Classification Model Research Articles

HHO optimized support vector machine classifier for traditional Chinese medicine syndrome differentiation of diabetic retinopathy

AIM: To develop a classifier for traditional Chinese medicine (TCM) syndrome differentiation of diabetic retinopathy (DR), using optimized machine learning algorithms, which can provide the basis for TCM objective and intelligent syndrome differentiation. METHODS: Collated data on real-world DR cases were collected. A variety of machine learning methods were used to construct TCM syndrome classification model, and the best performance was selected as the basic model. Genetic Algorithm (GA) was used for feature selection to obtain the optimal feature combination. Harris Hawk Optimization (HHO) was used for parameter optimization, and a classification model based on feature selection and parameter optimization was constructed. The performance of the model was compared with other optimization algorithms. The models were evaluated with accuracy, precision, recall, and F1 score as indicators. RESULTS: Data on 970 cases that met screening requirements were collected. Support Vector Machine (SVM) was the best basic classification model. The accuracy rate of the model was 82.05%, the precision rate was 82.34%, the recall rate was 81.81%, and the F1 value was 81.76%. After GA screening, the optimal feature combination contained 37 feature values, which was consistent with TCM clinical practice. The model based on optimal combination and SVM (GA_SVM) had an accuracy improvement of 1.92% compared to the basic classifier. SVM model based on HHO and GA optimization (HHO_GA_SVM) had the best performance and convergence speed compared with other optimization algorithms. Compared with the basic classification model, the accuracy was improved by 3.51%. CONCLUSION: HHO and GA optimization can improve the model performance of SVM in TCM syndrome differentiation of DR. It provides a new method and research idea for TCM intelligent assisted syndrome differentiation.

Machine learning assists the sensor array constructed by the tri-emission carbon dots to detect multiple metal ions

Metal ions are related to the health of daily life, which urges to be detected and identified by efficient sensors. We first synthesize tri-emission carbon dots for the functional determination of six metal ions and obtain the multi-dimension data to construct the fluorescent sensor array in the work. Inspired by the data-driven method, machine learning is employed in a sensor array to detect and analyze the six metal ions. The ion classification and concentration models are constructed to identify metal ion types and corresponding concentrations. The classification model could correctly discriminate six metal ions, reaching 99.5 % accuracy and the concentration model exhibits an excellent performance range from 30 to 330 μM, with a mean concentration difference value of 0.12 μM and R2 value of 0.9845 for the unknown sample. Furthermore, six metal ions in tap water also can be distinguished with 96 % accuracy and the recovery rate is between 101.89 % and 106.37 %. This work shows that the machine learning combined sensor array has significant advantages in detecting multiple metal ions and provides a novel thought for analyzing sensing data, accelerating the development of data-driven strategies in the sensing field. © 2001 Elsevier Science. All rights reserved.

Face mask classification using convolutional neural networks with facial image regions and super resolution

<p>Face mask classification is relevant to public health and safety, so an approach for face mask classification using Multi-Task Cascaded Convolutional Networks (MTCNN) for face detection on image data, ResNet152 architecture for feature extraction, and super-resolution method, BSRGAN, for enhanced image quality was proposed. The classification model was trained by a fully connected layer of neural networks. The goal is to classify each facial image into three classes: the image with a mask, without a mask, or with an incorrectly worn mask. The performance of each classification model on two real-world datasets was evaluated by Accuracy, Precision, Recall, and F1 score for different sets of input patterns which were features extracted from the facial image regions including their combinations. Using multiple image regions, i.e. face, nose, and mouth, as resources for preparing input features showed the improved classification performance compared to using single image regions. In addition, the super-resolution technique applied to medium or large-sized images can improve the performance of the face mask classification model. Our findings may further guide the development for greater effective models and techniques on face mask classification contributing to practical scenarios.</p>

Framework for multiple person identification using YOLOv8 detector: a transfer learning approach

