Search

Existing scanners produce paper images with different types of deformations such as noise, rotation and shear. These deformations affect the accuracy of the fingerprinting the document images, which entails utilizing advanced feature extraction operators. Existing feature extractor such as the Uniform Local Binary Patterns (ULBP) has been found to be limited in dealing with the global view of the texture and neglecting useful information about the images. This article presents an Automated Paper Fingerprinting (APF) method that deploys a combination approach for Gabor Filters (GF) and Uniform Local Binary Patterns (ULBP) called the GFULBP operator to cater for both local and global image information during the feature extraction process for higher texture classification accuracy. The APF method is evaluated by a standard dataset of 306 blank paper images derived from pre-existing scanner image dataset from Universiti Kebangsaan Malaysia (UKM) with properties ranges from 50 DPI, 100 DPI, and 150 DPI respectively. The images are captured by a flatbed scanner with 50 DPI, 100 DPI, and 150 DPI resolutions. Each image is represented by four patches that are segmented from specific locations of the image. The test results of the APF show that GFULBP is able to outperform the ULBP alone by 30.68% when the GF has a 5 scale and π/2 orientation degree. This work finds that the integration of Gabor filters and ULBP significantly enhances the feature extraction quality and fingerprinting accuracy. [ABSTRACT FROM AUTHOR]

[Display omitted] • 1. Developed a fast, non-destructive, and highly accurate method for identifying copy paper using spectral fusion technology. • 2. Utilized Raman and FTIR to characterize the "origin-manufacturer-brand" of copy paper found at crime scenes. • 3. Evaluated the impact of different preprocessing methods on the model's ability to distinguish copy paper. • 4. Validated the superiority of spectral fusion technology in enhancing classification accuracy. In order to provide more clues for ongoing investigations and case handling, as well as achieve fast, non-destructive, and accurate identification of copy paper found at crime scenes, this study aims to utilize advanced spectral fusion technology to characterize and identify the three-dimensional features of the "origin-manufacturer-brand" of copy paper. Confocal Raman Microscopic and Fourier transform infrared spectroscopy were employed to collect spectral data from 200 samples from four regions (Shandong, Henan, Shaanxi, Jiangsu). The effects of different preprocessing methods, such as Hilbert transformation and deconvolution, on the model's ability to distinguish were compared. Feature variables were extracted using principal component analysis, and Bayesian discriminant classification models were constructed based on single infrared spectroscopy, Raman spectroscopy, and three types of spectral fusion datasets. By comparing the classification accuracy of different models, the primary fusion based on the full spectrum dataset was selected as the optimal model for the three-dimensional feature classification of copy paper. The accuracy achieved for origin (96%), manufacturer (100%), and brand (100%) was satisfactory, and the classification results were highly accurate. This study provides valuable insights and serves as a reference for its application in forensic science research. [ABSTRACT FROM AUTHOR]

• Qualitative and quantitative detection of amine gases could be achieved by CSA. • A visible detection of beef freshness using the amine-responsive CSA was proposed. • ResNet34 had the best performance for beef freshness detection based on CSA. • T-SNE could further visualize and understand the classification process of DL. This study developed an innovative approach that combines a colourimetric sensor array (CSA) composed of twelve pH-response dyes with advanced algorithms, aiming to detect amine gases and assess the freshness of chilled beef. With the assistance of multivariate statistical analysis, the sensor array can effectively distinguish five amine gases and enable rapid quantification of trimethylamine vapour with a limit of detection (LOD) of 8.02 ppb and visually monitor the fresh levels of chilled beef. Moreover, the utilization of deep learning models (ResNet34, VGG16, and GoogleNet) for chilled beef freshness evaluation achieved an overall accuracy of 98.0 %. Furthermore, t -distributed stochastic neighbour embedding (t -SNE) visualized the feature extraction process and provided explanations to understand the classification process of deep learning. The results demonstrated that applying deep learning techniques in the process of pattern recognition of CSA can help in realizing the rapid, robust, and accurate assessment of chilled beef freshness. [ABSTRACT FROM AUTHOR]

The paper recommender system has provided great convenience for people to obtain knowledge of what they are interested in. Existing recommendation works mainly rely on learning entities' feature representations (network embedding) from the Heterogeneous Information Networks (HINs) through meta-paths. Most of them suffer from the difficulty of designing and selecting meta-paths in HIN. Moreover, changes in papers' captive audiences and users' reading favor in the recent trends are always covered up by long-term trends. To this end, we introduce a multi-attention aware recommendation method, named MARec. Specifically, to efficiently design and select meta-paths, we propose an auxiliary node-driven HIN construction method and combine it with the graph attention network (GAT) to learn the entities' feature representations. To endow the recommendation results with timeliness, we design an attention-aware Bi-directional LSTM (Bi-LSTM) and a compensation mechanism to incorporate the recent trend changes. Furthermore, to take advantage of the importance of different papers/users, we utilize an attention mechanism to capture their importance by adaptively fusing the interactive historical data of those paper/user entities. We use extensive experiments on three real-world datasets to show that our proposed MARec outperforms current representative baselines by 11.49%, 11.40%, and 13.37% on average on three main metrics. • A general heterogeneous information network towards simplifying meta-path design. • Embedding with attention mechanism avoids painstakingly selecting meta-paths. • Feature extraction under multi-time scale greatly improves the recommended results. • MARec demonstrates superior performance on different real-world domain datasets. [ABSTRACT FROM AUTHOR]

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

Breast cancer (BC) continues to be a prominent issue in global public health, emphasizing the need for precise and timely detection. This paper employs a deep learning (DL) approach to introduce an extensive methodology for categorizing histopathology images associated with breast cancer into automated binary classifications. The proposed framework architecture is validated on the standard database which is accessible to the public, called Breast Cancer Histopathological Database (BreakHis). Data augmentation techniques are employed for the pre-processing stage. This paper uses the DenseNet 121 pre-trained model for feature extraction and fully connected layers (FCL) to fine-tune the model further. In this experiment, the highest accuracy of 96.09% is observed with the 100X. The experimental results showed an improvement in accuracy for all the magnification factors compared to the existing works. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the most prevalent forms of cancer around the world. Initial diagnosis relies on visual assessment of the affected area, followed by detailed dermoscopic analysis. The development of an automated system for classifying skin lesions poses a considerable challenge due to inherent noise and subtle variability in lesion images. Deep convolutional neural networks have demonstrated exceptional proficiency in image classification tasks spanning diverse domains. This paper demonstrates an end-to-end classification architecture built on top of transfer learning with data augmentation. The proposed model capitalizes on pre-trained architectures such as DenseNet, VGG-16, and Inception for feature extraction, and employs fully connected dense layers for categorizing seven distinct types of lesions. Several data augmentation techniques are also used to handle the class imbalance problem. Extensive experimentation encompassing various hyperparameters, imbalanced data scenarios, and balanced datasets was conducted to refine the automated skin lesion system. The proposed approach achieved a notable accuracy of 98% on the HAM10000 dataset and 94% on the ISIC-2019 dataset. Importantly, the experimental findings surpassed the performance of current state-of-the-art models for lesion classification. Furthermore, this paper examines the impact of class imbalance and data augmentation on the model's accuracy. [ABSTRACT FROM AUTHOR]

