Intelligent Classification Research Articles

Feature selection based on snake optimizer for defect or damage classification in composite rolls via ultrasonic Rayleigh waves

Defects or damages on the surface or subsurface of composite rolls directly affect the quality of the rolled products, and their periodic inspection and accurate identification can provide a reference for the repair or replacement of composite rolls. Ultrasonic Rayleigh waves can non-destructively assess the surface or subsurface of composite rolls, during which similar original signals are perhaps generated for the defects or damages with different types or sizes, making it difficult to distinguish their types. Machine learning is proposed to solve these problems, and feature selection based on the ultrasonic Rayleigh waves mainly utilizes traditional methods such as ReliefF. However, these unsupervised methods have not been combined with specific classification algorithms. In this study, swarm intelligence optimization algorithms, including snake optimizer (SO), dung beetle optimizer (DBO), and grasshopper optimization algorithm (GOA), are investigated based on the support vector machine (SVM). Note that the utilized original signals are received on the left and right sides of defects or damages, and they are processed by segmentation, fast Fourier transform (FFT), and wavelet packet decomposition to build original feature sets. It is illustrated that Rayleigh waves passing through the defects or damages carry more valuable information about the types. In contrast, the ultrasonic waves reflected from the defects or damages can provide information about the types that the former does not contain. Furthermore, for the intelligent classification of defects or damages in composite rolls using ultrasonic Rayleigh waves, SO is more suitable for SVM and has certain advantages.

Exploring product style perception: A comparative eye-tracking analysis of users across varying levels of self-monitoring

Digital shopping applications and platforms offer consumers a numerous array of products with diverse styles and style attributes. Existing literature suggests that style preferences are determined by consumers’ genders, ages, education levels, and nationalities. In this study, we argue the feasibility and necessity of self-monitoring as an additional consumer variable impacting product style perception and preference through the utilization of eye-tracking technology. Three eye-movement experiments were conducted on forty-two participants (twenty males and twenty-two females; Age: M = 22.8, SD = 1.63). The results showed participants with higher levels of self-monitoring exhibited shorter total fixation durations and fewer fixation counts while examining images of watch product styles. In addition, gender exerted an interaction effect on self-monitoring’s impact, with female participants of high self-monitoring ability able to perceive differences in product styles more rapidly and with greater sensitivity. Overall, the results highlight the utility of self-monitoring as a research variable in product style perception investigations, as well as its implication for style intelligence classifiers, and style neuroimaging.

Social entertainment robot based on neural network algorithm in personalized music course simulation

This study focuses on the simulation of personalized music courses using social entertainment robots based on neural network algorithms, and introduces the current research status of music processing algorithms based on neural networks. A detailed explanation was provided on the training methods for neural network algorithms, including BP neural network training and music generation algorithms. Research was conducted on activation functions, music output detection, and loss function detection. A virtual music course system framework has been designed to provide students with personalized learning experiences. In a social entertainment robot based on neural network algorithms, a complete control node system was reconstructed, aiming to achieve interactive and entertainment effects of music courses through sensing technology. The control node system includes multiple key components, and the robot is able to perceive and recognize the actions, facial expressions, and sounds of students. Social entertainment robots have intelligent classification and recommendation functions, and this algorithm can intelligently classify and recommend music resources based on students’ music preferences, levels, and needs. By analyzing the personal preferences and learning progress of students, robots can provide customized music course content and learning materials for each student, improving learning effectiveness and personal interests.

Study on automatic lithology identification based on convolutional neural network and deep transfer learning

Automatic and fast rock classification identification is an important part of geotechnical intelligent survey system. Image based supervised deep learning analysis, especially for convolutional neural networks (CNN), has potential in optimizing lithologic classification and interpretation using borehole core images. However, the accuracy and efficiency of lithology identification models are low at present. In this work, a systematic and enormous rock data framework based on the geological rock classification system is firstly established to provide rock learning datasets. The dataset is composed of approximately 150,000 images of rock samples, which covers igneous rocks, sedimentary rocks, and metamorphic rocks. Secondly, based on CNN-deep transfer learning algorithm, an end-to-end, image-to-label rock lithology identification is established. Finally, the generalization of the proposed model and the field drilling core verification test show that the constructed intelligent rock recognition model has an ability to identify rocks quickly and accurately, and the recognition accuracy of 12 kinds of common engineering rocks is more than 95%. The proposed rock intelligent classification model provides a convenient and fast tool for field geologists and scientific researchers.

