Search

To overcome the deficiencies in segmenting hot spots from thermal infrared images, such as difficulty extracting the edge features, low accuracy, and a high missed detection rate, an improved Mask R-CNN photovoltaic hot spot thermal image segmentation algorithm has been proposed in this paper. Firstly, the edge image features of hot spots were extracted based on residual neural networks. Secondly, by combining the feature pyramid structure, an edge-guided feature pyramid structure was designed, and the hot spot edge features were injected into a Mask R-CNN network. Thirdly, an infrared spatial attention module was introduced into the Mask R-CNN network when feature extraction and the infrared features of the detected hot spots were enhanced. Fourthly, the size ratio of the candidate frames was adjusted self-adaptively according to the structural characteristics of the aspect ratio of the hot spots. Finally, the validation experiments were conducted, and the results demonstrated that the hot spot contours of thermal infrared images were enhanced through the algorithm proposed in this paper, and the segmentation accuracy was significantly improved. [ABSTRACT FROM AUTHOR]

The utilization of ultraviolet (UV) absorption spectroscopy for monitoring the concentration of specific decomposition gas components in gas-insulated switchgear (GIS) can provide a means to assess its insulation status. Nevertheless, UV optical modules currently deployed in the field are susceptible to external interferences like ambient noise and equipment vibrations. Real-time spectral data acquisition often suffers from significant noise contamination, directly impinging on subsequent feature extraction and detection accuracy. This paper presents an optimized singular value decomposition (SVD) noise reduction method for mitigating noisy spectral signals. First, each singular value within the noisy signal is transformed into a component signal. Next, the highest frequency value in the signal serves as an indicator to characterize the signal. Finally, the primary frequency values are arranged based on the decreasing singular values of the original noisy signal. The singular value corresponding to the first primary frequency value surpassing a preset threshold is selected as the effective order for denoising. Random noise with varying intensities was intentionally introduced to the UV spectral signal of sulfur dioxide (SO2), followed by noise reduction procedures. It is shown that the improved SVD noise reduction algorithm proposed in this paper enhances the signal-to-noise ratio (SNR) by 18.02% and 16.86%, and reduces the root-mean-square error (RMSE) by 15.13% and 14.92%, respectively, compared with the singular value difference spectrum (SVDS) denoising method and wavelet transform denoising method under the condition of low SNR. Furthermore, there exists a linear relationship between the concentration of SO2 samples and the eigenvalues of the UV spectra, demonstrating a higher linear goodness with a coefficient of 0.99735. The denoising method proposed in this paper does not require the manual setting of various types of parameters, and has a better ability to deal with the noise of UV spectral signals in engineering sites with complex environments. [ABSTRACT FROM AUTHOR]

As an important part of the power system, it is necessary to ensure the safe and stable operation of transmission lines. Due to long-term exposure to the outdoors, the lines face many insecurity factors, and foreign object intrusion is one of them. Traditional foreign object (bird's nest, kite, balloon, trash bag) detection algorithms suffer from low efficiency, poor accuracy, and small coverage, etc. To address the above problems, this paper introduces the RCDAM-Net. In order to prevent feature loss or useful feature compression, the RevCol (Reversible Column Networks) is used as the backbone network to ensure that the total information remains unchanged during feature decoupling. DySnakeConv (Dynamic Snake Convolution) is adopted and embedded into the C2f structure, which is named C2D and integrates low-level features and high-level features. Compared to the original BottleNeck structure of C2f, the DySnakeConv enhances the feature extraction ability for elongated and weak targets. In addition, MPDIoU (Maximum Performance Diagonal Intersection over Union) is used to improve the regression performance of model bounding boxes, solving the problem of predicted bounding boxes having the same aspect ratio as true bounding boxes, but with different values. Further, we adopt Decoupled Head for detection and add additional auxiliary training heads to improve the detection accuracy of the model. The experimental results show that the model achieves mAP50, Precision, and Recall of 97.98%, 98.15%, and 95.16% on the transmission tower line foreign object dataset, which is better to existing multi-target detection algorithms. [ABSTRACT FROM AUTHOR]

Due to the limitations of traditional retinal blood vessel segmentation algorithms in feature extraction, vessel breakage often occurs at the end. To address this issue, a retinal vessel segmentation algorithm based on a modified U-shaped network is proposed in this paper. This algorithm can extract multi-scale vascular features and perform segmentation in an end-to-end manner. First, in order to improve the low contrast of the original image, pre-processing methods are employed. Second, a multi-scale residual convolution module is employed to extract image features of different granularities, while residual learning improves feature utilization efficiency and reduces information loss. In addition, a selective kernel unit is incorporated into the skip connections to obtain multi-scale features with varying receptive field sizes achieved through soft attention. Subsequently, to further extract vascular features and improve processing speed, a residual attention module is constructed at the decoder stage. Finally, a weighted joint loss function is implemented to address the imbalance between positive and negative samples. The experimental results on the DRIVE, STARE, and CHASE_DB1 datasets demonstrate that MU-Net exhibits better sensitivity and a higher Matthew's correlation coefficient (0.8197, 0.8051; STARE: 0.8264, 0.7987; CHASE_DB1: 0.8313, 0.7960) compared to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Featured Application: The aim is to distinguish maturity, reduce labor costs, and solve the occurrence of false or missed detections caused by strawberry leaf occlusion. In view of the time-consuming and laborious manual picking and sorting of strawberries, the direct impact of image recognition accuracy on automatic picking and the rapid development of deep learning(DL), a Faster Regions with Convolutional Neural Network features (R-CNN) strawberry recognition method that combines Mixup data augmentation, a ResNet(Residual Network)50 backbone feature extraction network and a Soft-NMS (Non-Maximum Suppression) algorithm, named the MRS Faster R-CNN, is proposed. In this paper, the transfer learning backbone feature extraction network VGG (Visual Geometry Group) 16 and ResNet50 are compared, and the superior ResNet50 is selected as the backbone network of MRS Faster R-CNN. The data augmentation method of Mixup image fusion is used to improve the learning and generalization ability of the model. The redundant bboxes (bounding boxes) are removed through Soft-NMS to obtain the best region proposal. The freezing phase is added to the training process, effectively reducing the occupation of video memory and shortening the training time. After experimental verification, the optimized model improved the AP (Average Precision) values of mature and immature strawberries by 0.26% and 5.34%, respectively, and the P(Precision) values by 0.81% and 6.34%, respectively, compared to the original model (R Faster R-CNN). Therefore, the MRS Faster R-CNN model proposed in this paper has great potential in the field of strawberry recognition and maturity classification and improves the recognition rate of small fruit and overlapping occluded fruit, thus providing an excellent solution for mechanized picking and sorting. [ABSTRACT FROM AUTHOR]

