i-manager's Journal on Future Engineering and Technology (JFET)


Volume 20 Issue 4 July - September 2025

Research Paper

Green Hydrogen Integration in Electric Vehicles: Advancing Sustainable Transportation

Arun Kumar B. V.* , Sri Gowri K.**, Anantha Lakshmi V.***, Harish Reddy K.****, Masum Basha S.*****
*-***** G. Pulla Reddy Engineering College, Kurnool, Andhra Pradesh, India.
Kumar, B. V. A., Gowri, K. S., Lakshmi, V. A., Reddy, K. H., and Basha, S. M. (2025). Green Hydrogen Integration in Electric Vehicles: Advancing Sustainable Transportation. i-manager’s Journal on Future Engineering & Technology, 20(4), 1-8.

Abstract

Current transportation practices generate nearly one-quarter of global greenhouse gas (GHG) emissions, which justifies adopting sustainable mobility solutions. The potential of battery electric vehicles (BEVs) is limited by public anxiety about range restrictions and charging infrastructure development, together with their dependence on materials production. The analysis studies the potential of green hydrogen produced through renewable energy electrolysis as an additional energy carrier or co-storage method. The research examines various hydrogen production methods, beginning with alkaline electrolysis, PEM electrolysis, and solid oxide electrolysis, and extending to emerging biomass gasification and photocatalysis systems. This paper examines how electric vehicle technologies use hydrogen through FCEVs and hybrid powertrains by investigating their performance and infrastructure requirements and efficiency achievements. The assessment of green hydrogen's environmental effects depends on evaluations of greenhouse gas emissions over their lifecycle, along with water usage, resource utilization, and energy system efficiency. The paper establishes that green hydrogen together with BEV systems offers feasible solutions to reduce transportation emissions to zero while supporting heavy-duty and extensive distance travel needs.

Research Paper

Benchmarking Open-Source OCR Engines on Semantic Slide Regions in Educational Videos using a Subset of FITVID Dataset

Purushotham E.* , Kasarapu Ramani**, Shoba Bindu C.***
* Department of Computer Science and Engineering, Jawaharlal Nehru Technological University Kakinada (JNTUK), Kakinada, Andhra Pradesh, India.
** Department of Computer Science and Engineering, GITAM School of Technology, GITAM Deemed University, Bengaluru, Karnataka, India.
*** Department of Computer Science and Engineering, Jawaharlal Nehru Technological University College of Engineering, Ananthapuramu, Andhra Pradesh, India.
Purushotham, E., Ramani, K., and Bindu, C. S. (2025). Benchmarking Open-Source OCR Engines on Semantic Slide Regions in Educational Videos using a Subset of FITVID Dataset. i-manager’s Journal on Future Engineering & Technology, 20(4), 9-17.

Abstract

Optical Character Recognition (OCR) has a significant application in obtaining text from academic video material, particularly from lecture slides. Still, most of the available OCR assessments address documents holistically and do not consider structural and semantic variance contained in slide content. This paper comprehensively benchmarks five open-source OCR engines—Tesseract, EasyOCR, PaddleOCR, Keras-OCR, and DocTR—on labeled semantic regions of lecture slides, including titles, text boxes, tables, handwritten notes, headers, and footers. Because of architecture and runtime constraints, DocTR and Keras-OCR were excluded from the final performance comparison. The study examines OCR engine performance over these region categories using Word Error Rate (WER) and Character Error Rate (CER) as metrics. Findings indicate no one OCR engine stands out across categories: Tesseract works consistently on formatted text areas such as titles and headings, while PaddleOCR is best at identifying handwritten and tabular data. The results emphasize the necessity of region-aware OCR selection in applications for indexing lecture videos. This contribution offers a pragmatic benchmark and actionable recommendations for researchers and engineers constructing searchable educational content platforms.

Research Paper

Integration of LabVIEW and Arduino for Liquid Level Control

Gavhane V. B.* , Pawar A. M.**, Patil S. N.***
*-**** Department of Electronics, Tuljaram Chaturchand College of Arts, Science and Commerce, Baramati, Affiliated to Savitribai Phule Pune University, Pune, Maharashtra, India.
Shinde, K. P., Gavhane, V. B., Pawar, A. M., and Patil, S. N. (2025). Integration of Labview and Arduino for Liquid Level Control. i-manager’s Journal on Future Engineering & Technology, 20(4), 18-24.

Abstract

The rapid evolution in the field of electronic technologies, such as embedded technology, computer communication and network technology, microelectronics and sensor technologies, AI and machine learning, virtual instrumentation, and VLSI technologies, among others, enabled the vast proliferation of the field of electronic instrumentation. Due to this, the field of smart electronic systems is emerging in the fields of industry, automation, chemistry, medicine, and agriculture. Nowadays, integrating virtual instrumentation with sophisticated microcontrollers provides a suitable solution to meet the demand for advanced, smart instruments that simplify use and reduce design time across various applications. Therefore, this paper presents the design and implementation of an automated liquid level control system with the help of LabVIEW and Arduino. The present system is designed to maintain the liquid level in a tank at a desired level by automatically controlling a pump or valve based on real-time measurements obtained from an ultrasonic sensor or IR. The primary goal of the system is to provide a low-cost, efficient, and user-friendly solution for liquid level control in industrial applications. The system employs Arduino for data acquisition and control, while LabVIEW provides a graphical interface for monitoring and interacting with the system. This work demonstrates the feasibility of integrating hardware and software tools to automate and monitor liquid levels in real-time.

