Federated Learning for Secure and Privacy-Preserving Edge AI in Smart Cities
Leveraging Artificial Intelligence And Hybrid Algorithms For Student Career Planning And Self Development
An Eye-Tracking Arabic Letter Encoding System for Communication in Locked-In Syndrome Using Electrooculography
Leveraging Random Forest (RF) and Long Short term Memory Algorithms (LSTM) for Enhanced Cholera Outbreak Prediction and Response System
A Review of Metaheuristic Techniques with Emphasis on BRADO for Solving the N-Queens Puzzle
IoT-Driven Examination Security: A Multi-Module Approach to Prevent Paper Leaks
Optimal Routing for Emergency Vehicles using A*(A-Star) Algorithm
A Comprehensive Study on Emotion Detection from Facial Expressions using AI and Ml (Python)
Optimal Routing for Emergency Navigation using Swarm Intelligence
A Multiview Point Perspective on Clustering Algorithms for Similarity Evaluation
Leveraging Artificial Intelligence And Hybrid Algorithms For Student Career Planning And Self Development
Optimal Routing for Emergency Vehicles using A*(A-Star) Algorithm
A Review of Metaheuristic Techniques with Emphasis on BRADO for Solving the N-Queens Puzzle
IoT-Driven Examination Security: A Multi-Module Approach to Prevent Paper Leaks
A Comprehensive Study on Emotion Detection from Facial Expressions using AI and Ml (Python)
The rapid expansion of smart cities has led to the integration of Artificial Intelligence (AI) at the edge, enabling real-time decision-making for intelligent urban infrastructure. However, conventional centralized AI models pose critical challenges, including data privacy risks, security vulnerabilities, and high computational overhead. This paper investigates Federated Learning (FL) as a transformative paradigm to enhance security, privacy, and efficiency in edge AI systems for smart cities. Unlike traditional AI training methods, to cyber threats while ensuring compliance with data protection regulations. To address key challenges in heterogeneous smart city environments, we propose a hybrid optimization framework integrating differential privacy, secure multi-party computation (SMPC), and blockchain-based authentication. This approach strengthens resilience against adversarial attacks while ensuring secure model updates. Additionally, we introduce an adaptive aggregation mechanism, which dynamically adjusts model updates based on device reliability, data distribution, and network conditions, optimizing both learning efficiency and energy consumption in edge AI networks. Extensive experimentation on real-world smart city datasets demonstrates that the proposed framework enhances model accuracy, robustness, and privacy preservation compared to conventional AI approaches. Our findings establish Federated Learning as a cornerstone for secure, scalable, and privacy-aware AI in smart cities, facilitating trustworthy deployment of intelligent urban infrastructure. This research provides valuable insights for policymakers, researchers, and industry professionals, paving the way for next-generation AI-driven smart cities with enhanced security, privacy, and efficiency.
This project introduces an innovative AI-powered platform designed to transform the way students navigate career progression and skills development. At its core, the platform leverages advanced artificial intelligence algorithms to deliver highly personalized career recommendations, curated skill-building resources, and access to job and internship opportunities. Unlike traditional static career services, this system adapts to the unique strengths, weaknesses, and aspirations of each student. By analyzing user profiles, learning habits, and industry trends, it generates dynamic pathways that evolve as the student grows academically and professionally. Moreover, planning career paths has become increasingly complex, requiring a deep understanding of industry trends, skill requirements, and personal strengths. This paper introduces a machine learning-based platform aimed at providing personalized academic project suggestions and career path guidance. By analyzing students' academic history, interests, and career objectives, the platform offers tailored recommendations for projects and road maps that include both paid and free learning resources to master necessary skills. The system leverages hybrid recommendation algorithms that combine collaborative filtering with content-based filtering, enhanced by neural networks to provide more accurate and contextually relevant suggestions. This research explores the platform's development, methodologies, and testing, presenting a promising solution to bridge the gap between academia and industry readiness.
This study presents an Arabic letter encoding system for eye-tracking communication, aiding individuals with locked-in syndrome. Utilizing electrooculography (EOG), we translate eye movements into Arabic text, based on an already existing database. The contribution of the proposed approach is to assign specific stroke combinations to Arabic characters, akin to Katakana character formation. The first step is to analyze the specificity of the EOG signal. Then a study of Code-protocol- based eye input systems for Katakana characters is done. Based on these two concepts, first basic strokes for Arabic letters are proposed. followed by a proposition of Arabic letters encoding which is the main contribution of this paper. The second contribution is how to adapt this new encoding to extract corresponding EOG signal. Our system is distinctive in its semantic approach, where similar Arabic letters, having comparable eye-strokes share related eye-strokes, enhancing intuitiveness and ease of learning. The output of our work is a database of 2500 records. It allows researchers in this field to decode the EOG data into accurate Arabic text, demonstrating its potential as a non-verbal communication tool for physically challenge.
Zambia has been faced with a relentless public health crisis since 1977, that crisis being the water borne disease known as cholera. The recent one being from October 2023 to mid 2024 with over 10, 887 cases and 432 confirmed deaths, and this was the most severe outbreak ever recorded in the nation's history. The main causes being the nation’s lack of a robust surveillance and reporting systems, as well as the absence of a system that can analyze historical data and environmental factors(like rain and temperature) all these things contributed to the slow detection and delayed response to the new cases, allowing the outbreaks to grow. This was mainly due to the poor communication between the public communities and the national health bodies. That’s where this proposed system, Random Forest(RF) and Long Short Term Memory Model (LSTM). It is, an AI-driven, community platform that is integrated with real-time surveillance, predictive analysis, Geospatial mapping, community reporting, machine learning algorithms(Random Forest and LSTM) and historical data using a dataset(YEM-CHOLERA-EOC-DIS-WEEK-20160424- 20200621.csv) to control the outbreaks before the become national outbreaks.
This paper talks about using a new algorithm called BRADO to solve the N-Queens problem, which is a well-known puzzle in computer science. BRADO is inspired by how smart people migrate from one country to another — it’s a type of "swarm intelligence" method that works by simulating the behaviour of groups. To solve the N-Queens puzzle, the algorithm uses a cost function that helps it decide which moves are good or bad. It also uses a decision-making method called TOPSIS to fine-tune its settings for better performance. The results show that BRADO works better than other well-known algorithms like Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and a few others. It finds better solutions with fewer conflicts between queens. Overall, this study shows that BRADO is a powerful new tool for solving tricky problems and could be useful in many other areas of artificial intelligence in the future.
