Network Classifier Research Articles

Clustering and Classification of Time Series Sound Data

This scientific article addresses two critical tasks in data analysis—time series classification and clustering, particularly focusing on heart sound recordings. One of the main challenges in analyzing time series lies in the difficulty of comparing different series due to their variability in length, shape, and amplitude. Various algorithms were employed to tackle these tasks, including the Long Short-Term Memory (LSTM), KNN, recurrent neural network for classification and the K-means and DBSCAN methods for clustering. The study emphasizes the effectiveness of these methods in solving classification and clustering problems involving time series data containing heart sound recordings. The results indicate that LSTM is a powerful tool for time series classification due to its ability to retain contextual information over time. In contrast, KNN demonstrated high accuracy and speed in classification, though its limitations became apparent with larger datasets. For clustering tasks, the K-means method proved to be more effective than DBSCAN, showing higher clustering quality based on metrics such as silhouette score, Rand score, and others. The data used in this research were obtained from the UCR Time Series Archive, which includes heart sound recordings from various categories: normal sounds, murmurs, additional heart sounds, artifacts, and extra systolic rhythms. The analysis of results demonstrated that the chosen classification and clustering methods could be effectively used for diagnosing heart diseases. Furthermore, this research opens up new opportunities for further improvement in data processing and analysis methods, particularly in developing new medical diagnostic tools. Thus, this work illustrates the effectiveness of machine learning algorithms for time series analysis and their significance in improving cardiovascular disease diagnosis.

Leveraging In Silico Structure-Activity Models to Predict Acute Honey Bee (Apis mellifera) Toxicity for Agrochemicals.

In the realm of crop protection products, ensuring the safety of pollinators stands as a pivotal aspect of advancing sustainable solutions. Extensive research has been dedicated to this crucial topic as well as new approach methodologies in toxicity testing. Hence, within the agricultural and chemical industries, prioritizing pollinator safety remains a constant objective during the development of predictive tools. One of these tools includes computational models like quantitative structure-activity relationships (QSARs) that are valuable in predicting the toxicity of chemicals. This research uses bee toxicity data to develop artificial neural network classification models for predicting honey bee acute toxicity. Bee toxicity data from 1542 compounds were used to develop models; the sensitivity and specificity of the best model were 0.90 and 0.91, respectively. These in silico models can aid in the discovery of next-generation crop protection products. These tools can guide the screening and selection of next-generation crop protection molecules with high margins of safety to pollinators, and candidates with favorable sustainability profiles can be identified at the early discovery stage as precursors to in vivo data generation.

Chinese Verbal Fluency Deficiency in Temporal Lobe Epilepsy with and without Hippocampal Sclerosis: A Multiscale Study.

To test a Chinese character version of the phonemic verbal fluency task in patients with temporal lobe epilepsy (TLE) and assess the verbal fluency deficiency pattern in TLE with and without hippocampal sclerosis, a cross-sectional study was conducted including 30 patients with TLE and hippocampal sclerosis (TLE-HS), 28 patients with TLE and without hippocampal sclerosis (TLE-NHS), and 29 demographically matched healthy controls (HC). Both sexes were enrolled. Participants finished a Chinese character verbal fluency (VFC) task during functional MRI. The activation/deactivation maps, functional connectivity, degree centrality, and community features of the left frontal and temporal regions were compared. A neural network classification model was applied to differentiate TLE-HS and TLE-NHS using functional statistics. The VFC scores were correlated with semantic fluency in HC while correlated with phonemic fluency in TLE-NHS. Activation and deactivation deficiency was observed in TLE-HS and TLE-NHS (p < 0.001, k ≥ 10). Functional connectivity, degree centrality, and community features of anterior inferior temporal gyri were impaired in TLE-HS and retained or even enhanced in TLE-NHS (p < 0.05, FDR-corrected). The functional connectivity was correlated with phonemic fluency (p < 0.05, FDR-corrected). The neural network classification reached an area under the curve of 0.90 in diagnosing hippocampal sclerosis. The VFC task is a Chinese phonemic verbal fluency task suitable for clinical application in TLE. During the VFC task, functional connectivity of phonemic circuits was impaired in TLE-HS and was enhanced in TLE-NHS, representing a compensative phonemic searching strategy applied by patients with TLE-NHS.

