ASPG Menu
search

American Scientific Publishing Group

Research Feed

Found 3831 matches for "All Articles"
Journal of Intelligent Systems and Internet of Things | 2025

Path Planning in Mobile Robotics: A Comparative Review of Classical and AI-Driven Techniques

This research presents a comprehensive analysis of path planning and optimization techniques in mobile robotics, focusing on both classical algorithms and modern intelligent approaches. The study systematically reviews fundamental methods such as Dijkstra’s algorithm, the A* search algorithm, and artificial potential fields, together with evolutionary optimization approaches including genetic algorithms and swarm intelligence. It also explores the application of machine learning and deep reinforcement learning models that allow robots to adapt dynamically to complex and changing environments. The comparative evaluation highlights the strengths, weaknesses, and suitable application areas of each approach across scenarios involving obstacle avoidance, energy efficiency, real time adaptability, and multi robot coordination. Particular attention is given to the challenges of uncertain and dynamic environments, computational scalability, and sensor noise, which continue to limit the performance of autonomous navigation systems. By consolidating current advancements and emerging trends, this study provides a structured overview and critical synthesis of existing methodologies, offering a valuable reference for researchers, engineers, and practitioners. It also identifies important research gaps in intelligent hybrid planning, context aware learning and energy constrained mobility, outlining promising directions for the future development of autonomous robotic navigation systems.

groups
Mohammed KH. Al-Satooree mail -
H. A. El Shenbary mail -
Ashraf A. Gouda mail -
Mohammed Abdel Razek mail
link https://doi.org/10.54216/JISIoT.170125

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new
Fusion: Practice and Applications | 2025

Prediction of Coronary Heart Disease with Multiple Regression Method

Coronary heart disease, a prevalent cardiovascular condition, affects coronary arteries, causing progression over time. Factors include diabetes, hypertension, inactivity, and tobacco use. Treatment includes medications and surgery, while maintaining a balanced diet and regular physical activity can prevent it. This research aimed to develop and validate a predictive model for CHD occurrence, leveraging the power of multiple regression while considering a range of predisposing variables. This study uses a quantitative, retrospective design utilizing multiple regression analysis to predict the likelihood of coronary heart disease (CHD). The study involved 130 participants aged 24-85, with health history data on cardiovascular risk factors, blood pressure, cholesterol, smoking, BMI, and family history of heart disease. Multiple regression analysis was utilized to determine the significant predictors of CHD diagnosis. Significant relationships between responder variables and predictor factors in a multiple linear function are identified using multiple regression analysis. Our model discovered that a higher risk of coronary heart disease (CHD) was closely associated with both total cholesterol and BMI. The model included factors like systolic blood pressure, diabetes, physical activity, and smoking, but they had lower contributions to the prediction equation, despite cholesterol and BMI being the best predictors. This study successfully developed a multiple regression-based prediction model for CHD that can contribute to a more informed and potentially proactive approach to cardiac healthcare. Further work should focus on refining model accuracy and real-world clinical application.

groups
Elda Maraj mail -
Aida Bendo mail
link https://doi.org/10.54216/FPA.200210

Volume & Issue

Vol. Volume 20 / Iss. Issue 2

Details open_in_new
Fusion: Practice and Applications | 2026

Pan-Sharpening Landsat Images through the Component Substitution Methods

Remotely sensed images have played a valuable role in several applications such as image classification, feature extraction, land cover monitoring, and others; thus, the need for high-resolution satellite images has become necessary and essential. In order to produce images with very high spectral and spatial resolution, the pan-sharpening techniques—, which are regarded as a subset of data fusion techniques—combine the color information of the multispectral image from the same scene with the distinct geometric features of the panchromatic image. This work conducts a comparative analysis of four pansharpening methods (Gram, HIS, Brovey, and PC) specifically applied to Landsat 7 images, providing a thorough evaluation across multiple performance metrics. Also we introduce and apply performance metrics that not only measure quantitative accuracy (like RMSE and RASE) but also assess the preservation of spatial details, offering a more holistic evaluation of pansharpening techniques. The qualitative and quantitative results indicate that both GS and IHS techniques have accurate performance.