Human activity recognition(HAR) is an important research focus in ubiquitous computing. It has been widely applied in various domains, such as smart homes, healthcare assistance, and sports training. Accurate human activity recognition directly impacts the performance of downstream tasks. Existing methods for human activity recognition primarily rely on extracting temporal or spatial features from the data. These features are used for the task of human activity recognition. The existing methods mainly use CNN or RNN models to model the Euclidean correlations among spatially adjacent sensors or channels. However, non-Euclidean pairwise correlations among all sensors or channels are even critical for accurate classification, which has been ignored by the existing methods. In this paper, we incorporate fine-grained spatial structural data into the model to overcome these limitations. A novel deep learning model for human activity recognition is proposed, which is called the fine-grained data-oriented Spatial-Temporal Graph Transformer network (STGT). The introduction of the STGT model can eliminate the limitations of existing spatial feature extraction methods by leveraging a novel data organization approach proposed in this study. This model enhances the spatial features within the time feature extraction module for effective spatio-temporal feature extraction. We conducted experiments on four large-scale real-world HAR datasets to evaluate its performance. The experimental results demonstrate the superiority of our method over state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

• The increase of decoding precision of motor imaging EEG signal. • The hybrid TCN and ViT method achieves good results. • A shared convolution strategy and a dual-branching strategy. Brain-computer interface (BCI) is a technology that directly connects signals between the human brain and a computer or other external device. Motor imagery electroencephalographic (MI-EEG) signals are considered a promising paradigm for BCI systems, with a wide range of potential applications in medical rehabilitation, human–computer interaction, and virtual reality. Accurate decoding of MI-EEG signals poses a significant challenge due to issues related to the quality of the collected EEG data and subject variability. Therefore, developing an efficient MI-EEG decoding network is crucial and warrants research. This paper proposes a loss joint training model based on the vision transformer (VIT) and the temporal convolutional network (EEG-VTTCNet) to classify MI-EEG signals. To take advantage of multiple modules together, the EEG-VTTCNet adopts a shared convolution strategy and a dual-branching strategy. The dual-branching modules perform complementary learning and jointly train shared convolutional modules with better performance. We conducted experiments on the BCI Competition IV-2a and IV-2b datasets, and the proposed network outperformed the current state-of-the-art techniques with an accuracy of 84.58% and 90.94%, respectively, for the subject-dependent mode. In addition, we used t-SNE to visualize the features extracted by the proposed network, further demonstrating the effectiveness of the feature extraction framework. We also conducted extensive ablation and hyperparameter tuning experiments to construct a robust network architecture that can be well generalized. [ABSTRACT FROM AUTHOR]

Pattern recognition based on network connections has recently been applied to the brain-computer interface (BCI) research, offering new ideas for emotion recognition using Electroencephalogram (EEG) signal. However unified standards are currently lacking for selecting emotional signals in emotion recognition research, and potential associations between activation differences in brain regions and network connectivity pattern are often being overlooked. To bridge this technical gap, a data-driven signal auto-segmentation and feature fusion algorithm (DASF) is proposed in this paper. First, the Phase Locking Value (PLV) method was used to construct the brain functional adjacency matrix of each subject, and the dynamic brain functional network across subjects was then constructed. Next, tucker decomposition was performed and the Grassmann distance of the connectivity submatrix was calculated. Subsequently, different brain network states were distinguished and signal segments under emotional states were automatically extract using data-driven methods. Then, tensor sparse representation was adopted on the intercepted EEG signals to effectively extract functional connections under different emotional states. Finally, power-distribution related features (differential entropy and energy feature) and brain functional connection features were effectively combined for classification using the support vector machines (SVM) classifier. The proposed method was validated on ERN and DEAP datasets. The single-feature emotion classification accuracy of 86.57 % and 87.74 % were achieved on valence and arousal dimensions, respectively. The accuracy of the proposed feature fusion method was achieved at 89.14 % and 89.65 %, accordingly, demonstrating an improvement in emotion recognition accuracy. The results demonstrated the superior classification performance of the proposed data-driven signal auto-segmentation and feature fusion algorithm in emotion recognition compared to state-of-the-art classification methods. • A data-driven approach to capturing signals when emotions are triggered. Network parameters for different subjects were obtained through PLV calculations, forming a tensor. Tucker decomposition was then used to detect the brain network state of EEG signals, automatically identifying EEG segments during emotional activation. This method effectively screens signals in the state of emotional arousal for improved emotion recognition. • Using tensor to extract brain functional connectivity patterns under emotional states. Through tensor sparse representation, the functional brain connectivity network can be obtained to represent the emotional excitation state, and then the network connection features can be extracted. • Fusion features offer richer compensatory information for emotion recognition by combining activation difference features with connectivity features. [ABSTRACT FROM AUTHOR]

The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The huge variety of trees in varied topography severely hinders tree counting models to perform well. The purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees. Our method, termed as AdaTreeFormer, contains one shared encoder with a hierarchical feature extraction scheme to extract robust features from the source and target domains. It also consists of three subnets: two for extracting self-domain attention maps from source and target domains respectively and one for extracting cross-domain attention maps. For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains. We also adopt adversarial learning into the framework to further reduce the gap between source and target domains. Our AdaTreeFormer is evaluated on six designed domain adaptation tasks using three tree counting datasets, i.e. Jiangsu, Yosemite, and London. Experimental results show that AdaTreeFormer significantly surpasses the state of the art, e.g. in the cross domain from the Yosemite to Jiangsu dataset, it achieves a reduction of 15.9 points in terms of the absolute counting errors and an increase of 10.8% in the accuracy of the detected trees' locations. The codes and datasets are available at https://github.com/HAAClassic/AdaTreeFormer. [ABSTRACT FROM AUTHOR]

Auto-semantic segmentation is important for robots on unstructured and dynamic environments like planets where ambient conditions cannot be controlled and the scale is larger than that found indoors. Current learning-based methods have achieved breathtaking improvements on this topic. For onboard applications, however, all those methods still suffer from huge computational costs and are difficult to deploy on edge devices. In this paper, unlike previous transformer-based SOTA approaches that heavily relied on complex design, we proposed Light4Mars, a lightweight model with minimal computational complexity while maintaining high segmenting accuracy. We designed a lightweight squeeze window transformer module that focuses on window-scale feature extraction and is more effective in learning global and local contextual information. The aggregated local attention decoder is utilized to fuse semantic information at different scales, especially for unstructured scenes. Since there are few all-terrain datasets for semantic segmentation of unstructured scenes like Mars, we built a synthetic dataset SynMars-TW, referencing images collected by the ZhuRong rover on the Tianwen-1 mission and the Curiosity rover. Extensive experiments on SynMars-TW and the real Mars dataset, MarsScapes show that our approach achieves state-of-the-art performance with favorable computational simplicity. To the best of our knowledge, the proposed Light4Mars-T network is the first segmentation model for Mars image segmentation with parameters lower than 0.1M. Code and datasets are available at https://github.com/CVIR-Lab/Light4Mars. [ABSTRACT FROM AUTHOR]

