecture can be used in low power wearable IoT healthcare applications. [ABSTRACT FROM AUTHOR]

• A novel and improved deep residual network method is proposed for hyperspectral image fusion. Four modules including multi-scale input, improved residual, downsampling and double-channel pooling are designed to improve the model's ability to extract discriminating features. • A widened and deepened residual block is proposed in this paper, which effectively improves the classification accuracy of the mold. Compared with the basic residual block, this paper adds a 1×1 convolution after 3×3 convolution to increase the depth of the network. • Extensive experiments on multiple reference data sets show that the proposed algorithm achieves competitive performance and can effectively carry out hyperspectral image fusion. High-resolution hyperspectral images are rich in both spatial and spectral information and have numerous applications for target detection, recognition, and tracking. The method proposed in this paper consists of three specific modules: multi-scale input, improved residuals, down-sampling, and two-channel pooling. By using wider and deeper blocks of residuals, the classification accuracy of the model is significantly improved. To increase the depth of the network, 1×1 convolutions were added to the 3×3 convolutions compared to the basic residual block. This makes it easier to control the number of channels so that the information sensed and the features extracted are different during each convolution. In addition to the Elu activation function, the Dropout layer and the batch normalization layer for every 3×3 convolutions in the network, the residual network is enhanced by using two stacked residual blocks after the two-channel pooling layer. Extensive experiments on many well-known benchmark datasets have shown that the proposed method achieves competitive performance. [ABSTRACT FROM AUTHOR]

Feature extraction networks play a crucial role in classification algorithms. However, most convolutional neural networks use the form of residual block stacking to extract downstream features of images, and this simple form is not sufficient to obtain better classification performance. Therefore, this paper proposes a YOLOX detection framework based on an improved ConvNeXt which incorporates many advantages of Swin-Transformer with efficient classification performance. To address the problems of unstable IOU convergence and inaccurate regression coordinates of the algorithm, this paper adopts Manhattan distance as the new penalty term, and the new loss function combines the advantages of Euclidean distance and Manhattan distance, which has no gradient explosion in the early training period and can drop smoothly to a stable point in the late training period. The proposed algorithm is robust to negative effects such as dust, light, shadows, and occlusions, and is well-suited for masked-face detection in industrial and public scenarios. The proposed model is tested on the VOC dataset and the AIZOO open-source masked-face dataset, obtaining 5.58% AP improvement on the VOC dataset and reaching 96.665% AP on the masked-face dataset, which is better than other algorithms. • Designing a deep neural network to use for masked-face detection. • Anchor-free model is used to avoid time-consuming post-processing. • The improved ConvNeXt network improves classification performance. • Adopting Manhattan distance-based localization loss makes training stable. • The Mosaic data augmentation strategy alleviates the overfitting problem. [ABSTRACT FROM AUTHOR]

Lossy image compression is likely to produce blurred images which leads to erroneous image-level understanding. The human visual system (HVS) is focused on the area of interest present in the image. Motivated by this fact, we propose a compression-decompression algorithm focusing on the important content present in different parts of the image. Using the concept of the Guided Grad-CAM (Gradient-weighted Class Activation Mapping) technique to produce heat maps with the help of a heat map generator trained on ResNet-50, a saliency-guided encoding–decoding algorithm is developed. A wider multi-scale saliency guided convolutional neural network (MsSG-CNN) is designed, in which the notion of convolution with different size filters helps to obtain unique but different features. The feature extraction followed by multilevel fusion of features helps deep neural network (DNN) to capture contextual information and obtain high quality, good resolution, visually pleasing images with fine details. The proposed algorithm is tested on the Kodak benchmark dataset, CLIC 2019 challenging dataset, and FDDB facial images dataset. At low bit rates, the MS-SSIM of the proposed algorithm is found to be superior to JPEG, JPEG2000, BPG, WebP, and Minnen's approaches with approximately up to 60%, 24.80%, 11.43%, 23.08% & 75% gains respectively, which is quite a significant improvement, when tested on the Kodak dataset. Similarly, at high bit rates, the improvement in MS-SSIM is approximately up to 41.67%, 37.30%, 23.90% 34.21% & 13.33% when compared with JPEG, JPEG2000, BPG, WebP, and Minnen's approaches respectively. The improvement in PSNR at low and high bit rates is approximately up to 11.32%, 5%, 5.26% and 5.6%, 10.29%, 8.7% as compared to JPEG, Balle's, and Lee's algorithms respectively. The PSNR-HVS has been improved by approximately up to 27.27%, 19.15%, and 28.33%, 28% as compared to JPEG and Toderici's algorithms respectively at low and high bit-rates. A similar type of improvement is obtained with FDDB and CLIC 2019 datasets also, which is discussed in the paper. [ABSTRACT FROM AUTHOR]

Motivated by mixture of probabilistic principal component analysis (PCA), which is time-consuming due to expectation maximization, this paper investigates a novel mixture of probabilistic PCA with clusterings for process monitoring. The significant features are extracted by singular vector decomposition (SVD) or kernel PCA, and k -means is subsequently utilized as a clustering algorithm. Then, parameters of local PCA models are determined under each clustering model. Compared with PCA clustering, SVD based clustering only utilizes the nature basis for the components of the data instead of principal components of the data. Three clustering approaches are adopted and the effectiveness of the proposed approach is demonstrated by a practical coal pulverizing system. [ABSTRACT FROM AUTHOR]

Lossy image compression is likely to produce blurred images which leads to erroneous image-level understanding. The human visual system (HVS) is focused on the area of interest present in the image. Motivated by this fact, we propose a compression-decompression algorithm focusing on the important content present in different parts of the image. Using the concept of the Guided Grad-CAM (Gradient-weighted Class Activation Mapping) technique to produce heat maps with the help of a heat map generator trained on ResNet-50, a saliency-guided encoding–decoding algorithm is developed. A wider multi-scale saliency guided convolutional neural network (MsSG-CNN) is designed, in which the notion of convolution with different size filters helps to obtain unique but different features. The feature extraction followed by multilevel fusion of features helps deep neural network (DNN) to capture contextual information and obtain high quality, good resolution, visually pleasing images with fine details. The proposed algorithm is tested on the Kodak benchmark dataset, CLIC 2019 challenging dataset, and FDDB facial images dataset. At low bit rates, the MS-SSIM of the proposed algorithm is found to be superior to JPEG, JPEG2000, BPG, WebP, and Minnen's approaches with approximately up to 60%, 24.80%, 11.43%, 23.08% & 75% gains respectively, which is quite a significant improvement, when tested on the Kodak dataset. Similarly, at high bit rates, the improvement in MS-SSIM is approximately up to 41.67%, 37.30%, 23.90% 34.21% & 13.33% when compared with JPEG, JPEG2000, BPG, WebP, and Minnen's approaches respectively. The improvement in PSNR at low and high bit rates is approximately up to 11.32%, 5%, 5.26% and 5.6%, 10.29%, 8.7% as compared to JPEG, Balle's, and Lee's algorithms respectively. The PSNR-HVS has been improved by approximately up to 27.27%, 19.15%, and 28.33%, 28% as compared to JPEG and Toderici's algorithms respectively at low and high bit-rates. A similar type of improvement is obtained with FDDB and CLIC 2019 datasets also, which is discussed in the paper. [ABSTRACT FROM AUTHOR]

