ASPG Menu
search

American Scientific Publishing Group

Research Feed

Found 3841 matches for "All Articles"

A Hybrid Al-Biruni Earth Radius–Random Forest Model for Accurate and Efficient Student Performance Classification

The growing availability of educational data has prompted the use of machine learning methods to predict student academic performance and support data-driven decision-making in education. Nevertheless, such models for predicting performance rely heavily on proper data preprocessing, model selection, and optimal hyperparameter settings. This research proposes a hybrid predictive architecture that combines machine learning classifiers with bio-inspired metaheuristic optimization algorithms to improve classification efficiency in educational data mining. It is based on the xAPI-Edu.A dataset of 480 students’ demographic, academic, and behavioral characteristics is used to first analyze a set of baseline machine learning models, including Random Forest, XGBoost, Support Vector Machine, Multilayer Perceptron, K-Nearest Neighbors, and Gaussian Naive Bayes, using standard classification metrics. The initial experimental findings on the baseline layer show that the Random Forest classifier outperforms the other models before optimization, achieving accuracies of 0.8889 and 0.8814, and F-scores of 0.8889 and 0.8814, respectively, indicating strong generalization and equal discrimination among the classes. To further improve the predictive performance, the state-of-the-art metaheuristic algorithms, i.e., the Al-Biruni Earth Radius Optimizer (BER), the Gray Wolf Optimizer (GWO), the Particle Swarm Optimization (PSO), the Genetic Algorithms (GA) and the Whale Optimization Algorithms (WOA) are adopted to optimize the hyperparameters of the Random Forest. It has been experimentally demonstrated that every optimization approach provides a measurable performance increase, but the BER-optimized Random Forest consistently performs better. In particular, the BER-Random Forest model achieves an F-score of 0.9477 and an accuracy of 0.9439, both of which are much higher than the baseline configuration. Full statistical and visual analyses, such as kernel density estimation, Z-score heatmaps, and swarm plots, also support the strength, stability and superiority of the proposed BER-based optimization framework. Such findings demonstrate the effectiveness of metaheuristic-based hyperparameter optimization in educational predictive analytics and provide significant insights into the creation of intelligent, efficient, and data-driven systems of academic assistance.

groups
Mohamed E. Ghoneim mail
link https://doi.org/10.54216/JAIM.110203

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Intelligent Solar Radiation Forecasting Using Recurrent Deep Learning Models for Photovoltaic Energy Planning

Accurate solar radiation forecasting is essential for improving the reliability of photovoltaic energy generation and supporting effective solar battery management, particularly because solar radiation is highly variable and depends on nonlinear interactions among meteorological and temporal factors. Although conventional prediction methods can provide useful estimates, they often struggle to capture the sequential behavior of solar radiation caused by daily sunlight cycles, atmospheric variation, and changing weather conditions. Therefore, this study aims to develop and evaluate deep learning models for predicting Solar_radiation using meteorological data collected from the HI-SEAS weather station over four months, from September to December 2016, where the main input variables include temperature, humidity, pressure, wind direction, wind speed, and time-related features. Five recurrent deep learning models were implemented and compared, namely Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short Term Memory (BiLSTM), and Attention-LSTM. Before model training, the dataset was preprocessed by handling missing values, checking temporal consistency, arranging the observations chronologically, and applying Min–Max normalization to ensure stable learning. Model performance was assessed using multiple regression metrics, including MSE, RMSE, MAE, MBE, correlation coefficient, R2, RRMSE, NSE, and WI. The experimental results showed that BiLSTM achieved the best overall forecasting performance, with an MSE of 0.0014, RMSE of 0.0379, MAE of 0.0182, MBE of 0.0039, correlation coefficient of 0.9750, R2 of 0.9494, RRMSE of 0.3645, NSE of 0.9494, and WI of 0.9865. GRU and RNN also produced competitive results, achieving RMSE values of 0.0381 and 0.0382 and R2 values of 0.9489 and 0.9486, respectively, while Attention-LSTM showed comparatively lower performance with an RMSE of 0.0492 and R2 of 0.9149. These findings indicate that recurrent deep learning models are effective for learning nonlinear and temporal patterns in solar radiation data, with BiLSTM providing the most accurate and reliable predictions. The proposed forecasting framework can support photovoltaic energy planning and solar battery decision-making by estimating future solar radiation levels and helping determine whether solar energy utilization will be feasible under expected weather conditions.

groups
Mona Ahmed Yassen mail -
Mohamed Gamal Abdel-Fattah mail -
Islam Ismail mail -
Hossam El-Din Moustafa mail
link https://doi.org/10.54216/JAIM.110204