Extracting effective features from high-dimensional datasets is crucial for determining the accuracy of regression and classification models. Model predictions based on causality are known for their robustness. Thus, this paper introduces causality into feature selection and utilizes Feature Selection based on NOTEARS causal discovery (FSNT) for effective feature extraction. This method transforms the structural learning algorithm into a numerical optimization problem, enabling the rapid identification of the globally optimal causality diagram between features and the target variable. To assess the effectiveness of the FSNT algorithm, this paper evaluates its performance by employing 10 regression algorithms and 8 classification algorithms for regression and classification predictions on six real datasets from diverse fields. These results are then compared with three mainstream feature selection algorithms. The results indicate a significant average decline of 54.02% in regression prediction achieved by the FSNT algorithm. Furthermore, the algorithm exhibits exceptional performance in classification prediction, leading to an enhancement in the precision value. These findings highlight the effectiveness of FSNT in eliminating redundant features and significantly improving the accuracy of model predictions. [ABSTRACT FROM AUTHOR]

In this paper, we propose a wildlife detection algorithm based on improved YOLOv5s by combining six real wildlife images of different sizes and forms as datasets. Firstly, we use the RepVGG model to simplify the network structure that integrates the ideas of VGG and ResNet. This RepVGG introduces a structural reparameterization approach to ensure model flexibility while reducing the computational effort. This not only enhances the ability of model feature extraction but also speeds up the model computation, further improving the model's real-time performance. Secondly, we use the sliding window method of the Swin Transformer module to divide the feature map to speed up the convergence of the model and improve the real-time performance of the model. Then, it introduces the C3TR module to segment the feature map, expand the perceptual field of the feature map, solve the problem of backpropagation gradient disappearance and gradient explosion, and enhance the feature extraction and feature fusion ability of the model. Finally, the model is improved by using SimOTA, a positive and negative sample matching strategy, by introducing the cost matrix to obtain the highest accuracy with the minimum cost. The experimental results show that the improved YOLOv5s algorithm proposed in this paper improves mAP by 3.2% and FPS by 11.9 compared with the original YOLOv5s algorithm. In addition, the detection accuracy and detection speed of the improved YOLOv5s model in this paper have obvious advantages in terms of the detection effects of other common target detection algorithms on the animal dataset in this paper, which proves that the improved effectiveness and superiority of the improved YOLOv5s target detection algorithm in animal target detection. [ABSTRACT FROM AUTHOR]

Infrared images have good anti-environmental interference ability and can capture hot target information well, but their pictures lack rich detailed texture information and poor contrast. Visible image has clear and detailed texture information, but their imaging process depends more on the environment, and the quality of the environment determines the quality of the visible image. This paper presents an infrared image and visual image fusion algorithm based on deep learning. Two identical feature extractors are used to extract the features of visible and infrared images of different scales, fuse these features through specific fusion methods, and restore the features of visible and infrared images to the pictures through the feature restorer to make up for the deficiencies in the various photos of infrared and visible images. This paper tests infrared visual images, multi-focus images, and other data sets. The traditional image fusion algorithm is compared several with the current advanced image fusion algorithm. The experimental results show that the image fusion method proposed in this paper can keep more feature information of the source image in the fused image, and achieve excellent results in some image evaluation indexes. [ABSTRACT FROM AUTHOR]

With the strengthening of worldwide counter-terrorism initiatives, it is increasingly important to detect contrabands such as controlled knives and flammable materials hidden in clothes and bags. Terahertz (THz) imaging technology is widely used in the field of contraband detection due to its advantages of high imaging speed and strong penetration. However, the terahertz images are of poor qualities and lack texture details. Traditional target detection methods suffer from low detection speeds, misdetection, and omission of contraband. This work pre-processes the original dataset using a variety of image processing methods and validates the effect of these methods on the detection results of YOLOv7. Meanwhile, the lightweight and multi-object detection YOLOv7 (LWMD-YOLOv7) algorithm is proposed. Firstly, to meet the demand of real-time for multi-target detection, we propose the space-to-depth mobile (SPD_Mobile) network as the lightweight feature extraction network. Secondly, the selective attention module large selective kernel (LSK) network is integrated into the output of the multi-scale feature map of the LWMD-YOLOv7 network, which enhances the effect of feature fusion and strengthens the network's attention to salient features. Finally, Distance Intersection over Union (DIOU) is used as the loss function to accelerate the convergence of the model and to have a better localisation effect for small targets. The experimental results show that the YOLOv7 algorithm achieves the best detection results on the terahertz image dataset after the non-local mean filtering process. The LWMD-YOLOv7 algorithm achieves a detection accuracy P of 98.5%, a recall R of 97.5%, and a detection speed of 112.4 FPS, which is 26.9 FPS higher than that of the YOLOv7 base network. The LWMD-YOLOv7 achieves a better balance between detection accuracy and detection speed. It provides a technological reference for the automated detection of contraband in terahertz images. [ABSTRACT FROM AUTHOR]

Featured Application: The algorithms proposed in this paper can be applied to a wide range of infrastructure projects in the pre-survey process with the advantages of low cost and high practicality. At present, Chinese 3D reconstruction solutions using stereo cameras mainly face known, indoor, structured scenes; for the reconstruction of unstructured, larger-scale scenes with a large variety of texture information of different intensities, there are certain difficulties in ensuring accuracy and real-time processing. For the above problems, we propose a scene reconstruction method using stereo vision. Firstly, considering the influence of outdoor lighting and weather on the captured 2D images, the optimized SAD-FAST feature detection algorithm and stereo-matching strategy were employed in the stereo-matching stage to improve the overall efficiency and matching quality at this stage. Then, a homogenized feature extraction algorithm with gradient value decreasing step by step (GVDS) was used in the depth value calculation to ensure a sufficient number of feature points for strong texture information while extracting features from weak-texture areas, which greatly improved the quality and speed of unstructured scene reconstruction. We conducted experiments to validate the proposed method, and the results showed the feasibility of the proposed method and its high practical value. [ABSTRACT FROM AUTHOR]

