International Journal of Research and Development in Engineering Sciences
Open Access publication.
Engineering the Future: Emerging Trends in Technology & Management Volume I
About the Conference
The International Conference on Emerging Trends in Engineering, Technology and Management (ICETM-2025) aims to provide an interdisciplinary forum for academicians, researchers, scientists, and industrial personnel working in the areas of design and implementation of emerging technologies in the field of engineering, technology and management to exchange their views and share their expertise.
It is an opt platform for the researchers from various domains to discuss about recent innovations, emerging trends, concerns and practical challenges in the field of engineering, technology and management. Every session of this conference has been planned to explore various points of view, revelations, inventions, and discoveries from academicians, researchers, experts, educators, and scientists.
This occasion will provide a priceless forum for bringing up-and-coming developments in a variety of technical sectors. The engineering and management-based sessions will offer a wide range of insight that is both appealing and essential. One needs to be always vigilant when it comes to keeping up with the most recent trends, spotting the most difficult problems, or performing their own research in order to be on the cutting edge.
The ICETM-2025 is the ideal forum for enhancing one's standing among scholars and other research-related groups, as well as for participating in the dissemination of knowledge and expertise. All of this and more may be done at ICETM-2025, where attendees can gain from two days of intensive learning and networking. The submission of participants' articles to a variety of esteemed publications is also encouraged. Every participant will undoubtedly leave the event inspired and fired up.
Aim of the Conference
The International Conference on Emerging Trends in Engineering, Technology and Management (ICETM) aims to provide an international platform for researchers, academicians, and industry professionals to present original, high-quality research, exchange innovative ideas, and address emerging scientific and technological challenges. The conference promotes interdisciplinary collaboration, methodological rigor, research integrity, sustainable innovation, and the dissemination of impactful scholarly contributions with global relevance.
Objectives
International Conference on Emerging Trends in Engineering, Technology and Management (ICETM-2025) aims to provide an interdisciplinary forum for academicians, researchers, scientists, and industrial personnel working in the areas of design and implementation of emerging technologies in the field of engineering, technology and management to exchange their views and share their expertise.
It is an opt platform for the researchers from various domains to discuss about recent innovations, emerging trends, concerns and practical challenges in the field of engineering, technology and management. Every session of this conference has been planned to explore various points of view, revelations, inventions, and discoveries from academicians, researchers, experts, educators, and scientists.
This occasion will provide a priceless forum for bringing up-and-coming developments in a variety of technical sectors. The ICETM-2025 is the ideal forum for enhancing one's standing among scholars and other research-related groups, as well as for participating in the dissemination of knowledge and expertise. All of this and more may be done at ICETM-2025, where attendees can gain from two days of intensive learning and networking.
About the Book
Engineering the Future: Emerging Trends in Technology & Management – Volume I explores innovative developments in engineering, emerging technologies, digital transformation, and modern management practices. Featuring interdisciplinary research, practical applications, and forward-looking perspectives, this volume highlights technological advancements, sustainable solutions, and strategic approaches addressing contemporary industrial challenges and shaping future research, innovation, and global development.
Scope
The International Conference on Emerging Trends in Engineering, Technology and Management provides an interdisciplinary platform for original research, innovative methodologies, and technological advancements in engineering, computer science, artificial intelligence, information technology, electronics, communication, sustainable energy, industrial systems, business analytics, innovation, and management. The conference encourages evidence-based studies, practical applications, industry–academia collaboration, and sustainable solutions addressing global challenges. Contributions should demonstrate originality, methodological rigor, technical significance, and relevance to contemporary scientific and industrial developments.
Paper 1 · Pages 1 - 5
Activity of Blockchain Innovation in Secure Data Management and Strategies used to Forestall Assaults
Abstract
Blockchain technology with its promise of decentralized, transparent, and tamper-proof systems, it unquestionably captured the imagination of the technology industry and beyond. Blockchain technology has emerged as a revolutionary force that has the capacity to transform industries by enhancing security, ensuring data integrity, and enabling decentralized transactions. Regardless of its promising benefits, blockchain faces critical difficulties that need addressing to open its maximum capacity. In this paper we introduced tied down Information management, key moves and blueprints nitty gritty techniques to beat them.