groups
Asmaa Sadiq mail
link https://doi.org/10.54216/FPA.210123

Volume & Issue

Vol. Volume 21 / Iss. Issue 1

Details open_in_new
Journal of Cybersecurity and Information Management | 2026

Cascade Detection Technique for Face Mask ‎Recognition Based on YOLOv9 and CNN

Deep learning showed promise in many real-world applications. Recognition and item ‎identification are the most common. This publication tries to design and describe a system that can ‎classify people from images based on whether they are correctly wearing masks. The proposed ‎system is two-part. The first part is designed for facial detection using the YOLOv9 (You Only Look Once ‎version 9) compact deep learning model, which uses the mean intersection method over union to determine an optimal number of anchoring boxes and the Adam optimizer to improve facial detection efficacy. ‎The second component is a convolutional neural network for face feature extraction. These faces are ‎classified as a mask, without_mask, and incorrect_mask. These two components are integrated into ‎the proposed system for facemask recognition. ‎Empirical evaluations were conducted on the two self-collected datasets to train and evaluate the ‎proposed system's performance. The observed precision value of this system was 94.6% in the last ‎epoch; the recall value is 87.1%, and the mean average precision results are 92.74% as a face ‎detector. The classifier model train accuracy is 98.35%, and validation accuracy is 98.8%. Finally, the ‎comparative results indicated that the proposed framework was an effective model for face ‎detection, attaining a higher mean average precision value and outperforming other networks ‎assessed on the designated dataset for this task. The suggested network effectively detects and ‎classifies several faces in photos, including small faces in congested places.

groups
Amal Sufiuh Ajrash mail -
Wildan Jameel Hadi mail -
Ammar Hussein Jassim mail
link https://doi.org/10.54216/JCIM.170109

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new
Fusion: Practice and Applications | 2026

Black Fungus Disease Identification Using Deep Learning: A Case Study

Black fungus disease (mucormycosis) has emerged as a critical health threat, particularly during the COVID-19 pandemic, where immunosuppressed individuals have shown increased susceptibility to opportunistic fungal infections. The aggressive progression of mucormycosis and its high mortality rate, exacerbated by diagnostic delays, underscore the urgent need for accurate and automated detection systems. In this study, a deep learning-based diagnostic framework is proposed for the early identification of black fungus infection using convolutional neural networks (CNNs). Experimental pipelines were developed and evaluated. Several deep learning models based traditional CNN architectures including VGG16, VGG19, InceptionV3, and MobileNetV2 have been study on a structured dataset comprising high-resolution mucormycosis images. Comparative evaluations across both pipelines revealed that the MobileNetV2 architecture consistently outperformed other models, with accuracy reaching 99.86%, F1-score of 0.98, and minimal overfitting across validation datasets. The proposed system holds strong potential for real-world clinical deployment, particularly in resource-limited healthcare settings, offering rapid, scalable, and explainable AI-driven diagnostics to combat the rising threat of black fungus infections.

groups
Hanan Badri Salman mail -
Matheel Emaduldeen Abdulmunim mail
link https://doi.org/10.54216/FPA.210228

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2026

Assessing AI and Decision-Making Impacts on GCC Bank Efficiency through a Neutrosophic Lens