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

A Smart Retail Point-of-Sale System Using Machine Learning Forecasting and Application-Level Failover

Point-of-Sale (POS) systems support retail transaction processing, inventory management, and operational decisionmaking. However, many traditional POS systems rely on a single centralized database, creating a critical point of failure during server faults, database errors, or network disruptions. Conventional POS systems may also lack intelligent forecasting capabilities, causing inventory decisions to depend on manual estimation or fixed reorder rules. These limitations can lead to operational interruption, inventory inconsistency, and inefficient stock management. This study proposes a high-availability smart POS system integrated with AI-based inventory forecasting. The framework uses a dual-database architecture consisting of a primary database and a secondary backup database. Application-level failover redirects operations automatically when the primary database becomes unavailable, while an event-driven backup mechanism synchronizes important data after critical transactions. The forecasting component was developed using the Rossmann Store Sales dataset. Several models were evaluated, including Random Forest (RF), Bagging, CatBoost, XGBoost, and KNN Regressor. Optimization algorithms including PSO, MVO, HHO, and DE were also integrated with RF. The results showed that baseline RF achieved the best overall performance, with MSE = 0.080454, RMSE = 0.283643, MAE = 0.184264, R2 = 0.919712, and WI = 0.978542. Among optimized models, PSO + RF achieved the strongest optimizer-based result, with MSE = 0.081480 and RMSE = 0.285446. The implemented system also demonstrated successful database connectivity, failover readiness, and automatic backup execution. The findings confirm that the proposed framework can support continuous retail operation while providing accurate AI-based forecasting and inventory recommendations.

groups
Sara albuainain mail
link https://doi.org/10.54216/JAIM.110205

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Building Information Modeling in Syria: Obstacles and Requirements for Implementation

The crucial need for innovative sophisticated, and complex Architectural, engineering, and construction (AEC) industry projects with in-depth details makes traditional methods inappropriate for the completion of projects with desired efficiency, performance and productivity. Therefore, AEC projects in Syria suffered from myriad issues such as Behind the Schedule, over budget, inferior quality, low productivity, without sustainability and more. However, Building information Modelling (BIM) proves its capability to solve these issues. The aim of this study is to identify the obstacles and the critical influencing factors for applying BIM in Syria in the AEC industry. Extensive investigation for literature review and structured online questionnaire designed to achieve the study’s aim. SPSS and Excel were used to analyze the results. This study classified the obstacles related to three category: 1) Planning, Design and Auditing systems, 2) BIM System, 3) Management, Financial and Legal factors. In spite of, the government and clients play the vital role to mandate BIM, the mixed approach (top-down and bottom-up) is recommended to expedite BIM implementation. This study provides a novel contribution by identifying the main obstacles and developing new strategies for applying BIM in AEC and reconstruction which enhance projects quality, performance and efficiency.

groups
Mohamed H. Shaban mail -
Ashraf Elhendawi mail
link https://doi.org/10.54216/IJBES.010103

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

BIM Implementation Maturity Level and Proposed Approach for the Upgrade in Lithuania

Recently, Building information modelling (BIM) proves its capability to solve the raised AEC industry issues. Therefore, several countries and entities pursue to transform into BIM especially the developed countries. Lithuania as a European country has a great challenge to cap up with the surrounding environment to implement BIM. This study aims to determine the BIM maturity levels in Lithuania and supposed the missed steps to upgrade to the next level. Eighteen important Lithuanian construction projects awarded the most successful implementing BIM are chosen as a case study. Face-to-face interviews were conducted with several BIM experts whose work at the chosen projects. The analysis conducted by the most effective theoretical model entitled BIM Maturity Matrix (BIMM). The key findings of this research that Lithuania reached the BIM implementing maturity level 2 while some projects still at level 1 that proves the ability of Lithuanian AEC industry to softly and completely transfer the maturity to level 2 by the recommendation provided through the proposed approach at the end of the paper. These results provide a stunning opportunity to improve the AEC project performance and reap the benefits of implementing BIM. Future studies can develop a framework to improve the BIM implementation in Lithuania softly.

groups
Natalija Lepkova mail -
Rana Maya mail -
Sonia Ahmed mail -
Vaidotas Šarka mail
link https://doi.org/10.54216/IJBES.020102