Review Paper

The Role of Artificial Intelligence in Energy Efficiency Optimization

Tapiwa Robson Makumbe*
Harare Institute of Technology, Harare, Zimbabwe.
Makumbe, T. R. (2025). The Role of Artificial Intelligence in Energy Efficiency Optimization. i-manager’s Journal on Future Engineering & Technology, 20(4), 25-40.

Abstract

The integration of Artificial Intelligence (AI) into energy systems is driving significant advancements in energy efficiency across sectors such as manufacturing, transportation, and smart grids. AI enables advanced analytics and predictive modelling to monitor consumption patterns, identify inefficiencies, and develop adaptive energy management systems that respond to demand forecasts. In renewable energy, AI enhances performance by optimizing the design of wind turbine blades, solar panel placement, and maintenance schedules, ensuring maximum energy capture and operational efficiency. Beyond energy management, AI-driven automation in industry reduces waste, lowers costs, and supports sustainability. Smart grids powered by AI can dynamically balance supply and demand, predict fluctuations, prevent outages, and improve resilience. In transportation, AI-powered traffic systems, autonomous electric vehicles, and optimized logistics reduce fuel consumption, emissions, and operational expenses. However, challenges hinder widespread adoption. Data privacy concerns arise from reliance on extensive consumer data, requiring secure collection, processing, and storage. High implementation costs, particularly for small and medium-sized enterprises, along with the need for upgrading legacy infrastructures and hiring skilled personnel, present significant barriers. AI algorithms must also be refined for accuracy and adaptability to changing energy demands and climate conditions. Despite these challenges, AI offers vast potential for sustainable energy optimization. Collaboration among policymakers, industry leaders, and researchers is essential to develop regulatory frameworks, financial incentives, and standardized practices for AI integration. Investment in AI research will enhance adaptability, scalability, and seamless integration into existing systems. Future efforts should focus on refining AI models to accelerate the transition toward smarter, more sustainable energy solutions, enabling higher efficiency, reduced operational expenses, and a smaller environmental footprint for a sustainable global future.

Review Paper

The Evolution of AI-Based Maintenance in Gold Processing Mills

Ruvimbo Victoria Makuwaza*
Harare Institute of Technology, Harare, Zimbabwe.
Makuwaza, R. V. (2025). The Evolution of AI-Based Maintenance in Gold Processing Mills. i-manager’s Journal on Future Engineering & Technology, 20(4), 41-48.

Abstract

AI-driven predictive maintenance has transformed gold processing operations by moving maintenance strategies from reactive schedules to data-driven prognostics. Advanced algorithms and platforms such as machine learning, deep learning, computer vision, IoT, and digital twins now analyze real-time sensor data to detect emerging faults days or weeks before failures occur. These technologies have been deployed globally, from Australia's Newcrest mining IoT platform to Chinese gold company Shandong Mining's smart conveyors to South African ball mill monitoring, yielding significant benefits. For instance, AI interventions at a gold mill in South Africa averted a motor failure that traditional vibration monitoring missed, while a U.S.-IoT-enabled “soft sensor” at an Australian gold operation cut unplanned downtime with a payback under three months. Across projects, maintenance costs have fallen by double-digit percentages and downtime by over 50%. This paper reviews the global evolution and trends of AI-based maintenance in gold mills, surveys key AI technologies (AI/ML, computer vision, expert systems, IoT, and digital twins), presents case studies from Australia, South Africa, Canada, and China, and discusses challenges, return-on-investment (ROI), and future directions such as expanded edge AI and digital twin integration.

Review Paper

A Study on Design and Development of Low-Light Image Enhancement

Chandu D. Vaidya* , Gunjan P. Mohod**, Anushka P. Hedaoo***, Karishma S. Meshram****, Swayam A. Shahu*****, Sourabh Singh Chauhan******
*-****** Department of Computer Science and Engineering, S. B. Jain Institute of Technology, Management and Research, Nagpur, Maharashtra, India.
Vaidya, C. D., Mohod, G. P., Hedaoo, A. P., Meshram, K. S., Shahu, S. A., Chauhan, S. S. (2025). A Study on Design and Development of Low-Light Image Enhancement. i-manager’s Journal on Future Engineering & Technology, 20(4), 49-59.

Abstract

Images captured in low-light conditions typically suffer from reduced visibility, poor contrast, and excessive noise, making it challenging to extract meaningful details. These issues significantly impact applications such as surveillance, medical imaging, and autonomous systems, where clear and high-quality images are essential for accurate decision- making. Traditional enhancement techniques aim to improve brightness and contrast but frequently introduce artifacts or fail to adapt to varying lighting conditions. This research explores an advanced approach to low-light image enhancement that focuses on improving visibility while preserving natural details. By analyzing the structural and illumination properties of images, the proposed method enhances brightness, reduces noise, and maintains color consistency. The model is designed to adaptively enhance different regions of an image, ensuring a balanced improvement in both dark and bright areas. Experimental evaluations demonstrate that the proposed approach effectively enhances image clarity without over-amplifying noise or distorting details. Comparative analysis with conventional methods highlights its superior performance in producing visually appealing results suitable for real-world applications. This study contributes to the ongoing advancements in image processing by providing an efficient and adaptive solution for enhancing images captured in challenging lighting conditions.