Learning From Human Attention for Attribute-Assisted Visual Recognition.

With prior knowledge of seen objects, humans have a remarkable ability to recognize novel objects using shared and distinct local attributes. This is significant for the challenging tasks of zero-shot learning (ZSL) and fine-grained visual classification (FGVC), where the discriminative attributes of objects have played an important role. Inspired by human visual attention, neural networks have widely exploited the attention mechanism to learn the locally discriminative attributes for challenging tasks. Though greatly promoted the development of these fields, existing works mainly focus on learning the region embeddings of different attribute features and neglect the importance of discriminative attribute localization. It is also unclear whether the learned attention truly matches the real human attention. To tackle this problem, this paper proposes to employ real human gaze data for visual recognition networks to learn from human attention. Specifically, we design a unified Attribute Attention Network (A 2 Net) that learns from human attention for both ZSL and FGVC tasks. The overall model consists of an attribute attention branch and a baseline classification network. On top of the image feature maps provided by the baseline classification network, the attribute attention branch employs attribute prototypes to produce attribute attention maps and attribute features. The attribute attention maps are converted to gaze-like attentions to be aligned with real human gaze attention. To guarantee the effectiveness of attribute feature learning, we further align the extracted attribute features with attribute-defined class embeddings. To facilitate learning from human gaze attention for the visual recognition problems, we design a bird classification game to collect real human gaze data using the CUB dataset via an eye-tracker device. Experiments on ZSL and FGVC tasks without/with real human gaze data validate the benefits and accuracy of our proposed model. This work supports the promising benefits of collecting human gaze datasets and automatic gaze estimation algorithms learning from human attention for high-level computer vision tasks.

Weakly supervised semantic segmentation by knowledge graph inference

The weakly supervised semantic segmentation (WSSS) training based on image-level labels in convolutional neural network (CNN) is usually divided into two stages: multi-label classification and semantic segmentation. However, most of the existing work focuses on the improvement of the multi-label classification network stage, and little effort has been done to improve the performance of the downstream segmentation networks. In addition, CNN-based local convolution lacks in modeling extensive dependencies among categories. Therefore, in this paper, we propose a graph reasoning method to improve both the upstream and the downstream stages of the multi-label classification network and the semantic segmentation networks. In the multi-label classification network, we utilize external knowledge combined with a graph convolutional network (GCN) to perform global reasoning on the dependencies of each category. In the segmentation network, the Graph Reasoning Mapping Module (GRM) is proposed to explore the knowledge acquired from text corpora and facilitate contextual reasoning in various categories of image regions. The proposed GRM module is able to enhance the feature representation of local convolutions on the high-level semantics of the segmentation network, and adaptively learn the semantic consistency of each sample. We achieve state-of-the-art WSSS performance on PASCAL VOC 2012 and MS-COCO 2014 datasets with only image-level supervision. Extensive experiments on multi-label classification networks and semantic segmentation networks demonstrate the effectiveness of our proposed graph reasoning method on WSSS. Our code is available at:https://github.com/JIA-ZHANG666/GRM_layer.

Automatic Recognition of Multiple Emotional Classes from EEG Signals through the Use of Graph Theory and Convolutional Neural Networks.

Emotion is a complex state caused by the functioning of the human brain in relation to various events, for which there is no scientific definition. Emotion recognition is traditionally conducted by psychologists and experts based on facial expressions-the traditional way to recognize something limited and is associated with errors. This study presents a new automatic method using electroencephalogram (EEG) signals based on combining graph theory with convolutional networks for emotion recognition. In the proposed model, firstly, a comprehensive database based on musical stimuli is provided to induce two and three emotional classes, including positive, negative, and neutral emotions. Generative adversarial networks (GANs) are used to supplement the recorded data, which are then input into the suggested deep network for feature extraction and classification. The suggested deep network can extract the dynamic information from the EEG data in an optimal manner and has 4 GConv layers. The accuracy of the categorization for two classes and three classes, respectively, is 99% and 98%, according to the suggested strategy. The suggested model has been compared with recent research and algorithms and has provided promising results. The proposed method can be used to complete the brain-computer-interface (BCI) systems puzzle.