This paper proposes a three-stage online deep learning model for time series based on the ensemble deep random vector functional link (edRVFL). The edRVFL stacks multiple randomized layers to enhance the single-layer RVFL's representation ability. Each hidden layer's representation is utilized for training an output layer, and the ensemble of all output layers forms the edRVFL's output. However, the original edRVFL is not designed for online learning, and the randomized nature of the features is harmful to extracting meaningful temporal features. In order to address the limitations and extend the edRVFL to an online learning mode, this paper proposes a dynamic edRVFL consisting of three online components, the online decomposition, the online training, and the online dynamic ensemble. First, an online decomposition is utilized as a feature engineering block for the edRVFL. Then, an online learning algorithm is designed to learn the edRVFL. Finally, an online dynamic ensemble method, which can measure the change in the distribution, is proposed for aggregating all layers' outputs. This paper evaluates and compares the proposed model with state-of-the-art methods on sixteen time series. [ABSTRACT FROM AUTHOR]

Despite the good results that have been achieved in unimodal segmentation, the inherent limitations of individual data increase the difficulty of achieving breakthroughs in performance. For that reason, multi-modal learning is increasingly being explored within the field of remote sensing. The present multi-modal methods usually map high-dimensional features to low-dimensional spaces as a preprocess before feature extraction to address the nonnegligible domain gap, which inevitably leads to information loss. To address this issue, in this paper we present our novel I mbalance K nowledge- D riven Multi-modal Net work (IKD-Net) to extract features from multi-modal heterogeneous data of aerial images and LiDAR directly. IKD-Net is capable of mining imbalance information across modalities while utilizing a strong modal to drive the feature map refinement of the weaker ones in the global and categorical perspectives by way of two sophisticated plug-and-play modules: the G lobal K nowledge- G uided (GKG) and C lass K nowledge- G uided (CKG) gated modules. The whole network then is optimized using a joint loss function. While we were developing IKD-Net, we also established a new dataset called the N ational Agriculture Imagery Program and 3 D Elevation Program C ombined dataset in California (N3C-California) , which provides a particular benchmark for multi-modal joint segmentation tasks. In our experiments, IKD-Net outperformed the benchmarks and state-of-the-art methods both in the N3C-California and the small-scale ISPRS Vaihingen dataset. IKD-Net has been ranked first on the real-time leaderboard for the GRSS DFC 2018 challenge evaluation until this paper's submission. Our code and N3C-California dataset are available at https://github.com/wymqqq/IKDNet-pytorch. [ABSTRACT FROM AUTHOR]

The multispectral (MS) and the panchromatic (PAN) images represent complementary and synergistic spatial spectral information, how to make optimal use of the advantages of them has become a hot research topic. This paper proposes a selectable Transformer and Gist CNN network (STGC-Net). It designs a subspace similar recombination module (SSR-Module) based on non-negative matrix factorization (NMF) and the self-attention mechanism for feature decomposition. This can alleviate the redundant information of multi-modal data and extract their own singular and common features. Considering that the MS and the PAN images exhibit different advantageous properties, a selectable self-attention spectral feature extraction module (S 3 FE-Module) and a multi-stream Gist spatial feature extraction module (MGSFE-Module) are proposed for the different singular features. The former can refine the Transformer's input and simultaneously characterize the sequence information between channels for the MS image. The latter introduces the positional relationship between local features while extracting spatial features for the PAN image, thereby improving the accuracy of scene classification. Experimental results indicate that the proposed method performs better than the other methods. The relevant code of this paper is provided at: https://github.com/ru-willow/ST-GC-Net. • A subspace similar recombination module is proposed. • The selectable self-attention spectral feature extraction module is designed. • The multi-stream Gist spatial feature extraction module is introduced. [ABSTRACT FROM AUTHOR]

Accurate cloud and shadow detection is a crucial prerequisite for optical remote sensing image analysis and application. Multi-temporal-based cloud and shadow detection methods are a preferable choice to detect clouds in complex scenes (e.g., thin clouds, broken clouds and clouds with interference from artificial surfaces with high reflectivity). However, such methods commonly require cloud-free reference images, and this may be difficult to achieve in time-series data since clouds are often prevalent and of varying spatial distribution in optical remote sensing images. Furthermore, current multi-temporal-based methods have limited feature extraction capability and rely heavily on prior assumptions. To address these issues, this paper proposes a Siamese network (Siamnet) for cloud and shadow detection based on Time-Series cloudy Images, namely TSI-Siamnet, which consists of two steps: 1) low-rank and sparse component decomposition of time-series cloudy images is conducted to construct a composite reference image to cope with dynamic changes in the cloud distribution in time-series images; 2) an extended Siamnet with optimal difference calculation module (DM) and multi-scale difference features fusion module (MDFM) is constructed to extract reliable disparity features and alleviate semantic information feature dilution during the decoder part. TSI-Siamnet was tested extensively on seven land cover types in the well-known Landsat 8 Biome dataset. Compared to six state-of-the-art methods (including four deep learning-based methods and two classical non-deep learning-based methods), TSI-Siamnet produced the best performance with an overall accuracy of 95.05% and MIoU of 84.37%. In three more challenging experiments, TSI-Siamnet showed enhanced detection of thin and broken clouds and greater anti-interference to highly reflective surfaces. TSI-Siamnet provides a novel strategy to explore comprehensively the valid information in time-series cloudy images and integrate the extracted spectral-spatial–temporal features for reliable cloud and shadow detection. [ABSTRACT FROM AUTHOR]

Skin, as the crucial component of aircraft, should be milled along the edges of the frame to ensure the mounting accuracy. Traditional skin milling uses visual measurement and offline planning to generate a machining path that corresponds to the overall shape of the frame edge. To enhance adaptability and processing efficiency, an online planning method is proposed. However, it imposes greater demands on the computational efficiency, accuracy, and stability of the algorithm. In this paper, a real-time path planning method based on frame feature extraction and chronological feature optimization is proposed for the milling of attached frame-skin. The method uses a line laser to scan the surface features of both skin and frame structures, facilitating real-time extraction of feature structures. Periodic calculations of position and posture are conducted based on the time series, and a non-fitting method is used to generate a smooth and high-precision machining trajectory. The efficacy in achieving real-time path planning for the milling module is verified by experiments on prototypes of aircraft skin. The algorithm exhibits a duration of less than 8 ms in a run cycle, while maintaining accuracy within ± 0.5 mm. • Propose a real-time extraction method of the position and posture characteristics of the attached frame and skin structure. • Propose a path planning method using chronological features to improve path point continuity and establish a processing path. • The algorithm achieved a path planning period of less than 8 ms and maintained tracking path accuracy within ±0.5 mm. [ABSTRACT FROM AUTHOR]