The Gulf Cooperation Council (GCC) banking sector has experienced rapid digital transformation, regulatory shifts, and disruptions in recent years, especially during periods of crisis and recovery. Despite extensive studies on banking efficiency, there remains uncertainty and inconsistency regarding which bank-specific factors most influence performance. Traditional models often assume deterministic relationships, overlooking the indeterminate and ambiguous nature of real-world decision environments. Guided by Neutrosophic theory, this study reinterprets efficiency as a state influenced simultaneously by degrees of truth, falsity, and indeterminacy, acknowledging that the impact of Artificial Intelligence (AI) and Data-Driven Decision Making (DDDM) on efficiency may vary across contexts and times. The study analyzes 43 banks from six GCC countries between 2010 and 2024. In the first stage, efficiency is estimated using Data Envelopment Analysis (DEA). In the second stage, panel regression models are applied to examine the influence of bank-specific factors, including AI adoption, capital adequacy (CAR), asset quality (NPL), returns (ROA, ROI), branch footprint, and bank age. Within a Neutrosophic theoretical lens, these relationships are interpreted not as fixed or absolute but as having degrees of certainty and uncertainty that coexist within the decision environment. Findings reveal significant variation in efficiency across countries and banks. AI adoption, CAR, and ROA show strong positive associations with efficiency (high truth-values), while NPLs exhibit negative effects (high falsity values). ROI and branch footprint demonstrate mixed or indeterminate influences, suggesting that their roles depend on contextual and temporal factors. This perspective highlights how efficiency drivers in the GCC banking sector cannot be fully captured by binary or crisp evaluations. By applying Neutrosophic theory, this study provides a novel conceptual understanding of banking efficiency under uncertainty. It recognizes managerial and policy decisions are often made in environments where information is incomplete, contradictory, or evolving. The Neutrosophic interpretation enhances the explanatory depth of traditional efficiency analyses and offers a more flexible lens for understanding how digital transformation and AI adoption contribute to organizational performance amid indeterminacy.

groups
Aya Merhi mail -
Chadi Baalbaki mail
link https://doi.org/10.54216/IJNS.270236

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new
Fusion: Practice and Applications | 2026

A Deep Learning Model for Black Fungus Disease Identification Based on Optimization Techniques

Black fungus disease (mucormycosis) has emerged as a critical health threat, particularly during the COVID-19 pandemic, where immunosuppressed individuals have shown increased susceptibility to opportunistic fungal infections. This study presents a deep learning framework for the automated detection of mucormycosis infections from clinical imaging data. We propose a lightweight yet high-accuracy framework for image-based detection of mucormycosis that couples a pretrained MobileNetV2 backbone with a compact classification head whose key hyperparameters are tuned via Salp Swarm Optimization (SSO). The pipeline standardizes inputs to 224×224 RGB with ImageNet normalization, uses MobileNetV2 as a frozen feature extractor, and lets SSO search the head width uuu, dropout ppp, and learning rate η\etaη under early stopping. On a curated binary dataset (2,991 training / 747 validation images), the SSO search reached a peak validation accuracy of 99.87%, and the final model retrained with the best setting achieved 99.73% validation accuracy. The classification report shows near-perfect performance (diseased: precision/recall/F1 1.00; normal: precision/recall/F1 0.99), with an error rate of ≈0.27% (2/747) reflected in the confusion matrix. Against strong baselines—CNN (90.5%), VGG16 (95.0%), VGG19 (89.3%), InceptionV3 (97.9%)—MobileNetV2 + SSO ranks first while remaining computationally efficient. Grad-CAM visualizations confirm attention on peri-orbital and peri-lesional structures, supporting clinical plausibility. These results indicate that SSO-tuned MobileNetV2 offers state-of-the-art accuracy, interpretability, and deployment readiness for rapid mucormycosis screening.

groups
Hanan Badri Salman mail -
Matheel Emaduldeen Abdulmunim mail
link https://doi.org/10.54216/FPA.210124

Volume & Issue

Vol. Volume 21 / Iss. Issue 1

Details open_in_new
Fusion: Practice and Applications | 2026

Fusion-Driven Cognitive AI Model for Personalized Prediction in Multilevel Education Systems

Education in the twenty-first century is undergoing a profound transformation fueled by artificial intelligence (AI), the Internet of Things (IoT), and intelligent systems. Traditional and even early digital learning systems often relied on standardized pathways, limiting personalization and reducing learner engagement. To overcome these limitations, this study proposes and evaluates an IoT-enabled adaptive learning framework that integrates educational data analytics with intelligent algorithms to deliver real-time, personalized pathways for learners. Education in the twenty-first century is undergoing a profound transformation fueled by artificial intelligence (AI), the Internet of Things (IoT), and intelligent systems. Traditional and even early digital learning systems often relied on standardized pathways, limiting personalization and reducing learner engagement. To overcome these limitations, this study proposes and evaluates an IoT-enabled fusion-based adaptive learning framework that integrates educational data analytics, ensemble learning, and multi-modal intelligent algorithms to deliver real-time, personalized pathways for learners. The fusion of diverse data sources—ranging from quiz interactions and engagement logs to contextual signals from IoT devices such as smart sensors and wearables—ensures robust, context-aware decision-making. Experimental results using Kaggle datasets demonstrate that Random Forest outperforms XGBoost, with an accuracy rate of 87% and balanced F1-scores. This study shows how AI–IoT fusion can create equitable, eco-friendly, and inclusive learning spaces.