The BT-SAM-Net: a new framework of end-to-end periodic time-series fault diagnosis for aero-pipelines systems

Accurate recognition of aero-engine pipeline faults is of great significance for engine maintenance costs and downtime. Pipeline signals have a strong periodic time series correlation under strong pump source pressure pulsation stimulation. However, very few studies have considered the correlation of features at pulsation period time points. Additionally, it is challenging to realize intelligent fault diagnosis of weak characteristics of pipeline faults due to the influence of vibration-noise coupling of aero-engines. The time information feature extraction model combined with self-attention mechanism (BT-SAM-Net), a newly created fault detection framework end-to-end time-series and anti-noise, is presented for the aero-pipeline in order to close the aforementioned research gaps. The primary goal of the proposed framework is to accomplish intelligent classification tasks by using the measured aero-pipeline raw data as the model input. Firstly, a two-way time series information fusion model is creatively designed, which is the first attempt to analyze the difference in time series correlation characteristics of faults for aero-pipelines. Secondly, The BT-SAM-Net framework incorporates the self-attention mechanism as an optimization tool to enhance the ultimate decision-making accuracy of the framework. Thirdly, the BT-SAM-Net framework was compared with 7 other methods. The results show the superiority and stability by demonstrating the BT-SAM-Net framework can identify various aero-pipeline fault states with greater accuracy.

In-Situ Quality Intelligent Classification of Additively Manufactured Parts Using a Multi-Sensor Fusion Based Melt Pool Monitoring System

Although laser powder bed fusion (LPBF) technology is considered one of the most promising additive manufacturing techniques, the fabricated parts still suffer from porosity defects, which can severely impact their mechanical performance. Monitoring the printing process using a variety of sensors to collect process signals can realize a comprehensive capture of the processing status; thus, the monitoring accuracy can be improved. However, existing multi-sensing signals are mainly optical and acoustic, and camera-based signals are mostly layer-wise images captured after printing, preventing real-time monitoring. This paper proposes a real-time melt-pool-based in-situ quality monitoring method for LPBF using multiple sensors. High-speed cameras, photodiodes, and microphones were used to collect signals during the experimental process. All three types of signals were transformed from one-dimensional time-domain signals into corresponding two-dimensional grayscale images, which enabled the capture of more localized features. Based on an improved LeNet-5 model and the weighted Dempster-Shafer evidence theory, single-sensor, dual-sensor and triple-sensor fusion monitoring models were investigated with the three types of signals, and their performances were compared. The results showed that the triple-sensor fusion monitoring model achieved the highest recognition accuracy, with accuracy rates of 97.98%, 92.63%, and 100% for high-, medium-, and low-quality samples, respectively. Hence, a multi-sensor fusion based melt pool monitoring system can improve the accuracy of quality monitoring in the LPBF process, which has the potential to reduce porosity defects. Finally, the experimental analysis demonstrates that the convolutional neural network proposed in this study has better classification accuracy compared to other machine learning models.

Research on intelligent classification of weld defects based on improved ResNeXt network

Welding technology is widely used in the connection of metal workpieces, and then due to improper operation and other reasons, small defects may occur in the welding, which will lead to welding failure and hazardous accidents. Therefore, it is very important to accurately identify welding defects. The automatic defect identification method based on deep learning learns features directly from the full-focus mapping of weld defects and automatically classifies them; the ResNeXt network is selected for improvement, and the SK convolution unit is introduced into the original ResNeXt-50 network model to enhance the adaptive adjustment of sensory field; in order to alleviate the problem of the point-by-point convolution in the ResNeXt-50 which consumes a large amount of In order to alleviate the problem that point-by-point convolution in ResNeXt-50 consumes a large amount of computation, 1×1 group convolution is used instead of the original point-by-point convolution, and channel rearrangement is introduced to alleviate the problem of weakened information exchange of groups caused by group convolution. After improvement, the ResNeXt-50 network model can achieve a classification accuracy of 98.2%, which is 5.5% more than that of the original ResNeXt-50 on this paper's dataset, and the classification accuracy after T-sne visualization also has obvious separation boundary and clustering effects.