Online fault diagnostics is a crucial consideration for fuel cell systems, particularly in mobile applications, to limit downtime and degradation, and to increase lifetime. Guided by a critical literature review, in this paper an overview of Health management systems classified in a scheme is presented, introducing commonly utilised methods to diagnose FCs in various applications. In this novel scheme, various Health management system methods are summarised and structured to provide an overview of existing systems including their associated tools. These systems are classified into four categories mainly focused on model-based and non-model-based systems. The individual methods are critically discussed when used individually or combined aimed at further understanding their functionality and suitability in different applications. Additionally, a tool is introduced to evaluate methods from each category based on the scheme presented. This tool applies the technique of matrix evaluation utilising several key parameters to identify the most appropriate methods for a given application. Based on this evaluation, the most suitable methods for each specific application are combined to build an integrated Health management system. • HMS methods for FC diagnosis are introduced and classified into three main categories. • New scheme is introduced categorising HMS methods by approach and characteristics. • Matrix evaluation is introduced rating HMS methods for individual FC application. • Method properties affect classification results requiring evaluation for each use case. • For FCs, feature extraction, reduction and fault classification methods are chosen. [ABSTRACT FROM AUTHOR]

Due to the coupling of multiple physical fields inside proton exchange membrane fuel cell (PEMFC) and the complex and changeable external application scenarios, the faults of PEMFC system greatly affects its engineering application. The paper proposes an ensemble learning-based fault diagnosis method for PEMFC systems, utilizing five distinct algorithms to develop an integrated ensemble classifier for fault detection. The original sample dataset collected from fuel cells undergoes a process of deep feature extraction to obtain a composite feature sample dataset, which is then inputted into an ensemble classifier to establish a fault diagnosis model. The experimental data of four kinds of faults of 80 W fuel cell test bench, EC fuel cell system and 50 W water-cooled fuel cell test bench are analyzed by using this classification model. The results show that the accuracy and generalization of the ensemble learning algorithm for different fault diagnosis of PEMFC system in different application environments are verified. • Adopt multiple classification algorithms for fault modeling and diagnosis. • Good applicability to different faults is shown in different test scenarios. • Compared with a single algorithm, it has higher fault identification accuracy. [ABSTRACT FROM AUTHOR]

Feature extraction and matching play integral roles in autonomous vision navigation. As a typical morphological feature, craters can be used as navigation landmarks. However, the spin of small bodies introduces substantial variations in illumination and viewing angles within acquired images, thereby posing challenges to feature extraction and matching algorithms. Addressing these challenges, a deep learning-based approach emerges as pivotal in mitigating the limitations of existing navigation algorithms. This paper presents an algorithm designed to segment noteworthy craters and irregular regions on such small bodies, thereby furnishing crucial autonomous navigation data for missions involving uncharted terrains. By seamlessly integrating deep learning techniques with conventional computer vision-based feature description methods, the algorithm achieves matching segmentation results of noteworthy precision. The experimental results show that the algorithm has better results compared to the existing mainstream segmentation networks. And it can achieve the accurate matching of segmentation results. • Accurate segmentation of small-body craters via deep-learning Algorithms. • Gradient descriptor construction method based on segmentation results. • The proposed method has viewpoint, illumination, scale, and rotation invariance. [ABSTRACT FROM AUTHOR]

One important aspect of human behavior understanding is the recognition and monitoring of daily activities. An accurate activity recognition system can improve the quality of life in many key areas. The multi-metric feature extraction and DeepForest classifier designed in this paper effectively had solved the problems of incomprehensive feature extraction and insufficient classifier accuracy. First, this paper extracts a total of 450 dimensional feature vectors using mean, variance, maximum, skewness, minimum, kurtosis, regression of independent variables and sample entropy as feature indicators, so that the features of the original vectors can be presented comprehensively. The dimensionality of the feature set is too large, so PCA is used to reduce the dimensionality of the high-dimensional feature vector. After studying the relationship between the dimensionality reduction and the cumulative contribution rate, it is concluded that the cumulative contribution rate reaches 90% when the dimensionality is 15, which can retain the original features better. Then DeepForest was used as the classifier, and the reduced-dimensional feature set was used as the sample set to divide the training set and test set by 3:1. The model was tested on the test set after training, and the classification accuracy of the test set was 98.202%. Six classifiers, GaussianNB, SVM, K-NN, XGBoost, RandomForest and DecisionTree, were selected as the control experimental group, of which only the RandomForest model reached 97%, while the rest of the control models did not achieve 95% effect, indicating that DeepForest was more accurate in classifying human activities. Next, the generalisation ability of the DeepForest classifier was assessed using Monte Carlo Cross Validation (MCCV), K-fold and its confusion matrix. The MCCV validation used 50% of the data as the training set and 30% of the data as the test set, and set the number of splits to 10, resulting in a mean accuracy of 98.227%. The size of K in the K-fold validation was determined to be 8 based on the number of people conducting the human activity experiment, and the final mean accuracy value obtained was 97.790%. The combined confusion matrix from the K-fold validation (which aggregates the confusion matrix for each classification result) was calculated, and the results showed that the highest accuracy reached 100% for A9 and A14 classifications, where A5 and A10, A15 and A10, A12 and A5 were more likely to be confused, with the highest error rate for A5 classification, which was 4.167%, and the rest of the activity classifications were better. [ABSTRACT FROM AUTHOR]

Automatic identity recognition from ear images is an active research topic in the biometric community. The ability to secretly acquire images of the ear remotely and the stability of the ear shape over time make this technology a promising alternative for surveillance, authentication, and forensic applications. In recent years, significant research has been conducted in this area. Nevertheless, challenges remain that limit the commercial use of this technology. Several phases of the ear recognition system have been studied in the literature, from ear detection, normalization, and feature extraction to classification. This paper reviews the most recent methods used to describe and classify biometric features of the ear. We propose a first taxonomy to group existing approaches to ear recognition, including 2D, 3D, and combined 2D and 3D methods, as well as an overview of historical advances in this field. It is well known that data and algorithms are the essential components in biometrics, particularly in-ear recognition. However, early ear recognition datasets were very limited and collected in laboratory with controlled environments. With the wider use of deep neural networks, a considerable amount of training data has become necessary if acceptable ear recognition performance is to be achieved. As a consequence, current ear recognition datasets have increased significantly in size. This paper gives an overview of the chronological evolution of ear recognition datasets and compares the performance of conventional vs. deep learning methods on several datasets. We proposed a second taxonomy to classify the existing databases, including 2D, 3D, and video ear datasets. Finally, some open challenges and trends are debated for future research. [ABSTRACT FROM AUTHOR]

• A research article on detection and classification of various types of disfluencies such as Interjection, Sound Repetition, Word Repetition, Phrase Repetition, Revision and Prolongation is presented. • Various feature extraction techniques have been discussed for extracting meaningful information about the speech signals. • Various Machine learning algorithms have studied and analyzed to detect and classify the disfluencies in speech. • Various future research challenges in the present research are highlighted. Speech plays a vital role in communication, from expressing oneself, to utilizing speech-based platforms, speech is a necessity. Any disruption in speech is referred to as disfluency, and can impact one's quality of life. This paper presents an experimental study on various techniques for the detection and classification of speech disfluencies. Six different types of disfluencies are examined in this paper, namely Interjection, Sound Repetition, Word Repetition, Phrase Repetition, Revision and Prolongation (6 classes). However, this paper also goes a step further by including the clean speech signals as an added class alongside the six disfluencies, thereby making this work more robust with 7 classes. Various machine learning approaches have been investigated on the University College London Archive of Stuttered Speech (UCLASS) dataset; a standard disfluency dataset generated by University College London (UCL). Five different feature extraction techniques viz. Mel Frequency Cepstral Coefficients (MFCC), Linear Predictive Cepstral Coefficients (LPCC), Gammatone Frequency Cepstral Coefficients (GFCC), Mel-filterbank energy features, and Spectrograms have been used. Comparative analysis of various classifiers shows that MFCC, GFCC, and Spectrograms achieved greater than 90% accuracy on both 6 and 7 classes with the kNN classifier. As a future scope to this study, the authors aim to focus on tackling the challenges of detecting multiple disfluencies present simultaneously in a speech sample. [ABSTRACT FROM AUTHOR]