Industrial control protocol feature extraction is an important way to improve the accuracy and speed of industrial control protocol traffic classification. This paper firstly proposes a keyword feature extraction method for industrial control protocol, and then designs and implements an industrial control system (ICS) traffic classification based on this method. The proposed method utilizes the characteristics of the relatively fixed format of the industrial control protocol and the periodicity of the protocol traffic in ICS. The keyword features of the industrial control protocol can be accurately extracted after data preprocessing, data segmentation, redundant data filtering, and feature byte mining. A feature dataset is then formed. The designed ICS traffic classifier adopts decision tree and is trained with the feature dataset. Experiments are carried out on the open-source dataset. The results show that the proposed method achieves 99.99% classification accuracy, and the classification precision and classification recall rate reach 99.98% and 99.93%, respectively. The training time and predicting time of classifier are 0.34 s and 0.264 s, respectively, which meets the requirements of high precision and low latency of industrial control system. [ABSTRACT FROM AUTHOR]

With an increase in the use of software, the incidence of bugs and resulting maintenance costs also increase. In open source projects, developer reassignment accounts for approximately 50%. Software maintenance costs can be reduced if appropriate developers are recommended to resolve bugs. In this study, features are extracted by applying feature selection for each developer. These features are entered into CNN-LSTM algorithm to learn the model and recommend appropriate developers. To compare the performance of the proposed model, open source projects (Google Chrome, Mozilla Core, and Mozilla Firefox) were used to compare the performance of the proposed method with a baseline for developer recommendation. In this paper, the performance showed 54% for F-measure and 52% for accuracy in open source projects. The proposed model has improved and showed about a 13% more effective performance improvement than with DeepTriage. It was discovered that the performance of the proposed model was better. [ABSTRACT FROM AUTHOR]

The accurate localization of S1 and S2 is essential for heart sound segmentation and classification. However, current direct heart sound segmentation algorithms have poor noise immunity and low accuracy. Therefore, this paper proposes a new optimal heart sound segmentation algorithm based on K-means clustering and Haar wavelet transform. The algorithm includes three parts. Firstly, this method uses the Viola integral method and Shannon's energy-based algorithm to extract the function of the envelope of the heart sound energy. Secondly, the time–frequency domain features of the acquired envelope are extracted from different dimensions and the optimal peak is searched adaptively based on a dynamic segmentation threshold. Finally, K-means clustering and Haar wavelet transform are implemented to localize S1 and S2 of heart sounds in the time domain. After validation, the recognition rate of S1 reached 98.02% and that of S2 reached 96.76%. The model outperforms other effective methods that have been implemented. The algorithm has high robustness and noise immunity. Therefore, it can provide a new method for feature extraction and analysis of heart sound signals collected in clinical settings. [ABSTRACT FROM AUTHOR]

The accurate identification of the shape of the blast furnace (BF) burden surface is a crucial factor in the fault diagnosis of the BF condition and guides the charge operation. Based on the BF 3D point cloud data of phased array radar, this paper proposes a 3D burden surface feature definition system. Based on expert experience, the feature parameters of the burden surface are extracted. The voxel feature was extracted based on improved BNVGG. The optimized PointCNN extracts the point cloud features. The features of the burden surface were defined from three perspectives: the surface shape, voxel, and point cloud. The research of the 2D burden line is extended to the 3D burden surface, and the assumption of the symmetry of the BF is eliminated. Finally, the accuracy of the burden surface classification under each feature was evaluated, and the effectiveness of each feature extraction algorithm was verified. The experimental results show that the shape feature defined based on expert experience affects the recognition of the burden surface. However, it is defined from the data perspective and cannot accurately identify a similar burden surface shape. Therefore, the voxel features and point cloud features of the burden surface were extracted, improving the identification accuracy. [ABSTRACT FROM AUTHOR]

Three-dimensional object detection is the core of an autonomous driving perception system, which detects and analyzes targets around the vehicle to obtain their sizes, shapes, and categories to provide reliable operational decisions for achieving autonomous driving. To improve the detection and localization accuracy of multi-object targets such as surrounding vehicles and pedestrians in autonomous driving scenarios, based on PointPillars fast object detection network, a three-dimensional object detection algorithm based on the channel attention mechanism, ECA Modules-PointPillars, is proposed. Firstly, the improved algorithm uses point cloud columnarization features to convert a three-dimensional point cloud into a two-dimensional pseudo-image. Then, combining the 2D backbone network for feature extraction with the Efficient Channel Attention (ECA) modules to achieve the enhancement of the positional feature information in the pseudo-image and the weakening of the irrelevant feature information such as background noise. Finally, the single-shot multibox detector (SSD) algorithm was used to complete the 3D object detection task. The experimental results show that the improved algorithm improves the mAP by 3.84% and 4.04% in BEV mode and 3D mode, respectively, compared to PointPillars, which improves the mAP by 4.64% and 5.89% in BEV mode and 3D mode, respectively, compared to F-PointNet, improves the mAP by 11.78% and 14.19% in BEV mode and 3D mode, respectively, compared to VoxelNet, and improves the mAP by 9.47% and 6.55% in BEV mode and 3D mode, respectively, compared to SECOND, demonstrating the effectiveness and reliability of the improved algorithms in autonomous driving scenarios. [ABSTRACT FROM AUTHOR]

Wireless communications are increasingly vulnerable to malicious jamming attacks due to the inherent openness and broadcast nature. In this regard, a novel anti-jamming scheme based on knowledge graph is proposed in this paper, where the knowledge graph which contains the prior knowledge of the commonly-used jamming patterns is utilized to make the fast anti-jamming decision with low complexity. Specifically, for the known jamming patterns, the anti-jamming strategy is directly extracted based on the search from the knowledge graph by using the sensing information. On the other hand, for the unknown jamming patterns, a time-frequency domain feature extraction method is first proposed to extract the jamming feature and match the jamming patterns in the knowledge graph. As such, multiple anti-jamming strategies can be obtained by the knowledge graph search. Finally, the optimal strategy can be achieved by the two communication decision criteria-based strategy fusion. The simulation results showed that the time-frequency domain feature extraction method can well extract the time-frequency domain feature of the jamming pattern, and the proposed algorithm has high decision accuracy and robustness. [ABSTRACT FROM AUTHOR]