Secure Your Network: Building a Hybrid Intrusion Detection System in Java

Abstract: To protect the system from different types of intrusions, an intrusion detection system ID is required. It is essential to analyse the communication in order to classify the material as malicious or helpful. The usage of intrusion detection systems for cyber security shouldn't add to the processing time required for classification. These days, classification algorithms are utilized in conjunction with machine learning approaches to identify harmful data or intrusions. KDD cup 99 is the data set that was used in the experiment. Hybrid classification models can be used to adjust the performance of individual classification methods. This model blends rule-based algorithms with categorization techniques. An additional degree of security is provided by the combination of machine and human intelligence in classification. Precision, recall, F-Measure, and Mean Age Precision are used to validate an algorithm. The algorithm has a 92.35 percent accuracy rate. Even after merging our human-written criteria with traditional machine learning classification techniques, the model's accuracy is still considered satisfactory. However, there is still room for improvement and a more specific classification of the attack

Assessment of artificial intelligence to detect gasoline in fire debris using HS-SPME-GC/MS and transfer learning.

Due to the complex nature of the chemical compositions of ignitable liquids (IL) and the interferences from fire debris matrices, interpreting chromatographic data poses challenges to analysts. In this work, artificial intelligence (AI) was developed by transfer learning in a convolutional neural network (CNN), GoogLeNet. The image classification AI was fine-tuned to create intelligent classification systems to discriminate samples containing gasoline residues from burned substrates. All ground truth samples were analyzed by headspace solid-phase microextraction (HS-SPME) coupled with a gas chromatograph and mass spectrometer (GC/MS). The HS-SPME-GC/MS data were transformed into three types of image presentations, that is, heatmaps, extracted ion heatmaps, and total ion chromatograms. The abundance and mass-to-charge ratios of each scan were converted into image patterns that are characteristic of the chemical profiles of gasoline. The transfer learning data were labeled as "gasoline present" and "gasoline absent" classes. The assessment results demonstrated that all AI models achieved 100 ± 0% accuracy in identifying neat gasoline. When the models were assessed using the spiked samples, the AI model developed using the extracted ion heatmap obtained the highest accuracy rate (95.9 ± 0.4%), which was greater than those obtained by other machine learning models, ranging from 17.3 ± 0.7% to 78.7 ± 0.7%. The proposed work demonstrated that the heatmaps created from GC/MS data can represent chemical features from the samples. Additionally, the pretrained CNN models are readily available in the transfer learning workflow to develop AI for GC/MS data interpretation in fire debris analysis.

Discovery of Jupiter Family Comet 2011 UG104 Through AI Enhanced Citizen Science

We report the discovery of cometary activity from minor planet 2011 UG104, which we classify as a Jupiter Family Comet (JFC). This discovery was aided by our Artificial Intelligence (AI) classification system: TailNet. JFC's, short-period comets with eccentric Jupiter-crossing orbits, originate from the Kuiper Belt and thus give us unique insight into the composition and distribution of volatiles in the outer solar system, past and present. Our AI assistant TailNet first classified 2011 UG104 as active, which was affirmed by Citizen Scientists on our NASA Partner Program Active Asteroids. Through further archival image searches our science team found evidence of activity on 2011 UG104 on three separate observations from 2021 February to 2021 April (81.°8 < f < 95.°0).