Diamond wire sawing is one of the key technologies for wafering in the semiconductor industry. The transverse vibration of the wire during sawing will generate additional displacement that not only reduces the as-cut wafer quality but increases the critical adhesion gap between the wires, which is an important factor limiting the development of diamond wire slicing technology toward narrower kerf loss and thinner as-cut wafer. The vibration measurement of the diamond wire provides an indispensable test basis for its vibration control. Therefore, a machine vision-based transverse vibration measurement method of diamond wire is developed in this paper. The approximate edge position of the wire in the image midline is obtained to crop the region of interest in the image by using the maximum continuous same-directional pixel gradient algorithm and thus reduce the computing time. The wire edges in the image are accurately extracted by an adaptive image segmentation method proposed based on the image histogram. According to the surface topography characteristics of diamond wire, a feature extraction algorithm based on the multiple inward line fitting using the least square method is proposed, which can effectively detect the position of the inner diameter boundary of the diamond wire. Accordingly, the equation of the central axis of the wire in the image is obtained to realize the transverse vibration detection of the diamond wire. To conclude, a diamond wire vibration measurement experiment is conducted and the machine vision detection results are compared with the vibration displacement measured by the accelerometer at the same position of the wire end. The results show that the measurement error of the machine vision vibration inspection is generally small for the different types of diamond wires and the different frequencies of the wire transverse vibration, which means that the measurement method proposed in this paper has good accuracy, and applicability, and robustness. • An adaptive image segmentation method based on image histogram is presented to extract outer contour edges of diamond wire. • A feature extraction algorithm based on multiple inward line fitting is proposed to detect diamond wire inner boundaries. • A machine vision-based vibration measurement method of wire vibration with good accuracy, applicability, and robustness is developed. [ABSTRACT FROM AUTHOR]

With the scale expansion of industrial processes, safety has become one of its important links and the requirements for safety monitoring are getting higher. How to realize timely and effective fault diagnosis, especially for incipient faults, has attracted more discussion and research. This paper proposes a novel pattern classification integrated global−local preserving projections (GLPP) and improved adaptive rank-order morphological filter (IAROMF) for fault diagnosis. First, in order to preserve the global manifold information and local manifold information of the data, GLPP is introduced to extract the features of the data to obtain the test signal and the template signal. Second, AROMF transformation is performed on the test signal and template signal to obtain the output trend feature. Third, as the pattern matching by Euclidean distance-based AROMF has the restriction of sequence timing and the feature points need to be strictly corresponding, the Weighted Dynamic Time Warping (WDTW) distance is used to calculate the total error of iteration between the template trend and the output trend. In order to prove the effectiveness of the method proposed in this paper, a case study was carried out on the Tennessee Eastman (TE) process. The experiment results illustrated that the novel pattern classification method proposed in this paper has higher diagnostic accuracy than other fault diagnosis methods, especially for incipient faults. [ABSTRACT FROM AUTHOR]

Voice cloning methods have been used in a range of ways, from customized speech interfaces for marketing to video games. Current voice cloning systems are smart enough to learn speech characteristics from a few samples and produce perceptually unrecognizable speech. These systems pose new protection and privacy risks to voice-driven interfaces. Fake audio has been used for malicious purposes and is difficult to classify what is real and fake during a digital forensic investigation. This paper reviews the issue of deep-fake audio classification and evaluates the current methods of deep-fake audio detection for forensic investigation. Audio file features were extracted and visually presented using MFCC, Mel-spectrum, Chromagram, and spectrogram representations to further study the differences. Harnessing the different deep learning techniques from existing literature were compared using five iterative tests to determine the mean accuracy and the effects thereof. The results showed a Custom Architecture gave better results for the Chromagram, Spectrogram, and Me-Spectrum images and the VGG-16 architecture gave the best results for the MFCC image feature. This paper contributes to further assisting forensic investigators in differentiating between synthetic and real voices. [ABSTRACT FROM AUTHOR]

Speech is one of the most promising features that reflects the underlying emotion of a human being. There are some measurable parameters in speech signals that reveal a persons affective state. Speech Emotion Recognition (SER) is a process of identifying the emotional elements in communication regardless of contextual relevance. Leveraging studies have taken place in this area. This paper proposes an ensemble model to automatically classify emotion from speech signals to one among the seven emotional classes neutral, calm, angry, sad, happy, fear, disgust, and surprised. In this work, speech spectral features have been extracted using Mel Frequency Cepstral Coefficient (MFCC). An emotion classification model based on 2-Dimensional Convolutional Neural Networks (2D-CNN) and eXtreme Gradient Boosting (XG-Boost) is proposed in this paper. This work also compares the performance of the proposed ensemble model with baseline models and other ensemble models. The accuracy of each model on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset is computed and the proposed model shows maximum accuracy in classifying emotions. [ABSTRACT FROM AUTHOR]

Understanding the rules of grammar and linguistic features is essential to understanding the context of a language, which helps to understand that language. Similarly, for Natural Language processing, the linguistic feature allows understanding of the language. This paper introduced how Coreference, Word-sense, and Semantic knowledge (CWS) of linguistic features work. It would improve the Natural Language Understanding (NLU) and Natural Language Processing (NLP) tasks of any NLP model and NLP applications (either existing or new). This paper proposed a CWS pipeline method to enhance the efficiency and performance of NLP applications like text summarization, information retrieval, question-answer, machine reading comprehension, etc. The proposed CWS pipeline model used a pre-trained CoNLL-2012 coreference dataset extracted from the famous Ontonotes-5.0 dataset for the English language. The model implementation is done in Python language. The performance evaluation is done using the standard CoNLL-2012 coreference dataset for the English language. The coreference marked output is evaluated against the manually tagged gold standard dataset. The proposed CWS pipeline model gives 78.98% of the average F1 score on the MUC metric, 1.78% higher than the previous models' top result. CWS pipeline model performs better than existing models. [ABSTRACT FROM AUTHOR]