Segmentation of bowel sounds (BS) events is a significant task of automatic BS monitoring. Recently, deep learning (DL) has been utilized to realize the segmentation of BS events. However, most researchers treat BS segmentation as a traditional classification problem, which causes that more precise locations for the occurrence of BS events are unable to obtained. Besides, the performance of segmentation of BS events is easily affected by thresholds of model output in practical applications. To tackle these issues, in this paper, a lightweight DL-based BS segmentation algorithm is proposed. The one-dimensional convolution layers and bidirectional gate recurrent unit (GRU) layers are adopted to enhance the ability of feature extraction. A loss function named shape loss is proposed to reduce the sensitivity of model to thresholds. Moreover, a portable BS monitoring device is developed to realize data acquisition, display and algorithm deployment. Based on this device, experiments on human and rats are conducted to verify the effectiveness of our proposed approach. Experimental results shows that the proposed method outperforms other comparison methods with the higher f1-scores and lower sensitivity to thresholds. [ABSTRACT FROM AUTHOR]

The continuous malicious software (malware) attacks on smartphones pose a serious threat to the security of users, especially the dominant platform Android. Data-driven methods based on machine learning algorithms are a promising way to defend against that. In this paper, we explore the limitations of this kind of methods in improving the performance of malware detection, e.g., considering each feature in isolation and relying on balanced class data, and propose a multi-model ensemble framework MEFDroid by combining individual predictors, where hybrid deep learning based feature extraction methods are adopted to learn meaningful features from raw data. Besides, a novel fusion scheme is exploited to fuse multi-level representations and mine their correlations to maximize the utilization of original information. To evaluate the effectiveness of the MEFDroid framework, we conduct a step-by-step model justification experiment to investigate how the proposed algorithms (i.e., ESAES, EDAES and EDAFS) enhance the malware detection performance gradually. We also compare the proposed algorithms with classical machine learning methods, conventional sampling solutions for the imbalance problem. Besides, we investigate the reliability of our proposed methods using another public dataset. Our extensive experimental results demonstrate that the target model EDAFS in MEFDroid outperforms others in terms of most metrics, which means that it is an effective alternative solution to detect Android malware. [ABSTRACT FROM AUTHOR]

• Proposes an end-to-end network for biphasic image change detection. • Can better solve the problem of detection errors. • High degree of automation in the calculation process. • Enhanced feature extraction module was inroduced. Change detection is an effective means of monitoring surface changes. In order to solve the problem of reducing detection accuracy in remote sensing image change detection methods that only focus on extracting deep semantic information while ignoring high-resolution shallow information, this paper proposes an end-to-end multi-side output fusion deep supervised network for high-resolution biphasic remote sensing image change detection. The enhanced feature extraction module is used to increase the Receptive field and capture multi-scale features. The dense skip connection module utilizes skip connections to fuse shallow position information and deep semantic information, alleviating the problem of feature information loss. The deep supervision module with multiple side-outputs fusion utilizes the information complementarity between different scale feature maps, combined with multi-scale prediction maps, to improve the robustness of target scale changes. The combined Loss function is used to alleviate the problem of imbalance between positive and negative samples, so that more attention is paid to the learning of changing characteristics in the process of training the network. The proposed method was validated on CDD dataset and DSIFN dataset, with F1 scores of 91.58% and 86.69%, respectively, which were improved by 1.00% and 5.53% compared to the suboptimal network. [ABSTRACT FROM AUTHOR]

To segment railway track regions in real-time for intrusion detection and improving security, this paper proposes an efficient railway track region segmentation network (ERTNet) based on the encoder–decoder architecture. Firstly, to ensure the lightweight of the encoder, depthwise convolution and the channel shuffle are utilized to construct sandglass-type feature extraction unit. Secondly, a feature-matching-based cross-fusion decoder is utilized to fuse deep and shallow feature maps. Thirdly, the knowledge distillation is employed with large-scale Deeplab v3+ as the teacher model to improve performance. Additionally, a loss function is proposed to penalize pixel points with large offsets. Finally, the ERTNet is validated on the self-built dataset, achieving an MIoU (Mean Intersection over Union) of 92.4% , which is 5.22% improvement over the benchmark model. ERTNet achieves a balance between segmentation accuracy and computational efficiency, requiring only 0.5 M parameters and 0.92 G FLOPs (Floating Point Operations). [Display omitted] • Visual perception is utilized to identify foreign object intrusion into railroad. • Deep learning based ERTNet model is proposed for track region pixel extraction. • ERTNet is built with lightweight neural network and cross-fusion decoder. • Optimizing training modes with knowledge distillation and new loss function. • ERTNet fits real-time needs and helps to improve the safety of rail construction. [ABSTRACT FROM AUTHOR]

The occurrence of production accidents can be effectively reduced by monitoring workers' operating behaviors in real time. However, most of the monitoring tasks are currently performed by the monitoring personnel, which takes up a lot of manpower and material resources. To solve this problem, a YOLOv5-SFE algorithm is proposed in this paper for real-time detection and recognition of workers' operating behaviors. The YOLOv5-SFE algorithm makes the following contributions: (1) During data preprocessing, a hash sampling algorithm is used to extract frames with low similarity. (2) A feature enhancement module is designed and integrated into YOLOv5 to distinguish between valid and invalid information. (3) A convolution-based spatio-temporal feature fusion module is designed and is inserted after the extraction of spatial features to extract the temporal features between multiple frames. The videos of workers' operating behaviors are from factories' industrial scene. The improved algorithm in this paper was trained and tested on the dataset. Compared with the original algorithm, the accuracy of the algorithm improves from 89.3% to 94.7%, the recall improves from 81.5% to 90.8%, and the mean average precision(mAP) improves from 88.2% to 92%. The results show that the improved algorithm is able to accurately detect and recognize workers' operating behaviors in real time, thereby improving the safety of the production process. [ABSTRACT FROM AUTHOR]