In practical applications, the intelligence of wheeled mobile robots is the trend of future development. Object detection for wheeled mobile robots requires not only the recognition of complex surroundings, but also the deployment of algorithms on resource-limited devices. However, the current state of basic vision technology is insufficient to meet demand. Based on this practical problem, in order to balance detection accuracy and detection efficiency, we propose an object detection algorithm based on a combination of improved YOLOv4 and improved GhostNet in this paper. Firstly, the backbone feature extraction network of original YOLOv4 is replaced with the trimmed GhostNet network. Secondly, enhanced feature extraction network in the YOLOv4, ordinary convolution is supplanted with a combination of depth-separable and ordinary convolution. Finally, the hyperparameter optimization was carried out. The experimental results show that the improved YOLOv4 network proposed in this paper has better object detection performance. Specifically, the precision, recall, F1, mAP (0.5) values, and mAP (0.75) values are 88.89%, 87.12%, 88.00%, 86.84%, and 50.91%, respectively. Although the mAP (0.5) value is only 2.23% less than the original YOLOv4, it is higher than YOLOv4_tiny, Eifficientdet-d0, YOLOv5n, and YOLOv5 compared to 29.34%, 28.99%, 20.36%, and 18.64%, respectively. In addition, it outperformed YOLOv4 in terms of mAP (0.75) value and precision, and its model size is only 42.5 MB, a reduction of 82.58% when compared to YOLOv4's model size. [ABSTRACT FROM AUTHOR]

In the evolving landscape of device-free localization techniques, Wi-Fi channel state information (CSI) emerges as a pivotal tool for environmental sensing. This study introduces a novel fingerprint localization algorithm. It employs an improved Hybrid Grey Wolf Particle Swarm Optimization (IPSOGWO) in combination with Multi-Output Support Vector Regression (MSVR) to enhance indoor positioning accuracy. To counteract the limitations of standard DBSCAN and PCA in noise reduction and feature extraction from complex nonlinear data, we propose an adaptive denoising algorithm based on spatial clustering (A-DBSCAN) and an autoencoder to efficiently denoise and extract features from CSI amplitude to improve the localization accuracy. Additionally, we introduce a new position update strategy, bolstering the optimization efficiency of the PSOGWO algorithm. This refined approach is instrumental in determining the globally optimal hyperparameters in MSVR, leading to enhanced model prediction accuracy. Two indoor scenario experiments were conducted to evaluate our method, yielding average localization errors of 0.59 m and 1.12 m, marking an improvement in localization performance compared to existing methods. [ABSTRACT FROM AUTHOR]

An improved recommendation algorithm based on Conditional Variational Autoencoder (CVAE) and Constrained Probabilistic Matrix Factorization (CPMF) is proposed to address the issues of poor recommendation performance in traditional user-based collaborative filtering algorithms caused by data sparsity and suboptimal feature extraction. Firstly, in the data preprocessing stage, a hidden layer is added to CVAE, and random noise is introduced into the hidden layer to constrain the data features, thereby obtaining more accurate latent features and improving the model's robustness and generative capability. Secondly, the category of items is incorporated as auxiliary information in CVAE to supervise the encoding and decoding of item data. By learning the distribution characteristics of the data, missing values in the rating data can be effectively reconstructed, thereby reducing the sparsity of the rating matrix. Subsequently, the reconstructed data is processed using CPMF, which optimizes the feature extraction performance by imposing constraints on user features. Finally, the prediction rating of a user for an item can be obtained through the matrix product of user and item feature matrices. Experimental results on the MovieLens-100K and MovieLens-1M datasets demonstrate the effectiveness and superiority of the proposed algorithm over four comparative algorithms, as it exhibits significant advantages in terms of root mean square error and mean absolute error metrics. [ABSTRACT FROM AUTHOR]

Images captured in low-brightness environments typically have low brightness, low contrast, and high noise levels, which significantly affect the overall image quality. To improve the image quality, a low-brightness image enhancement algorithm based on multi-scale fusion is proposed. First, a novel brightness transformation function is used for the generation of two images with different brightnesses. Then, the illumination estimation technique is used to construct a weight matrix, which facilitates the extraction of advantageous features from each image. Finally, the enhanced image is obtained by the fusion of two images using the weight matrix and the pyramid reconstruction algorithm. The proposed method has a better enhancement effect as shown by the experimental results. Compared to other image enhancement algorithms, it has lower evaluation values in the natural image quality evaluator (NIQE) and lightness order error (LOE) indices. The lowest average NIQE value of the proposed algorithm in each dataset is 2.836. This further demonstrates its superior performance. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has been applied to the field of recommendation, which can learn complex user interaction features and make better recommendations. However, deep learning only focuses on the interaction of high-order features and neglects the low-order features. The DeepFM model combines the linear FM (Factorization Machines) model and the deep DNN (Deep Neural Network) model to realize the interactive learning of low-order and high-order features, but it does not take into account that user interests will change dynamically with time. When the data sparsity is high, it cannot be effectively recommended. Based on this, an improved DeepFM recommendation algorithm that combines depth feature extraction was proposed, named fDeepFM. Firstly, the word features are transformed into low-dimensional dense vectors through the Embedding layer. Then Doc2Vec is combined to mine item features with context, and the two are stitched together as the input to the FM model and DNN model. Subsequently, user features are input to the GRU (Gated Cyclic Unit) model according to different cycles to mine user features. Finally, the results of the FM model, DNN model, and GRU model are combined by linear stitching as the overall output of the fDeepFM model. Experiments were carried out on Movielens-20M and Amazon data sets. The experimental results showed that MAE, RMSE, F1-score, and AUC on the Movielens-20M data set were optimized by 1.69%, 2.4%, 1.67%, and 2.28%, respectively; On the Amazon dataset, MAE, RMSE, F1-score, and AUC are optimized by 3.2%, 3.86%, 1.63%, and 2.2% respectively compared with DeepFM. [ABSTRACT FROM AUTHOR]