Data security has become a basic need in today's world as it shifts more and more toward an all-online mode of operation. All sorts of data and information are now passed from one entity to another over a variety of transmission channels as well as stored on virtual online repositories, and a large chunk of that information is highly private. Over this stream of technological advancements, various data security techniques like encryption, data hiding, etc. have been developed to provide security while transmitting or storing data. This paper proposes an approach to hiding one image inside another image by using CNN in for feature extraction and processing. The proposed model works on the principles of the auto-encoder architecture and is made up of two modules one of which is responsible for the task of processing the secret image and extracting n features and the incorporating those features in the cover image ion such a manner that the cover image retains its original visual qualities and also the secret image gets hidden in it, that module is the Hiding network/Encoder. The other part of this network is the one responsible to then extract the hidden secret image and them create back to its original, this paper is the Reveal network/Decoder. The proposed model is implemented on ImageNet and Pascal-VOC datasets with images of different sizes. In order to judge the models ability to hide the image and to extract is back, PSNR and SSIM are used as performance evaluation Metrics. [ABSTRACT FROM AUTHOR]

The objective of this study is to test the applicability of Mechanomyographic (MMG) sensors for the diagnosis of Carpal Tunnel Syndrome (CTS) as well as for the follow-up of the post-surgical evolution. After reviewing the literature, three types of MMG sensors (force sensor, accelerometer and infrared) had been selected to compare with the Electromyographic (EMG) signal widely used in clinical evaluation. Three tests (two static and one dynamic) were then defined to evaluate thenar atrophy and thumb opposition strength as well as grip strength. This paper makes a description of the tests that had been carried out, starting from the procedure implemented for the application of the sensors and ending at the method used for sensor readout. Preliminary results obtained from a sample of twelve volunteers, which includes one with CTS surgery performed less than six months ago, are promising namely those from the measurement of thumb opposition strength. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a progressive neurodegenerative disease. Early detection and intervention are crucial in preventing the progression of AD. To achieve efficient and scalable AD auto-detection based on structural Magnetic Resonance Imaging (sMRI), a lightweight neural network using multi-slice sMRI is proposed in this paper. The backbone for feature extraction is based on ShuffleNet V1 architecture, which is effective for overcoming the limitations posed by limited sMRI data and resource-restricted devices. In addition, we incorporate Efficient Channel Attention (ECA) to capture cross-channel interaction information, enabling us to effectively enhance features of disease associated brain regions. To optimize the model, we employ both cross entropy loss and triplet loss functions to constrain the predicted probabilities to the ground-truth labels, and to ensure appropriate representation of distances between different classes in the learned features. Experimental results show that the classification accuracies of our method for AD vs. CN, AD vs. MCI, and MCI vs. CN classification tasks are 95.00%, 87.50%, and 85.62% respectively. Our method utilizes only 3.42 M parameters and 6.08G FLOPs, while maintaining a comparable level of performance compared to the other 5 latest lightweight methods. This model design is computationally efficient, allowing it to process large amounts of data quickly and accurately in a timely manner. Additionally, it has the potential to advance the intelligent detection of Alzheimer's disease on devices with limited computing capabilities. [ABSTRACT FROM AUTHOR]

To detect the oil leakage problem of the power transformer in time and guarantee the normal operation of the power system, this paper proposes a lightweight-attention YOLOv8s, called LA_YOLOv8s, for oil leakage detection in the power transformer. First, the idea of lightweight structure + attention is used to redesign the backbone and neck of the original network respectively, which greatly reduces the number of parameters and calculation amount, but also retains strong feature extraction ability. Second, the dynamic head frame Dyhead is used to improve the representation ability of the detection head. Finally, the Wise-IoU bounding box loss function with a dynamic non-monotonic focusing mechanism is used to further improve the overall performance of the model by balancing the learning of high and low-quality samples. Using a self-constructed outdoor power transformer oil leakage dataset for training and testing, the results show that compared with the original model, the attention of LA_YOLOv8s becomes focused, enabling the network to detect oil leaks in power transformers better. LA_YOLOv8s greatly reduces the number of parameters and computation, while maintaining the same detection performance as the original network, which is conducive to engineering deployment. • The backbone and neck of YOLOv8s are redesigned. • The Dyhead is introduced to enhance the detection capability of the head network. • Introduced Wise-IoU to trade off the learning between low-quality and high-quality samples better. • Parameters and computation drop by 55.9% and 36.9%, respectively, with less than 1% change in precision, recall, and mAP. • A visualization algorithm is used to preliminarily validate the reliability of the model. [ABSTRACT FROM AUTHOR]

Human age and gender prediction from facial images has garnered significant attention due to its importance in various applications. Traditional models struggle with large-scale variations in unfiltered images. Convolutional Neural Networks (CNNs) have emerged as effective tools for facial analysis due to their robust performance. This paper presents a novel CNN approach for robust age and gender classification using unconstrained real-world images. The CNN architecture includes convolution, pooling, and fully connected layers for feature extraction, dimension reduction, and mapping to output classes. Adience and UTKFace datasets were utilized, with the best training and testing accuracies achieved using an 80% training and 20% testing data split. Robust image pre-processing and data augmentation techniques were applied to handle dataset variations. The proposed approach outperformed existing methods, achieving age prediction accuracies of 86.42% and 81.96%, and gender prediction accuracies of 97.65% and 96.32% on the Adience and UTKFace datasets, respectively. [ABSTRACT FROM AUTHOR]

Diagnosis of incipient faults of metro train bearings is a difficult problem under the double masking of strong wheel-rail impact interference and background noise. A novel feature extraction method using improved complementary complete local mean decomposition with adaptive noise (ICCELMDAN) and mixture correntropy-based adaptive feature enhancement (AFE) is proposed in this paper. The ICCELMDAN method uses a proposed complementary adaptive noise-assisted iterative sifting method to improve its anti-mixing and anti-splitting performance, and then can extract the complete feature from faulty bearing signals under strong background noise. The AFE method adaptively obtains the optimal parameters of mixture correntropy (MC) by employing a newly developed fault energy of mixture correntropy as the objective function in the marine predators algorithm (MPA), and can enhance the weak fault characteristic signal under strong wheel-rail impact interferences. The proposed method effectively combines the complete feature extraction capability of ICCELMDAN and the powerful feature enhancement capability of AFE, which can accurately diagnose the weak faults of metro train bearings under strong wheel-rail impact interferences in simulated and practical scenarios. Furthermore, it outperforms the existing methods in completeness of feature extraction, diagnosis accuracy and robustness from the comparative studies. • Present a complementary adaptive noise-assisted iterative sifting method. • Enhance the impulse interference suppress adaptability by a mixture correntropy based AFE method. • Extract complete feature of incipient bearing fault by a proposed ICCELMDAN method. • Diagnose the incipient faults of metro bearing under strong wheel-rail interference and background noise. [ABSTRACT FROM AUTHOR]