Non-contact identification of cattle is the basis for cattle management, insurance claims, and traceability of milk sources and meat products. In order to lower the threshold of deep learning technology in practical application and improve the recognition accuracy, this paper uses the localization and classification paradigm, fills the image and proposes the LKA (Locate Key Area) module, which further improves the identification accuracy of cattle without using any labeling information. To avoid the impact of different collection devices, we use three brands of mobile phones and two cameras to collect data. Due to the fact that CNN features do not have scale invariance, the image is filled as a square, and the filling value is discussed. Finally, (0,0,0) is selected for filling. In order to reduce the labeling of new data, the face, torso, and body of the cattle are first detected, and then automatically trimmed to build a classification dataset. In order to further improve the accuracy of classification, LKA module is proposed. This module locates key areas based on the results of class activation map and uses shallow features for monitoring. Thereby completing fine-grained feature extraction without supervision information. Finally, the features of different parts are adjusted for fusion recognition. Experiments were conducted on the head, torso, and whole of cattle. Based on the ResNet50 network architecture, after filling the image into a square, the recognition accuracy has been improved by 0.30%, 0.21%, and 0.43%, respectively. After further adding LKA modules, the accuracy rates were improved by 0.59%, 0.59%, and 0.45%, respectively. In the fusion experiment, ResNet50_LKA and MobileNetV3_LKA achieves 100% accuracy. Experiments have realized dataset construction and fine-grained feature extraction without labeled information, and achieved high recognition accuracy, proving the effectiveness of our method. [ABSTRACT FROM AUTHOR]

This paper investigated a multi-variable power quality disturbance identification algorithm (MPQDIA) applying the Stockwell transform (ST), Hilbert transform (HT) and rule based decision tree (RBDT). Voltage waveform with associated power quality disturbances (PQDs) are realized by the mathematical formulation in compliance with standard IEEE-1159. These voltage signals with PQDs are processed applying the ST and HT for computing the index for power quality identification (IPI) and index for power quality location (IPL). IPI and IPL plots effectively identify and locate the PQDs of simple nature and multiple nature. Four features are extracted from data sets of IPI and IPL. These features are considered as input for the RBDT to classify the PQDs. MPQDIA is effectively tested for identification, to locate and to classify the total 21 PQDs of simple as well as multiple natures. Performance of MPQDIA is analysed in terms of rightly and wrongly categorized PQDs in noise free environment and considering noise of 20 dB SNR (signal to noise ratio) level. Efficiency of MPQDIA is compared with the ST and RBDT based algorithm, WT based fast Kurtogram and decision tree powered algorithm, and ST and RBDT powered method in terms of classification accuracy, noise level for which performance is not affected, effectiveness to detect the simple nature and multiple nature PQDs. It is established that MPQDIA effectively recognizes the PQDs on a real time power system network. Study is performed with the help of MATLAB software. • Multivariable PQ identification algorithm (MPQDIA) using ST, HT and RBDT designed. • Index for PQ identification (IPI) and location (IPL) are designed. • Features computed from IPI and IPL are used by RBDT to classify PQDs. • MPQDIA effectively identify, locate and classify PQDs of simple and complex nature. • MPQDIA has better performance with existing methods and recognizes PQD in real time. [ABSTRACT FROM AUTHOR]

Robot object detection is important for the realisation of robot intelligence. Currently, deep learning-based object detection algorithms are used for robotic object detection. However, it faces some challenges in practical applications, such as the fact that robots frequently use resource-constrained devices, resulting in detection algorithms with long computation times and undesired detection rates. In order to address these concerns, this paper proposes a lightweight object detection algorithm for robots with an improved YOLOv5. To reduce the amount of processing required for feature extraction and increase the speed of detection, the C3Ghost and GhostConv modules have been introduced into the YOLOv5 backbone. The DWConv module was used in conjunction with the C3Ghost module in the YOLOv5 neck network to further reduce the number of model parameters and maintain accuracy. The CA (Coordinated Attention) module is also introduced to improve the extraction of features from detected objects and suppress irrelevant features, thus improving the algorithm's detection accuracy. To verify the performance of the method, we tested it with a self-built dataset (4561 robot images in total) and the PascalVOC dataset respectively. The results show that compared with the YOLOv5s on the self-built dataset, the algorithm has a 54% decrease in FLOPs and a 52.53% decrease in the number of model parameters without a decrease in mAP (0.5). The effectiveness and superiority of the algorithm is demonstrated through case studies and comparisons. • Lightweight C3Ghost and GhostConv modules are introduced in the YOLOv5 backbone network to achieve model compression and maintain detection accuracy and speed. • C3Ghost and DWConv modules are introduced in YOLOv5 neck network to further reduce model parameters and improve the speed of feature fusion. • CA (Coordinated attention) module is also introduced to enhance the extraction of relevant features and suppress irrelevant features to improve the detection accuracy of the algorithm. • To demonstrate the algorithm's ability to solve real-world problems, we produced a dataset for the object detection task in the RoboMasterAI challenge hosted by DJI and experimentally verified that our proposed object detection algorithm is effective. [ABSTRACT FROM AUTHOR]

• A novel deep evolutionary clustering (ADSMTDE) to overcome clustering drawbacks. • Improving the auto-encoder by applying sparsity constraint and manifold learning. • To enhance clustering, evolutionary algorithm is adopted to optimize solutions. • Employing an incremental clustering technique to perform clustering dynamically. • ADSMTDE is competitive and superior to over the latest deep clustering methods. Most deep clustering methods despite utilizing complex networks to learn better from data, use a shallow clustering method. These methods have difficulty in finding good clusters due to the lack of ability to handle between local search and global search to prevent premature convergence. In other words, they do not consider different aspects of the search and it causes them to get stuck in the local optimum. In addition, the majority of existing deep clustering approaches perform clustering with the knowledge of the number of clusters, which is not practical in most real scenarios where such information is not available. To address these problems, this paper presents a novel automatic deep sparse clustering approach based on an evolutionary algorithm called Multi-Trial Vector-based Differential Evolution (MTDE). Sparse auto-encoder is first applied to extract embedded features. Manifold learning is then adopted to obtain representation and extract the spatial structure of features. Afterward, MTDE clustering is performed without prior information on the number of clusters to find the optimal clustering solution. The proposed approach was evaluated on various datasets, including images and time-series. The results demonstrate that the proposed method improved MTDE by 18.94% on average and compared to the most recent deep clustering algorithms, is consistently among the top three in the majority of datasets. [ABSTRACT FROM AUTHOR]

