Foundation University Journal of Engineering and Applied Sciences
Not a member yet
56 research outputs found
Sort by
Autism Spectrum Disorder Detection using Facial Expression
Get PDFAutism Spectrum Disorder (ASD) is a complex neurological disorder that has an impact on communication, language, and social skills. Early identification of ASD patients, particularly in children, could make it easier to design and implement the best therapy approach at the appropriate time. Analyzing facial characteristics, eye contact, and other aspects of human faces can be used to detect ASD. To better accurately identify children with ASD in the early stages, an improved transfer-learning-based autism face recognition framework is proposed in this paper. This study will improve the accuracy of ASD detection and classification of normal and autistic, using machine learning and deep learning approaches. This study detects and classifies Autistic and non-autistic human faces, Using the Deep learning-based CNN model, the study also analyzes the pre-trained transfer learning approaches with the proposed model. Results reveal that the proposed model has better detection and classification results having 99 % Accuracy. Based on our accuracy we propose that the diagnosis of autism spectrum disorders can be done effectively using facial images
Reinforcement Learning for Optimizing Bio-Composite Processing Conditions under Local Constraints
Get PDFThis study proposes a high-performance, reinforcement learning-based optimization framework for bio-composite processing, leveraging the Soft Actor-Critic (SAC) algorithm within a constrained decision-making context. Conventional optimization methods in composite manufacturing often face limitations in balancing multiple interdependent objectives such as mechanical performance, energy efficiency, constraint adherence, and production throughput. To overcome these limitations, this work integrates a high-fidelity digital twin environment with a constrained Markov Decision Process (CMDP) formulation, enabling the SAC agent to learn optimal control strategies in real time while respecting operational boundaries. The proposed model was benchmarked against Proximal Policy Optimization (PPO) and Genetic Algorithm (GA) across four key metrics: tensile strength, energy consumption, constraint violation rate, and cycle time. SAC demonstrated superior performance with a mean tensile strength of 71.5 MPa, energy usage of 1.12 kWh per cycle, and a cycle time of 290 seconds—all achieved with the lowest constraint violation rate of 1.8%. These improvements were statistically validated through one-way ANOVA and Tukey’s HSD tests. Additionally, a 10-fold cross-validation using Latin Hypercube Sampling confirmed the generalizability of the SAC policy under diverse, unseen environmental conditions. The findings substantiate the viability of SAC as a real-time, constraint-sensitive optimizer for advanced composite processing. Its ability to intelligently navigate multi-objective trade-offs and adapt to process variability makes it a promising solution for decentralized and resource-constrained manufacturing environments. This research advances the integration of intelligent control in sustainable materials engineering and sets the stage for future deployment in real-world industrial applications
A Research-Intensive Framework to Automate the Business Operations of a Smart Water Distribution System
Get PDFTypically, software solutions are developed based on generic assumptions without proper, well-defined research methodologies, leading to applications that may not satisfy the needs of a particular target market. In this paper, a combination of qualitative and quantitative approaches was designed to critically analyze the existing water distribution systems. The research-intensive approach helps to build a framework (Aquarise Intelflow) that caters to the real-world actual issues of the stakeholders. Aquarise Intelflow is a smart technology-based water delivery and distribution framework that provides a rich set of features to address the inefficiencies of existing market solutions. It gives a smooth experience to clients by offering subscription and delivery plans, request/process orders, and tracking deliveries. Vendors are equipped with an interactive management dashboard. Evaluation results of Aquarise Intelflow highlight its performance, including minimum manual intervention with enhanced customer satisfaction. In a nutshell, the proposed solution bridges the existing operational gaps in water distribution systems
Enhancing Online Safety for Underage Children: Integrating Parental Control and Customization Solution