Nowadays, for controlling crime, surveillance cameras are typically installed in all public places to ensure urban safety and security. However, automating Human Activity Recognition (HAR) using computer vision techniques faces several challenges such as lowlighting, complex spatiotemporal features, clutter backgrounds, and inefficient utilization of surveillance system resources. Existing attempts in HAR designed straightforward networks by analyzing either spatial or motion patterns resulting in limited performance while the dual streams methods are entirely based on Convolutional Neural Networks (CNN) that are inadequate to learning the long-range temporal information for HAR. To overcome the above-mentioned challenges, this paper proposes an optimized dual stream framework for HAR which mainly consists of three steps. First, a shots segmentation module is introduced in the proposed framework to efficiently utilize the surveillance system resources by enhancing the lowlight video stream and then it detects salient video frames that consist of human. This module is trained on our own challenging Lowlight Human Surveillance Dataset (LHSD) which consists of both normal and different levels of lowlighting data to recognize humans in complex uncertain environments. Next, to learn HAR from both contextual and motion information, a dual stream approach is used in the feature extraction. In the first stream, it freezes the learned weights of the backbone Vision Transformer (ViT) B-16 model to select the discriminative contextual information. In the second stream, ViT features are then fused with the intermediate encoder layers of FlowNet2 model for optical flow to extract a robust motion feature vector. Finally, a two stream Parallel Bidirectional Long Short-Term Memory (PBiLSTM) is proposed for sequence learning to capture the global semantics of activities, followed by Dual Stream Multi-Head Attention (DSMHA) with a late fusion strategy to optimize the huge features vector for accurate HAR. To assess the strength of the proposed framework, extensive empirical results are conducted on real-world surveillance scenarios and various benchmark HAR datasets that achieve 78.6285%, 96.0151%, and 98.875% accuracies on HMDB51, UCF101, and YouTube Action, respectively. Our results show that the proposed strategy outperforms State-of-the-Art (SOTA) methods. The proposed framework gives superior performance in HAR, providing accurate and reliable recognition of human activities in surveillance systems. [ABSTRACT FROM AUTHOR]

Segmentation of tissues in magnetic resonance (MR) images is vital for effective analysis of brain pathology. However, existing approaches for brain MR image segmentation and feature extraction have limitations such as high computational costs and lower accuracy. To overcome these challenges, this paper presents an integrated approach, termed PSO-Guided Segmentation with U-Net and CNN Classification, for the detection and quantification of brain pathology in MR images. The proposed algorithm combines Particle Swarm Optimization (PSO) for enhanced feature extraction, for the classification CNN while segmentation can be done through U-Net. Numerous tests show that the suggested algorithm performs more effectively and accurately than existing techniques in terms of sensitivity and accuracy. By utilizing cutting-edge technologies like Convolutional Neural Networks (CNN), Particle Swarm Optimization (PSO), and U-Net, significant progress has been made in enhancing the accuracy of MR image segmentation and tumor detection. Compared to traditional methods, our proposed methodology outperforms, enhancing accuracy and sensitivity by approximately 0.44%, significantly decreasing computational expenses while maintaining high precision. However, due to the dynamic nature of technology advancements, it remains imperative to continually explore and develop novel frameworks and algorithms to further improve accuracy and achieve the highest level of performance. [ABSTRACT FROM AUTHOR]

Breast cancer is become the most prevailing and fastest growing disease. In medical imaging, the use of machine learning and deep learning algorithms is essential. Classification of the tumor to predict the chemotherapy response for survival is trivial. In this paper, an innovative Gaussian-Wiener filter combination is used for de-noising the MRI images. These pre-processed images with good image quality are selected for tumor detection. On the basis of these pre-processed outputs, important features are extracted to determine the spatial relationship between the image pixels which results in better texture analysis for the tumor images. Analysis is made on the ISPY-2 trial breast MRI database. Results are analyzed which gives better image quality performance for MRI images. The filters and feature extraction method analyzed is used further in the segmentation and optimization process for breast detection and diagnosis to get the best accuracy of nearly 100%. The results also show better texture analysis for extracting features using GLCM based method. Furthermore, the MRI images for these methods used are explained for better performance in the process of breast cancer detection and diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel approach for the early detection of skin disorders, aiming to improve the prediction accuracy and precision. Our motivation lies in addressing the challenges posed by the uncertainty in skin lesion features. To achieve this, we employ fuzzy-based segmentation techniques to enhance the quality of skin disorder image processing. Additionally, we explore the integration of intensity data to further refine the segmented images. Our methodology consists of three main steps: segmentation, feature extraction, and classification. We begin by inputting the image into the segmentation phase, followed by the application of a fuzzy c-means clustering process to improve the segmentation output. From the resulting segmented image, we extract features using local binary pattern and local Gabor XOR pattern techniques. These features are then subjected to classification, employing a hybrid classifier that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. The use of this hybrid classifier is particularly significant, as it leverages the strengths of both CNN and LSTM to enhance the predictive power of our model. Through rigorous experimentation, we have achieved promising results. Our proposed method exhibits an impressive accuracy of 94.6% and precision of 95.5% in comparison to the Conventional FCM Model, which only achieves an accuracy of 87% and precision of 82.5%. [ABSTRACT FROM AUTHOR]

This paper focuses on the automated extraction of textural features from segmented Sentinel-1A Synthetic Aperture Radar (SAR) imagery, which was captured on 25th August 2017. Textural properties play a pivotal role in discerning regions of interest in satellite imagery, essential for precise classification in diverse applications, including remote sensing, medical image analysis, biometric analysis, and document image analysis. To achieve this, the Local Adaptive Threshold (LAT) technique was employed for segmenting the foreground and background areas of the pre-processed vertical transmit-vertical receive (VV) polarized Sentinel-1A SAR data. The approach relies on second-order statistics, specifically co-occurrence measures, which evaluate the relationships between pairs of pixels within their local neighbourhood's in the input image. Four fundamental second-order statistical measures, namely correlation, energy, homogeneity, and contrast, were computed using the Grey Level Co-occurrence Matrix (GLCM). The GLCM was generated by quantizing the foreground region of the segmented grey-scale image into different levels, including 8, 16, and 64 grey levels, considering two inter-pixel distances, d=1 and d=2, and adopting an omni-directional orientation (θ = 00, 450, 900, 1350).The results underscore the effectiveness of the GLCM-based approach in computing second-order statistical texture measures from the segmented SAR image. Notably, the findings highlight that quantizing the image to Ng=8 with d=1 and considering omni-directional statistical measures (θ = 00, 450, 900, 1350) significantly enhances performance. [ABSTRACT FROM AUTHOR]

Stress is a psychological or emotional strain that occurs due to adverse experiences in human life. This paper showcases the application of deep learning in detecting stress levels in continuous audio signals in the Distress Analysis Interview Corpus Wizard of Oz (DAIC-WOZ) database. The features that have been experimented with are Gammatone Frequency Cepstral Coefficients (GFCC), Log Filter Bank (Log-Filter Bank), Mel Frequency Cepstral Coefficients (MFCC), chroma, and Linear Predictive Coding (LPC). Five deep learning models were evaluated: Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Bidirectional LSTM (Bi-LSTM), k-fold CNN with the k value as 5, and a fusion model of CNN, LSTM, and attention. Upon evaluating the performance metrics of all the models, it is concluded that the k-fold CNN model with k as 5 performs well with continuous audio signals. The model has achieved an accuracy of 80% when it is trained on MFCC, GFCC, and Log-F Bank features which are observed to be the optimal features in the stress analysis. [ABSTRACT FROM AUTHOR]

