Learning Classifiers Research Articles

Investigating response behavior through TF-IDF and Word2vec text analysis: A case study of PISA 2012 problem-solving process data

The process data in computer-based problem-solving evaluation is rich in valuable implicit information. However, its diverse and irregular structure poses challenges for effective feature extraction, leading to varying degrees of information loss in existing methods. Process-response behavior exhibits similarities to textual data in terms of the key units and contextual relationships. Despite the scarcity of relevant research, exploring text analysis methods for feature recognition in process data is significant. This study investigated the efficacy of Term Frequency-Inverse Document Frequency (TF-IDF) and Word to Vector (Word2vec) in extracting response behavior features and compared the predictive, analytical, and clustering effects of classical machine learning methods (supervised and unsupervised) on response behavior. An analysis of the PISA 2012 computer-based problem-solving dataset revealed that TF-IDF effectively extracted key response behaviors, whereas Word2vec captured effective features from sequenced response behaviors. In addition, in supervised machine learning using both methods, the random forest model based on TF-IDF performed the best, followed by the SVM model based on Word2vec. Word2vec-based models outperformed TF-IDF-based ones in the F1-score, accuracy, and recall (except for precision) across the logistic regression, k-nearest neighbor, and support vector machine algorithms. In unsupervised machine learning, the k-means algorithm effectively clustered different response behavior patterns extracted by these methods. The findings underscore the theoretical and methodological transferability of these text analysis methods in educational and psychological assessment contexts. This study offers valuable insights for research and practice in similar domains by yielding rich feature representations, supplementing fine-grained assessment evidence, fostering personalized learning, and introducing novel insights for educational assessment.

ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting.

Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This article proposes a novel hybrid hierarchical deep-learning (DL) model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (ES) and a recurrent neural network (RNN). ES extracts dynamically the main components of each individual TS and enables on-the-fly deseasonalization, which is particularly useful when operating on a relatively small dataset. A multilayer RNN is equipped with a new type of dilated recurrent cell designed to efficiently model both short and long-term dependencies in TS. To improve the internal TS representation and thus the model's performance, RNN learns simultaneously both the ES parameters and the main mapping function transforming inputs into forecasts. We compare our approach against several baseline methods, including classical statistical methods and machine learning (ML) approaches, on STLF problems for 35 European countries. The empirical study clearly shows that the proposed model has high expressive power to solve nonlinear stochastic forecasting problems with TS including multiple seasonality and significant random fluctuations. In fact, it outperforms both statistical and state-of-the-art ML models in terms of accuracy.

A topological approach for semi-supervised learning

Nowadays, Machine Learning and Deep Learning methods have become the state-of-the-art approach to solve data classification tasks. In order to use those methods, it is necessary to acquire and label a considerable amount of data; however, this is not straightforward in some fields, since data annotation is time consuming and might require expert knowledge. This challenge can be tackled by means of semi-supervised learning methods that take advantage of both labelled and unlabelled data. In this work, we present new semi-supervised learning methods based on techniques from Topological Data Analysis (TDA). In particular, we have created two semi-supervised learning methods following two topological approaches. In the former, we have used a homological approach that consists in studying the persistence diagrams associated with the data using the bottleneck and Wasserstein distances. In the latter, we have considered the connectivity of the data. In addition, we have carried out a thorough analysis of the developed methods using 9 tabular datasets with low and high dimensionality. The results show that the developed semi-supervised methods outperform the results obtained with models trained with only manually labelled data, and are an alternative to other classical semi-supervised learning algorithms.