Keywords: Finney Attack, Race Attack, Time jacking Attack, Data Management, Security
Paper 2 · Pages 6 – 13
Empowering Communication: A Web Application for Deaf, Mute, and Sign Language Interpretation
Abstract
The inability to communicate effectively because of communication barriers severely restricts deaf and mute individuals from getting in touch with those who do not know sign language. A new web-based system has been developed to provide an effortless communication solution between users who are deaf, mute and Sign language users. The system implements Django as its backend framework collected with text- to- Sign language conversion and speech-to-text capabilities towards establish successful communication. Through the application users have the option to provide text or audio content that gets translated into American Sign language (ASL) animations through hand gesture visualization from MediaPipe. The system enables automatic speech recognition through the Speech Recognition library and functions as an ASR tool to convert spoken words into text. The Google Translator API enables native language translation of this recorded text which expands communication possibilities to different user groups. From datasets obtained through Kaggle the training of a Convolutional Neural Network model reaches 99% accuracy for sign recognition leading to accurate communication. The application creates a manageable interface which enables people with speech and hearing difficulties to get real-time Sign language animations as visual outputs. The novel system surpasses typical assistive communication solutions because it cuts out the requirement for human Sign language interpreters to provide inclusive communication channels. This proposed web application will increase accessible interactions thus promoting more social integration opportunities for both deaf and mute users. The system will be improved through language expansion of Sign language interpretation and a mobile app adaptation for maximized accessibility. The system incorporates components related to Communication accessibility, Sign language recognition, speech-to-text, ASL animation and employs CNN models in conjunction with Django framework.
Keywords: Media Pipe, automatic speech recognition, and utilizes Google Translator API
Paper 3 · Pages 14 – 18
Towards Generalizable Models in Software Failure Prediction: A Machine Learning Approach
Abstract
The inability to communicate effectively because of communication barriers severely restricts deaf and mute This paper highlights the challenges of generalizing models and dealing with contradictory evidence. Additionally, it explores the potential to enhance software failure prediction by integrating multiple research efforts. Traditional methods of failure prediction could not be highly task-specific due to the fact that not all tasks had access to the same data. To overcome these challenges and achieve better prediction accuracy, you can employ feature selection techniques, data resampling strategies, and machine learning processes. The project includes exploring the use of different datasets and enhancing model training to accelerate problem detection and ensure that solutions are compatible with different software configurations. Software quality assurance methods can be improved and made more adaptable as a direct result of the findings.
Keywords: Software Fault Prediction, Cross-Project Analysis, Imbalanced Data, ML, SQA
Paper 4 · Pages 19 – 25
91.2% Accurate, 88% Safer: RL-Powered Decision Systems for Microbial Risk Mitigation in Food Logistics
Abstract
The current paper concentrates on the data of food safety sensors on four key environmental parameters, including the temperature, humidity, microbial load, and transport time. The parameters were observed with histograms of 1000 samples, thus providing the information about the refrigeration controls, risks of microbial contamination and hazards in transit. The results potentially will be used to design reinforcement learning (RL) tools to plan dynamic inspection and routing to enhance food safety management.
Keywords: Software Fault Prediction, Cross-Project Analysis, Imbalanced Data, ML
Paper 5 · Pages 26 - 31
Internet of Things Security for Smart Homes & Industry: Mechanisms and Challenges
Abstract
Applications in Vehicular Networks : With the increase of Internet of Things?(IoT) devices applications area, widespread deployment of and new markets for a variety of connected devices, robust security mechanisms are required to mitigate escalating cyber-attack scenarios. This is?a brief summary of the full research paper on IoT secure techniques. The?peculiar characteristic of IoT that connects everything with others everywhere, introduces many issues originated from the heterogeneous devices, different communication protocols and constrained deployment environment. This paper examines the current IoT security scenario?and focuses on the highly crucial issue of ensuring data integrity. the current paper outlines a list of the security control tools that are used as elements of hardening IoT implementations with the purposes of malicious attack, unauthorized access, and data breaches. These types of security measures as the device authentication and secure communications protocols and encrypting algorithms are studied in detail depending on where they are used and their effectiveness in various IoT environments. Considering the evolution of IoT at present, we consider the state-of-the-art of secure mechanisms and security methods on a theoretical and practical basis. Based on an in-depth analysis of the issue of the looming cyber threats, the article is a part of the current discussion of strengthening the security stance of IoT systems.