Video surveillance extensively uses person detection and tracking technology based on video. The majority of person detection and classification techniques currently in use encounter challenges in video sequences brought on by occlusion, ambient lighting, and variations in human facial position. This paper proposed an effective person identification and classification system based on deep learning, which comprises a you only look once at version 8 (YOLOv8) detection and classification model, to classify human faces in video sequences accurately. This work proposes a new staff-detection and classification (S-DEC) dataset for comprehensive performance evaluation. visual tracker benchmark (VTB) standard database is used for performance comparison with the proposed S-DEC dataset. The proposed technique achieved 98.67% precision accuracy. For the S-DEC dataset, the system gave 94.67% accuracy in identifying facial images from a video sequence of 38 people addressing the pose variation occlusion challenge. Earlier methods used to provide approximately 85% to 90% results taking more execution time. Many existing techniques were successful in detecting people only-identification of the detected person has been done in limited papers. The proposed method uses the cross-stage partial connections (CSPDarknet53) model, integrated with YOLOv8, to achieve faster results. The proposed framework took 35 minutes to train a deep learning model. A testing time of 2 minutes ensured that the proposed framework outplayed other existing methodologies and successfully identified extra information about the detected person.

Enhancing EEG-based brain-computer interface systems through efficient machine learning classification techniques

Advances in the fields of neuroscience and computer science have greatly enhanced the human brain’s ability to communicate and interact with the surrounding environment. In addition, recent steps in machine learning (ML) have increased the use of electroencephalography (EEG)-based BCIs for artificial intelligence (AI) applications. The prevailing challenge in recording EEG sensor data is that the captured signals are mixed with noise, which makes their effective use difficult. Therefore, strengthening the classification stage becomes extremely important and plays a major role in addressing this problem. In this study, we chose five most widely used classification models that obtained the best results in this field and tested them on two open-source databases. We also focused on improving the hyperparameters of each algorithm to obtain best results. Our results indicate excellent results on the first dataset and acceptable for most models on the second, while RF showed superior performance on both with an accuracy of 100% on the first dataset and 86.47% on the second. This was achieved with the lowest training costs, and better performance compared to previous works we evaluated that used the same databases. These results provide valuable insights and advance the development of brain-computer interface (BCI) technology and design.

Factor analysis influencing Mobile JKN user experience using sentiment analysis

<span lang="EN-US">Social security administration for health or Badan Penyelenggara Jaminan Sosial Kesehatan (BPJS Kesehatan), as a public legal entity, has a critical role in the health of the Indonesian population. BPJS Kesehatan introduced the Mobile national health insurance or </span><em><span lang="EN-US">jaminan kesehatan nasional</span></em><span lang="EN-US"> (JKN) application to enhance its services, enabling Indonesians to access it directly. Nevertheless, the rating of the Mobile JKN application on the Google Play Store has shown a gradual decline over time. Therefore, this study was conducted to analyze the factors influencing the user experience of the Mobile JKN application, utilizing the review data obtained from the Google Play Store. Sentiment analysis using the Naïve Bayes (NB) classification model and support vector machine (SVM) combined with synthetic minority oversampling technique (SMOTE) and slang word replacement. The results obtained an accuracy value of 93.33%, precision of 93.76%, recall of 93.33%, and F1-score of 93.43%. A further analysis was conducted using online service quality factors to obtain the main factors influencing the experience of Mobile JKN application users. The evaluation findings revealed that factors of security, ease of use, and timeliness are three fundamental aspects that should be given immediate attention by BPJS Kesehatan while improving the Mobile JKN application in the future.</span>

Fault diagnosis method of PEMFC system based on ensemble learning

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.

Supervised and unsupervised learning models for pharmaceutical drug rating and classification using consumer generated reviews

Optimization of medication therapy depends on maximizing benefits and minimizing side effects of medications. This research showed how a joint approach using text mining, natural language processing, and machine learning can provide information for personalized and optimized medication therapy. Reviews on the benefits and side effects of prescription and over-the-counter medications were used to determine how well an integrated supervised and unsupervised learning could learn medication satisfaction. Supervised learning with naïve-Bayes, non-linear support vector machine with radial basis function kernels, and random forests with CART decision trees was measured by a micro-aggregated Matthews correlation coefficient and a macro-averaged F1 measure. Random forests outperformed support vector machines by almost 250% and naive-Bayes by 600% on the two evaluation metrics. All models did better with three rating levels, instead of five. Topic modelling and stacked cluster analysis were coupled with parts-of-speech tagging and text mining operations to establish a robust data preprocessing procedure to eliminate noisy features from the data. Unsupervised topic modelling and clustering represented an exploratory validation of how easy supervised classification would be. Well-defined latent topics were discovered including topics on “sleep quality”, “the opportunity to get back to work”, and “weight gain”. Overlapping clusters revealed that incorporating more information on social, demographic, or medical history variables could improve classifier performance. This research provided evidence that medication satisfaction can be learned with carefully designed joint supervised, unsupervised, and natural language learning techniques.