Comparison of classical Machine Learning-based algorithms to predict Triplex Forming Oligonucleotides

Machine learning algorithms can be utilized to tackle genomic challenges in biological systems, such as identifying therapeutic targets for drug development and searching for effective treatments for chronic diseases like cancer. Triplex-forming oligonucleotides (TFOs) can recognize specific sites in the major groove of duplex DNA sequences, aiding in the identification of therapeutic targets via computational methods. This study aims to compare the performance of five classical machine learning algorithms—Support Vector Machine (SVM), k-Nearest Neighbours (kNN), Decision Tree (DT), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—in classifying single-stranded DNA into TFOs. Three datasets were created from an oligo library targeting the supF gene, developed by Kaufmann et al., and used to train the algorithms. The classifiers were optimized through hyperparameter tuning and their performance was evaluated using accuracy, precision, recall, and F1-score metrics. SVM and kNN achieved less than 90 percent accuracy, while DT, RF, and XGBoost, which used tree-based methods, attained over 90 percent accuracy. The XGBoost model showed the best performance with over 96 percent accuracy in classifying single-stranded DNA into TFOs. This study demonstrates that supervised machine learning techniques are effective for accurately classifying single-stranded DNA into TFOs.

Antiprotozoal peptide prediction using machine learning with effective feature selection techniques

BackgroundProtozoal pathogens pose a considerable threat, leading to notable mortality rates and the ongoing challenge of developing resistance to drugs. This situation underscores the urgent need for alternative therapeutic approaches. Antimicrobial peptides stand out as promising candidates for drug development. However, there is a lack of published research focusing on predicting antimicrobial peptides specifically targeting protozoal pathogens. In this study, we introduce a successful machine learning-based framework designed to predict potential antiprotozoal peptides effective against protozoal pathogens. ObjectiveThe primary objective of this study is to classify and predict antiprotozoal peptides using diverse negative datasets. MethodsA comprehensive literature review was conducted to gather experimentally validated antiprotozoal peptides, forming the positive dataset for our study. To construct a robust machine learning classifier, multiple negative datasets were incorporated, including (i) non-antimicrobial, (ii) antiviral, (iii) antibacterial, (iv) antifungal, and (v) antimicrobial peptides excluding those targeting protozoal pathogens. Various compositional features of the peptides were extracted using the pfeature algorithm. Two feature selection methods, SVC-L1 and mRMR, were employed to identify highly relevant features crucial for distinguishing between the positive and negative datasets. Additionally, five popular classifiers i.e. Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, and XGBoost were used to build efficient decision models. ResultsXGBoost was the most effective in classifying antiprotozoal peptides from each negative dataset based on the features selected by the mRMR feature selection method. The proposed machine learning framework efficiently differentiate the antiprotozoal peptides from (i) non-antimicrobial (ii) antiviral (iii) antibacterial (iv) antifungal and (v) antimicrobial with accuracy of 97.27 %, 93.64 %, 86.36 %, 90.91 %, and 89.09 % respectively on the validation dataset. ConclusionThe models are incorporated in a user-friendly web server (www.soodlab.com/appred) to predict the antiprotozoal activity of given peptides.

Identifying neuroimaging biomarkers in major depressive disorder using machine learning algorithms and functional near-infrared spectroscopy (fNIRS) during verbal fluency task

One of the most prevalent psychiatric disorders is major depressive disorder (MDD), which increases the probability of suicidal ideation or untimely demise. Abnormal frontal hemodynamic changes detected by functional near-infrared spectroscopy (fNIRS) during verbal fluency task (VFT) have the potential to be used as an objective indicator for assessing clinical symptoms. However, comprehensive quantitative and objective assessment instruments for individuals who exhibit symptoms suggestive of depression remain undeveloped. Drawing from a total of 467 samples in a large-scale dataset comprising 289 MDD patients and 178 healthy controls, fNIRS measurements were obtained throughout the VFT. To identify unique MDD biomarkers, this research introduced a data representation approach for extracting spatiotemporal features from fNIRS signals, which were subsequently utilized as potential predictors. Machine learning classifiers (e.g., Gradient Boosted Decision Trees (GBDT) and Multilayer Perceptron) were implemented to assess the ability to predict selected features. The mean and standard deviation of the cross-validation indicated that the GBDT model, when combined with the 180-feature pattern, distinguishes patients with MDD from healthy controls in the most effective manner. The accuracy of correct classification for the test set was 0.829 ± 0.053, with an AUC of 0.895 (95 % CI: 0.864–0.925) and a sensitivity of 0.914 ± 0.051. Channels that made the most important contribution to the identification of MDD were identified using Shapley Additive Explanations method, located in the frontopolar area and the dorsolateral prefrontal cortex, as well as pars triangularis Broca's area. Assessment of abnormal prefrontal activity during the VFT in MDD serves as an objectively measurable biomarker that could be utilized to evaluate cognitive deficits and facilitate early screening for MDD. The model suggested in this research could be applied to large-scale case-control fNIRS datasets to detect unique characteristics of MDD and offer clinicians an objective biomarker-based analytical instrument to assist in the evaluation of suspicious cases.

