International Journal of Information Technology, Research and Applications

Role of Machine and Deep Learning Algorithms in Secure Intrusion Detection Systems (IDS) for IOT & Smart Cities

2024-09-30T18:06:01+00:00

In this study the authors have examines various machine learning algorithms that could be used in IDS for making secure IoT and Smart Cities. The study examines various deep learning architectures of supervised, unsupervised, and semi-supervised learning methods to improve security and resource usage. Federated learning, edge computing, explainable AI, adversarial machine learning defense, and transfer learning are also explored for smart farming and IoT challenges. Machine learning has the potential to improve security and agricultural sustainability, but it must be researched and developed.

Towards a Data Governance Model for Enhanced Data Quality Management: A study of Public Sector Organizations in Guyana

2024-09-14T22:03:05+00:00

Public sector organisations in Guyana recognise the need to handle and manage sensitive data properly. Proper data governance is the solution. Identifying the factors that would influence the design of data governance models helps to ensure the creation of a solid model and data quality management. This study accumulated factors from the literature and presented them to IT professionals in Guyana. The Contingency Model served as a base for the identified factors to work together to create a company-specific model for data quality management. Thematic analysis was employed to analyse nine (9) interview transcriptions from medium to high-level personnel across different public sector organisations in Guyana. The factors identified were refined to the Guyanese context. Culture emerged as an indigenous factor in this study. This research resulted in an emergent model that can now be used to design data governance models for public sector organisations in Guyana

Classifying Malware in Android Applications Using Recurrent Neural Networks and Transfer Learning Techniques

2024-12-05T18:48:39+00:00

Today, malware activities are a significant security threat to Android applications. These risks are capable of stealing important information and creating havoc in the economy and our social and financial fabric. Cybercrime traffic focuses on Android apps since these continually connect to the Internet [1]. In this paper, a new technique for detecting the presence of malware in Android applications is presented, using Recurrent Neural Network (RNN) and transfer learning. The growth in the number of Android malware threats calls for a reliable and efficient method of detection of the malware. Our approach exploits the characteristics of RNNs for analysing sequential data and transfer learning for using a pre-trained model for a different task. The experimental results show that our model has high accuracy in classifying malware, verifying the reasonability of applying RNNs and transfer learning in the field of malware identification. The significance of using the graph-based approach to identify malicious parts of Android applications from the packet capture is evidenced by the experimental results, proposing that this technique performs better than traditional machine learning algorithms and can improve the current malware detection system in Android applications.

IoT Evolution: Revolutionary Developments in Recent Years

2024-12-26T04:01:08+00:00

The term "Internet of Things," or IoT, comes from blending the words "Internet" and "things." It refers to a network made up of everyday objects like cars, appliances, and more. These items come with sensors, software, and the ability to connect to the internet, allowing them to collect and share data [1]. Recently, IoT has woven itself into various parts of our lives, from smart cities and homes to offices, businesses, and even agriculture. Now, even simple items like lights, locks, and machines are part of this growing IoT world. This shift has changed how we manage both important and routine systems, making our lives safer, easier, and more efficient [2]. In 2024, there will be 5.35 billion internet users or 66.2 percent of the world's population. With 97 million new people using the internet for the first time in 2023, the number of internet users has increased by 1.8% in the last 12 months.[3]. In this paper, we will look closely at how IoT has evolved, identify key changes that have occurred, explore their impact on IoT's growth, and discuss what these changes might mean for the future of IoT.

The AI-Driven Sentiment Classification via Combinatorial Techniques and Reasoning

2024-12-22T02:17:00+00:00

This paper proposes an AI-driven approach to sentiment analysis, leveraging mathematical concepts such as permutations, along with logical reasoning techniques. The method involves splitting the text; permutations are used to extract n-grams. AI-driven logic is then applied for feature scoring. Finally, fuzzy logic integrates these scores to classify sentiments. This approach focuses on enhancing sentiment classification accuracy by blending AI-based features.