Amongst all biometric-based personal authentication systems, a fingerprint that gives each person a unique identity is the most commonly used parameter for personal identification. In this paper, we present an automatic fingerprint-based authentication framework by means of fingerprint enhancement, feature extraction, and matching techniques. Initially, a variant of adaptive histogram equalization called CLAHE (contrast limited adaptive histogram equalization) along with a combination of FFT (fast Fourier transform), and Gabor filters are applied to enhance the contrast of fingerprint images. The fingerprint is then authenticated by picking a small amount of information from some local interest points called minutiae point features. These features are extracted from the thinned binary fingerprint image with a hybrid combination of Harris and SURF feature detectors to render significantly improved detection results. For fingerprint matching, the Euclidean distance between the corresponding Harris-SURF feature vectors of two feature points is used as a feature matching similarity measure of two fingerprint images. Moreover, an iterative algorithm called RANSAC (RANdom SAmple Consensus) is applied for fine matching and to automatically eliminate false matches and incorrect match points. Quantitative experimental results achieved on FVC2002 DB1 and FVC2000 DB1 public domain fingerprint databases demonstrate the good performance and feasibility of the proposed framework in terms of achieving average recognition rates of 95% and 92.5% for FVC2002 DB1 and FVC2000 DB1 databases, respectively. [ABSTRACT FROM AUTHOR]

Although the spectrum sensing algorithms based on deep learning have achieved remarkable detection performance, the sensing performance is easily affected by adversarial attacks due to the fragility of neural networks. Even slight adversarial perturbations lead to a sharp deterioration of the model detection performance. To enhance the defense capability of the spectrum sensing model against such attacks, an unsupervised learning-based spectrum sensing algorithm with defending adversarial attacks (USDAA) is proposed, which is divided into two stages: adversarial pre-training and fine-tuning. In the adversarial pre-training stage, encoders are used to extract the features of adversarial samples and clean samples, respectively, and then decoders are used to reconstruct the samples, and comparison loss and reconstruction loss are designed to optimize the network parameters. It can reduce the dependence of model training on labeled samples and improve the robustness of the model to attack perturbations. In the fine-tuning stage, a small number of adversarial samples are used to fine-tune the pre-trained encoder and classification layer to obtain the spectrum sensing defense model. The experimental results show that the USDAA algorithm is better than the denoising autoencoder and distillation defense algorithm (DAED) against FGSM and PGD adversarial attacks. The number of labeled samples used in USDAA is only 11% of the DAED. When the false alarm probability is 0.1 and the S N R is −10 dB, the detection probability of the USDAA algorithm for the fast gradient sign method (FGSM) and the projected gradient descent (PGD) attack samples with random perturbations is above 88%, while the detection probability of the DAED algorithm for both attack samples is lower than 69%. Additionally, the USDAA algorithm has better robustness to attack with unknown perturbations. [ABSTRACT FROM AUTHOR]

In the process of image shooting, due to the influence of angle, distance, complex scenes, illumination intensity, and other factors, small targets and occluded targets will inevitably appear in the image. These targets have few effective pixels, few features, and no obvious features, which makes it difficult to extract their effective features and easily leads to false detection, missed detection, and repeated detection, thus affecting the performance of target detection models. To solve this problem, an improved faster region convolutional neural network (RCNN) algorithm integrating the convolutional block attention module (CBAM) and feature pyramid network (FPN) (CF-RCNN) is proposed to improve the detection and recognition accuracy of small-sized, occluded, or truncated objects in complex scenes. Firstly, it incorporates the CBAM attention mechanism in the feature extraction network in combination with the information filtered by spatial and channel attention modules, focusing on local efficient information of the feature image, which improves the detection ability in the face of obscured or truncated objects. Secondly, it introduces the FPN feature pyramid structure, and links high-level and bottom-level feature data to obtain high-resolution and strong semantic data to enhance the detection effect for small-sized objects. Finally, it optimizes non-maximum suppression (NMS) to compensate for the shortcomings of conventional NMS that mistakenly eliminates overlapping detection frames. The experimental results show that the mean average precision (MAP) of target detection of the improved algorithm on PASCAL VOC2012 public datasets is improved to 76.2%, which is 13.9 percentage points higher than those of the commonly used Faster RCNN and other algorithms. It is better than the commonly used small-sample target detection algorithm. [ABSTRACT FROM AUTHOR]

The effective decoding of motor imagination EEG signals depends on significant temporal, spatial, and frequency features. For example, the motor imagination of the single limbs is embodied in the μ (8–13 Hz) rhythm and β (13–30 Hz) rhythm in frequency features. However, the significant temporal features are not necessarily manifested in the whole motor imagination process. This paper proposes a Multi-Time and Frequency band Common Space Pattern (MTF-CSP)-based feature extraction and EEG decoding method. The MTF-CSP learns effective motor imagination features from a weak Electroencephalogram (EEG), extracts the most effective time and frequency features, and identifies the motor imagination patterns. Specifically, multiple sliding window signals are cropped from the original signals. The multi-frequency band Common Space Pattern (CSP) features extracted from each sliding window signal are fed into multiple Support Vector Machine (SVM) classifiers with the same parameters. The Effective Duration (ED) algorithm and the Average Score (AS) algorithm are proposed to identify the recognition results of multiple time windows. The proposed method is trained and evaluated on the EEG data of nine subjects in the 2008 BCI-2a competition dataset, including a train dataset and a test dataset collected in other sessions. As a result, the average cross-session recognition accuracy of 78.7% was obtained on nine subjects, with a sliding window length of 1 s, a step length of 0.4 s, and the six windows. Experimental results showed the proposed MTF-CSP outperforming the compared machine learning and CSP-based methods using the original signals or other features such as time-frequency picture features in terms of accuracy. Further, it is shown that the performance of the AS algorithm is significantly better than that of the Max Voting algorithm adopted in other studies. [ABSTRACT FROM AUTHOR]

A reduced reference quality assessment algorithm for image retargeting by earth mover's distance is proposed in this paper. In the reference image, all the feature points are extracted using scale invariant feature transform. Let the histograms of image patch around each feature point be local information, and the histograms of saliency feature as global information. Those feature information is extracted at the sender side and transmitted to the receiver side. After that, the same feature information extraction process is performed for the retargeted image at the receiver side. Finally, all feature information of the reference and retargeted images is used collectively to compute the quality of the retargeted image. An overall quality score is calculated from the local and global similarity measure using earth mover's distance between reference and retargeted images. The key step in our algorithm is to provide an earth mover's distance metric in a manner that indicates how the local and global information in the reference image is preserved in corresponding retargeted image. Experimental results show that the proposed algorithm can improve the image quality scores on four common criteria in the retargeted image quality assessment community. [ABSTRACT FROM AUTHOR]