Keywords: Internet of Things secure Mechanism, Encryption methods, Cyber security basics, Security protocols
Paper 6 · Pages 32 – 37
Smart Education Generate with AI Video
Abstract
Smart education empowered by AI is transforming the conventional learning environment by utilizing advanced technologies to deliver customized, engaging, and interactive educational experiences. With the use of AI’s -driven tools, students can access personalized content tailored to their unique progress, strengths, and areas for improvement. AI-generated video resources, including adaptive tutorials, interactive lessons, and real-time assessments, boost student engagement and retention of knowledge, creating a more effective and accessible learning experience. AI also helps teachers by automating administrative tasks and providing insightful data on student performance, freeing them up to focus more on efficient teaching strategies. The incorporation of AI-created educational videos promotes an inclusive and immersive learning atmosphere, accommodating a variety of learning preferences. This strategy bridges the divide between traditional and digital education, granting students more autonomy over their learning paths. By integrating AI into educational videos, institutions can better allocate resources, implement timely learning interventions, and ultimately foster a more equitable educational experience for everyone. The synergy of AI with smart education systems heralds a future where technology and teaching methodologies coexist seamlessly to unlock each student's full potential.
Keywords: Education, Adaptive Video Content, Engaging Lessons, Educational Tech, Intelligent, Online Education
Paper 7 · Pages 38 – 41
Waste Reduction and Environmental Protection in EV Load Forecasting
Abstract
This essay focuses on the use of Gated Recurrent Unit (GRU) model to forecast electric vehicle (EV) energy demand to bolster the energy grid alone and its sustainability. The system that is proposed to predict the energy demand in a 24-hour time frame is the processing of the historical EV charging data. The model training is conducted using time-series data and evaluated using the metrics of mean squared error (MSE) and mean absolute error (MAE). Results indicate that the GRU model can be used to model the trends of energy demand and help to proactively operate the grid and increase the penetration of renewable energy.
Keywords: EV Vehicles, Internet of Things, Security Protocols, AI, ML, DL
Paper 8 · Pages 42 – 47
Copper Oxide Nanoparticles Synthesized by Precipitation Method Towards Biomedical Applications
Abstract
Chemical processes to sustainable and eco- friendly techniques. Of these, green synthesis, also known as biosynthesis has been found to be a viable approach that exploits biological systems, and their biomolecular constituents, to create nanoparticles. It is not only the most environmentally friendly, but also presents unique operational capabilities such as cost-effectiveness, energy efficiency and just one-pot reactions at ambient temperatures. Green synthesis offers a safer and more eco-friendly solution by not requiring the utilization of dangerous reagents and the special conditions of the conventional processes. This review will give a critical summary of the principles of the green synthesis, and more specifically its mechanistic nature in biological and chemical pathways. They provide critical comparisons with the traditional methods and give an assessment of the sophisticated characterization tools that are needed to authenticate the structural, morphological, and functional characteristics of synthesized nanomaterials. Furthermore, some uses of green-synthesized nanoparticles are examined in the biomedicine, environmental cleanup, farming, and technologies in the energy sector. Existing issues such as scalability, reproducibility and mechanistic ambiguities are critically examined and possible ways of overcoming these challenges are presented. This body of evidence supports the case of green synthesis as not only an environmentally friendly alternative, but also as an extremely versatile and technologically better platform that can produce functionally improved nanomaterials to be used in industrial and biomedical innovations in the future. This paper discusses the synthesis of copper oxide nanoparticles (CuO NPs) with Carica papaya leaf extract as the reducing and stabilizing agents. Using the leaves in the precipitation technique, rapid production of CuO NPs was easily biosynthesized and pollution-free without any environmental harmful effects. X-ray diffraction (XRD), Fourier-transform infrared spectroscopy (FT-IR), and scanning electron microscopy (SEM) were used to determine the properties of the nanoparticles. The size of the particles measured using the Scherer equation showed that they were between 50- 60 nm in samples prepared through chemical precipitation. The manufactured CuO NPs had the right characteristics to be used in biomedical uses, which points to the possibility of green synthesis offering sustainable nanotechnology.