Rapid discrimination between wild and cultivated Ophiocordyceps sinensis through comparative analysis of label-free SERS technique and mass spectrometry

Ophiocordyceps sinensis is a genus of ascomycete fungi that has been widely used as a valuable tonic or medicine. However, due to over-exploitation and the destruction of natural ecosystems, the shortage of wild O. sinensis resources has led to an increase in artificially cultivated O. sinensis. To rapidly and accurately identify the molecular differences between cultivated and wild O. sinensis, this study employs surface-enhanced Raman spectroscopy (SERS) combined with machine learning algorithms to distinguish the two O. sinensis categories. Specifically, we collected SERS spectra for wild and cultivated O. sinensis and validated the metabolic profiles of SERS spectra using Ultra-Performance Liquid Chromatography coupled with Orbitrap High-Resolution Mass Spectrometry (UPLC-Orbitrap-HRMS). Subsequently, we constructed machine learning classifiers to mine potential information from the spectral data, and the spectral feature importance map is determined through an optimized algorithm. The results indicate that the representative characteristic peaks in the SERS spectra are consistent with the metabolites identified through metabolomics analysis, confirming the feasibility of the SERS method. The optimized support vector machine (SVM) model achieved the most accurate and efficient capacity in discriminating between wild and cultivated O. sinensis (accuracy = 98.95%, 5-fold cross-validation = 98.38%, time = 0.89s). The spectral feature importance map revealed subtle compositional differences between wild and cultivated O. sinensis. Taken together, these results are expected to enable the application of SERS in the quality control of O. sinensis raw materials, providing a foundation for the efficient and rapid identification of their quality and origin.

X-Ray Source Classification Using Machine Learning: A Study with EP-WXT Pathfinder LEIA

X-ray observations play a crucial role in time-domain astronomy. The Einstein Probe (EP), a recently launched X-ray astronomical satellite, emerges as a forefront player in the field of time-domain astronomy and high-energy astrophysics. With a focus on systematic surveys in the soft X-ray band, EP aims to discover high-energy transients and monitor variable sources in the universe. To achieve these objectives, a quick and reliable classification of observed sources is essential. In this study, we developed a machine learning classifier for autonomous source classification using data from the EP-WXT Pathfinder—Lobster Eye Imager for Astronomy (LEIA) and EP-WXT simulations. The proposed Random Forest classifier, built on selected features derived from light curves, energy spectra, and location information, achieves an accuracy of approximately 95% on EP simulation data and 98% on LEIA observational data. The classifier is integrated into the LEIA data processing pipeline, serving as a tool for manual validation and rapid classification during observations. This paper presents an efficient method for the classification of X-ray sources based on single observations, along with implications of most effective features for the task. This work facilitates rapid source classification for the EP mission and also provides valuable insights into feature selection and classification techniques for enhancing the efficiency and accuracy of X-ray source classification that can be adapted to other X-ray telescope data.