The task of logo detection is desirable and important for various fields. However, it is challenging and difficult to identify logos in complex scenarios as a logo can appear in different styles and platforms. Logo images include diverse contexts, sizes, projective transformation, resolution, illumination and fonts, which make it more difficult to detect a logo. To address these issues, we presented a deep learning-based algorithm for logo detection called LogoNet. It includes an hourglass like top-down bottom-up feature extraction network, a spatial attention module and an anchorfree detection head similar to CenterNet. In order to improve performance, in this paper, an extended version of LogoNet is proposed, called—Dual-Attention LogoNet, that exploits different attention mechanisms more efficiently. The incorporated channel-wise and spatial attention modules refine and generate robust and balanced feature maps to predict visual and semantic information more accurately. In addition, we propose a lightweight architecture for both LogoNet and Dual-Attention LogoNet for practical applications. The proposed lightweight architecture significantly reduces the number of network parameters and improves the inference time to address the real-time performance while maintaining accuracy. Furthermore, to address the domain shift problem in practical applications, we also propose an adversarial-learning-based domain adaptation approach, which is easily adaptable to any anchorfree detectors. Our attention-based method shows a 1.8% improvement in accuracy compared to the state-of-the-art detection network on the FlickrLogos-32 dataset. Our proposed domain adaptation approach significantly improves performance by 1.3% mAP compared to direct transfer on the target domain without increasing any labeling cost and network parameters. [ABSTRACT FROM AUTHOR]

The health condition monitoring of rotating machinery can avoid the disastrous failure and guarantee the safe operation. The vibration-based fault diagnosis shows the most attractive character for fault diagnosis of rotating machinery (FDRM). Recently, Lempel-Ziv complexity (LZC) has been investigated as an effective tool for FDRM. However, the LZC only performs single-scale analysis, which is not suitable to extract the fault features embedded in vibrational signal over multiple scales. In this paper, a novel complexity analysis algorithm, called hierarchical Lempel-Ziv complexity (HLZC), was developed to extract the fault characteristics of rotating machinery. The proposed HLZC method considers the fault information hidden in both low-frequency and high-frequency components, resulting in a more accurate fault feature extraction. The superiority of the proposed HLZC method in detecting the periodical impulses was validated by using simulated signals. Meanwhile, two experimental signals were utilized to prove the effectiveness of the proposed HLZC method in extracting fault information. Results show that the proposed HLZC method had the best diagnosing performance compared with LZC and multi-scale Lempel-Ziv complexity methods. [ABSTRACT FROM AUTHOR]

Fast and accurate feature extraction can lay a solid foundation for scene reconstruction and visual odometry. However, this has been rather a difficult problem for the focused plenoptic camera. In this paper, to the best of our knowledge, we first introduce an accurate and fast feature extraction algorithm based on central projection stereo focal stack (CPSFS). Specifically, we propose a refocusing algorithm that conforms to the central projection with regard to the center of main lens, which is more accurate than traditional one. On this basis, the feature is extracted on the CPSFS without calculating dense depth maps and total focus images. We verify the precision and efficiency of the proposed algorithm through simulated and real experiments, and give an example of scene reconstruction based on the proposed method. The experimental results show that our feature extraction algorithm is able to support the feature-based scene reconstruction via focused plenoptic camera. [ABSTRACT FROM AUTHOR]

Recently, demand for handwriting recognition, such as automation of mail sorting, license plate recognition, and electronic memo pads, has exponentially increased in various industrial fields. In addition, in the image recognition field, methods using artificial convolutional neural networks, which show outstanding performance, have been applied to handwriting recognition. However, owing to the diversity of recognition application fields, the number of dimensions in the learning and reasoning processes is increasing. To solve this problem, a principal component analysis (PCA) technique is used for dimensionality reduction. However, PCA is likely to increase the accuracy loss due to data compression. Therefore, in this paper, we propose a line-segment feature analysis (LFA) algorithm for input dimensionality reduction in handwritten text recognition. This proposed algorithm extracts the line segment information, constituting the image of input data, and assigns a unique value to each segment using 3 × 3 and 5 × 5 filters. Using the unique values to identify the number of line segments and adding them up, a 1-D vector with a size of 512 is created. This vector is used as input to machine-learning. For the performance evaluation of the method, the Extending Modified National Institute of Standards and Technology (EMNIST) database was used. In the evaluation, PCA showed 96.6% and 93.86% accuracy with k-nearest neighbors (KNN) and support vector machine (SVM), respectively, while LFA showed 97.5% and 98.9% accuracy with KNN and SVM, respectively. [ABSTRACT FROM AUTHOR]

To accurately measure the critical dimensions of flat parts using machine vision, an inspection method based on the adaptive chord inclination angle progressively screening the segmentation points of graphic elements was proposed in this study. The method doubled the size of the part image using bicubic interpolation, extracted the single-pixel contour with more detailed information, and designed an adaptive step size to obtain the front and back chord inclination angles of the contour. The method of complementing the front and back chord inclination angles was employed to avoid the negative effects of contour jaggedness, thereby obtaining the contour segmentation points after the initial screening. The segmentation points obtained in the initial sieving were divided into different point clusters according to the distance, and the contour, which was segmented by two segmentation points in different point clusters, was fitted using the least squares. The fitting results were evaluated, and all the fitting results were selected using the improved non-maximum suppression (NMS) algorithm to obtain the precisely selected segmentation points of the graphic elements. Consequently, the segmented individual graphic elements were fitted with the segmentation points as constraints to obtain the key dimensions of the closed part. The developed method could accurately find the contour segmentation points, and the relative error was less than 0.6%. [ABSTRACT FROM AUTHOR]

