Volume 14 | Issue 4 |

 Abstract

The Internet of Things is based on the concept of layered design. A range of technologies are used by each tier for information transmission, capacity, and preparation. This study aims to assess the present Internet of Things architecture with respect to the risks and vulnerabilities associated with IoT-enabled devices, as well as potential assurance procedures in light of equipment limits and novel information transfer methodologies. We then discuss IOT applications and architecture. A list of successful real-time IOT applications now in use is as follows: Emerging technologies include things like self-driving cars, smart grids, traffic management systems, logistic management hierarchies, environment monitoring, building safety applications, and many more.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Artificial Intelligence (AI) has moved the practice of marketing from a traditional activity into a domain that is intensely driven by intelligence and data. The framework combines behavioral insights, neuromarketing, and AI-driven predictive analytics to offer an innovative approach for consumer intelligence and strategic decision-making. Neuromarketing is a method for exploring unconscious emotional and cognitive responses; behavioral insights explain decision-making biases and preferences while predictive analytics employs massive data in order to anticipate consumer behavior. This research proposes a conceptual framework between marketing performance, decision quality, and customization effectiveness with Artificial Intelligence (AI)-based consumer intelligence. The Effects of Integrated Consumer Intelligence Series Using Survey Data, Evidence from Neuromarketing Experiments and AI-Based Predictive Modeling: This mixed-method study employing survey data and experimental evidence from neuromarketing as well as AI-based predictive modelling to unlock the strategic marketing effects. We anticipate that the findings can help advance theory through the can provide a bridge between cognitive neuroscience in conjunction with AI-decomposed today, precision marketing, consumer engagement, and competitive advantage in the digital economy.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Consumer Intelligence, Neuromarketing, Predictive Analytics, Behavioral Insights, Strategic Marketing, Decision Intelligence

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid growth of social media platforms has significantly increased the spread of misinformation and fake news. Manual verification of news content is slow, expensive, and unsuitable for large- scale data processing. This paper presents an automated fake news detection system using Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning techniques. Textual news data is preprocessed using tokenization, stop-word removal, and lemmatization. Feature extraction is performed using TF-IDF vectorization and word embeddings. Multiple classification models including Logistic Regression, Support Vector Machine (SVM), Naive Bayes, and Long Short-Term Memory (LSTM) networks are trained and evaluated. Experimental results show that deep learning models outperform traditional machine learning methods, achieving an accuracy of up to 96%. The proposed system provides a scalable and efficient solution for identifying fake news in digital platforms.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Fake News Detection, NLP, Machine Learning, Deep Learning, Text Classification, LSTM, TF-IDF.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid growth of mobile technologies and the increasing demand for contactless, efficient, and personalized services have significantly transformed the hospitality industry. Traditional restaurant management systems rely heavily on manual processes such as printed menus, verbal order taking, and counter-based billing, which often lead to inefficiencies, longer waiting times, human errors, and limited customer engagement. This paper proposes a Smart Dining Experience System, an Android-based intelligent restaurant management application designed to automate menu management, order processing, billing, and customer interaction. Developed using Android Studio, the system employs Java and XML for front-end development and SQLite for backend data management. Restaurant administrators can dynamically manage digital menus, while customers can browse food items, place orders, track preparation time, receive personalized food recommendations, and make digital payments using smart phones. A frequency-based recommendation algorithm analyzes customer order history to enhance personalization. Experimental evaluation indicates reduced service time, improved order accuracy, and increased customer satisfaction. The study demonstrates that mobile-based smart dining solutions can effectively modernize restaurant operations and enhance overall service quality.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Dining Experience, Restaurant Automation, Android Application, Digital Menu, Food Recommendation System, SQLite, Mobile Payment