Automatic Sucker Rod Pump Fault Diagnostics by Transfer Learning using GoogLeNet Integrated Machine Learning Classifiers

Oil and gas extraction is vital for meeting the energy needs of a growing global population. Artificial lift (AL) systems play a crucial role in oilfields, especially when reservoir pressure is low. Among these systems, sucker rod pumps (SRPs) are extensively employed for onshore hydrocarbon recovery operations. However, SRPs are susceptible to mechanical failures and operational challenges arising from evolving reservoir conditions. This study proposes an approach for fault diagnosis in SRPs using real-time data from sensors and machine learning (ML) algorithms to detect anomalies and patterns associated with potential problems. The proposed method involves deep learning (DL) for automated feature extraction from dynamometer cards and error-correcting output codes (ECOC) model-based supervised machine learners for efficiently assessing the operational state of the SRP. By forecasting potential failures, preemptive measures can be taken to minimize downtime and reduce maintenance costs. The application of ML in the analysis of SRP provides a potential tool for diagnosing and predicting failures, improving productivity efficiency, and reducing downtime. Also, the accuracy of Convolutional Neural Networks (CNN) models was compared with that of CNN-ECOC model-based learners in this study, and the results demonstrated that integrating algorithms such as Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) with the network caused significant improvements in the accuracy; however, Decision Tree (DT) and Naive Bayes (NB) did not perform well in the pattern classification task. Specifically, the GoogLeNet model achieved improved accuracy of 96.40% and 99.40% when SVM and k-NN were integrated, respectively. Conversely, with DT and NB, the accuracies dropped to 66.30% and 75.10%, respectively.

Arabic Dialect Identification in Social Media: A Hybrid Model with Transformer Models and BiLSTM

Arabic Dialect Identification (ADI) is a challenging task in natural language processing applications due to its diversity and regional variations. Despite previous efforts, this task is still difficult. Therefore, this study aims to use transformers to address the issue of ADI on social media. A combination of two hybrid models is proposed in this study: one that combines Bidirectional Long Short-Term Memory (BiLSTM) with CAMeLBERT, and the second model that combines the BiLSTM model with AlBERT. In addition, a novel dataset comprising 121,289 user-generated comments from various social media network platforms and four major Arabic dialects (Egyptian, Jordanian, Gulf and Yemeni) was introduced. Several experiments have been conducted using conventional Machine Learning Classifiers (MLCs) and Deep Learning Models (DLMs) as baselines to measure the performance and effectiveness of the proposed models. In addition, binary classification is performed between two dialects to determine which are closest to each other. The performance of the model is measured using common metrics such as precision, recall, F-score and F-measure. Experiment results demonstrate the superior efficiency of the proposed hybrid models in ADI, CAMeLBERT with BiLSTM and ALBERT with BiLSTM, which both recorded an accuracy of 87.67% and 86.51%, respectively.

Autism detection based on autism spectrum quotient using weighted average ensemble method

Autism spectrum disorder (ASD) is a condition that occurs in an individual, wherein it is accompanied by various symptoms such as difficulties in socializing with others. Early detection of ASD patients can assist in preventing various symptoms caused by ASD. The focus of this research is to automate the diagnosis of ASD in an individual based on the results of the autism spectrum quotient (AQ) using weighted average ensemble method. Initially, preprocessing is carried out on the dataset to ensure optimal performance of the resulting model. In the preprocessing step, the filling of missing values and feature selection occurs, where the feature selection method being utilized is p-value. The model in this research uses the weighted average ensemble method, which is the model that combines three machine learning classification algorithms. Eight classification algorithms are tested to identify the three algorithms with the best performance, namely gaussian Naïve Bayes (NB), logistic regression (LR), and random forest (RF). Following the testing, the model constructed using the weighted average ensemble method exhibits the highest performance compared to the model built using a single classification algorithm. The performance matrix used to measure the model’s performance is area under the curve (AUC)/receiver operating characteristic (ROC), with the developed model achieving an AUC/ROC value of 0.912.