We present an algorithm to find corresponding authors of patents and scientific articles. The authors are given as records in Scopus and the Chinese Patents Database. This issue is known as the record linkage problem, defined as finding and linking individual records from separate databases that refer to the same real-world entity. The presented solution is based on a record linkage framework combined with text feature extraction and machine learning techniques. The main challenges were low data quality, lack of common record identifiers, and a limited number of other attributes shared by both data sources. Matching based solely on an exact comparison of authors' names does not solve the records linking problem because many Chinese authors share the same full name. Moreover, the English spelling of Chinese names is not standardized in the analyzed data. Three ideas on how to extend attribute sets and improve record linkage quality were proposed: (1) fuzzy matching of names, (2) comparison of abstracts of patents and articles, (3) comparison of scientists' main research areas calculated using all metadata available. The presented solution was evaluated in terms of matching quality and complexity on ≈250,000 record pairs linked by human experts. The results of numerical experiments show that the proposed strategies increase the quality of record linkage compared to typical solutions. [ABSTRACT FROM AUTHOR]

Fire-detection technology is of great importance for successful fire-prevention measures. Image-based fire detection is one effective method. At present, object-detection algorithms are deficient in performing detection speed and accuracy tasks when they are applied in complex fire scenarios. In this study, a lightweight fire-detection algorithm, Light-YOLOv5 (You Only Look Once version five), is presented. First, a separable vision transformer (SepViT) block is used to replace several Cross Stage Partial Bottleneck with 3 convolutions (C3) modules in the final layer of a backbone network to enhance both the contact of the backbone network to global information and the extraction of flame and smoke features; second, a light bidirectional feature pyramid network (Light-BiFPN) is designed to lighten the model while improving the feature extraction and balancing speed and accuracy features during a fire-detection procedure; third, a global attention mechanism (GAM) is fused into the network to cause the model to focus more on the global dimensional features and further improve the detection accuracy of the model; and finally, the Mish activation function and SIoU loss are utilized to simultaneously increase the convergence speed and enhance the accuracy. The experimental results show that compared to the original algorithm, the mean average accuracy (mAP) of Light-YOLOv5 increases by 3.3%, the number of parameters decreases by 27.1%, and the floating point operations (FLOPs) decrease by 19.1%. The detection speed reaches 91.1 FPS, which can detect targets in complex fire scenarios in real time. [ABSTRACT FROM AUTHOR]

This paper proposes a robust strategy to select the load identification features, which is based on particle resampling to promote the performance for the successive load identification. Firstly, the sliding window incorporated with the bilateral cumulative sum control chart (CUSUM) method is utilized to obtain the load event. Then, the minimum inner-class variance, using the time-serial data, is introduced to judge the happened time as precise as possible, thus marking the changing point of the state of load for the following feature extraction. Due to the fluctuating data of current and voltage sampled by the monitoring device, the particle resampling method, containing the importance principle, is applied to find the steady and effectiveness point, ensuring that the obtained features have the desired fit with its actual features. The fitness measurement is then carried out by using the 2-D fuzzy theory. Finally, the proposed method was tested on the real household measurements in the labs. The result demonstrates an improvement in obtaining the desired load features when applied to the real household for the following load identification. [ABSTRACT FROM AUTHOR]

Orthogonal transformations, proper decomposition, and the Moore–Penrose inverse are traditional methods of obtaining the output layer weights for an extreme learning machine autoencoder. However, an increase in the number of hidden neurons causes higher convergence times and computational complexity, whereas the generalization capability is low when the number of neurons is small. One way to address this issue is to use the fast iterative shrinkage-thresholding algorithm (FISTA) to minimize the output weights of the extreme learning machine. In this work, we aim to improve the convergence speed of FISTA by using two fast algorithms of the shrinkage-thresholding class, called greedy FISTA (G-FISTA) and linearly convergent FISTA (LC-FISTA). Our method is an exciting proposal for decision-making involving the resolution of many application problems, especially those requiring longer computational times. In our experiments, we adopt six public datasets that are frequently used in machine learning: MNIST, NORB, CIFAR10, UMist, Caltech256, and Stanford Cars. We apply several metrics to evaluate the performance of our method, and the object of comparison is the FISTA algorithm due to its popularity for neural network training. The experimental results show that G-FISTA and LC-FISTA achieve higher convergence speeds in the autoencoder training process; for example, in the Stanford Cars dataset, G-FISTA and LC-FISTA are faster than FISTA by 48.42% and 47.32%, respectively. Overall, all three algorithms maintain good values of the performance metrics on all databases. [ABSTRACT FROM AUTHOR]

The deep learning feature extraction method and extreme learning machine (ELM) classification method are combined to establish a depth extreme learning machine model for wood image defect detection. The convolution neural network (CNN) algorithm alone tends to provide inaccurate defect locations, incomplete defect contour and boundary information, and inaccurate recognition of defect types. The nonsubsampled shearlet transform (NSST) is used here to preprocess the wood images, which reduces the complexity and computation of the image processing. CNN is then applied to manage the deep algorithm design of the wood images. The simple linear iterative clustering algorithm is used to improve the initial model; the obtained image features are used as ELM classification inputs. ELM has faster training speed and stronger generalization ability than other similar neural networks, but the random selection of input weights and thresholds degrades the classification accuracy. A genetic algorithm is used here to optimize the initial parameters of the ELM to stabilize the network classification performance. The depth extreme learning machine can extract high-level abstract information from the data, does not require iterative adjustment of the network weights, has high calculation efficiency, and allows CNN to effectively extract the wood defect contour. The distributed input data feature is automatically expressed in layer form by deep learning pre-training. The wood defect recognition accuracy reached 96.72% in a test time of only 187 ms. [ABSTRACT FROM AUTHOR]

To address the problem of the low recognition rate of time-frequency domain methods gearbox fault identification, a method featuring decision-level fusion of DS evidence theory and GA-BP algorithm was proposed in the present study. Firstly, the fault data of each state of the gearbox was classified, based on which the time-frequency domain features were extracted and 19 significant features have been selected. Secondly, the accuracy of the traditional BP algorithm was compared with that of the GA-BP algorithm. On this basis, it has been concluded that the GA-BP algorithm is highly accurate, and the local diagnostic results obtained by the GA-BP algorithm have been used as the basic probability. Finally, the DS evidence theory is currently used to fuses with the GA. In addition, the final fault identification of the gearbox can be achieved by using the DS evidence theory and the multi-sensor local diagnosis results obtained by the GA-BP algorithm for decision fusion. The results of the simulations and experiments showed that the method proposed has improved accuracy over a single algorithm for fault identification of gearboxes, respectively. [ABSTRACT FROM AUTHOR]