Multi-granularity tooth analysis via YOLO-based object detection models for effective tooth detection and classification

Accurate detection and classification of teeth is the first step in dental disease diagnosis. However, the same class of tooth exhibits significant variations in surface appearance. Moreover, the complex geometrical structure poses challenges in learning discriminative features among the different tooth classes. Due to these complex features, tooth classification is one of the challenging research domains in deep learning. To address the aforementioned issues, the presented study proposes discriminative local feature extraction at different granular levels using YOLO models. However, this necessitates a granular intra-oral image dataset. To facilitate this requirement, a dataset at three granular levels (two, four, and seven teeth classes) is developed. YOLOv5, YOLOv6, and YOLOv7 models were trained using 2,790 images. The results indicate superior performance of YOLOv6 for two-class classification problems. The model generated a mean average precision (mAP) value of 94%. However, as the granularity level is increased, the performance of YOLO models decreases. For, four and seven-class classification problems, the highest mAP value of 87% and 79% was achieved by YOLOv5 respectively. The results indicate that different levels of granularity play an important role in tooth detection and classification. The YOLO’s performance gradually decreased as the granularity decreased especially at the finest granular level.

Application of Deep Learning Classification Model for Regional Evaluation of Roof Pressure Support Evolution Effects Over Time in Coal Mining Face

Hydraulic support leg pressure serves as a crucial indicator for assessing work face support quality. Current evaluation methods for support quality primarily concentrate on static analyses-like inadequate initial support force, pressure overrun, and uneven bracket force-while neglecting dynamic column pressure changes. This paper introduces a model for assessing hydraulic support quality using deep learning techniques. Real-time data is preprocessed into a spatio-temporal pressure sub-matrix sample, which is then inputted into the model. This process assesses the support quality type and characterizes its dynamic evolution within the area. The model facilitates the identification of dynamic support quality effects in the working face area, aiding operators in making targeted adjustments to hydraulic support status. Experimental results revealed that the optimized LeNet-5 network-adjusting parameters like convolutional layer count, kernel size, and ReLU activation function-achieved the highest classification accuracy of 85.25% for support quality, surpassed other networks. Furthermore, the improved LeNet-5 network outperformed other networks in both F1 score and recall. Additionally, the improved LeNet-5 network achieved faster convergence to the optimal solution, accelerated training speed. This highlighted its advantages in evaluating the spatio-temporal support quality of hydraulic supports in smart mining operations.

Breast cancer detection through attention based feature integration model

<span lang="EN-US">Breast cancer is detected by screening mammography wherein X-rays are used to produce images of the breast. Mammograms for screening can detect breast cancer early. This research focuses on the challenges of using multi-view mammography to diagnose breast cancer. By examining numerous perspectives of an image, an attention-based feature-integration mechanism (AFIM) model that concentrates on local abnormal areas associated with cancer and displays the essential features considered for evaluation, analyzing cross-view data. This is segmented into two views the bi-lateral attention module (BAM) module integrates the left and right activation maps for a similar projection is used to create a spatial attention map that highlights the impact of asymmetries. Here the module's focus is on data gathering through medio-lateral oblique (MLO) and bilateral craniocaudal (CC) for each breast to develop an attention module. The proposed AFIM model generates using spatial attention maps obtained from the identical image through other breasts to identify bilaterally uneven areas and</span><span lang="EN-US">class activation map (CAM) generated from two similar breast images to emphasize the feature channels connected to a single lesion in a breast. AFIM model may easily be included in ResNet-style architectures to develop multi-view classification models.</span>

Hybrid deep learning model for YouTube spam comment detection

Social media platforms, including YouTube and Facebook, allow users to interact through comments and videos. However, the openness of these platforms also makes them susceptible to spammers engaging in phishing, malware distribution, and advertisement dissemination. In response, our study introduces an innovative technique for detecting features indicative of spam within comments associated with shared videos. The initial phase involves data collection from the University of California, Irvine (UCI) machine learning repository and preprocessing using tokenization and lemmatization. Subsequently, a rigorous feature selection process is executed, and experiments are conducted with various proposed classification models. The performance evaluation demonstrates outstanding accuracy in identifying spam comments on YouTube: convolutional neural network with gated recurrent unit (CNN-GRU) at 95.92%, convolutional neural network with long short-term memory (CNN-LSTM) at 95.41%, convolutional neural network with bidirectional long short-term memory (CNN-biLSTM) at 96.43%, gated recurrent unit (GRU) at 95.41%, long short-term memory (LSTM) at 94.13%, and bidirectional long short-term memory (biLSTM) at 96.94% and convolutional neural network (CNN) at 94.64%. These results highlight the substantial contribution of our approach to spam detection and the fortification of online security.