An intelligent model for classifying supraventricular tachycardia mechanisms based on 12-lead wearable electrocardiogram devices

To develop an intelligent model for differential diagnosis of atrioventricular nodal re-entrant tachycardia (AVNRT) and atrioventricular re-entrant tachycardia (AVRT) using 12-lead wearable electrocardiogram devices. A total of 356 samples of 12-lead supraventricular tachycardia (SVT) electrocardiograms recorded by wearable devices were randomly divided into training and validation sets using 5-fold cross validation to establish the intelligent classification model, and 101 patients with the diagnosis of SVT undergoing electrophysiological studies and radiofrequency ablation from October, 2021 to March, 2023 were selected as the testing set. The changes in electrocardiogram parameters before and during induced tachycardia were compared. Based on multiscale deep neural network, an intelligent diagnosis model for classifying SVT mechanisms was constructed and validated. The 3-lead electrocardiogram signals from Ⅱ, Ⅲ, and Ⅴ1 were extracted to build new classification models, whose diagnostic efficacy was compared with that of the 12-lead model. Of the 101 patients with SVT in the testing set, 68 were diagnosed with AVNRT and 33 were diagnosed with AVRT by electrophysiological study. The pre-trained model achieved a high area under the precision-recall curve (0.9492) and F1 score (0.8195) for identifying AVNRT in the validation set. The total F1 scores of the lead Ⅱ, Ⅲ, Ⅴ1, 3-lead and 12-lead intelligent diagnostic models in the testing set were 0.5597, 0.6061, 0.3419, 0.6003 and 0.6136, respectively. Compared with the 12-lead classification model, the lead-Ⅲ model had a net reclassification index improvement of -0.029 (P=0.878) and an integrated discrimination index improvement of -0.005 (P=0.965). The intelligent diagnostic model based on multiscale deep neural network using wearable electrocardiogram devices has an acceptable accuracy for classifying SVT mechanisms.

Adap-BDCM: Adaptive Bilinear Dynamic Cascade Model for Classification Tasks on CNV Datasets.

Copy number variation (CNV) is an essential genetic driving factor of cancer formation and progression, making intelligent classification based on CNV feasible. However, there are a few challenges in the current machine learning and deep learning methods, such as the design of base classifier combination schemes in ensemble methods and the selection of layers of neural networks, which often result in low accuracy. Therefore, an adaptive bilinear dynamic cascade model (Adap-BDCM) is developed to further enhance the accuracy and applicability of these methods for intelligent classification on CNV datasets. In this model, a feature selection module is introduced to mitigate the interference of redundant information, and a bilinear model based on the gated attention mechanism is proposed to extract more beneficial deep fusion features. Furthermore, an adaptive base classifier selection scheme is designed to overcome the difficulty of manually designing base classifier combinations and enhance the applicability of the model. Lastly, a novel feature fusion scheme with an attribute recall submoduleis constructed, effectively avoiding getting stuck in local solutions and missing some valuable information. Numerous experiments have demonstrated that our Adap-BDCM model exhibits optimal performance in cancer classification, stage prediction, and recurrence on CNV datasets. This study can assist physicians in making diagnoses faster and better.

Intelligent classification and personalized recommendation of E-commerce products based on machine learning

With the rapid evolution of the Internet and the exponential proliferation of information, users encounter information overload and the conundrum of choice. Personalized recommendation systems play a pivotal role in alleviating this burden by aiding users in filtering and selecting information tailored to their preferences and requirements. This paper undertakes a comparative analysis between the operational mechanisms of traditional e-commerce commodity classification systems and personalized recommendation systems. It delineates the significance and application of personalized recommendation systems across e-commerce, content information, and media domains. Furthermore, it delves into the challenges confronting personalized recommendation systems in e-commerce, including data privacy, algorithmic bias, scalability, and the cold start problem. Strategies to address these challenges are elucidated. Subsequently, the paper outlines a personalized recommendation system leveraging the BERT model and nearest neighbor algorithm, specifically tailored to address the exigencies of the eBay e-commerce platform. The efficacy of this recommendation system is substantiated through manual evaluation, and a practical application operational guide and structured output recommendation results are furnished to ensure the system's operability and scalability.

