Search

The fixed sliding window is the commonly used technique for signal segmentation in human activity recognition (HAR). However, the fixed sliding window may not produce optimal segmentation because human activities have varying durations, especially for transitional activities (TAs). This is because a large window size may contain activity signals belonging to different activities, and a small window size may split the activity signal into multiple windows. Furthermore, the fixed sliding window does not consider the relationship between adjacent windows, which may affect the performance of the HAR model. In this study, we propose a similarity segmentation approach (SSA) that exploits the temporal structure of the activity signal within the window segmentation process. Specifically, the proposed approach segments each window into subwindows and extracts the inner features by measuring the similarity between them. The inner features are used to measure the dissimilarity between the adjacent windows. The proposed approach is able to distinguish between transitional and nontransitional windows, which achieves more effective segmentation and classification processes. Two public datasets are used for the evaluation. The experimental results show that the proposed approach can distinguish TAs from basic activities (BAs) at 97.65% accuracy, which enhanced the accuracy of TAs recognition compared to the fixed sliding window by 33.41%. Also, our approach achieved accuracy for activity recognition of 92.71% and 86.65% for both datasets, respectively, which exceeds the fixed sliding window by 2.29% and 3.93% for both datasets, respectively. These results are significant and exceed the accuracy of the state-of-the-art models.

Purpose: The study aims to propose a predictive model that combines personality and demographic factors to predict student academic performance (SAP). This research study works on understanding, enhancing and applying techniques to enhance the prediction of SAP. Design/methodology/approach: The authors gathered information from 305 university students from Al-Zintan University Libya. The study uses a survey questionnaire to collect data on essential variables. The purpose of the questionnaire is to discover variables that affect students' academic performance. The survey questionnaire has 44 closed questions with Likert scale designs that were distributed to a variety of college students at the start of the first semester of 2022. It includes questions about demographics, personality, employment and institutional aspects. The authors proposed a predictive model to identify the main fundamental components, consisting of one dependent variable (SAP) and five independent constructs. The suggested model is tested using partial least squares (PLS) and structural equation modeling (SEM), which perform better than covariance-based structural equation modeling (CB-SEM). PLS-SEM performs well with smaller sample sizes, even for complicated models. Findings: The study results show that the proposed model accurately predicted the student's academic performance. The personality trait variables are a key factor that determines the actual student's academic performance. The student's academic performance is significantly impacted by each variable in the personality trait variables as well. Originality/value: The process of validating research was done empirically through the accuracy and efficiency of model performance. The study differs from previous studies in that it accumulated a wide range of factors from different dimensions, including student demographics and personality trait factors. The authors developed a structural equation model to predict students' academic performance.

Building classification models in activity recognition is based on the concept of exchangeability. While splitting the dataset into training and test sets, we assume that the training set is exchangeable with the test set and expect good classification performance. However, this assumption is invalid due to subject variability of the training and test sets due to age differences. This happens when the classification models are trained with adult dataset and tested it with elderly dataset. This study investigates the effects of subject variability on activity recognition using inertial sensor. Two different datasets—one locally collected from 15 elders and another public from 30 adults with eight types of activities—were used to evaluate the assessment techniques using ten-fold cross-validation. Three sets of experiments have been conducted: experiments on the public dataset only, experiments on the local dataset only, and experiments on public (as training) and local (as test) datasets using machine learning and deep learning classifiers including single classifiers (Support Vector Machine, Decision Tree, K-Nearest Neighbors), ensemble classifiers (Adaboost, Random Forest, and XGBoost), and Convolutional Neural Network. The experimental results show that there is a significant performance drop in activity recognition on different subjects with different age groups. It demonstrates that on average the drop in recognition accuracy is 9.75 and 12% for machine learning and deep learning models respectively. This confirms that subject variability concerning age is a valid problem that degrades the performance of activity recognition models.