Featured Application: This study proposes a novel cross-channel DWRPCA algorithm for multi-channel pulse signal de-noising. This algorithm can extract features from multiple cycles in each channel with dynamic weighting according to the signal patterns of channels in a single sensor. This algorithm can separate noise from the main frequency band of the input pulse signal. Pulse wave analysis (PWA) has been widely used in the medical field. A novel multi-channel sensor is employed in arterial pulse acquisition and brings richer physiological information to PWA. However, the noise of this sensor is distributed in the main frequency band of the pulse signal, which seriously interferes with subsequent analyses and is difficult to eliminate by existing methods. This study proposes a cross-channel dynamic weighting robust principal component analysis algorithm. A channel-scaled factor technique is used to manipulate the weighting factors in the nuclear norm. This factor can adaptively adjust the weights among the channels according to the signal pattern of each channel, optimizing the feature extraction in multi-channel signals. A series of performance evaluations were conducted, and four well-known de-noising algorithms were used for comparison. The results reveal that the proposed algorithm achieved one of the best de-noising performances in the time and frequency domains. The mean of h1 in the amplitude relative error (ARE) was 23.4% smaller than for the WRPCA algorithm. Moreover, our algorithm could accelerate convergence and reduce the computational time complexity by approximately 34.6%. These results demonstrate the performance and efficiency of the algorithm. Meanwhile, the idea can be extended to other multi-channel physiological signal de-noising and feature extraction fields. [ABSTRACT FROM AUTHOR]

Numerous investigations have been conducted to enhance the motor imagery-based brain–computer interface (BCI) classification performance on various aspects. However, there are limited studies comparing their proposed feature selection framework performance on both objective and subjective datasets. Therefore, this study aims to provide a novel framework that combines spatial filters at various frequency bands with double-layered feature selection and evaluates it on published and self-acquired datasets. Electroencephalography (EEG) data are preprocessed and decomposed into multiple frequency sub-bands, whose features are then extracted, calculated, and ranked based on Fisher's ratio and minimum-redundancy-maximum-relevance (mRmR) algorithm. Informative filter banks are chosen for optimal classification by linear discriminative analysis (LDA). The results of the study, firstly, show that the proposed method is comparable to other conventional methods through accuracy and F1-score. The study also found that hand vs. feet classification is more discriminable than left vs. right hand (4–10% difference). Lastly, the performance of the filter banks common spatial pattern (FBCSP, without feature selection) algorithm is found to be significantly lower (p = 0.0029, p = 0.0015, and p = 0.0008) compared to that of the proposed method when applied to small-sized data. [ABSTRACT FROM AUTHOR]

Research on flourishing public bike-sharing systems has been widely discussed in recent years. In these studies, many existing works focus on accurately predicting individual stations in a short time. This work, therefore, aims to predict long-term bike rental/drop-off demands at given bike station locations in the expansion areas. The real-world bike stations are mainly built-in batches for expansion areas. To address the problem, we propose LDA (Long-Term Demand Advisor), a framework to estimate the long-term characteristics of newly established stations. In LDA, several engineering strategies are proposed to extract discriminative and representative features for long-term demands. Moreover, for original and newly established stations, we propose several feature extraction methods and an algorithm to model the correlations between urban dynamics and long-term demands. Our work is the first to address the long-term demand of new stations, providing the government with a tool to pre-evaluate the bike flow of new stations before deployment; this can avoid wasting resources such as personnel expense or budget. We evaluate real-world data from New York City's bike-sharing system, and show that our LDA framework outperforms baseline approaches. [ABSTRACT FROM AUTHOR]

Critical technique errors are very often performed by patients in the use of Dry Powder Inhalers (DPIs) resulting in a reduction of the clinical efficiency of such medication. Those critical errors include: pure inhalation, non-arming of the device, no exhalation before or after inhalation, and non-holding of breath for 5–10 s between inhalation and exhalation. In this work, an audio-based classification method that assesses patient DPI user technique is presented by extracting the the non-silent audio segments and categorizing them into respiratory sounds. Twenty healthy and non-healthy volunteers used the same placebo inhaler (Bretaris Genuair Inhaler) in order to evaluate the performance of the algorithm. The audio-based method achieved an F1-score of 89.87% in classifying sound events (Actuation, Inhale, Button Press, and Exhale). The significance of the algorithm lies not just on automatic classification but on a post-processing step of peak detection that resulted in an improvement of 5.58% on the F1-score, reaching 94.85%. This method can provide a clinically accurate assessment of the patient's inhaler use without the supervision of a doctor. [ABSTRACT FROM AUTHOR]

Due to the particularity of the jacket structure of offshore platforms and the complexity of the marine environment, there have been few effective localization and autonomous control methods for underwater robots that are designed for cleaning tasks. To improve this situation, a fusion bat algorithm (BA) online optimized fuzzy control method using vision localization was developed based on the constraints of the underwater operational environment. Vision localization was achieved based on images from a catadioptric panoramic imaging system. The features of the pipe edge and the boundary of the area covered by biofouling were obtained by image processing and feature extraction. The feature point chosen as the "highest" point of the boundary was calculated by projection transformation to generate the reference path. The specialized fuzzy controller was designed to drive the robot to track the reference path, and an improved bat algorithm with dynamic inertia weight and differential evolution method was developed to optimize the scale factors of the fuzzy controller online. The control method was simulated and further implemented on an underwater pipe-cleaning robot (UPCR), and the results indicate its rationality and validity. [ABSTRACT FROM AUTHOR]

We propose a local feature descriptor based on moment. Although conventional scale invariant feature transform (SIFT)-based algorithms generally use difference of Gaussian (DoG) for feature extraction, they remain sensitive to more complicated deformations. To solve this problem, we propose MIFT, an invariant feature transform algorithm based on the modified discrete Gaussian-Hermite moment (MDGHM). Taking advantage of MDGHM's high performance to represent image information, MIFT uses an MDGHM-based pyramid for feature extraction, which can extract more distinctive extrema than the DoG, and MDGHM-based magnitude and orientation for feature description. We compared the proposed MIFT method performance with current best practice methods for six image deformation types, and confirmed that MIFT matching accuracy was superior of other SIFT-based methods. [ABSTRACT FROM AUTHOR]