Search

College student education and management can be enhanced through a data‐driven approach involving student surveys, academic records, and text analysis to understand student interests and concerns. Effective categorization of relevant topics enables universities to provide tailored support and educational content, thus improving the quality of education and fostering student success and well‐being by adapting to evolving student needs and aspirations. The primary contribution of this work is demonstrating the effectiveness of semisupervised learning methods in educational content classification, providing a robust solution for enhancing college student education and management with limited labeled data. The objective of this study was to evaluate the feasibility of using semisupervised learning methods in educational content classification using the Yahoo Answers dataset. For the Yahoo_500 dataset, the supervised neural network achieved a best evaluation accuracy of 0.6565, an average precision of 0.6539, an average recall of 0.6565, and an average F1 score of 0.6547. In contrast, semisupervised approaches, Dash, FixMatch, and FreeMatch, consistently demonstrated superior performance. Among the evaluated semisupervised architectures, FreeMatch achieved the highest best evaluation accuracy (0.6759), average precision (0.6739), average recall (0.6759), and average F1 score (0.6744). The Yahoo_2000 dataset, which benefited from an increased labeled data pool, exhibited a similar trend with semisupervised approaches consistently surpassing the supervised approach. FreeMatch maintained its top performing position in several categories, including computers and Internet, consumer electronics, and business and finance, with impressive F1 score of ≥0.753. Overall, the semisupervised approaches prove highly effective in improving model performance, highlighting its practical advantages. These results underscore the robustness of semisupervised approaches and their capability to improve classification performance even with limited labeled data. Employing semisupervised learning on the Yahoo Answers dataset and additional data sources for college student management and education can be a powerful tool for gaining insights into students' interests and concerns. [ABSTRACT FROM AUTHOR]

Air pollution is increasing profusely in Indian cities as well as throughout the world, and it poses a major threat to climate as well as the health of all living things. Air pollution is the reason behind degraded indoor air quality (IAQ) in urban buildings. Carbon dioxide (CO2) is the main contributor to indoor pollution as humans themselves are one of the generating sources of this pollutant. The testing and monitoring of CO2 consume cost and time and require smart sensors. Thus, to solve these limitations, machine learning (ML) has been used to predict the concentration of CO2 inside an office room. This study is based on the data collected through real-time measurements of indoor CO2, number of occupants, area per person, outdoor temperature, outer wind speed, relative humidity, and air quality index used as input parameters. In this study, ten algorithms, namely, artificial neural network (ANN), support vector machine (SVM), decision tree (DT), Gaussian process regression (GPR), linear regression (LR), ensemble learning (EL), optimized GPR, optimized EL, optimized DT, and optimized SVM, were used to predict the concentration of CO2. It has been found that the optimized GPR model performs better than other selected models in terms of prediction accuracy. The result of this study indicated that the optimized GPR model can predict the concentration of CO2 with the highest prediction accuracy having R , RMSE, MAE, NS, and a20-index values of 0.98874, 4.20068 ppm, 3.35098 ppm, 0.9817, and 1, respectively. This study can be utilized by the designers, researchers, healthcare professionals, and smart city developers to analyse the indoor air quality for designing air ventilation systems and monitoring CO2 level inside the buildings. [ABSTRACT FROM AUTHOR]

Abstract Energy management is an interesting research area for wireless sensor networks. Relevant dutycycling (or sleep scheduling) algorithm has been actively studied at MAC, routing, and application levels. Low power listening (LPL) MAC is one of effective dutycycling techniques. This paper proposes a novel approach called dual wake-up LPL (DW-LPL). Existing LPL scheme uses a preamble detection method for both broadcast and unicast, thus suffers from severe overhearing problem at unicast transmission. DW-LPL uses a different wake-up method for unicast while using LPL-like method for broadcast; DW-LPL introduces a receiver-initiated method in which a sender waits a signal from receiver to start unicast transmission, which incurs some signaling overhead but supports flexible adaptive listening as well as overhearing removal effect. Through analysis and Mote (Telosb) experiment, we show that DW-LPL provides more energy saving than LPL and our adaptive listening scheme is effective for energy conservation in practical network topologies and traffic patterns.