Volume & Issue

Vol. Volume 2 / Iss. Issue 1

Details open_in_new

Effects of Knowledge Management on Organizational Performance

The main purpose of this paper is to evaluate the impact of knowledge management (KM) on organizational performance of Microsoft Corporation. The study will also inform global entrepreneurs regarding the importance and application of KM in workplaces. The study will discuss the modification and technological integration that are required to derive desired outcomes from KM. The research will also evaluate the contribution of KM to career development and opportunities for the employees. Modern organizations need to enhance their products and services continue to be the first choice of customers. The KM has enabled organizations to determine the changing demands and requirements of customers. Therefore, it can be opined that the research aims to analyse the significance of KM in modern organizations, employees, and competitiveness. 

groups
Ghoson Taleb mail -
Faris Almansour mail
link https://doi.org/10.54216/AJBOR.050201

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

Mitigating Hot Spot Problem in Wireless Sensor Networks using Political Optimizer Based Unequal Clustering Technique

Wireless Sensor Network (WSN) encompasses a set of wirelessly connected sensor nodes in the network for tracking and data gathering applications. The sensors in WSN are constrained in energy, memory, and processing capabilities. Despite the benefits of WSN, the sensors closer to the base station (BS) expels their energy faster. It suffers from hot spot issues and can be resolved by the use of unequal clustering techniques. In this aspect, this paper presents a political optimizer-based unequal clustering scheme (POUCS) for mitigating hot spot problems in WSN. The goal of the POUCS technique is to choose cluster heads (CHs) and determine unequal cluster sizes. The POUCS technique derives a fitness function involving different input parameters to minimize energy consumption and maximize lifetime of the network. To showcase the enhanced performance of the POUCS technique, a comprehensive experimental analysis takes place, and the detailed comparison study reported the better performance of the POUCS technique over the recent techniques.

groups
Sahil Verma mail -
Sanjukta Gain mail
link https://doi.org/10.54216/JCIM.080201

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

Advancements in Encryption Techniques for Enhanced Data Security Over Cloud

With the advancements in internet technologies and increased transactions over the internet the threats for data security increased many folds than ever. Nowadays message application services are in great demand, as they offered end-to-end encryption (E2EE) that is essential to provide security to the users while communication takes place between parties. Today  messaging application service is in great use for communication. For making communication over the network.  This paper presents that security is essential while communication takes place between users and how E2EE offers security to the users. Consumers' concerns related to the security and privacy of their data are growing day by day with increased inter-connectivity. We examine the existing mobile message service encryption protocols that provide security and the features which preserve privacy for messenger applications and also evaluate the technical challenges involved for its  implementations.

groups
Rishu mail -
Vijay Kumar Sinha mail -
Shruti Aggarwal mail
link https://doi.org/10.54216/JCIM.080202

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

Analysis of Coronavirus Pandemic Spread in India Using Epidemiological Model

In this paper, a methodology for dissecting information of the coronavirus has been introduced and the conduct of the coronavirus in India has been concentrated with the assistance of the epidemiological SIR model. The model considered is of the sort of "nonstop contamination" according to which tainted occupants proceeded in a similar compartment until getting recuperated by treatment or demise. The forecast depends on gathered auxiliary information for a specific period from the online assets. SIR(Susceptible, Invective, Removed Class) model has been applied to the information and in the wake of breaking down the security of the differential conditions, the condition appears to be insecure and seen that the destructive infection must be controlled with wellbeing measures however isn't be destroyed soon.

groups
Divya S mail -
Vijay Kumar Sinha mail -
Shruti Aggarwal mail
link https://doi.org/10.54216/AJBOR.050202

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

Feature Selection Optimization Model for Business Risk Assessment Model

Financial risk assessment becomes a hot research topic among financial firms or companies to assess the financial status and thereby avoid future crises. Earlier studies have focused on statistical models for the assessment of financial risks and the recently developed machine learning (ML) models find useful to improve the assessment performance. In this aspect, this study introduces a novel Butterfly Optimization based Feature Selection with Classification Model for Financial Risk Assessment (BOFS-CFRA) technique. The proposed BOFS-CFRA technique involves pre-processing at the primary stage to get rid of unwanted data. In addition, K-means clustering approach is developed to group the financial data into clusters. Then, the BOFS technique is applied to choose the subset of features from the clustered data. Finally, the classification of financial risks takes place by the use of functional link neural network (FLNN). In order to ensure the enhanced performance of the BOFS-CFRA technique, a series of simulations were carried out and the results are inspected under various measures. The simulation outcome portrayed the supremacy of the BOFS-CFRA technique over the other financial risk assessment models in terms of several performance measures.

groups
Noura Metawa mail -
Mohamed Elhoseny mail
link https://doi.org/10.54216/AJBOR.020104

Volume & Issue

Vol. Volume 2 / Iss. Issue 1

Details open_in_new