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Attendance monitoring is an essential administrative task in educational institutions for tracking student participation and academic engagement. Conventional attendance methods such as manual roll calls and signature-based systems are time-consuming, error-prone, and vulnerable to proxy attendance. This paper presents a face recognition-based automated attendance management system using computer vision and deep learning techniques. The proposed system captures real-time facial images through a camera and performs face detection and recognition using convolutional neural network-based models. Facial features are extracted and matched against a pre-trained student database, and attendance records are automatically updated in a centralized storage system. The system eliminates manual intervention and ensures secure, contactless attendance recording. Experimental evaluation was conducted in a controlled classroom environment using a dataset of enrolled students. Performance was measured using recognition accuracy, False Acceptance Rate (FAR), and False Rejection Rate (FRR). The results demonstrate that the proposed system achieves high recognition accuracy and significantly reduces attendance processing time compared to traditional methods. The system provides a reliable and scalable solution for intelligent attendance management in educational institutions. The system achieved a recognition accuracy of 96.2%, with a False Acceptance Rate of 1.8% and a False Rejection Rate of 2.0%.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Face Recognition, Automated Attendance, Deep Learning, Computer Vision, Biometric Authentication, CNN, Image Processing.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid advancement of digital technologies has significantly transformed modern computing environments, particularly through the integration of Artificial Intelligence (AI) with cloud computing. Cloud computing enables organizations to access scalable computing resources, storage, and services over the internet, eliminating the need for costly on-premise infrastructure. When combined with AI technologies such as machine learning, deep learning, and big data analytics, cloud platforms become powerful environments capable of processing massive datasets, generating insights, and supporting intelligent decision-making.This paper examines the evolution of AI cloud computing, beginning with early cloud infrastructure models and progressing through stages such as big data integration, machine learning adoption, and the development of AI-as-a-Service platforms. It also highlights the core technologies that enable AI cloud systems, including machine learning, deep learning, big data analytics, Internet of Things (IoT), and automated machine learning tools. The study further discusses the major benefits of AI cloud computing, such as cost efficiency, scalability, faster innovation, and improved data management.In addition, the paper explores key real-world applications across industries including healthcare, finance, transportation, smart cities, and e-commerce. While the adoption of AI cloud computing continues to grow, challenges such as data privacy concerns, cybersecurity risks, high data dependency, and technical complexity remain significant considerations.Finally, the paper outlines future trends shaping the next generation of AI cloud systems, including edge AI, intelligent automation, quantum computing integration, and advanced privacy-preserving technologies.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Cloud Computing, Machine Learning, Deep Learning, Big Data Analytics, AI-as-a-Service (AIaaS), Internet of Things (IoT), Edge Computing, Intelligent Automation, Digital Transformation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Honey pots have evolved from static decoy systems into intelligent, adaptive components of modern cyber security architectures. This survey paper presents a comparative analysis of traditional and modern honey pot technologies, emphasizing their integration with artificial intelligence (AI), machine learning (ML), block chain, reinforcement learning, and cloud-native orchestration. We synthesize recent advancements and categorize honey pot systems by interaction level, deployment strategy, and technological augmentation. Comparative tables highlight the evolution of capabilities, scalability, and operational effectiveness. The paper concludes with insights into best practices and future research directions for deploying deception-based defenses in dynamic threat environments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Honeypots, Cyber security, Deception Technology, Machine Learning, Reinforcement Learning, Block chain,Cloud Security.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Real-Time Disaster Management system is designed to improve emergency response efficiency through automated processing of disaster-related information. Traditional disaster management systems rely on manual communication and delayed decision-making, which often result in slow response and increased damage. The proposed system uses rule-based artificial intelligence techniques to analyze emergency messages, determine severity levels, assign priority, and generate alerts in real time [5]. The system also detects duplicate messages to avoid repeated alerts and maintains structured records in a centralized database [7]. An admin dashboard enables monitoring of emergency messages, alert delivery status, and disaster history. The system reduces response time, improves coordination, and enhances disaster preparedness and management effectiveness.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Real-Time Disaster Management , Emergency Response , Artificial Intelligence, Rule-Based System ,Severity Analysis , Priority Assignment , Automated Alerts, Duplicate Detection , Centralized Database , Disaster Preparedness

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Smart Dormitory Management Tracking System is a comprehensive web-based application designed to modernize and automate hostel administration processes within educational institutions. Traditional dormitory management systems rely heavily on manual record-keeping, including physical registers and spreadsheet-based documentation. These conventional approaches often result in data inconsistency, delayed updates, difficulty in monitoring occupancy, and increased administrative workload. The proposed system introduces a centralized digital platform that integrates multiple hostel management functions such as student registration, room allocation, attendance monitoring, fee management, complaint handling, and reporting. The application is structured with role-based access control to ensure that administrators, wardens, and students can access only authorized modules. The system enhances operational efficiency by automating repetitive tasks, maintaining structured database records, and enabling real-time monitoring of room occupancy and student activities. Secure authentication mechanisms are implemented to protect sensitive data and prevent unauthorized access. By reducing manual dependency and improving transparency, the Smart Dormitory Management Tracking System provides a scalable and reliable solution suitable for institutional deployment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Dormitory Management System, Web-Based Automation, Occupancy Tracking, Access Control, Student Information System, Real-Time Monitoring

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

With the rapid growth of digital communication platforms such as SMS, email, and social media, cyber threats like spam, phishing, and scam messages have become increasingly sophisticated and context-driven. Traditional detection systems mainly rely on keyword matching and predefined patterns, which often fail to identify the underlying intent behind malicious communications, leading to reduced detection accuracy. This paper proposes an Intent-Aware Artificial Intelligence approach for proactive threat detection in digital communications by focusing on understanding the sender's intent using Natural Language Processing (NLP), contextual analysis, and machine learning techniques. The system analyzes linguistic patterns, behavioral cues, and contextual semantics to detect manipulation strategies such as urgency, deception, and fraudulent intent before user interaction. Additionally, the proposed model supports adaptive learning to handle evolving threat patterns and can be deployed using edge Intelligence to ensure privacy preservation and real-time processing without heavy cloud dependency. This approach aims to enhance detection accuracy, reduce false positives, and provide a more intelligent, adaptive, and human-like security mechanism for modern communication systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Intent-Aware AI, Cyber Threat Detection, Natural Language Processing, Contextual Analysis, Phishing Detection, Adaptive Learning, Edge Intelligence, Spam Detection, Fraud Detection, Behavioral Analysis, Real-Time Processing

  License

Creative Commons Attribution 4.0 and The Open Definition