International Journal of Intelligent Computing Systems

Abstract:

Social media has become an integral part of student life, influencing communication, collaboration, and learning behaviors. While it provides valuable opportunities for academic engagement, excessive use can lead to distractions and diminished academic outcomes. This study examines the impact of Social Media Usage (SMU) on Student Academic Performance (SAP), with a focus on how demographic factors such as gender, department, and program type shape social media behavior. It also investigates the application of statistical and machine learning techniques to predict academic outcomes and develop AI-driven dashboards for identifying at-risk students. A structured questionnaire was distributed to 150 students from selected colleges, resulting in 135 responses. After validating the data for completeness and accuracy, 80 responses were retained for analysis. Using a Simple Random Sampling (SRS) method ensured unbiased representation of participants. The collected data comprised demographic variables, social media usage patterns, and academic performance indicators. Correlation analysis was used to identify relationships between variables, ANOVA examined demographic influences, and linear regression assessed predictive effects. Additionally, machine learning methods were integrated to improve predictive accuracy and reveal hidden patterns in the data. The findings reveal that SMU has a significant and measurable impact on SAP, with both positive and negative effects depending on usage patterns. Demographic factors such as gender, department, and program type significantly moderated the relationship between social media engagement and academic performance. Moreover, the AI-driven dashboards effectively identified students at risk of underperformance, offering educators a visual and actionable tool to design targeted interventions. This study provides valuable insights for students and educators seeking to strike a balance between social media engagement and academic success. By combining traditional statistical methods with machine learning and AI-based visualization, the research demonstrates a comprehensive and practical framework for understanding and managing the complex interplay between social media behavior and academic performance. These insights can inform institutional strategies aimed at promoting responsible social media use and supporting at-risk students in higher education.

Abstract:

Floods continue to be one of the destructive natural disasters, disrupting millions of lives and causing most significant economic losses annually. The need for accurate and timely flood forecasting is critical for effective disaster prevention and mitigation. Traditional hydrological and statistical models struggle to represent the nonlinear relationships between rainfall, soil moisture, and river discharge. This paper proposes a machine learning (ML)-based flood forecasting framework that leverages historical and real hydrological data to enhance accuracy and adaptability. Supervised learning algorithms- Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression, and Multi-Layer Perceptron were implemented and evaluated. Among these, MLP demonstrated superior predictive performance due to its ability to capture complex nonlinear dependencies. The proposed model achieved higher accuracy and faster response time than traditional models, establishing a scalable and intelligent decision-support system for flood management.

Abstract:

The project developed by us will enable the traffic light to switch from red to green based on traffic density. The easy way to control a traffic light by using timer for each section since, we proposed a system for controlling the traffic light by image processing. This paper presents an adaptive traffic light controller based on fuzzy logic for improving the traffic flow on an isolated intersection. A set of fuzzy rules has been made that, using the collected information from road detectors (queue length, arrival flow, and exit flow), computes the amount of time for which the next phase should be shortened or extended. The proposed fuzzy control system is constituted of two parts: one for the primary driveway (with a higher volume of vehicles) and for the secondary driveway (with a lower volume of vehicles).

Abstract:

Reviews are the most crucial opinions delivered by individuals based on their experiences with a product or service. Analyzing reviews aims to boost brand reputation, ensure quality, earn customer trust, pinpoint areas for improvement, and differentiate a business from its competitors. The study aims to explore individual perspectives on emotional tendencies by employing a deep learning-based text mining approach called opinion mining, on the Disneyland reviews dataset. General Data cleansing techniques are applied to eliminate irrelevant or noisy information. To analyze perception this study utilized the Text Blob package to extract polarities of the text, phrases, or words. Furthermore, this study employed a sophisticated K-Fold Cross Validated LSTM model, which leverages deep learning to classify sentiments and provide predictive analysis. In short, the model is a type of artificial intelligence that can understand and interpret emotions or opinions expressed in text data through the LSTM network and the cross-validation technique. By integrating the strengths of both methods, the proposed model enables the identification of people’s perceptions and ensures performance stability. The findings show that model performance resulted in an average accuracy of 0.9435 and f1-score of 0.936. In a comprehensive evaluation of abilities, the K-fold LSTM technique outperformed traditional machine learning methods.