International Journal of Artificial Intelligence of Things (AIoT) in Communication Industry

AgriBot: IoT-enabled Autonomous Robotic System for Real-time Soil and Environmental Monitoring in Precision Agriculture

Abdullateef Ogundipe — 2026-01-02

Agriculture, as a foundation of food security and economic development, increasingly depends on technological innovations to address rising demands for efficiency, sustainability, and productivity. Traditional farming practices often struggle with inefficiencies in monitoring and resource management, creating a need for intelligent solutions. This study presents AgriBot, an autonomous agricultural robot designed to support precision farming through real-time monitoring of soil and environmental conditions. Leveraging IoT-enabled sensors, embedded microcontrollers, and a web-based dashboard, AgriBot collects and analyzes data to provide actionable insights for farmers. Experimental evaluation showed that the proposed system achieved approximately 95% obstacle detection accuracy during autonomous navigation and about 90% accuracy in soil moisture sensing across varying soil conditions. Additionally, real-time control and monitoring were supported with response latencies below 500 ms and continuous operation of up to 4–5 hours, demonstrating the system’s suitability for practical precision agriculture applications.

AI-assisted GEOINT for Border Security: A LEO-centric Architecture Integrating IMINT, UAV Reconnaissance, and OSINT

Settapong Malisuwan — 2026-01-27

Border security operations require persistent monitoring, timely detection, and reliable decision support across large and diverse geographic areas. Traditional approaches based on single sensors or isolated intelligence sources often struggle to provide comprehensive situational awareness under changing environmental and operational conditions. This paper proposes an AI-assisted geospatial intelligence (GEOINT) architecture to support military and security border operations by integrating Low Earth Orbit (LEO) satellite imagery intelligence (IMINT), Unmanned Aerial Vehicle (UAV) reconnaissance, and Open-Source Intelligence (OSINT) within a unified framework. The proposed architecture adopts a layered approach in which LEO satellites provide wide-area and persistent monitoring, optical and synthetic aperture radar (SAR) sensors offer complementary observation capabilities, and UAVs serve as tactical gap-fillers for localized verification and responsive reconnaissance. Artificial intelligence is embedded within the processing layer to support object detection, change detection, and information fusion, with the primary goal of assisting analysts in managing large data volumes and prioritizing areas of interest. Human-in-the-loop control is maintained throughout the workflow to ensure accountability, transparency, and operational relevance. Rather than presenting performance metrics or sensitive implementation details, the paper focuses on architectural design, operational roles, and illustrative border security scenarios. The results highlight how the integration of satellite IMINT, UAV data, OSINT, and AI-assisted analysis can enhance situational awareness and decision support while remaining aligned with established GEOINT doctrine and ethical considerations. The proposed framework provides a practical foundation for future development of border security GEOINT systems.

Application of Artificial Neural Network Control Techniques for Torque Ripple Mitigation in Bearingless Synchronous Motors

Baridakara Deesor — 2026-02-16

This paper investigates the application of Artificial Neural Network (ANN)-based control techniques for mitigating torque ripple in bearingless synchronous motors, a critical challenge in high-precision electric drive systems. The increasing deployment of electric motors in industrial automation, robotics, renewable energy, and aerospace applications has intensified the demand for advanced control strategies that ensure smooth torque production, reduced vibration, and reliable long-term operation. Torque ripple in synchronous motor drives leads to periodic torque pulsations that cause mechanical stress, acoustic noise, performance degradation, and reduced service life. The main objective of this study is to design and evaluate an ANN-based control framework capable of effectively minimizing torque ripple under varying operating conditions. The proposed method exploits the nonlinear mapping and adaptive learning capabilities of neural networks to dynamically adjust control parameters in response to system variations. A detailed motor drive model was developed and implemented in the MATLAB/Simulink environment using operational data obtained from industrial installations to enhance practical relevance. Two industrial motor samples from Nigeria were used for validation: an 11.0 kW, 400 V motor from the BUA industrial facility and an 11.0 kW, 690 V motor from the Indorama plant, both with distinct speed and efficiency ratings. Simulation results show that the ANN-based controller achieved approximately 35.4% reduction in torque ripple compared with conventional control methods, leading to smoother torque profiles, reduced mechanical loading, lower noise emission, and improved control accuracy. The findings confirm the effectiveness and robustness of ANN-based control for torque ripple mitigation in bearingless synchronous motor applications.

An Integrated AI Mock Interview System

K. Vanitha — 2026-05-21

In the rapidly evolving digital recruitment landscape, the traditional methodologies of candidate assessment are being challenged by the need for scalable, objective, and high-integrity interview preparation systems. This study presents an integrated AI-driven mock interview framework that harmonizes large language models (LLMs) with real-time computer vision (CV) to simulate rigorous professional environments. The proposed architecture utilizes a PHP-based backend coupled with a MySQL relational database for structured data persistence of candidate profiles and performance metrics. To ensure session integrity without compromising user privacy, the framework incorporates a sophisticated multi-modal proctoring mechanism. This module employs MediaPipe Face Mesh for client-side, edge-based inference of 468 3D facial landmarks, enabling real-time gaze tracking and head-pose estimation without requiring server-side video storage. For dynamic conversational interaction, the system leverages the Llama 3.3 model, optimized via the Groq LPU (language processing unit) inference infrastructure. This integration maintains sub-500 ms response latencies, thereby preserving the natural cadence of human dialogue and mitigating the “uncanny valley” effect often found in high-latency AI agents. Furthermore, the system implements a dual-layered evaluation engine: a semantic NLP parser for technical accuracy and a multi-modal sentiment analyzer that correlates vocal pitch, textual intent, and behavioral cues. Experimental results, derived from a pilot study of 50 diverse professional resumes and 100 simulated sessions, indicate a 94% accuracy rate in distraction detection and a strong statistical correlation ($r > 0.85$) between AI-generated scoring and human expert assessments. The framework provides a privacy-conscious, low-latency, and scalable solution for mitigating interview anxiety while establishing a standardized benchmark for modern performance evaluation.

Artificial Intelligence-based Industrial Automation for Smart Manufacturing

Samiksha Shravan Lokhande — 2026-05-25

Artificial intelligence (AI) is transforming industrial automation by enhancing efficiency, accuracy, and decision-making processes in modern industries. The integration of AI technologies such as machine learning, computer vision, and data analytics enables automated systems to perform complex tasks with minimal human intervention. This study presents an overview of the role of AI in industrial automation, focusing on its applications in predictive maintenance, quality control, robotics, and process optimization. AI-driven systems can analyze large volumes of data in real time, identify patterns, and make intelligent decisions, thereby reducing operational costs and improving productivity. Furthermore, AI improves safety by minimizing human involvement in hazardous environments and enhances product quality through precise monitoring and control. The study also discusses the challenges associated with AI implementation, including high initial costs, data security concerns, and the need for skilled professionals. Despite these challenges, the adoption of AI in industrial automation continues to grow due to its long-term benefits and potential for innovation. The findings indicate that AI is a key driver in the development of smart industries and Industry 4.0, enabling more flexible, efficient, and intelligent manufacturing systems.