Conditional Nonlinear Optimal Perturbation (CNOP) method is an effective way to study the predictability of oceanic and climatic events. A framework combining the Feature Extraction method and Intelligent Algorithm (FEIA) is frequently used to solve CNOP because it is gradient-free and scalable at high-dimensional scales. However, the fixed latent subspace of FEIA framework makes it challenging to achieve both the quality of solutions and the solving efficiency. To overcome this bottleneck, this paper proposes Dimension Shifting based Intelligent Algorithm (DSIA) framework to solve CNOP in the large-scale model. DSIA framework adopts the dimension shifting strategy, which dynamically shifts search particles in different low-dimensional spaces. To verify the feasibility of DISA framework, we take a Regional Ocean Modeling System (ROMS) model of double-gyre variation as an experimental case. In experiments, we figure out that the selection of feature extraction method and the shifting dimension set are two influential factors for the performance of DSIA framework. Besides, in comparative experiments, DSIA framework yields better objective function values and more valid CNOP than FEIA framework. Moreover, convergence experiments demonstrate DSIA framework can solve CNOP with an appropriate number of function evaluations and has better convergence performance. In conclusion, experimental results prove that DSIA improves both quality of CNOP and solving efficiency. • We design Dimension Shifting based Intelligent Algorithm framework to solve Conditional Nonlinear Optimal Perturbation (CNOP). • Dimension shifting strategy can balance the quality of solutions with the solving efficiency. • The framework is applied to a Regional Ocean Modeling System model of double-gyre variation. • Settings affecting the framework's performance are analyzed. • The framework shows higher quality of CNOP and better solving efficiency than FEIA framework. [ABSTRACT FROM AUTHOR]

• The proposed method adopts K-means, FFT, and coefficient of kurtosis to improve the signal preprocessing ability of SGMD, which makes different types of disturbance features easy to be extracted. • It adopts an optimization algorithm to optimize the feature extraction of multiple methods and the disturbance identification of ELM, which improves the accuracy of feature extraction and disturbance identification. • It adopts tent chaotic mapping and adaptive parameters to further improve the optimization performance of MPA. Power quality is the quality of electrical energy in the power system. And the power quality disturbances (PQDs) in the power system lead to severe consequences for the equipment's life and the operator's safety. The accurate disturbance identification is a crucial prerequisite to managing power quality. Currently, the identification accuracy of PQDs needs to be improved, especially in high-intensity noise environments. In this paper, a novel power quality identification method based on adaptive symplectic geometric mode decomposition (ASGMD) and tent chaotic map and adaptive parameter method improved marine predators algorithm (IMPA) optimization is proposed. Firstly, the PQDs are pre-processed by adaptive symplectic geometric mode decomposition with K-means, fast Fourier transform, coefficient of kurtosis, and wavelet thresholding to reduce the noise component. Secondly, twenty-three PQDs features of the wavelet transform, fast Fourier transform, and mathematical statistics are optimally selected by IMPA to improve the identification accuracy and efficiency. Finally, the PQDs with selected features are recognized by the extreme learning machine with optimized weights and biases. IMPA improves the uniformity of the initial population distribution and the optimization process of three iterative phases, thus promoting the search accuracy of the optimal features, input weights, and biases. The proposed method has more accurate identification accuracy and fast identification speed by simulating different noise intensity environments than other methods. Remarkably, the identification accuracy reaches 91% in high-intensity noise environments of 10dB This method has practical significance for PQDs identification of large areas, long periods, and high noise-resistant. [ABSTRACT FROM AUTHOR]

The bearing fault impact impulses induced by the contact between components with drawback, is difficult to be detected at sprouting stage due to the interference of background noise, harmonics, random shocks, etc. In this paper, an impulse feature enhanced weighted sparse representation (IFEWSR) algorithm is proposed to accurately detect the weak bearing fault impact feature from incipient stage condition monitoring (CM) signal. Firstly, a modified fault period estimation method is presented to improve the robustness and reduce the computational complexity of recently proposed algorithms. Secondly, a novel weighting strategy on wavelet coefficients, indicated by the period-assisted corelated kurtosis of envelope spectrum (CKSES), is presented to denote the contribution of subband signals for sparse representation calculation framework. In addition, the mean normalized energy-weight deviation (MNEWD) rule is proposed to evaluate the performance of the weighting algorithm on subband signals which is blank at present. Thirdly, a novel fault feature enhancement technique is developed to better capture the bearing fault feature information. The effectiveness and superiority of the proposed method are proved by simulation and experiments. Results show that the proposed IFEWSR method provides higher accuracy for incipient fault feature extraction and outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

• To accommodate high-bit-width infrared images, we propose the pre-processing and augmentation algorithm without data compression. • A multi-scale feature extraction network based on ConvNext was built to adapt the infrared images of low-resolution. • The coordinate attention module is introduced in the ConvNeXt block to focus on targets and suppress the background, and a split attention module is introduced in the neck to enhance feature fusion ability. • The algorithm offers significant performance improvements over prevalent object detection algorithms, comparative experiment on the FLIR dataset shows that the algorithm outperforms the YOLOv5 by 3% and Faster R-CNN by 5.6% in map50 and has significant advantages in parameters and FLOPs. Transfer learning is widely used in infrared object detection algorithms, but these algorithms developed from visible usually ignored the characteristic of infrared images. In this paper, we propose a new object detection algorithm YOLO-CIR based on YOLO and ConvNext for infrared (IR) images. Specifically, to accommodate high-bit-width infrared images, we propose the augmentation algorithm for infrared images and improve the pre-processing algorithm without bit-width compression. In addition, a multi-scale feature extraction network based on ConvNext was built to adapt the infrared images of low-resolution. Moreover, the coordinate attention module is introduced in the ConvNeXt block to focus on targets and suppress the background, and a split attention module is introduced in the neck to enhance feature fusion ability. The algorithm offers significant performance improvements over prevalent object detection algorithms, comparative experiment on the FLIR dataset shows that the algorithm outperforms the YOLOv5 by 3% and Faster R-CNN by 5.6% in map50 and has significant advantages in parameters and FLOPs. [ABSTRACT FROM AUTHOR]

Accurately detect vehicles or pedestrians from 3D point clouds (3D object detection) is a fast developing research topic in autonomous driving and other domains. The fundamental component for feature extraction in 3D object detection is Set Abstraction (SA), which can downsample points while aggregating points to extract features. However, the current SA ignores the geometric and semantic properties of point clouds and may miss to detect remote small objects. In this paper, FocusSA is proposed, which consists two modules for enhancing useful feature extraction in the SA layer to improve 3D object detection accuracy. At first, Focused FPS (FocFPS) is proposed to evaluate the foreground and boundary scores of the points and reweighs the Furthest Point Sampling (FPS) using the evaluated scores to retain more contextual points in downsampling. Then a Geometry-aware Feature Extraction (GeoFE) module is proposed to add geometric information to enrich the awareness of geometric structure in feature aggregation. To evaluate the performances of the proposed methods, we conduct extensive experiments on three difficulty levels of Car class in KITTI dataset. The experimental results show that on "moderate" instances, our results outperform the state-of-the-art method by 1.08%. Moreover, FocusSA is easy to be plugged in popular architectures. [ABSTRACT FROM AUTHOR]