Soil classification based on unsupervised learning using cone penetration test data

Borehole data obtained during geological surveys are the most essential source for understanding soil stratification. It is a prerequisite to know the soil classes up to some depths prior to any construction. However, the direct method to identify the soil classes by drilling boreholes and testing soil samples is costly. A cost-effective alternative is the Cone Penetration Testing (CPT), which is one of the most popular soil investigation methods. This paper explores the intelligent classification of soil layers based on CPT data using three unsupervised machine learning methods: K-means, Gaussian Mixture Process, and BIRCH. The research investigates the classification performance of different models in scenarios with 2 combinations, 3 combinations, 4 combinations, and 5 combinations. The results indicate that the Gaussian Mixture Process method exhibits the best classification performance, followed by the BIRCH method, while K-means performs relatively poorly. Using unsupervised learning for intelligent soil layer classification offers a fast and clear process, but the accuracy still requires further improvement. This study provides a valuable reference for future soil classification studies.

Exploring an Intelligent Classification Model for the Recognition of Automobile Sounds Based on EEG Physiological Signals

The advancement of an intelligent automobile sound switching system has the potential to elevate the market standing of automotive products, with the pivotal prerequisite being the selection of automobile sounds based on the driver’s subjective perception. The subjective responses of diverse individuals to sounds can be objectively manifested through EEG signals. Therefore, EEG signals are employed herein to attain the recognition of automobile sounds. A subjective evaluation and EEG signal acquisition experiment are designed involving the stimulation of three distinct types of automobile sounds, namely comfort, power, and technology sounds, and a comprehensive database of EEG signals corresponding to these three sound qualities is established. Then, a specific transfer learning model based on a convolutional neural network (STL-CNN) is formulated, where the method of training the upper layer parameters with the fixed bottom weights is proposed to adaptively extract the EEG features related to automobile sounds. These improvements contribute to improving the generalization ability of the model and realizing the recognition of automobile sounds fused with EEG signals. The results of the comparison with traditional support vector machine (SVM) and convolutional neural network (CNN) models demonstrate that the accuracy of the test set of the STL-CNN model reaches 91.5%. Moreover, its comprehensive performance, coupled with the ability to adapt to individual differences, surpasses that of both SVM and CNN models. The demonstrated method in the recognition of automobile sounds based on EEG signals is of significance for the future implementation of switching driving sound modes fused with EEG signals.

A sensitivity indicator screening and intelligent classification method for the diagnosis of T2D-CHD.

The prevalence of Type 2 Diabetes Mellitus (T2D) and its significant role in increasing Coronary Heart Disease (CHD) risk highlights the urgent need for effective CHD screening within this population. Despite current advancements in T2D management, the complexity of cardiovascular complications persists. Our study aims to develop a comprehensive CHD screening model for T2D patients, employing multimodal data to improve early detection and management, addressing a critical gap in clinical practice. We analyzed data from 699 patients, including 471 with CHD (221 of these also had T2D) and a control group of 228 without CHD. Employing strict diagnostic criteria, we conducted significance testing and multivariate analysis to identify key indicators for T2D-CHD diagnosis. This led to the creation of a neural network model using 21 indicators and a logistic regression model based on an 8-indicator subset. External validation was performed with an independent dataset from an additional 212 patients to confirm the models' generalizability. The neural network model achieved an accuracy of 90.7%, recall of 90.78%, precision of 90.83%, and an F-1 score of 0.908. The logistic regression model demonstrated an accuracy of 90.13%, recall of 90.1%, precision of 90.22%, and an F-1 score of 0.9016. External validation reinforced the models' reliability and effectiveness in broader clinical settings. Our AI-driven diagnostic models significantly enhance early CHD detection and management in T2D patients, offering a novel, efficient approach to addressing the complex interplay between these conditions. By leveraging advanced analytics and comprehensive patient data, we present a scalable solution for improving clinical outcomes in this high-risk population, potentially setting a new standard in personalized care and preventative medicine.