Classification of tea leaf disease using convolutional neural network approach

Leaf diseases on tea plants affect the quality of tea. This issue must be overcome since preparing tea drinks requires high-quality tea leaves. Various automatic models for identifying disease in tea leaves have been developed; however, their performance is typically low since the extracted features are not selective enough. This work presents a classification model for tea leaf disease that distinguishes six leaf classes: algal spot, brown, blight, grey blight, helopeltis, red spot, and healthy. Deep learning using a convolutional neural network (CNN) builds an effective model for detecting tea leaf illness. The Kaggle public dataset contains 5,980 tea leaf images on a white background. Pre-processing was performed to reduce computing time, which involved shrinking and normalizing the image prior to augmentation. Augmentation techniques included rotation, shear, flip horizontal, and flip vertical. The CNN model was used to classify tea leaf disease using the MobileNetV2 backbone, Adam optimizer, and rectified linear unit (ReLU) activation function with 224×224 input data. The proposed model attained the highest performance, as evidenced by the accuracy value 0.9455.

Improved performance of fake account classifiers with percentage overlap features selection

Feature selection plays a crucial role in the development of high-performance classification models. We propose an innovative method for detecting fake accounts. This method leverages the percentage overlap technique to refine feature selection. We introduce our technique upon earlier work that showcased the enhanced efficacy of the Naïve Bayesian classifier through dataset normalization. Our study employs a dataset of account profiles sourced from Twitter, which we normalize using the Min-Max method. We analyze the results through a series of comprehensive experiments involving diverse classification algorithms—such as Naïve Bayes, decision tree, k-nearest neighbors (KNN), deep learning, and support vector machines (SVM). Our experimental results demonstrate a 100% accuracy achieved by the SVM and deep learning classifiers. The results are attributed to the percentage overlap technique, which facilitates the identification of four highly informative features. These findings outperform models with more extensive feature sets, underscoring the efficacy of our approach.

Deep Learning Enabled Diabetic Retinopathy Diagnosis Using Retinal Fundus Images

Abstract: This paper pivots on (DR) is a leading cause of blindness worldwide. Early detection and effective management are crucial in preventing damage to the retina. In recent years, (DL) techniques have shown promise in aiding the DR. This paper aims to investigate the diagnosis of using (CNNs) for automated DR screening. The study utilized a available patient dataset of retinal images to train and testing CNN model for DR detection and classification. Results showed that given (DL) techniques achieved with accurately in both tasks, outperforming existing state-of-the-art methods. The findings suggest the (DL) algorithms can aid in the early detection and management of DR, potentially reducing the burden of the condition on healthcare systems and improving patient outcomes

Unveiling Crash Casualties: A Neural Network Model for Crash Type Classification Using Traffic Datasets

Abstract: Traffic accidents, a significant public health burden with substantial economic costs, necessitate proactive measures for sustainable transportation. This study investigates the efficacy of neural networks in predicting crash types using traffic data. We propose a deep learning model that leverages the power of recurrent neural networks (RNNs) for sequential traffic pattern analysis and convolutional neural networks (CNNs) for extracting spatial features from traffic data. The model, trained on a labeled traffic dataset, learns to identify patterns and relationships between traffic characteristics (e.g., speed, volume, weather) and different crash types (e.g., rear-end collision, single-vehicle). The evaluation focuses on the model's accuracy in predicting crash types using metrics like precision, recall, and F1-score. This research contributes to the development of intelligent traffic management systems (ITMS) that can proactively identify and mitigate potential accidents, ultimately enhancing road safety and promoting a more sustainable transportation future.The implementation results indicate that the proposed method yields an accuracy of 82.93% approximately.