This aims to propose a collaborative filtering algorithm based on embedding representation and word embedding techniques, namely UI2vec. According to the joint feature extraction network designed in this paper, UI2vec embeds users and items on the potential space at the same time, and uses the item similarity between them to predict the user's content of interest. Then a generative model VUI2vec with more stable performance is proposed based on UI2vec, which maps users and items as independent Gaussian distributions and obtains the approximate posterior distribution of both by variational inference. The recommendation performance of UI2vec and VUI2vec is evaluated on TaFeng, Movielens, and Netflix datasets. The impact of important superparameters within the model on performance is investigated. The experimental results show that compared with the baseline model, the proposed methods performs consistently well. • UI2vec and VUI2vec as collaborative filtering-based recommendation systems. • It is based on embedding representation of users or items. • Performance is competitive with the state of the art on real-world datasets. • Results encourage integrating collaborative filtering with deep learning. [ABSTRACT FROM AUTHOR]

• Microalgae identification to solve the issues of harmful algae blooms. • The classification of potential algae strains for valuable bioactive compounds. • Machine learning and deep learning techniques for smart algae identification. • Image acquisition with consideration of robust dataset to enhance accuracy. • Incorporate various image pre-processing module to improve classification results. The identification of microalgae species is an important tool in scientific research and commercial application to prevent harmful algae blooms (HABs) and recognizing potential microalgae strains for the bioaccumulation of valuable bioactive ingredients. The aim of this study is to incorporate rapid, high-accuracy, reliable, low-cost, simple, and state-of-the-art identification methods. Thus, increasing the possibility for the development of potential recognition applications, that could identify toxic-producing and valuable microalgae strains. Recently, deep learning (DL) has brought the study of microalgae species identification to a much higher depth of efficiency and accuracy. In doing so, this review paper emphasizes the significance of microalgae identification, and various forms of machine learning algorithms for image classification, followed by image pre-processing techniques, feature extraction, and selection for further classification accuracy. Future prospects over the challenges and improvements of potential DL classification model development, application in microalgae recognition, and image capturing technologies are discussed accordingly. [ABSTRACT FROM AUTHOR]

The Open Circuit (OC) faults occurring in switches of Multilevel Converters (MLC) may lead to undesirable operation of the converter. Therefore, fault detection and its localization in minimum time are necessary. This paper focuses on the fast fault detection algorithm based on the two samples technique and the fault localization algorithm using the Entropy of Wavelet Packets (EWP) as a feature. The EWP feature is used to classify and localize the OC faults in Insulated Gate Bipolar Transistors (IGBTs) of three-phase, three-level inverter using Support Vector Machine (SVM) based fault classification algorithm. The proposed technique can detect the fault in single IGBT and multiple IGBTs in a lesser time range of microseconds to 0.33 ms. It gives better performance and accuracy (99.70%) than previously proposed SVM algorithms, as the EWP-based feature extraction process used in this paper is simple and accurate with a less computational burden. [Display omitted] • An observer-based algorithm is proposed using two samples-based technique. • The Entropy of Wavelet Packets (EWP-SVM) technique is used for fault diagnosis. • The proposed algorithm can detect the faults in a single IGBT and multiple IGBTs. • The technique is faster and accurate than techniques available in the literature. • The comparison of detection time of different techniques is also discussed. [ABSTRACT FROM AUTHOR]

Detection transformer (DETR) combines convolutional neural network (CNN) with transformer, providing a more advanced idea. In this paper, an object detection model based on DETR is proposed for fire and smoke detection. Compared with other methods that based on deep learning, the proposed one simplifies the pipeline of detection and builds an end-to-end detector. At the same time, the original DETR model usually requires long training time and large amount of computation, resulting in relatively poor performance in detection speed and accuracy, and it shows to be not friendly for small or early fire detection. Therefore, when designing the proposed network model, a normalization-based attention module is added in the feature extraction stage to highlight the effective features, being beneficial to the process of encoding. A multiscale deformable attention is also used in the encoder–decoder structure, accelerating therefore, the process of convergence during the training of the model, which includes the enhancement of the detection of small objects. Also, considering the cost of computation, the number of layers in the encoder–decoder structure is redefined to reduce the complexity of the model, and that also reduces the requirements of the application equipment. Detailed experiments are conducted on three self-built datasets and two public video sets. The results show that, the proposed method has an excellent performance on all of the datasets considered here. [ABSTRACT FROM AUTHOR]

1 Creating a dataset for estimating depth from target foreground and background scene variations. 2 Creation of relationships between depth of person, foreground and background scene field. 3 Dealing with perspective errors in depth predictions while capturing still photographs of person along camera axial line. This paper proposes a new technique to achieve a person's depth from a single image by considering the target foreground and background scene variations in extreme weather conditions within 40 meters range. For this purpose series of images are captured on each person at successive intervals. The height, distance, foreground, and background features are extracted using an object detection deep learning framework. The obtained features are then subsequently trained by the Gradient Booster Regressor to predict the depth information. Furthermore, the algorithm is tested on various images and is validated with ground truth depth data. The findings presented in this paper attest to the reliability of the methodology used for depth estimation. [Display omitted] [ABSTRACT FROM AUTHOR]

• The novelty of the work presented in this paper is that a information fusion algorithm of the maximum multi-modal weight decision is proposed. The emotion recognition scheme is developed by using the multi-modal information fusion algorithm. • Another major contribution of this work is the innovative conversion of traditional EEG data into corresponding EEG topographic maps for the emotion recognition. • Besides, this paper builds a multi-scale feature extraction network model for the facial expression recognition. In view of the low accuracy of the traditional emotion recognition methods based on facial expressions, an emotion recognition method based on maximum weight multi-modal information fusion of electroencephalographs (EEGs) and facial expression information is proposed in this paper. First, the induced emotional EEG data is converted into the corresponding EEG topographic map data and sent to the convolutional network for training and outputting decision information. Second, the illumination compensation method is utilized to filter the noise of the face image data. Then, the face image data is trained in the multi-scale feature extraction network, and the decision information is output. Finally, aiming at the decision-level information fusion, a weighted fusion method is proposed in this paper for emotion recognition. Experimental tests show that the recognition accuracy of the multi-scale feature extraction network on the CK+ data set and Fer2013 data reached 94.4% and 72%, respectively. Simultaneously, the multi-modal information fusion method achieves 92.6% accuracy in emotion recognition. [Display omitted] The novelty of the work presented in this paper is that a fusion method of maximum weight decision information is proposed. Emotion recognition is realized by the weighted fusion of EEG information and facial expression information. Another major contribution of this work is the innovative conversion of traditional EEG data into corresponding state EEG topographic maps for processing and analysis. Besides, this paper builds a multi-scale feature extraction network for emotion recognition. The graphical abstract of this paper is as below. [ABSTRACT FROM AUTHOR]