Intelligent Recognition of Valid Microseismic Events Based on Self-supervised Learning

The identification of valid microseismic events is a crucial stage in the processing of microseismic data and plays a central role in subsequent monitoring and early warning of rockburst disasters. However, obtaining microseismic data is difficult, and manually identifying effective microseismic signals is even more challenging. Therefore, exploring high-precision intelligent classification methods with limited labeled data is necessary. In this study, we applied a self-supervised learning method based on contrastive learning to classify small samples of labeled data. Firstly, use large unlabeled data to pre-train SimCLR (a simple contrastive learning framework) for transfer learning to classify small sample labeled data. The classification accuracy was 87.14%, an increase of 11.3% compared to the supervised-deep-learning method. Furthermore, we directly applied the pre-trained SimCLR to the microseismic data of various projects, achieving a classification accuracy of 86.70%. This demonstrates strong classification performance and generalization and provides valuable technical support for the subsequent monitoring and warning of rockburst disasters.

Reinvestigating the performance of artificial intelligence classification algorithms on COVID-19 X-Ray and CT images

There are concerns that artificial intelligence (AI) algorithms may create underdiagnosis bias by mislabeling patient individuals with certain attributes (e.g., female and young) as healthy. Addressing this bias is crucial given the urgent need for AI diagnostics facing rapidly spreading infectious diseases like COVID-19. We find the prevalent AI diagnostic models show an underdiagnosis rate among specific patient populations, and the underdiagnosis rate is higher in some intersectional specific patient populations (for example, females aged 20-40 years). Additionally, we find training AI models on heterogeneous datasets (positive and negative samples from different datasets) may lead to poor model generalization. The model's classification performance varies significantly across test sets, with the accuracy of the better performance being over 40% higher than that of the poor performance. In conclusion, we developed an AI bias analysis pipeline to help researchers recognize and address biases that impact medical equality and ethics.

Data dimensionality reduction for an optimal switching mode classification applied to a step-down power converter

Abstract A dimensional reduction algorithm is applied to an intelligent classification model with the purpose of improving the efficiency and accuracy. The proposed classification model, used to distinguish the operating mode: Hard- and Soft-Switching, is presented and an analysis of the synchronized rectified step-down converter is done. With the aim of improving the accuracy and reducing the computational cost of the model, three different methods for dimensional reduction are applied to the input dataset of the model: self-organizing maps, principal component analysis and correlation matrix. The obtained results show how the number of variable is highly reduced and the performance of the classification model is boosted: the results manifest an improve in the accuracy and efficiency of the classification.

Using deep learning-based artificial intelligence electronic images in improving middle school teachers' literacy.

With the rapid development of societal information, electronic educational resources have become an indispensable component of modern education. In response to the increasingly formidable challenges faced by secondary school teachers, this study endeavors to analyze and explore the application of artificial intelligence (AI) methods to enhance their cognitive literacy. Initially, this discourse delves into the application of AI-generated electronic images in the training and instruction of middle school educators, subjecting it to thorough analysis. Emphasis is placed on elucidating the pivotal role played by AI electronic images in elevating the proficiency of middle school teachers. Subsequently, an integrated intelligent device serves as the foundation for establishing a model that applies intelligent classification and algorithms based on the Structure of the Observed Learning Outcome (SOLO). This model is designed to assess the cognitive literacy and teaching efficacy of middle school educators, and its performance is juxtaposed with classification algorithms such as support vector machine (SVM) and decision trees. The findings reveal that, following 600 iterations of the model, the SVM algorithm achieves a 77% accuracy rate in recognizing teacher literacy, whereas the SOLO algorithm attains 80%. Concurrently, the spatial complexities of the SVM-based and SOLO-based intelligent literacy improvement models are determined to be 45 and 22, respectively. Notably, it is discerned that, with escalating iterations, the SOLO algorithm exhibits higher accuracy and reduced spatial complexity in evaluating teachers' pedagogical literacy. Consequently, the utilization of AI methodologies proves highly efficacious in advancing electronic imaging technology and enhancing the efficacy of image recognition in educational instruction.