A Hybrid Model for Dry Waste Classification using Transfer Learning and Dimensionality Reduction

The categorization of waste plays a crucial part in efficient waste management, facilitating the recognition and segregation of various waste types to ensure appropriate disposal, recycling, or repurposing. With the growing concern for environmental sustainability, accurate waste classification systems are in high demand. Traditional waste classification methods often rely on manual sorting, which is time-consuming, labor-intensive, and prone to errors. Hence, there is a need for automated and efficient waste classification systems that can accurately categorize waste materials. In this research, we introduce an innovative waste classification system that merges feature extraction from a pretrained EfficientNet model with Principal Component Analysis (PCA) to reduce dimensionality. The methodology involves two main stages: (1) transfer learning using the EfficientNet-CNN architecture for feature extraction, and (2) dimensionality reduction using PCA to reduce the feature vector dimensionality. The features extracted from both the average pooling and convolutional layers are combined by concatenation, and subsequently, classification is performed using a fully connected layer. Extensive experiments were conducted on a waste dataset, and the proposed system achieved a remarkable accuracy of 99.07%. This outperformed the state-of-the-art waste classification systems, demonstrating the effectiveness of the combined approach. Further research can explore the application of the proposed waste classification system on larger and diverse datasets, optimize the dimensionality reduction technique, consider real-time implementation, investigate advanced techniques like ensemble learning and deep learning, and assess its effectiveness in industrial waste management systems.

Data & Semantic Analysis Fake News Detection Based Domain-Specific Auto Encoder Learning

Abstract: Efforts to create technology for automatically detecting fake news are actively underway as the spread of misinformation on social media continues to escalate. However, most of these approaches primarily concentrate on the linguistic and structural aspects of fake news, such as identifying sources or authors, message length, and the frequency of negative language. In contrast, our study introduces a phony news detection model leveraging machine learning that incorporates user behaviors, news, and social capital-based social network dynamics. We used the XG Boost model to evaluate each feature's significance and identify the critical elements affecting the identification of fake news to capture the variables related to the spread of phony news entirely. We implemented SVM, RF, LR, CART, and NNET, well-known machine learning classification models, using these identified factors and assessed how well they detected bogus news. This work used a cross-validation process to prevent overfitting and to generalize the established models. Additionally, the predicted accuracy of the established models was compared. The RF model had the best forecast accuracy, about 94%, while the NNET had the worst performance rate, about 92.1%. As disinformation is created and disseminated with growing sophistication, the results of this study should improve the effectiveness of false news detection systems.

Advanced Ensemble Framework for Diabetes Outcome Forecasting

Abstract: Diabetes is one of the chronic diseases, which is increasing from year to year. Developing an automated system that can detect diabetes patients plays an important role in medical science. A stack classifier model is designed for the detection of diabetes by combining three base estimators such as Random Forest Classifier, LightGBM Classifier, and K-Nearest Neighbors Classifier, and Logistic Regression as meta-classifiers. The data preprocessing includes transforming categorical variables into numerical format. Each base learner is trained on the preprocessed data and predictions are made. In the meta learner stage, Logistic Regression is trained to make predictions based on the predictions of the base learners. The goal of the meta learner is to learn how to combine the predictions of the base learners to make a more accurate final prediction on whether the patient is diabetic or not. The use of a stacking classifier improves prediction accuracy compared to using a single classifier. The developed model gives an accuracy of 98%. The 5-fold cross validation is used to get a more robust estimation of generalization error. Thus, the developed model offers a means to enhance early detection and elevate the quality of care for diabetic patients.

Application of artificial intelligence and machine learning techniques to the analysis of dynamic protein sequences.

We apply methods of Artificial Intelligence and Machine Learning to protein dynamic bioinformatics. We rewrite the sequences of a large protein data set, containing both folded and intrinsically disordered molecules, using a representation developed previously, which encodes the intrinsic dynamic properties of the naturally occurring amino acids. We Fourier analyze the resulting sequences. It is demonstrated that classification models built using several different supervised learning methods are able to successfully distinguish folded from intrinsically disordered proteins from sequence alone. It is further shown that the most important sequence property for this discrimination is the sequence mobility, which is the sequence averaged value of the residue-specific average alpha carbon B factor. This is in agreement with previous work, in which we have demonstrated the central role played by the sequence mobility in protein dynamic bioinformatics and biophysics. This finding opens a path to the application of dynamic bioinformatics, in combination with machine learning algorithms, to a range of significant biomedical problems.