The wafer map is obtained by testing each die in the wafer during semiconductor production for defects and marking the defective die. The classification of wafer maps can provide evidence for problems occurring in the production process, so as to solve the problems and reduce the costs. Before classifying the wafer map, the most important thing is feature extraction. In addition to a certain spatial pattern, the wafer map also has a lot of noise, which affects the process of feature extraction. When the traditional DBSCAN algorithm is used for filtering, it is necessary to manually determine the value of Eps and MinPts parameters, and the selection of the parameters directly affects the accuracy of the clustering. Therefore, this paper proposes an automatic parameter filtering method based on DBSCAN, which can solve the traditional drawbacks of manually parameters setting, the algorithm is a Self-Adaptive DBSCAN-based method for wafer bin map, we call it SA-DBSCANWBM. This method selects a comprehensive index of cluster intra-cluster density and inter-cluster density to evaluate the optimal parameters. The experimental results show that the algorithm proposed in this paper can automatically and reasonably select better parameters and has a good clustering effect, which helpful for subsequent feature extraction and classification. • We proposed a self-adaptive DBSCAN-based method for wafer bin map defect pattern classification. • This algorithm can achieve good clustering effect and solve the disadvantage of traditional manual parameter setting. • It implies a potential method for evaluation on wafer bin map defect pattern classification. [ABSTRACT FROM AUTHOR]

• 3 layer neural networks outperform other ML algorithms in automated assessments. • In subjective assignments, deep neural networks can improve score prediction. • Word embeddings and linguistic feature results in more precise text mining models. • Extraction and selection of appropriate features can improve results. Machine learning (ML) has recently gained popularity in a variety of domains for automating tasks. This has also been used in the evaluation of student responses/ assignments. This paper presents a qualitatively enhanced methodology for automated score prediction of subjective assignments. To consider all the major aspects of a human grader, 21 linguistic features related to syntactical, grammatical, sentimental, and readability are analyzed from the assignments. This study makes use of the ASAP competition dataset from Kaggle. The evaluation metric used is Quadratic Weighted Kappa (QWK), which measures the agreement between the human graded score and the predicted score. The effect of appropriate feature selection has been observed using Mutual Information Regression. Four ML algorithms are investigated on identified linguistic features. 3 Layer Neural Network with feature selection performed well among all chosen ML algorithms with average QWK of 0.678. To include the benefits of deep learning, a new hybrid model (LF-BiLSTM-att-FS) is proposed that combines a higher level deep neural network (DNN) with the selected features. Pre-trained Glove embedding is used to include contextual information of the text. The proposed model results demonstrated an improvement in overall accuracy, with an average QWK value of 0.768. [ABSTRACT FROM AUTHOR]

Research about recommender systems emerges over the last decade and comprises valuable services to increase different companies' revenue. While most existing recommender systems rely either on a content-based approach or a collaborative approach, there are hybrid approaches that can improve recommendation accuracy using a combination of both approaches. Even though many algorithms are proposed using such methods, it is still necessary for further improvement. This paper proposes a recommender system method using a graph-based model associated with the similarity of users' ratings in combination with users' demographic and location information. By utilizing the advantages of Autoencoder feature extraction, we extract new features based on all combined attributes. Using the new set of features for clustering users, our proposed approach (GHRS) outperformed many existing recommendation algorithms on recommendation accuracy. Also, the method achieved significant results in the cold-start problem. All experiments have been performed on the MovieLens dataset due to the existence of users' side information. • We propose a recommendation system using graph-based features and Autoencoders. • We investigate and analyze each step of the method to find the best setup. • We examine the method with the most popular evaluation metrics and datasets. • Results show an improvement in comparison with basic and state of the art methods. [ABSTRACT FROM AUTHOR]

The quality of direction of arrival (DOA) estimation is affected by factors such as noise and interferences in wireless communication and other systems. By employing the benefits of cyclostationary signal analysis, which includes immunity to noise and interferences, in this paper, a simple high-resolution DOA estimation method is proposed. Most of the cyclostationary-based DOA estimation methods depend on the statistical properties of the received signals (e.g., the cyclic correlation matrix). Unlike them, in the proposed method, the received signal directly enters a DOA estimation loop containing a normalized least mean square (NLMS) adaptive algorithm. The method has high resolution and performance and low computational complexity in comparison with its counterparts. Moreover, it is befitting for signals in the presence of noise (Gaussian and impulsive) and interferences. Simulation results validate the efficiency of the proposed method from different aspects in comparison with other related studies. [ABSTRACT FROM AUTHOR]

[Display omitted] • SentiWordNet lexicon is used for generating sentiment features of email data. • Probabilistic Latent Semantic Analysis algorithm is used for clustering. • The sentiment sequence of thread and thread size are identified. • Evaluated the proposed model using accuracy, precision, recall and F-measure. Email messaging is the most common way of providing effective communication between internauts. Consequently, the total sent and received emails count will be increased. But, the internaut can't remember all such emails. Even though email thread identification approaches give satisfactory benefits to the internauts, but they may fail to alert them for a cause to identify the sentiments behind an email thread. To address, this issue Probabilistic Latent Semantic Analysis clustering algorithm has been used in this paper to identify the email sentiment thread sequence. The sentiment and the thread sequence within the emails have been discovered as clustering sentiment polarity and temporal categories with the help of PLSA clusters. At the initial stage, we used three feature extraction methods, latent semantic analysis (LDA), bag of words (BoW), TF-IDF and SentiWordNet (SWN) lexicon for generating sentiment features of email. Next, Probabilistic Latent Semantic Analysis algorithm is used to form email clusters based on sentiment features. Thus, it helps to identify thread sentiment and sequence of sentiment threads. Email threads give a mechanism by which any user will be able to find out the sequence in the thread on the basis of sentiment analysis of email related to a specific set of communication during a specific time period. Various parameters evaluation measures have been considered in this work to evaluate the proposed model such as accuracy, precision, recall and F-measure, and the proposed algorithm is compared with other standard algorithms. Furthermore, a statistical test has also been performed. [ABSTRACT FROM AUTHOR]

• An evaluation scheme is developed to detect the health status of rolling bearing. • Mixed-scale model combining with CEEMDAN and SVDE is constructed to extract fault features adaptively. • Pt-SNE algorithm is provided for high-dimensional features reduction. Accurate and efficient fault diagnosis for rolling bearing is essential to ensure the reliable and safe operation of mechanical equipment. In this paper, a hybrid hierarchical fault diagnosis method based on scale-variable dispersion entropy (SVDE) and parametric t-distributed stochastic neighbor embedding (Pt-SNE) algorithm, systematically combining the statistics analysis principle and machine learning technique, is proposed. First, an initial evaluation scheme with regard to the health state of bearing is implemented by the SVDE theory blended with the statistical analysis technology. Second, if fault appears, a novel mixed-scale model, integrating series mode with multi-scale factor, is established based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and SVDE for further improvement of feature extraction performance. Subsequently, a Pt-SNE algorithm is provided to reduce the features for higher accuracy and speed of diagnosis. Finally, the obtained low-dimensional representations after reduction can be imported in Softmax classifier for fault recognition. Two vibration datasets are used for bearing fault diagnosis. The experimental results prove the superior performances of the proposed method, and it has better practicability in engineering problems compared with other existing approaches. [ABSTRACT FROM AUTHOR]