Enhancing the Decision Tree Algorithm to Improve Performance Across Various Datasets

Background: The Village Fund is an initiative by the central government to promote equitable regional development. However, it has also led to corruption. Many Indonesians share their opinions on the Village Fund on social media platforms like X, and news coverage is extensive on portals like detik.com. Objective: This study aims to classify data from social media and news coverage to enhance understanding. Methods: The research improves the decision tree algorithm by integrating other algorithms and techniques such as XGBoost and SMOTE. Ensuring high accuracy is vital for the credibility of machine learning classifications among the public. The study uses two different datasets, necessitating varied testing approaches. For the news portal dataset, a single test with seven labels is conducted, followed by enhancement with XGBoost. The X dataset undergoes two tests with datasets of 1200 and 3078 entries, using three labels. Conclusion: The evaluation results indicate that the highest accuracy achieved with the news portal data was 82%, thanks to a combination of decision tree algorithms with various parameters and the balancing effect of SMOTE. For the Twitter dataset with 3078 entries, the highest accuracy reached 95%, attributed to the application of ensemble techniques, particularly boosting.

Comparative analysis of heart failure prediction using machine learning models

Heart failure is a critical health problem worldwide, and its prediction is a major challenge in medical science. Machine learning has shown great potential in predicting heart failure by analyzing large amounts of medical data. Heart failure prediction with the help of machine learning classification algorithms involves the use of models such as decision trees, logistic regression, and support vector machines to identify and analyze potential risk factors for heart failure. By analyzing large datasets containing medical and lifestyle-related variables, these models can accurately predict the likelihood of heart failure occurrence in individuals. In our research, the heart failure prediction and comparison are done using Logistic Regression, KNN, SVM, decision tree and random forest The accurate identification of high-risk individuals enables early intervention and better management of heart failure, reducing the risk of mortality and morbidity associated with this condition. Overall, machine learning algorithms play a major role in improving the accuracy of heart failure risk assessment, allowing for more personalized and effective prevention and treatment strategies.

CBAM VGG16: An efficient driver distraction classification using CBAM embedded VGG16 architecture

Driver monitoring systems (DMS) are crucial in autonomous driving systems (ADS) when users are concerned about driver/vehicle safety. In DMS, the significant influencing factor of driver/vehicle safety is the classification of driver distractions or activities. The driver’s distractions or activities convey meaningful information to the ADS, enhancing the driver/ vehicle safety in real-time vehicle driving. The classification of driver distraction or activity is challenging due to the unpredictable nature of human driving. This paper proposes a convolutional block attention module embedded in Visual Geometry Group (CBAM VGG16) deep learning architecture to improve the classification performance of driver distractions. The proposed CBAM VGG16 architecture is the hybrid network of the CBAM layer with conventional VGG16 network layers. Adding a CBAM layer into a traditional VGG16 architecture enhances the model’s feature extraction capacity and improves the driver distraction classification results. To validate the significant performance of our proposed CBAM VGG16 architecture, we tested our model on the American University in Cairo (AUC) distracted driver dataset version 2 (AUCD2) for cameras 1 and 2 images. Our experiment results show that the proposed CBAM VGG16 architecture achieved 98.65% classification accuracy for camera 1 and 97.85% for camera 2 AUCD2 datasets. The CBAM VGG16 architecture also compared the driver distraction classification performance with DenseNet121, Xception, MoblieNetV2, InceptionV3, and VGG16 architectures based on the proposed model’s accuracy, loss, precision, F1 score, recall, and confusion matrix. The drivers’ distraction classification results indicate that the proposed CBAM VGG16 has 3.7% classification improvements for AUCD2 camera 1 images and 5% for camera 2 images compared to the conventional VGG16 deep learning classification model. We also tested our proposed architecture with different hyperparameter values and estimated the optimal values for best driver distraction classification. The significance of data augmentation techniques for the data diversity performance of the CBAM VGG16 model is also validated in terms of overfitting scenarios. The Grad-CAM visualization of our proposed CBAM VGG16 architecture is also considered in our study, and the results show that VGG16 architecture without CBAM layers is less attentive to the essential parts of the driver distraction images. Furthermore, we tested the effective classification performance of our proposed CBAM VGG16 architecture with the number of model parameters, model size, various input image resolutions, cross-validation, Bayesian search optimization and different CBAM layers. The results indicate that CBAM layers in our proposed architecture enhance the classification performance of conventional VGG16 architecture and outperform the state-of-the-art deep learning architectures.