groups
Asma Abdulmana Alhamadi mail
link https://doi.org/10.54216/FPA.210125

Volume & Issue

Vol. Volume 21 / Iss. Issue 1

Details open_in_new
International Journal of Neutrosophic Science | 2026

Integrating Neutrosophic Analysis into Economic Growth and Sustainable Development Evaluation

Mathematically, this study aims to analyze the dynamic linkage between economic growth and sustainable development by employment of integrated econometric–neutrosophic approach. Standard econometric models typically fail to address the risk, ambiguity and multi-dimensionality of sustainability indicators. In comparison, the neutrosophic approach – based on truth, indeterminacy and falsity – provides a solid tool for expressing uncertainty and vagueness with respect to socio-economic assessments. The article creates the ability to use quantitative data together with indeterminacy level (neutrosophic decision making) for evaluating a more complete effort of the sustainability–growth continuum, i.e., beyond only measurable results we evaluate confidence and indeterminacy embedded within them which can be seen by policy makers. Empirical evidence comes from a transition economy characterized by the significant structural reforms and modernization over recent years that clearly shows how strong economic growth can be accompanied by continuing environmental pressures. We compare the official statistics with regards to GDP growth and CO2 emissions per capita that are predicted from 2018 till 2023, in order to analyze whether environmental sustainability develops in line with economic development. Results show that the economy is resilient and growing consistently, while environmental performance is mixed, indicating partial decoupling of growth from sustainability.

groups
Muhammad Eid Balbaa mail -
Ebru Ozbilge mail -
Emre Ozbilge mail
link https://doi.org/10.54216/IJNS.270237

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new
International Journal of Neutrosophic Science | 2025

Neutrosophic Z-Number Framework for Intelligent Multi-Objective Solid Transportation Systems

Transportation optimization remains a critical challenge in international businesses, particularly given the inherent uncertainties of supply chain networks. This paper proposes a novel machine learning-based model for solving multi-objective, multi-item solid transportation problems that fundamentally advances beyond existing fuzzy and neutrosophic approaches. Our key innovation lies in the synergistic integration of neutrosophic Z-numbers (NZNs) with adaptive machine learning techniques, creating a framework that simultaneously captures value vagueness, information reliability, and dynamic uncertainty patterns capabilities absent in conventional fuzzy transportation models. Unlike traditional fuzzy methods that treat all uncertainty uniformly, our NZN representation provides a three-dimensional structure incorporating truth, indeterminacy, and falsity measures, each with associated reliability metrics. This enriched uncertainty modeling enables three ground breaking advancements over existing approaches: (1) a neural scoring system that autonomously learns optimal NZN comparison functions from historical decision patterns, overcoming the limitations of static aggregation operators in fuzzy systems; (2) LSTM networks that jointly forecast demand values and their reliability evolution under uncertainty; and (3) reinforcement learning optimizers that dynamically balance economic efficiency with information quality in routing decisions. Computational experiments demonstrate superior performance compared to six established baseline methods, including traditional fuzzy, intuitionistic fuzzy, neutrosophic, and pure machine learning approaches. Our hybrid framework achieves a 23.4% reduction in transportation costs and 35.4% improvement in uncertainty handling compared to conventional fuzzy transportation models, with statistically significant improvements (p < 0.001) across all evaluation metrics. By coupling the theoretical rigor of neutrosophic mathematics with the adaptive power of machine learning, this study provides businesses with a transformative decision-support system for transportation planning under real-world uncertainty conditions.

groups
Muhammad Kamran mail -
Anns Uzair mail -
Muhammad Tahir mail -
Muhammad Farman mail -
Ixtiyarov Farxod mail -
Mohamed Hafez mail
link https://doi.org/10.54216/IJNS.260421

Volume & Issue

Vol. Volume 26 / Iss. Issue 4

Details open_in_new