Keywords: Copper nanoparticles, Carica Papaya Leaves, Biosynthesis, Biomedical
Paper 9 · Pages 48 - 56
Improved Multicarrier PWM Technique for Harmonic Reduction by Using APOD method for Cascaded H-bridge DC/AC Converters
Abstract
Conventional modulation techniques used in cascaded H-bridge multilevel (CHB) DC/AC converters often spawn the noticeable quantity of harmonics of low frequency in an output voltage. The latter usually leads to a high-peak output current, impacting adversely on performance and reliability of industrial motor drive systems. To tackle these drawbacks, this research develops an improved Multicarrier Pulse-Width Modulation (MCPWM) method based on an alternative Phase Opposition Disposition (APOD) approach. A proposed MCPWM method significantly mitigates harmonic content in an output AC voltage by keeping the continuous output current with reduced peak magnitude. A harmonic mitigation algorithm is presented, which dynamically modifies switching frequency and modulation index of semiconductor devices based on a switching angles of a MCPWM pulse. An algorithm specially deals with a 5th, 7th and 11th-order harmonics and reveals a novel range of switching angles, at which their amplitudes become minimal. One of the significant achievements of this work is the development of a novel real-time switching angle estimation technique which avoids solving complex nonlinear equations. This approach reduces not only computation time but also hardware complexity, hence making medium-capacity FPG an implementation viable. A proposed technique is authenticated by theoretical analysis, MATLAB/Simulink simulations, and exploratory verification using the three-phase FPGA-based CHB multilevel inverter prototype. Comparative analysis against state-of-the-art techniques will reveal superior efficacy of a proposed technique in terms of harmonic suppression, computational efficiency, and hardware simplicity, thus making it a practical solution for industrial power electronics applications.
Keywords: Copper nanoparticles, Carica Papaya Leaves, Biosynthesis, Biomedical
Paper 10 · Pages 57 – 67
Modelling and Analysis of Renewable Energy Integration and Electric Vehicle Impact on Microgrid Performance: The PSO-Based MPPT and ANFIS-Controlled Battery Approach
Abstract
The rapid rise in pollution levels and green house gas emissions has accelerated an adoption of Electrical Vehicles (EVs), which are expected to play the pivotal role in a future energy landscape. As EVs integrate with electrical grids, their impact on voltage profiles and grid load distribution becomes increasingly significant. This study explores an integration of renewable energy sources, EVs into the microgrid and with the emphasis on energy production and consumption optimization. In this analysis, the diesel generator is a microgrid, Photovoltaic (PV) array coupled with the wind farm and the Vehicle-to-Grid system near a load. A paper introduces the model for a PV array that employs Maximum Power Point Tracking (MPPT) through Particle Swarm Optimization (PSO) to maximize an efficiency of a solar energy conversion. Furthermore, it investigates battery control using Adaptive Neuro-Fuzzy Inference System (ANFIS) to manage a storage and distribution of energy from both renewable sources and EVs. A microgrid is designed to cater to an energy demands of various establishments, including hospitals, universities, and EV charging stations. The comprehensive analysis of a micro grid’s performance, with the particular focus on effects of EV integration, is presented using MATLAB/Simulink, revealing an influence of EVs on an overall network stability and energy management.
Keywords: ANFOIS, V2G, EV Vehicles, MATLAB, PSO
Paper 11 · Pages 68 – 75
Hybrid Fuzzy Logic–Based Maximum Power Extraction for Wind Energy Systems
Abstract
In this paper wind turbines power generation global power extraction design was done by using the MATLAB/Simulink. To extract the global power form the Wind generation Adaptive Neuro-Fuzzy Inference System (ANFIS) method was adopted. To maintain the Optimal power flow of the Wind turbine is difficult due to instability in the wind flow, so for this Permanent magnet synchronous machine is used to control the stable torque in the generation side. Here the ANFIS controller gave the better result compared to normal traditional controllers, such as Fuzzy and the P&O algorithms.