In the current era of internet, a huge volume of opinionated sentiment reviews is generated on a daily basis. Normally, such reviews are enriched with deep sentiments and express the opinions on various features of a product or service under consideration. Identification of a set of important domain features opens an opportunity to build automatic product and service summarization system. It is observed that the common phenomena is to consider the frequently appearing words as the domainb features. However, not all frequently appearing words can be domain-specific features. In this paper, a novel Domain Feature Miner (DOMINER) approach is proposed for robust extractive summarization. The entire domain feature set mining problem is modelled as a clustering problem. Firstly, the bond energy based clustering technique is employed to cluster the domain features based on their frequency and co-appearance counts. Later, relevant clusters are extracted for the final set of domain feature set retrieval. The Proposed DOMINER scheme is extensively evaluated against quantitative performance metrics such as precision, recall, and F-score for six diversified domains such as Cellphone, Camera, Laptop, Tablet, Television, and Hotel. Experimental results on benchmark data sets reveal that proposed DOMINER scheme mines high quality of domain feature from unstructured reviews evident from precision, recall, and F-score values as 78.10%, 64.21%, and 70.48%, respectively against state of the art existing schemes. The high quality domain features extraction from DOMINER help generate the robust extractive summaries for product and services. [ABSTRACT FROM AUTHOR]

Image feature extraction and matching constitute fundamental steps in computer vision and image analysis, enabling various applications ranging from object recognition to scene reconstruction. Object recognition is one of the major applications of artificial intelligence. Since last two decades, different techniques for object recognition were given by researchers from across the world. This paper presents a novel approach for automatic target recognition in autonomous weapons by matching connected graph of feature pixels. The Moving and Stationary Target Acquisition and Recognition (MSTAR) is taken for experimental purpose. The Proposed model has three stages for a target recognition; Image Denoising, Feature extraction & graph generation, and feature matching. Firstly, a sample image of targets taken from the MSTAR is taken as an input. Further, input sample is de-noised and features are extracted using Speeded-Up Robust Features (SURF) algorithm. Thereafter, a graph is created using feature pixels and this complete process is repeated with test image. Further, both graphs are compared using a proposed feature graph matching algorithm which results an recognition accuracy score. Proposed model is tested over the MSTAR dataset and it resulted in varying accuracy at different feature matching thresholds. [ABSTRACT FROM AUTHOR]

Accurate and timely fault diagnosis is a vital task to ensure process safety of modern industrial facilities. Motivated by the complex variations of process signals and mutual coupling of faults, this paper presents a multi-feature-based fault diagnosis method based on the weighted timeliness Broad Learning System (BLS). The proposed method fuses multiple features extracted from the original process data to improve the fault diagnosis performance, and makes the diagnosis model suitable for dynamic fault diagnosis problems by incorporating the BLS. The major contributions of this study are twofolds: 1) A systematic multi-feature extraction method is proposed to extract long-term trend features, short-term trend features, and binary alarm signals, which reflect the direction and amplitude changes of process signals under faulty conditions; 2) a weighted timeliness BLS structure with multiple fault-sensitive features as the input is proposed to ensure the dynamic characteristics of the fault diagnosis model. The designed fault diagnosis model can be updated in an incremental manner, and thus can improve the model updating efficiency while ensuring accuracy. The effectiveness and superiority of the proposed method is demonstrated by a case study based on the Tennessee Eastman benchmark process. [ABSTRACT FROM AUTHOR]

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

Existing RGB-D tracking algorithms advance the performance by constructing typical appearance models from the RGB-only tracking frameworks. There is no attempt to exploit any complementary visual information from the multi-modal input. This paper addresses this deficit and presents a novel algorithm to boost the performance of RGB-D tracking by taking advantage of collaborative clues. To guarantee input consistency, depth images are encoded into the three-channel HHA representation to create input of a similar structure to the RGB images, so that the deep CNN features can be extracted from both modalities. To highlight the discriminatory information in multi-modal features, a feature enhancement module using a cross-attention strategy is proposed. With the attention map produced by the proposed cross-attention method, the target area of the features can be enhanced and the negative influence of the background is suppressed. Besides, we address the potential tracking failure by introducing a long-term mechanism. The experimental results obtained on the well-known benchmarking datasets, including PTB, STC, and CTDB, demonstrate the superiority of the proposed RGB-D tracker. On PTB, the proposed method achieves the highest AUC scores against compared trackers across scenarios with five distinct challenging attributes. On STC and CDTB, our FECD obtains an overall AUC of 0.630 and an F-score of 0.630, respectively. • The single-channel depth maps were encoded into three-channel HHA images. • A feature enhancement method with a cross-attention module to enhance features. • A long-term tracking mechanism to detect failures and recapture lost targets. • Experiments were conducted on several standard tracking benchmarking datasets. [ABSTRACT FROM AUTHOR]

This paper proposes a fast protection scheme of a hybrid AC/DC distribution network based on features extraction of the decomposed signals. The signal decomposition is achieved using discrete wavelets transform (DWT). The proposed scheme offers three main functions, fast fault detection for both network sides, AC fault classification with the ability to identify the faulted phase/ phases, and protection coordination between AC and DC sides. In addition, the scheme is based on local measurement so no need for extra-cost for communication infrastructure. The absence of communication reduces the overall cost and, as a most important feature, it reduces the fault clearing time. The system is thoroughly analyzed under many types of faults in both AC and DC sides. Also, different disturbance conditions are considered which used in threshold determination. The simulation results show that the proposed protection scheme was not only able to protect the system but also it offers a generalized fast acting communication-less approach. [ABSTRACT FROM AUTHOR]

This paper introduces an automated method for classifying electrocardiograms (ECG) with the aim of enhancing both accuracy and speed in interpreting ECG results, thus contributing to the early detection of cardiovascular diseases (CVD). The model in this study employs a deep feature extraction technique combined with Ensemble Bagged Trees (EBT) to identify Ventricular Ectopic Beats (VEB). Data is sourced from the MIT-BIH Arrhythmia database, and model performance is assessed through ten-fold cross-validation. On the validation dataset, the proposed model achieves an accuracy of 98.24% and an F1 score of 97.66%. When independently tested on the MIT-BIH dataset, it demonstrates an accuracy of 98.31% and an F1 score of 89.22%. These outcomes highlight the model's ability to attain exceptional accuracy and F1 scores on both validation and testing datasets. [ABSTRACT FROM AUTHOR]

Speech Emotion Recognition (SER) refers to the ability of Machine Learning (ML) and Deep Learning (DL) techniques to accurately predict people's emotional states from speech signals. significant progress has been achieved in the SER domain involving the incorporation of DL models to introduce novel features extraction processes. This paper introduces the use of deep representations learned from the multi-modal Large Language Model (LLM) called ImageBind. These representations were subsequently provided as input to the Nu-Support Vector Machine (Nu-SVM) with RBF kernel for the classification task. The experiments were executed using the IEMOCAP database within the context of a Speaker-Dependent (SD) scenario. The method achieved a noteworthy overall accuracy rate of 80.58% for the four emotions of IEMOCAP, representing a substantial improvement over well-established methods in the existing body of literature. Thus, affirming that the proposed methodology, founded upon ImageBind representations, introduces a novel perspective to the field of SER. [ABSTRACT FROM AUTHOR]