Get PDFSocial media has greatly affected society as we know it today, most especially for teenagers and children under the age of 10, termed as ‘underage children’. This requires a comprehensive understanding of its effects and risks. This study focuses on what parents think about their children’s usage of social media applications. By surveying parents, we aimed to learn more about their beliefs, concerns, and how they manage their children’s online activities and experiences. Our research identified a significant gap between parental awareness and their children’s online experiences. This lack of understanding is concerning because social media platforms are ubiquitous. Many parents lack a thorough understanding of the potential risks and challenges their underage children encounter in this digital environment. Additionally, existing safety measures, even within supposedly child-safe platforms like YouTube Kids, focus only on video content, neglecting potential vulnerabilities in other areas. This highlights the necessity for parental perspectives in shaping safer online spaces for minors. Our Proposed model addresses the current limitations by providing a social media experience with integrated parental controls. The proposed model includes features such as content sharing control, message control, Login/Logout timings, and customizable ad preferences. The model was stimulated by the literature review and a preliminary research study, which adopts a data-driven approach to enhance child safety within the digital landscape. Future research should involve user testing of the proposed model with focused group discussions, along with their validation and analysis
SDN-based Intrusion Detection and Prevention System Against ARP Spoofing Attacks
Get PDFSoftware Defined Networking (SDN) separates the control plane from the data plane, enabling centralized configuration through the SDN controller. While this centralization simplifies management, it also makes the controller’s ARP table a critical target, as the stateless nature of ARP allows spoofing attacks. To mitigate this vulnerability, we propose an Intrusion Detection and Prevention System integrated as a controller module. The system monitors ARP and DHCP packets, maintaining a permanent ARP table synchronized with a DHCP table to ensure reliable IP–MAC bindings. The IDPS applies four validation checks in both IP and MAC address scanning modules, ensuring robust detection and prevention of spoofed packets. To achieve scalability, the design employs hashmaps for all lookups, ensuring that each check executes in constant time (O(1)), independent of network size. While this methodology introduces a higher baseline mitigation time (~2.2s) compared to some lightweight approaches, it guarantees predictable performance at scale and comprehensive coverage of spoofing attacks
A Multistage CNN with Branch Concatenation for Classification of Dementia Using MRI Data
Get PDFAlzheimer’s Disease (AD) is the most common type of dementia and is caused by the accumulation of amyloid-beta plaques in the brain. Worldwide cases of dementia are expected to triple by 2050, which underscores the importance of early diagnosis. In our work, we proposed a multibranched CNN with three concatenations among the branches and tested the method on a dataset accessed from Kaggle. We also implement the SMOTE algorithm on the dataset to overcome class imbalance. The proposed CNN achieved 99.64% accuracy and 99.89% F1-Score on test data and outperformed the various existing methods. The proposed architecture is special because of its ability to extract intricate features at finer levels. The research paves the pathway for improved treatment plans and better prognosis of AD
Design and Construction of a Sustainable IoT based Solar Energy-Powered Smart Water Consumption Tracking System
Get PDFWater security and scarcity are major challenges in Pakistan, particularly in developing countries. There is a need for the sustainable implementation of a water consumption tracking system for control and monitoring using solar energy. This study aims to analyze water consumption to tackle the urgent worldwide concerns of water conservation and effective water resource management. By implementing solar-powered intelligent water-monitoring equipment, this prototype offers a new way to monitor and manage water usage. This scheme was controlled and monitored using an Arduino-based controller integrated with turbidity and water flow sensors to switch the motor using modern technologies. This prototype must be implemented because water security is a global challenge where freshwater is becoming increasingly rare. The goal of these systems is to transfer these parameters using an Internet of Things (IoT)-based system and control and monitor water resources via web applications. The system's real-time monitoring of consumption trends changes to sustainable water management. The system costs less compared to conventional SCADA-based systems. The proposed system achieved 92% efficiency without any external fossil fuel-based power sources. The comparative analysis shows that the proposed system prototype offers efficiency, cost-effectiveness, and scalability compared to traditional systems. The designed system delivers an economical and optimal solution for real-time data analytics for small-scale applications to advance the field. This sustainable technology enables people, communities, and organizations to play a significant role in protecting water supplies and maintaining their accessibility for future generations