Keywords: ANFIS, Fuzzy Logic, WECS, IC, Energy Systems
Paper 12 · Pages 76 – 82
A Comprehensive Overview of Machine Learning based Crop Recommendation Analysis
Abstract
Today in the world, the crop recommendations and predictions are highly required by the farmers to enhance the production of the crop. The paper will set out to review the different studies conducted on crop recommendations to enhance the crop production in India. The thorough research of multiple literature works can provide an insight into the fact that machine learning (ML) techniques play a crucial role in crop forecasting and advisory. The different ML algorithms that have been very effective in predicting the results are addressed with both pros and cons. This paper discusses the parameters employed in datasets, as well as, standard procedure employed to forecast the crop recommendations. Lastly different ML and crop prediction performance indicators are given. This whole paper provides the discussion of crop recommendation methodology.
Keywords: Crop Recommendations, crop prediction, Machine Learning, AI, DL
Paper 13 · Pages 83 – 88
A Survey on Ultra-Lightweight and Energy-Efficient Deep Learning Models for Resource-Constrained IoT Devices
Abstract
This survey of literature examines the recent developments in ultra-lightweight and energy-efficient deep learning models which are specifically created to fit devices with limited resources and that are deployed in the IoT. The survey examines the ways of reducing model size and optimization of computation and balancing security and energy efficiency. The research on lightweight encryption and object recognition proves the application of these models in low-power settings in practice. The questionnaire will serve to present an overall picture of the methods and algorithms that allow the effective application of deep learning to the limited Internet of Things devices.
Keywords: Machine Learning, DL, AI, IoT Devices, LSTM, GIFT, UAVs
Paper 14 · Pages 89 – 93
Cyber Threat Intelligence Platform for Real-Time Attack Detection using SIEM
Abstract
Cybersecurity threats are rising in frequency and sophistication, which calls for the enhancement of better, real-time threat detection systems. This paper introduces a cyber threat intelligence (CTI) platform that combines a deep learning-based detection model with real-time log analysis with the utilization of security information and event management (SIEM) systems. A deep neural network trained with stochastic gradient descent (SGD) is at the heart of the proposed gadget, which uses log data to detect malicious activity. Logs are collected and consumed from the Wazuh platform, permitting real-time correlation and possibility tracking. A tailored dashboard presents a friendly interface for visualizing alerts and designs. The suggested structure mixes detection precision, machine scalability, and functioning responsiveness in changing network environments. Experimental outcomes demonstrate that the model is highly accurate and responsive in determining dangers, structuring its feasibility for real-time business environments.
Keywords: Cyber Threat Intelligence, Deep Neural Network, Real-Time Detection, SIEM, Wazuh
Paper 15 · Pages 94 – 104
Design of Hybrid renewable Energy & Storage System for Grid Connected Loads
Abstract
The following paper discusses one of the uses of artificial intelligence for the purpose of optimize the functioning of storing energy facilities with renewable energy sources, like solar and wind power. It begins by outlining the theoretical background of the renewable energy production process, technologies of energy storage with the emphasis on battery-based ones, and AI-based optimization strategies. This is followed by a study of how AI methods including machine learning and evolutionary algorithms may be applied to increase the competence, reliability, and economical feasibility of hybrid renewable energy systems. MATLAB is applied to simulate the practical situations of the solar photovoltaic panels, wind turbines, and battery storage systems. These simulations apply AI algorithms to optimise the way energy flows, how it is stored, and load balancing in dynamically changing environmental conditions. Case studies and simulated outcomes are provided that assess an efficacy and issues that come with the incorporation of AI. These results show that AI-based optimization helps to improve the concert of renewable Energy storage systems significantly and helps the transition to more ecologically friendly and low-carbon vitality infrastructure based on TFE.
Keywords: Cyber Threat Intelligence, Deep Neural Network, Real-Time Detection, SIEM, Wazuh, Network Security
Paper 16 · Pages 105 – 115
Analysis of Single Phase Induction motor controlling of an Electric Vehicle through a Reduced Switch Multilevel Inverters
Abstract
Multilevel inverters (MLIs) have gained an increasingly high profile in the area of power electronics because they are compact in their design and high efficiency, particularly in electric vehicles (EVs) and photovoltaic (PV) systems. This study introduces an innovative MLI architecture leveraging the switched capacitor (SC) methodology to generate higher voltage levels with fewer components. By cascading SC units, an inverter design remains streamlined, effectively reducing a need for multiple active switches and gate driver circuits. This results in the more cost-effective, compact, and reliable system. To ensure stable DC voltage from a solar input, the fuzzy logic controller (FLC) is implemented in conjunction with the Single Input Multi Output (SIMO) converter, which boosts an input voltage above a DC link level. A proposed inverter topology is evaluated against other reduced-switch MLI configurations acquired from metrics like total harmonic distortion (THD), efficiency, and component count. Simulations, conducted in MATLAB/Simulink, along with experimental testing under variable load conditions, validate a practicality and performance of a design for use in EVs and renewable energy technologies.