• A novel dimensionality reduction method based on t-SNE and DBSCAN is proposed. • A RUL prediction method using LSTM with t-SNE-DBSCAN is proposed. • Internal dimensionality correlation of features is considered into RUL prediction. The remaining useful life (RUL) prediction has received increasing research attention in recent years due to its essential role in improving industrial manufacturing systems' productivity and reliability. High dimensionality time-series data is collected during the system's operating time with the implementation of various sensors. To monitor the machining tool's RUL, a novel multisensor fusion method based on t-SNE-DBSCAN dimensionality reduction is proposed in this paper to aggregate the multiple sensor measurements into a healthy indication that represents the RUL. The robust MCD-Estimator is used to denoise multidimensional sensor data, flag the outliers, and enhance the robustness of the denoising process. The high dimensional statistical features are extracted, and the dimensionality is reduced with t-distributed Stochastic Neighbor Embedding (t-SNE) according to the RUL labels, and optimum features selected by Density-Based Spatial Clustering of Application with Noise algorithm (DBSCAN). Ultimately, Long Short-Term Memory (LSTM) is adopted for RUL estimation with multisensor fusion. A case study with a practical application of the proposed approach, which can be demonstrated, is compared with state-of-the-art methods by evaluating its performance and migration capability in different working conditions. [ABSTRACT FROM AUTHOR]

• An innovatively improved SIFT structure that addresses the thorough feature extraction in all forgery cases. • A fast keypoint-label matching (FKLM) that creates groups of keypoint-label so that every high-dimensional feature is assigned into one of these groups. • A coarse-to-fine filtering relying on intrinsic attributes of exact keypoint-matches is designed to reduce false keypoint-matches effectively. • The adaptive block filling relying on true keypoint-matches contributes to the accurate and efficient suspicious region filling. Video copy-move forgery detection (VCMFD) is a significant and greatly challenging task due to a variety of difficulties, including a huge amount of video information, diverse forgery types, rich forgery objects, and homogenous forgery sources. These difficulties raise four unresolved key challenges in VCMFD: i) ineffective detection in some popular forgery cases; ii) inefficient matching in processing numerous video pixels with hundred-dimensional features under dozens of matching iterations; iii) high false positive (F P) in detecting forgery videos; iv) low trade-off of efficiency and effectiveness in filling forgery region, and even failing in indicating forgeries at the pixel level. In this paper, a novel VCMFD method is proposed to address these issues: i) an innovatively improved SIFT structure that can address the thorough feature extraction in all video copy-move forgery cases; ii) a novel fast keypoint-label matching (FKLM) algorithm is proposed that creates some keypoint-label groups so that every high-dimensional feature is assigned into one of these groups. As a result, matching of video pixels can be directly done on a small number of keypoint-label groups only, leading to a nearly 500% raise in matching efficiency; iii) a new coarse-to-fine filtering relying on intrinsic attributes of exact keypoint-matches is designed to more effectively reduce the false keypoint-matches; iv) the adaptive block filling relying on true keypoint-matches contributes to the accurate and efficient suspicious region filling, even at the pixel level. Finally, the suspicious region locations with the forgery vision persistence concept indicate forgery videos. Compared to the state-of-art methods, the experiments show that our proposed method achieves the best detection accuracy, lowest F P , and improved at least 16% and 8% of F 1 scores on the GRIP 2.0 dataset and a combination of SULFA 2.0 & REWIND datasets. Furthermore, the proposed method is with low computational time (4.45 s/Mpixels), which is about 1/2-1/3 times of the latest DFMI-BM (8.02 s/Mpixels) and PM-2D (13.1 s/Mpixels) methods. [ABSTRACT FROM AUTHOR]

Steganography is a practice of covert communication by hiding secret or payload information inside a cover source medium. Fraudulent entities may make use of it to communicate secretly and pose a great threat to law enforcement agencies. Universal steganalysis is a counter attack designed to identify steganography regardless of the steganographic process involved. As minute payloads that ride over covers, evade detection, steganalysts need to resort to high dimensional feature sets that extract residues in every possible way and a powerful classifier with higher computational power. In this paper, a novel universal steganalyzer driven by Empirical Mode Decomposition technique which is an adaptive and highly efficient method to analyze non-linear and non-stationary signals is proposed. Using this technique, the suspicious digital images are decomposed into intrinsic mode functions and residues to gradually remove the image contents to reveal the feeble artifacts caused by steganographic algorithms. Frobenius norm computed from these components further highlight the distortions. A low dimensional feature with a simple thresholding function assisting the steganalytic community in a blind and generic way can definitely be viewed as a boon to the domain. The proposed method is tested upon spatial content-adaptive steganographic algorithms (HUGO, WOW, S-UNIWARD) and content-independent least significant bit steganographic algorithms (LSBR, LSBM, LSBMR, LSBR2). The experimental results show that the proposed method is able to achieve improved accuracies when compared with Spatial Rich Model, Wu Net, Ye Net and Hybrid CNN. The execution time for the proposed method is also far less compared to state-of-the-art steganalyzers. [Display omitted] • Novel universal steganalyzer capable of predicting stego images irrespective of the steganographic process to address the toughest problem of low volume steganalysis. • Normalized feature extraction technique from Empirical Mode Decomposition (EMD) components is proposed for steganalysis application. • Very low dimensional feature set is proposed which is efficiently combined with a threshold-based decision function to achieve universal steganalysis. • High detection accuracy is achieved to detect content-adaptive and content-independent steganographic methods in low to very low volume payload bins. [ABSTRACT FROM AUTHOR]

A motor imagery (MI) based brain computer interface (BCI) is a challenging nonmuscular connection system used to independently perform movement-related tasks. It is gaining increasing prominence in helping paralyzed individuals communicate with the real world. Achieving better classification accuracy is the major concern in the field of motor imagery-based BCI. To upgrade the classification performance, relevant features play a vital role. The relevant features can be selected by the extreme gradient Bayesian optimization (XGBO) method. In this paper, a combination of time-, frequency-, and spatial-related MI features are extracted to design a reliable MI-BCI system. The proposed method incorporates the XGBO algorithm for feature selection and the random forest for the classification of EEG signals. The potency of the proposed system was investigated using two public EEG datasets (BCI Competition III dataset IIIa and dataset IVa). A novel XGBO algorithm increases the accuracy and reduces the time consumption by reducing the dimensionality of features. The proposed algorithm selects the minimum number of features that increase the computational efficacy for MI-based BCI systems. The proposed method is compared with ANOVA, sequential forward selection, recursive feature elimination, and LASSO methods and the accuracy rate is increased with the lowest computation time. The proposed method achieves mean accuracies of 94.44% and 88.72% and classification errors of 5.56% and 11.28% for Datasets IIIa and IVa, respectively. It outperforms four state-of-art methods with 0.87% and 0.59% increases in the accuracy for Datasets IIIa and IVa, respectively. • A novel feature selection method enhances the classification of EEG signals. • The time, spatial and frequency domain of EEG motor imagery features are extracted. • Predominant EEG Features are selected using the proposed XGBO method. • XGBO method is compared with existing feature selection methods. • The proposed method increases accuracy and reduces the computation time. [ABSTRACT FROM AUTHOR]