Fatigue Crack Detection Based on Semantic Segmentation Using DeepLabV3+ for Steel Girder Bridges

Artificial intelligence technology is receiving more and more attention in structural health monitoring. Fatigue crack detection in steel box girders in long-span bridges is an important and challenging task. This paper presents a semantic segmentation network model for this task based on DeepLabv3+, ResNet50, and active learning. Specifically, the classification network ResNet50 is re-tuned using the crack image dataset. Secondly, with the re-tuned ResNet50 as the backbone network, a crack semantic segmentation network was constructed based on DeepLabv3+, which was trained with the assistance of active learning. Finally, optimization for the probability threshold of the pixel category was performed to improve the pixel-level detection accuracy. Tests show that, compared with the crack detection network based on conventional ResNet50, this model can improve MIoU from 0.6181 to 0.7241.

Neural network classification of technological development projects in Russian companies: Perspectives of extreme project management

To achieve the goals of sustainable socio-economic development and ensure the technological sovereignty of the Russian Federation, it is critically important to choose effective methods of technological project management. The article develops a novel toolkit for neural network classification of technological development projects in Russian companies and justifies the use of extreme project management to such endeavors. The methodological framework resides in the concepts of project lifecycle management and data mining. The study employed the following research methods: textual analysis of project documentation using large language models, and intelligent project classification based on two-dimensional projection of multidimensional clusters using Orange Data Mining. The research draws upon regulatory documents in the field of Russia’s scientific and technological development and open databases on Russian companies’ projects. The work proposes a new neural network classification toolkit based on a large language model. We have found that most development projects related to critical and end-to-end technologies are characterized by low certainty of goals and solutions, which necessitates applying extreme approaches to manage them. The findings can be used by Russian companies for reasoning the choice of a project management model, as well as by experts when evaluating technological development projects.

Detection of Alzheimer’s disease using pre-trained deep learning models through transfer learning: a review

Due to the progress in image processing and Artificial Intelligence (AI), it is now possible to develop automated tool for the early detection and diagnosis of Alzheimer’s Disease (AD). Handcrafted techniques developed so far, lack generality, leading to the development of deep learning (DL) techniques, which can extract more relevant features. To cater for the limited labelled datasets and requirement in terms of high computational power, transfer learning models can be adopted as a baseline. In recent years, considerable research efforts have been devoted to developing machine learning-based techniques for AD detection and classification using medical imaging data. This survey paper comprehensively reviews the existing literature on various methodologies and approaches employed for AD detection and classification, with a focus on neuroimaging techniques such as structural MRI, PET, and fMRI. The main objective of this survey is to analyse the different transfer learning models that can be used for the deployment of deep convolution neural network for AD detection and classification. The phases involved in the development namely image capture, pre-processing, feature extraction and selection are also discussed in the view of shedding light on the different phases and challenges that need to be addressed. The research perspectives may provide research directions on the development of automated applications for AD detection and classification.

Deep neural networks integrating genomics and histopathological images for predicting stages and survival time-to-event in colon cancer.

There exists an unexplained diverse variation within the predefined colon cancer stages using only features from either genomics or histopathological whole slide images as prognostic factors. Unraveling this variation will bring about improved staging and treatment outcomes. Hence, motivated by the advancement of Deep Neural Network (DNN) libraries and complementary factors within some genomics datasets, we aggregate atypia patterns in histopathological images with diverse carcinogenic expression from mRNA, miRNA and DNA methylation as an integrative input source into a deep neural network for colon cancer stages classification, and samples stratification into low or high-risk survival groups. The genomics-only and integrated input features return Area Under Curve-Receiver Operating Characteristic curve (AUC-ROC) of 0.97 compared with AUC-ROC of 0.78 obtained when only image features are used for the stage's classification. A further analysis of prediction accuracy using the confusion matrix shows that the integrated features have a weakly improved accuracy of 0.08% more than the accuracy obtained with genomics features. Also, the extracted features were used to split the patients into low or high-risk survival groups. Among the 2,700 fused features, 1,836 (68%) features showed statistically significant survival probability differences in aggregating samples into either low or high between the two risk survival groups. Availability and Implementation: https://github.com/Ogundipe-L/EDCNN.