Comparative Analysis of GRU and LSTM based Models for Pose Estimation in Pakistan Sign Language Recognition
Get PDFThis study explores Sign Language Recognition (SLR) within the context of Pakistan Sign Language (PSL), aiming to bridge communication gaps between signers and non-signers. Sign languages employ handshapes, body gestures, and facial expressions to facilitate communication, addressing the worldwide linguistic needs of deaf communities. While significant efforts have been devoted to global SLR and Sign Language Translation (SLT) systems, limited attention has been paid to PSL. To address this gap, we propose a novel approach for dynamic word-level SLR, incorporating manual and non-manual features. The proposed method utilizes pose estimation RNN-based architectures (GRU and LSTM) on both our proprietary pronoun-based video dataset and the PkSLMNM dataset. By extracting key points from 3D coordinates within individuals, we propose several optimization functions for original and augmented datasets. We then compare the sequential classification potential of GRUs and LSTMs. Our findings reveal that GRU outperforms LSTM, achieving a 4% improvement in real-time classification accuracy on both augmented and original datasets, with an overall accuracy of 98.61%
AI-Enabled Lifecycle Analysis of Sustainable Composites for Nigeria’s Low-Cost Housing Sector
Get PDFThe intersection of sustainable material development and artificial intelligence (AI) presents transformative opportunities for addressing Nigeria’s growing affordable housing deficit. This study investigates the lifecycle performance of four agro-based composite materials, like bamboo-cement panels, palm kernel shell concrete, rice husk ash blended cement, and coconut coir–stabilized earth blocks, tailored for application in low-cost housing across Nigeria’s diverse climatic zones. A comprehensive methodology combining experimental testing, lifecycle assessment (LCA), and AI-based predictive modeling, including Artificial Neural Networks (ANN), Random Forest, and Gradient Boosting adopted to evaluate the structural, environmental, and economic suitability of each composite. Mechanical and thermal properties were assessed in accordance with ASTM standards, while lifecycle environmental impacts, including global warming potential (GWP) and embodied energy, were modeled using OpenLCA and the ReCiPe Midpoint method. Economic performance was evaluated over a 30-year horizon. ANN models achieved R² values of up to 0.94, affirming their utility in predictive lifecycle analysis. The results demonstrated significant performance trade-offs. Bamboo-cement offered the highest compressive strength but incurred the greatest GWP and cost. Rice husk ash composites emerged as the most environmentally and economically sustainable option. Coconut coir–earth blocks exhibited superior thermal insulation at low cost but limited structural performance. The study provides a robust, replicable framework for material selection and sustainability optimization in emerging economies and recommends integration of AI-enhanced LCA tools into Nigeria’s national building codes to guide evidence-based material choices. By embedding AI into LCA workflows, this research enables evidence-based decision-making for climate-resilient, affordable housing in Nigeria
Deep Learning for Disease Classification in Teledermatology System Using Dermoscopic Skin Images
Get PDFIn recent years, the popularity of Deep Learning has surged. Among the most well-known architectures in Deep Learning are Neural Networks, including Convolutional, Recurrent, and Generative Adversarial Networks. Convolutional Neural Networks (CNNs) have become an important architecture for image classification tasks due to their superior accuracy and performance. Skin cancer, the most common form of human cancer, has an extremely high cure rate when detected and treated at an earlier stage. However, automated categorization of skin lesions is challenging due to the fine-grained heterogeneity in their appearance. This study proposed a CancerVisionNet (CNNs) model to predict and categorize seven distinct types of skin lesions. The "Human Against Machine with 10000 training images" (HAM10000) dataset, which contains dermoscopic images, is used in this research to evaluate the proposed method for diagnosing and organizing skin disorders. ReLU as an activation function is employed to handle non-linearity in hidden layers. Our proposed method achieved a higher accuracy (79.6%) than other state-of-the-art methods such as with accuracies of 75.03% and 74.3%. This paper shows the effectiveness of the proposed method in disease classification using dermoscopic skin images in the context of teledermatology