The advances of intelligent fault diagnosis in recent years show that deep learning has strong capability of automatic feature extraction and accurate identification for fault signals. Nevertheless, data scarcity and varying working conditions can degrade the performance of the model. More recently, a tool has been proposed to address the above challenges simultaneously. Meta-learning, also known as learning to learn, uses a small sample to quickly adapt to a new task. It has great application potential in few-shot and cross-domain fault diagnosis, and thus has become a promising tool. However, there is a lack of a survey to conclude existing work and look into the future. This paper comprehensively investigates deep meta-learning in fault diagnosis from three views: (i) what to use, (ii) how to use, and (iii) how to develop, i.e. algorithms, applications, and prospects. Algorithms are illustrated by optimization-, metric-, and model-based methods, the applications are concluded in few-shot cross-domain fault diagnosis, and open challenges, as well as prospects, are given to motivate the future work. Additionally, we demonstrate the performance of three approaches on two few-shot cross-domain tasks. Typical meta-learning methods are implemented and available at https://github.com/fyancy/MetaFD. • Review the advances of meta-learning in fault diagnosis for the first time. • Demonstrate deep meta-learning in fault diagnosis via algorithms and applications. • Illuminate meta-learning algorithms by mathematical optimization. • Stimulate future work with open challenges and prospects. [ABSTRACT FROM AUTHOR]

• Proposed cycle envelope spectral segmentation method based to optimize EWT. • Calculate the similarity of the envelope spectra of adjacent signals to optimize the components. • A new indicator called sensitive IMFs assessing index (SIAI) was designed to identify fault information. The empirical wavelet transform (EWT) has made outstanding contributions in the field of fault diagnosis. However, when EWT processes complex signals, there may be modal aliasing or meaningless components. In order to solve the spectral segmentation defect of the EWT method and improve its ability to extract bearing fault features, this paper proposes a new algorithm to improve EWT. In order to weaken the influence of extreme points in the complex Fourier spectrum on modal differentiation, the cycle envelope spectral segmentation method is proposed. The maximum envelope fitting method not only reduces the number of useless extreme points, but also highlights each mode. The number of filters is reduced while suppressing the interference of noise on the modal. The components that contain similar information in the result will be merged based on their correlation. Then sensitive IMFs assessing index (SIAI) is proposed to combine correlation and symmetry of the signal, and obtains the characteristics of time domain, frequency domain, and amplitude domain to extract fault information. Locomotive bearing and wind turbine gearbox bearing fault data verified the effectiveness of the method. [ABSTRACT FROM AUTHOR]

Snoring is an important characteristic of obstructive sleep apnea-hypopnea syndrome (OSAHS). Snoring sound can be used to develop a non-invasive approach for automatically screening OSAHS. In this paper, a snoring detection algorithm based on acoustic features and the XGBoost was proposed. The Fisher Ratio (FR) method was used for feature selection and the 23-dimensional feature set was extracted from the original 58-dimensional feature to reduce computational complexity. A variety of training and test data split methods were used to evaluate the performance of the proposed model. In addition, the proposed method was compared with the deep learning method on the independent subjects training set and test set. The accuracy of the reduced feature set by the proposed model was 87.22% and the deep learning model 87.26% on independent subjects training set and test set, the prediction time of the deep learning model on the test set was around 238 ms, the prediction time of XGBoost was around 58 ms, and the computing efficiency of XGBoost is higher than that of the deep learning model. The results show that the proposed method achieves a good balance between computational cost and performance. These results provide an important method for fast and real-time classification and evaluation of snoring for OSAHS. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient segmentation algorithm and the significance of texture features over segmentation in multispectral satellite images. In order to preserve the complete details about the earth's surface, initially texture features are extracted from the multispectral satellite images. Texture features are very important in remotely sensed images, since it has the capability to interpret micro and macro level features present in the images. This method has been effectively tested over multi-temporal LANDSAT data set of Hanoi and Balcoc region of vietnam. Qualitative observations made in the proposed work suggest that the addition of DOOG (Difference of Offset Gaussian) filter and texture features provide improved segmentation results compared to traditional methods. As per the quantitative investigations, the proposed method outperforms other contemporary methods in terms of Random Index (RI), Variance of Information (VOI) and Global Consistency Error (GCE). [ABSTRACT FROM AUTHOR]

Feature selection in real-world data mining problems is essential to make the learning task efficient and more accurate. Identifying the best feature selection algorithm, among the many available, is a complex activity that still relies heavily on human experts or some random trial-and-error procedure. Thus, the automated machine learning community has taken some steps towards the automation of this process. In this paper, we address the metalearning challenge of recommending feature selection algorithms by proposing a novel meta-feature engineering model. Our model considers a broad collection of meta-features that enable the study of the relationship between the dataset properties and the feature selection algorithm performance in terms of several criteria. We arrange the input meta-features into eight categories: (i) simple, (ii) statistical, (iii) information-theoretical, (iv) complexity, (v) landmarking, (vi) based on symbolic models, (vii) based on images, and (viii) based on complex networks (graphs). The target meta-features emerge from a multi-criteria performance measure, based on five individual performance indexes, that assesses feature selection methods grounded in information, distance, dependence, consistency, and precision measures. We evaluate our proposal using a recently developed framework that extracts the input meta-features from 213 benchmark datasets, and ranks the assessed feature selection algorithms, to fill in the target meta-features in meta-bases. This evaluation uses five state-of-the-art classification methods to induce recommendation models from meta-bases: C4.5, Random Forest, XGBoost, ANN, and SVM. The results showed that it is possible to reach an average accuracy of up to 90% applying our meta-feature engineering model. This work is the first to use an extensive empirical evaluation to provide a careful discussion of the strengths and limitations of more than 160 meta-features. These meta-features, while designed to aid the task of feature selection algorithm recommendation, can readily be employed in other metalearning scenarios. Therefore, we believe our findings are a valuable contribution to the fields of automated machine learning and data mining, as well as to the feature extraction and pattern recognition communities. • A novel meta-feature engineering model recommends feature selection algorithms. • The proposal obtains promising results from 213 datasets with hit rates of up to 90%. • Some simple, landmarking, image, and graph-based input meta-features highlighted. • A multi-criteria performance measure rigorously assesses candidate algorithms. • Chains of binary or multiclass classifiers can efficiently rank candidate algorithms. [ABSTRACT FROM AUTHOR]