Conv-RGNN: An efficient Convolutional Residual Graph Neural Network for ECG classification

Background and objective:Electrocardiogram (ECG) analysis is crucial in diagnosing cardiovascular diseases (CVDs). It is important to consider both temporal and spatial features in ECG analysis to improve automated CVDs diagnosis. Significant progress has been made in automated CVDs diagnosis based on ECG with the continuous development of deep learning. Current most researches often treat 12-lead ECG signals as synchronous sequences in Euclidean space, focusing primarily on extracting temporal features while overlooking the spatial relationships among the 12-lead. However, the spatial distribution of 12-lead ECG electrodes can be more naturally represented using non-Euclidean data structures, which makes the relationships among leads more consistent with their intrinsic characteristics. Methods:This study proposes an innovative method, Convolutional Residual Graph Neural Network (Conv-RGNN), for ECG classification. The first step is to segment the 12-lead ECG into twelve single-lead ECG, which are then mapped to nodes in a graph that captures the relationships between the different leads through spatial connections, resulting in the 12-lead ECG graph. The graph is then used as input for Conv-RGNN. A convolutional neural network with a position attention mechanism is used to extract temporal sequence information and selectively integrate contextual information to enhance semantic features at different positions. The spatial features of the 12-lead ECG graph are extracted using the residual graph neural network. Results:The experimental results indicate that Conv-RGNN is highly competitive in two multi-label datasets and one single-label dataset, demonstrating exceptional parameter efficiency, inference speed, model performance, and robustness. Conclusion:The Conv-RGNN proposed in this paper offer a promising and feasible approach for intelligent diagnosis in resource-constrained environments.

An Agent-Based Method for Feature Recognition and Path Optimization of Computer Numerical Control Machining Trajectories.

In recent years, artificial intelligence technology has seen increasingly widespread application in the field of intelligent manufacturing, particularly with deep learning offering novel methods for recognizing geometric shapes with specific features. In traditional CNC machining, computer-aided manufacturing (CAM) typically generates G-code for specific machine tools based on existing models. However, the tool paths for most CNC machines consist of a series of collinear motion commands (G01), which often result in discontinuities in the curvature of adjacent tool paths, leading to machining defects. To address these issues, this paper proposes a method for CNC system machining trajectory feature recognition and path optimization based on intelligent agents. This method employs intelligent agents to construct models and analyze the key geometric information in the G-code generated during CNC machining, and it uses the MCRL deep learning model incorporating linear attention mechanisms and multiple neural networks for recognition and classification. Path optimization is then carried out using mean filtering, Bézier curve fitting, and an improved novel adaptive coati optimization algorithm (NACOA) according to the degree of unsmoothness of the path. The effectiveness of the proposed method is validated through the optimization of process files for gear models, pentagram bosses, and maple leaf models. The research results indicate that the CNC system machining trajectory feature recognition and path optimization method based on intelligent agents can significantly enhance the smoothness of CNC machining paths and reduce machining defects, offering substantial application value.

A simplified adversarial architecture for cross-subject silent speech recognition using electromyography

