BOHR International Journal of Internet of things, Artificial Intelligence and Machine Learning

Stock price prediction through an artificial intelligence model using basic, technical, and macroeconomic indicators

Eui-Bang Lee, Heon Baek — Sat, 17 May 2025 00:00:00 +0000

This study aims to analyze and predict future stock values more accurately. We proposed a stock price prediction model based on an artificial intelligence model using basic stock price data and technological and macroeconomic indicators. As a result of the experiment, the model using the features of adding technical indicators to the actual stock index (basic indicators) has better performance than the model using basic indicators and forecast performance by adding basic, technical, and macroeconomic indicators. Comparing artificial intelligence algorithms, the LightGBM model performed better than the deep neural network model and random forest model.

Recent AI-based smart farming for monitoring and security in sub-Saharan Africa regions

Anayo Chukwu Ikegwu, Chibueze Valentine Ikpo, Tosin Oladayo Akinwande — Thu, 05 Jun 2025 00:00:00 +0000

Artificial intelligence (AI) has revolutionized smart farming in sub-Saharan Africa, especially in Nigeria, which still relies mostly on agriculture with conventional methods, which suffer problems such as pest infestations, erratic weather patterns, and threats to farm security, decreasing productivity. The agricultural practice continues to be an important sector in sub-Saharan African regions, especiallyWest African countries such as Ghana, Cameroon, Mali, Cabo Verde, Nigeria, etc., contributing meaningfully to the economy and serving livelihoods for a large proportion of agriculturalists of the population. The emergence of AI-powered smart farming provides enabling ways to monitor and protect agricultural processes in the regions. This review paper highlights how AI-based technologies such as machine learning, computer vision, Internet of Things sensors, and drone surveillance contributed to the improvement of precision farming, crop health monitoring, and possible real-time threat detection. The study further discusses AI in farming monitoring and farming security. In addition, challenges and solutions of AI technology for smart farming were discussed. The implication of this study will ensure that the agricultural practice receives a technology-enabled framework to foster the acceleration of AI-driven capacity building, digital infrastructure investment, and legislative assistance to enable a seamless practice. The advent of smart farming can transform Africa’s agricultural sector, which can lead to resilience and economic growth variability.

Artificial intelligence as a tool for knowledge management

Dragisa V Obradovic, Nebojsa Denic, Goran Nestorovic, Dragan D Obradovic — Mon, 27 Oct 2025 00:00:00 +0000

Information and communication technologies and knowledge management represent one of the basic features of modern society. The needs of modern society and economy for better and more efficient products and services condition the constant development of the technological sector. One of the latest and most significant phenomena in the field of technology is artificial intelligence (AI), that is, the possibility of computer programs to replace human intelligence and human work in many activities and activities. The goal of the paper is to point out the importance of future research on AI in various areas of law, for which the need will inevitably arise in the near future.

The scoping review and prospects on wearable health technology

Kajal Arvind Pradhan — Sun, 09 Nov 2025 00:00:00 +0000

One of the most fascinating areas of technology is wearable medical devices. These wearables provide a constant stream of health care data for disease diagnosis and treatment, in addition to helping users live healthier lifestyles by continuously monitoring physiological signals and analyzing metabolic state. This article seeks to cover all the various facets of wearable technology, such as its historical evolution and certain essential characteristics.

Real-time forensic analysis in internet of things environments: bridging readiness and investigation for cyber resilience

Oyeyemi Kuku, Alexandros Chrysikos, Shahram Salekzamankhani — Sun, 23 Nov 2025 00:00:00 +0000

With the exponential expansion of the Internet of Things (IoT) networks, the threat of cyberattacks has become particularly high across vulnerable sectors such as healthcare, smart infrastructure, and industrial control systems. Conventional centralized forensics has disadvantages in scalability, data privacy, and the ability to identify synchronized attacks quickly. This paper addresses the above shortcomings by proposing a new Federated Graph Convolutional Network (Fed-GCN) architecture for real-time forensic examination in distributed IoT settings. Its principal goal is to build a privacy-preserving graph-based solution that supports readiness in the forensic environment and defense against the transmission of raw data. The innovations in the work are the conjoint use of graph neural networks to detect contextual attacks, federated learning to ensure data confidentiality, and integration with blockchain-based logging to bind the evidence chain and produce immutable evidence. Among other outcomes, the proposed Fed-GCN architecture was coded in Python and tested on a multi-class intrusion dataset including 18,428 data samples and 79 features. The experimental performance is better than that of traditional methods, with 97.3% accuracy, a 94.2% F1-score, and a low false-positive rate of 6.7%. 100% forensic integrity check and evidence verification were achieved, with 96.4% evidence completeness in the logs and low communication overhead, demonstrating that it can be deployed in edge-based environments. Therefore, the proposed Fed-GCN can play a significant role in implementing forensic intelligence in IoT ecosystems by providing scalable, secure, and regulation-compliant solutions.

Enhancing senior wellness: monitoring and managing heart health with IoT-powered healthcare solutions for the elderly

Sinna Lebbe Fathima Ruksana — Thu, 11 Dec 2025 00:00:00 +0000

The development of technology across all spheres of society has led to a waste of elders’ desire for efficient
management and monitoring of their cardiac health. Internet of Things (IoT) is a significant and helpful technology
that helps to address the issues that seniors experience on a daily basis. This project’s primary goals include
continuously monitoring the elderly to detect heart problems early and treat them, giving doctors and caregivers
access to the elderly’s status and information to provide real-time alarms, developing a system for routinely
monitoring the elderly with automated reminders, and safeguarding the elderly’s sensitive information. Numerous
health indicators, including body temperature (BT), heart rate (HR), and heartbeat rate (BPM) are used to track the
health of the elderly in real time. The system has two modes of operation: automated and manual. In automated
mode, alerts are generated based on predetermined threshold conditions, and elderly users can manually trigger
emergency notifications if they sense unusual circumstances. Additionally, the device assists in providing the
elders’ GPS location in the event that they experience an emergency. In addition to offering a reliable real-time
monitoring system with accurate senior location tracking in just a few minutes, the system also facilitates effective
communication through short message service (SMS) and phone calls and contributes to a user-friendly design.
Additionally, this technology offers elderly users easy accessibility so they can use it effectively. This IoT-based
healthcare solution gives caregivers peace of mind, improves the safety and well-being of the elderly, and offers a
strong foundation for managing heart health.