Wasserstein generative adversarial network with gradient penalty and convolutional neural network based motor imagery EEG classification

Objective.Due to the difficulty in acquiring motor imagery electroencephalography (MI-EEG) data and ensuring its quality, insufficient training data often leads to overfitting and inadequate generalization capabilities of deep learning-based classification networks. Therefore, we propose a novel data augmentation method and deep learning classification model to enhance the decoding performance of MI-EEG further.Approach.The raw EEG signals were transformed into the time-frequency maps as the input to the model by continuous wavelet transform. An improved Wasserstein generative adversarial network with gradient penalty data augmentation method was proposed, effectively expanding the dataset used for model training. Additionally, a concise and efficient deep learning model was designed to improve decoding performance further.Main results.It has been demonstrated through validation by multiple data evaluation methods that the proposed generative network can generate more realistic data. Experimental results on the BCI Competition IV 2a and 2b datasets and the actual collected dataset show that classification accuracies are 83.4%, 89.1% and 73.3%, and Kappa values are 0.779, 0.782 and 0.644, respectively. The results indicate that the proposed model outperforms state-of-the-art methods.Significance.Experimental results demonstrate that this method effectively enhances MI-EEG data, mitigates overfitting in classification networks, improves MI classification accuracy, and holds positive implications for MI tasks.

Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults.

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately.

A two-stream decision fusion network for cervical pap-smear image classification tasks

Deep learning, especially Convolution Neural Networks (CNNs), has demonstrated superior performance in image recognition and classification tasks. They make complex pattern recognition possible by extracting image features through layers of abstraction. However, despite the excellent performance of deep learning in general image classification, its limitations are becoming apparent in specific domains such as cervical cell medical image classification. This is because although the morphology of cervical cells varies between normal, diseased and cancerous, these differences are sometimes very small and difficult to capture. To solve this problem, we propose a two-stream feature fusion model comprising a manual feature branch, a deep feature branch, and a decision fusion module. Specifically, We process cervical cells through a modified DarkNet backbone network to extract deep features. In order to enhance the learning of deep features, we have devised scale convolution blocks to substitute the original convolution, termed Basic convolution blocks. The manual feature branch comprises a range of traditional features and is linked to a multilayer perceptron. Additionally, we design three decision feature channels trained from both manual and deep features to enhance the model performance in cervical cell classification. Our proposed model demonstrates superior performance when compared to state-of-the-art cervical cell classification models. We establish a 15-category 148762 cervical cytopathology image dataset (CCID). In addition, we additionally conducted experiments on the SIPaKMeD dataset. Numerous experiments show that our proposed model performs excellently compared to state-of-the-art classification models. The outcomes illustrate that our approach can significantly aid pathologists in accurately evaluating cervical smears.