Keywords: EVs, SIMO, THD, MATLAB, FLC, Machine Learning
Paper 17 · Pages 116 – 121
Intelligent Multi-Model Deep Learning Approach for Accurate Leukaemia Diagnosis and Stage Classification
Abstract
Leukaemia, a malignant disorder of the blood and bone marrow, requires early and accurate detection to improve patient survival and treatment planning. Traditional manual examination of peripheral blood smears is labor-intensive, prone to errors, and subject to observer variability. This study proposes an automated framework for leukemia detection and stage prediction using multi model convolutional neural networks with transfer learning. Four pre-trained architectures—ResNet50, DenseNet121, MobileNetV2, and EfficientNetB3are fine-tuned on microscopic blood smear images to classify healthy and leukemic cells as well as predict disease stages. Each model is evaluated across standard performance metrics, with accuracy considered the primary benchmark for model selection. Experimental results reveal that among the tested architectures, this model achieving the highest accuracy emerges as the optimal choice for reliable leukaemia detection and stage prediction.
Keywords: Leukaemia Detection, Stage Prediction, Convolutional Neural Networks
Paper 18 · Pages 122 – 127
Smart IoT-Based Air Quality Monitoring and Analysis System Using ESP32 and Firebase
Abstract
The growing rates of air pollution are both highly hazardous to the human environment and health, and require effective and real-time monitoring solutions. This project is proposing a Smart IoT-based Air Quality Monitoring and Analysis System with ESP32 and Firebase. The suggested device combines several air quality sensors and ESP32 microcontroller to measure the parameters considered important in the environment (temperature, humidity, concentrations of harmful gases) continuously. The data obtained is sent wirelessly to Firebase cloud platform where real-time data can be stored, visualized and accessed remotely using web or mobile apps. The system has been built to offer quality, low-price and scalable monitoring to fit both urban and rural settings. With Firebase, users can monitor air quality patterns and get notifications when the pollution is above predetermined levels and securely store the data and synchronize it in real time. Moreover, the system aims to facilitate data analysis to identify patterns and possible sources of pollution, which can be used in informed decision-making and environmental consciousness. The proposed solution will improve accessibility and efficiency of environmental monitoring by integrating IoT technology with cloud computing. ESP32 is used, which means that the system has low power consumption and high connectivity reliability, which makes it feasible to be used in the continuous deployment. Altogether, the given project proves to be a good example of the efficient use of smart environmental monitoring, as it contributes to the improvement of the healthier lifestyle and helps to develop sustainable upcoming research works.
Keywords: IoT, Air Quality Monitoring, ESP32, Firebase, Smart System, Pollution Analysis
Paper 19 · Pages 128 – 135
A Review on Lung Cancer Identification and Prediction using Machine Learning
Abstract
Lung cancer is accountable for more deaths each year than all of the other leading cancers - breast, colon and prostate diseases – combined, and is the leading cause of cancer death worldwide. A major problem to manage this disease is that there are no detectable symptoms early on and most of the time the disease is diagnosed at later and more advanced stage when it can no longer be treated effectively. Traditional screening modalities (chest x-ray and sputum cytology) have shown poor success rates and although improvements in imaging/staging technology have occurred, five year survival rates are still not high. Machine learning (ML) and artificial intelligence (AI) algorithms are emerging as a potential solution to enhance the early detection, classification and prediction of lung cancer status. Several recent ML models such as deep learning, support vector machines and ensemble models for the identification and prediction of lung cancer are explored. We report their performance, data sets investigated, and shortcomings and discuss these findings in the context of future work directed towards clinically useful diagnostic systems.
Keywords: Lung Cancer, Machine Learning, AI, Ages, Human Beings