Objective. The decline in the performance of electromyography (EMG)-based silent speech recognition is widely attributed to disparities in speech patterns, articulation habits, and individual physiology among speakers. Feature alignment by learning a discriminative network that resolves domain offsets across speakers is an effective method to address this problem. The prevailing adversarial network with a branching discriminator specializing in domain discrimination renders insufficiently direct contribution to categorical predictions of the classifier.Approach. To this end, we propose a simplified discrepancy-based adversarial network with a streamlined end-to-end structure for EMG-based cross-subject silent speech recognition. Highly aligned features across subjects are obtained by introducing a Nuclear-norm Wasserstein discrepancy metric on the back end of the classification network, which could be utilized for both classification and domain discrimination. Given the low-level and implicitly noisy nature of myoelectric signals, we devise a cascaded adaptive rectification network as the front-end feature extraction network, adaptively reshaping the intermediate feature map with automatically learnable channel-wise thresholds. The resulting features effectively filter out domain-specific information between subjects while retaining domain-invariant features critical for cross-subject recognition.Main results. A series of sentence-level classification experiments with 100 Chinese sentences demonstrate the efficacy of our method, achieving an average accuracy of 89.46% tested on 40 new subjects by training with data from 60 subjects. Especially, our method achieves a remarkable 10.07% improvement compared to the state-of-the-art model when tested on 10 new subjects with 20 subjects employed for training, surpassing its result even with three times training subjects.Significance. Our study demonstrates an improved classification performance of the proposed adversarial architecture using cross-subject myoelectric signals, providing a promising prospect for EMG-based speech interactive application.

LEVERAGING DEEP LEARNING FOR IMPROVED CYCLONE FORCASTING

Tropical cyclones (TCs) are frequently rarest but one of the foremost dangerous weather phenomena to arise over tropical oceans, usually creating huge issues with nearly ninety storms globally annually. Early detection and monitoring of TCs are necessary for the early warning of areas in danger. Since these storms originate over the open ocean and frequently out at sea many miles of continental regions, they are detected using remote sensing. In this paper, we propose an automatic method to identify the formation of TCs through satellite images combining a deep learning architecture. The methodology is based on a two-stage deep learning framework: Mask CNN as detector stage—second wind speed filter and lastly Convolutional Neural Network (CNN) for classification. The best possible performance is obtained by hyperparameter optimization using Bayesian Optimization across the pipeline. Results show that the proposed method achieves a precision, specificity, and accuracy of 97.10%, 97.59%, and 86.55% in test images respectively KEYWORDS— Convolutional Neural Networks (CNN), Deep Learning, Cyclone Detection and Tracking, Tropical cyclone Intensity.

Metadata augmented deep neural networks for wild animal classification

Camera trap imagery has become an invaluable asset in contemporary wildlife surveillance, enabling researchers to observe and investigate the behaviors of wild animals. While existing methods rely solely on image data for classification, this may not suffice in cases of suboptimal animal angles, lighting, or image quality. This study introduces a novel approach that enhances wild animal classification by combining specific metadata (temperature, location, time, etc) with image data. Using a dataset focused on the Norwegian climate, our models show an accuracy increase from 98.4% to 98.9% compared to existing methods. Notably, our approach also achieves high accuracy with metadata-only classification, highlighting its potential to reduce reliance on image quality. This work paves the way for integrated systems that advance wildlife classification technology.

Optimization of the convolutional neural network classification model under the background of innovative art teaching models

To improve students’ ability to recognize and appreciate artworks, and further enhance their academic performance and classroom satisfaction, this study explores the application of the Convolutional Neural Network (CNN) model based on optimization in art teaching. Firstly, the importance and challenges of art teaching are analyzed. Secondly, the principle and structure of CNN and its application in the classification field are expounded, and then the CNN classification model is optimized. Finally, the effectiveness of the optimized model is verified by experiments. Experimental results show that the optimized model’s accuracy is up to 95.2% in the performance evaluation. The training time of the optimized model is much lower than that of the traditional model, and this model still maintains 95.2% accuracy under the noise of 14.7%. In addition, the accuracy of the optimized model on the unseen test data is 92%. In comparing teaching experiment results, by introducing the CNN classification model, Class B students’ average score of art homework has increased by 4.3 points. The score for class satisfaction is 8.1 points. This indicates that the optimized CNN model has significant advantages in art teaching and can effectively improve students’ classroom satisfaction and academic performance. Therefore, this study has specific reference significance for the innovation of the art teaching model.

Enhancing Missense Variant Pathogenicity Prediction with MissenseNet: Integrating Structural Insights and ShuffleNet-Based Deep Learning Techniques.