Continuation of Learning During COVID-19 Situation in Nepal

This study explored the obstacles and ways of continuation for learning faced by school teachers during and after the COVID-19 situation. The quantitative cross-sectional survey research design was adopted. All the school teachers of Nepal were the population for this study and the sample size was 226. The online survey method was adopted for the data collection tools. A set of closed and open-ended questionnaires were distributed to respondents and data was collected using Google Forms. The study seeks the relationship between the independent variables (age, experience of teaching, school location, teacher’s residence, access to the internet, access to digital devices, knowledge about ICTs interest in online teaching) and dependent variables (continuation of online teaching). It was found that the community teaching and homework/ assignment methods were applicable to the rural areas. Continuing online teaching would be inconvenient for the students who had no internet access. According to the teacher's response, it was found that about 90% of students had no access to the internet. Although online teaching was suitable for the COVID-19 situation, it was biased for the maximum number of students. The teacher's interest and the obstacles in the online class and continuation of learning are significantly co-related (0.003 and 0.000 respectively). There was no significant difference between male and female teachers in continuation for online learning but a greater percentage of males are involved in online classes than females. The experienced teachers equally continued their learning of digital skills. There was a problem with the internet/ wifi/ 3G/ 4G network in rural areas. Teacher adjusted their teaching and learning activities even if they had no access to a laptop. The study concludes that teachers are ready for online classes and they regularly update their digital skills with changing times but digital divides created a serious problem with conducting online classes. So, the Government of Nepal should pay attention to teacher training, integration of digital skills in the curriculum, and proper allocation of budget for infrastructure development.

A New Hybrid Model for Artificial Intelligence Assisted Tire Defect Detection: CTLDF+EnC

This paper focuses on an artificial intelligence based worn tire detection system proposed to detect cracks in the tires of vehicle drivers. Although drivers are generally aware of the importance of tire tread depth and air pressure, they are not aware of the risks associated with tire oxidation. However, tire oxidation and cracks can cause significant problems affecting driving safety. In this paper, we propose a new hybrid architecture for tire crack detection, CTLDF+EnC (Cascaded Transfer Learning Deep Features + Ensemble Classifiers), which uses deep features from pre-trained transfer learning methods in combination with ensemble learning methods. The proposed hybrid model utilizes features from nine transfer learning methods and classifiers including Stacking, Soft and Hard voting ensemble learning methods. Unlike X-Ray image-based applications for industrial use, the model proposed in this study can work with images obtained from any digital imaging device. Among the models proposed in the study, the highest test accuracy value was obtained as 76.92% with the CTLDF+EnC (Stacking) hybrid model. With CTLDF+EnC (Soft) and CTLDF+EnC (Solid) models, 74.15% and 72.92% accuracy values were obtained respectively. The results of the study show that the proposed hybrid models are effective in detecting tire problems. In addition, a low-cost and feasible structure is presented.

The advancements and future prospects of pedestrian action recognition based on machine learning algorithms

This paper highlights the shift from classical machine learning to deep learning models and describes the fundamental methodology and developments in pedestrian activity recognition. The four main steps of the workflow are the gathering of datasets, pre-processing, designing and training the model, and evaluating the outcome. To extract pedestrian feature vectors, data must first be collected, cleaned, and processed from public or proprietary datasets. These vectors are used to train deep learning or machine learning models, which are subsequently assessed and fine-tuned for use in practical applications such as behaviour analysis and surveillance. For action recognition, conventional machine learning techniques like Random Forests (RF) and Support Vector Machines (SVM) have been used. SVMs, despite their potential for computing complexity, identify the best hyperplanes for classification. The categorization rates for a variety of human behaviours have been enhanced by a combination strategy utilizing SVMs and decision trees. As shown in a study that uses smartphone accelerometers to accurately identify everyday activities, RFs can manage enormous datasets. Deep learning models that automatically learn complicated feature representations, such as VA-fusion, AGC-LSTM, and LC-POSEGAIT, provide improved performance. These models capture minute differences in pedestrian behaviour using CNNs, RNNs, and LSTM architectures. Interpretability, generalization to new datasets, and computing demands are some of the difficulties they encounter. Future developments could include using transfer learning to improve performance in many circumstances, combining deep learning and expert systems for improved interpretability, and utilizing distributed computing for processing in an effective manner.