The classification of missense variant pathogenicity continues to pose significant challenges in human genetics, necessitating precise predictions of functional impacts for effective disease diagnosis and personalized treatment strategies. Traditional methods, often compromised by suboptimal feature selection and limited generalizability, are outpaced by the enhanced classification model, MissenseNet (Missense Classification Network). This model, advancing beyond standard predictive features, incorporates structural insights from AlphaFold2 protein predictions, thus optimizing structural data utilization. MissenseNet, built on the ShuffleNet architecture, incorporates an encoder-decoder framework and a Squeeze-and-Excitation (SE) module designed to adaptively adjust channel weights and enhance feature fusion and interaction. The model's efficacy in classifying pathogenicity has been validated through superior accuracy compared to conventional methods and by achieving the highest areas under the Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves (Area Under the Curve and Area Under the Precision-Recall Curve) in an independent test set, thus underscoring its superiority.

Detection and recognition of the invasive species, Hylurgus ligniperda, in traps, based on a cascaded convolution neural network.

Hylurgus ligniperda, an invasive species originating from Eurasia, is now a major forestry quarantine pest worldwide. In recent years, it has caused significant damage in China. While traps have been effective in monitoring and controlling pests, manual inspections are labor-intensive and require expertise in insect classification. To address this, we applied a two-stage cascade convolutional neural network, YOLOX-MobileNetV2 (YOLOX-Mnet), for identifying H. ligniperda and other pests captured in traps. This method streamlines target and non-target insect detection from trap images, offering a more efficient alternative to manual inspections. Two cascade convolutional neural network models were employed in two stages to detect both target and non-target insects from images captured in the same forest. Initially, You Only Look Once X (YOLOX) served as the target detection model, identifying insects and non-insects from the collected images, with non-insect targets subsequently filtered out. In the second stage, MobileNetV2, a classification network, classified the captured insects. This approach effectively reduced false positives from non-insect objects, enabled the inclusion of additional classification terms for multi-class insect classification models, and utilized sample control strategies to enhance classification performance. Application of the cascade convolutional neural network model accurately identified H. ligniperda, and Mean F1-score of all kinds of insects in the trap was 0.98. Compared to traditional insect classification, this method offers great improvement in the identification and early warning of forest pests, as well as provide technical support for the early prevention and control of forest pests. © 2024 Society of Chemical Industry.

Leveraging tabular GANs for malicious address classification in ethereum network

The popularity of ethereum for cryptocurrency transactions attracts malicious actors to engage in illegal activities like phishing, ponzi, and gambling. Previous studies have focused mainly on phishing due to the large number of phishing addresses. However, there is no work done on ponzi or gambling classification due to the limited availability of these addresses, which makes their classification more challenging. In this paper, we propose a machine learning (ML) based method for classifying malicious addresses in ethereum, with a specific focus on phishing, ponzi, and gambling addresses. We use a selective upsampling technique through the tabular generative adversarial network (GAN) to solve limited data problems. We perform not only binary but also multiclass classification on various feature extraction methods, including Trans2Vec and Node2Vec, using Ethereum transactional data. We evaluate our method on F1 score, precision, recall, and accuracy. Our results show that the proposed method is effective in ponzi and gambling detection when compared with the state-of-the-art.

Classification method of seabed sonar image substrate based on ELM-AdaBoost

The results of sediment classification are affected by the measurement environment. The water depth has a significant impact on the sound propagation, and the acoustic characteristics will be different under different water depths. In addition, seabed topography, sediment types and their distribution, acoustic frequency, equipment types and settings, and suspended substances in water will all affect the original sonar data. In order to obtain accurate classification results, a seabed sonar image classification method based on Elm AdaBoost is proposed. The original sound intensity data is compensated for gain and the anomaly is eliminated. After preprocessing the multi beam sonar data, the image texture feature is extracted from the gray level co-occurrence matrix as the feature vector for classification, and the elm classifier is constructed. The elm is enhanced by AdaBoost. The calculated feature is input into the elm AdaBoost network for sediment classification, and the result is output. Simulation results show that the proposed method effectively improves the accuracy of sediment classification, and verifies the feasibility of this method.