Search
102 articles for “ML”
-
Deep Reinforcement Learning-Based MPPT for PV Systems Under Partial Shading: A Hybrid Metaheuristic-Optimized Control Framework.
Abstract: Partial shade and quickly changing environmental conditions make Maximum Power Point Tracking (MPPT) in photovoltaic (PV) arrays particularly difficult. In these situations, traditional algorithms frequently fail to find the global optimum or experience sluggish convergence and steady-state oscillations. To obtain reliable, real-time MPPT under non-uniform irradiance, this research suggests a hybrid control architecture that combines a deep recurrent reinforcement learning (DRL) agent with metaheuristic-based parameter optimization and a digital-twin training …
Published in International Journal of Electrical Power System and Technology · Vol. 12, Issue 1, 2026 · pp. 35–46 Read article
-
Deep Reinforcement Learning-Based MPPT for PV Systems Under Partial Shading: A HybridMetaheuristic-Optimized Control Framework.
Abstract: Partial shade and quickly changing environmental conditions make Maximum Power Point Tracking (MPPT) in photovoltaic (PV) arrays particularly difficult. In these situations, traditional algorithms frequently fail to find the global optimum or experience sluggish convergence and steady-state oscillations. To obtain reliable, real-time MPPT under non-uniform irradiance, this research suggests a hybrid control architecture that combines a deep recurrent reinforcement learning (DRL) agent with metaheuristic-based parameter optimization and a digital-twin training …
Published in International Journal of Electrical Power System and Technology · Vol. 12, Issue 1, 2026 Read article
-
Optimizing Internal Combustion Engine Performance and Fleet Fuel Economy through Machine Learning and AI using Big Data Analytics
Abstract: Abstract This paper presents a software-defined operational intelligence approach for optimizing internal combustion engine performance and fleet fuel economy using Big Data Analytics combined with Machine Learning and Artificial Intelligence. Real-world vehicle data is transformed into engineered features and virtual sensing outputs to estimate fuel consumption, driver behaviour, and component health without additional hardware. The proposed system integrates fuel optimization, predictive maintenance, driver assistance, and sustainability assessment into a unified …
Published in International Journal of I.C. Engines and Gas Turbines · Vol. 12, Issue 1, 2026 · pp. 1–7 Read article
-
Hybrid Machine Learning and Deep Learning approach for Adaptive congestion control in 5G/6G Network
Abstract: The rapid growth of data traffic, fueled by emerging applications such as autonomous systems, augmented reality (AR), virtual reality (VR), and the Internet of Things (IoT), poses major challenges for modern communication networks. With the rollout of 5G and the continuous transition to 6G, sophisticated congestion control techniques are needed to satisfy the demanding requirements of massive machine-type communication (mMTC), ultra-reliable low-latency communication (URLLC), and improved mobile broadband (eMBB). Conventional …
Published in International Journal of Telecommunications & Emerging Technologies · Vol. 11, Issue 2, 2025 · pp. 1–8 Read article
-
Climate Change Modeling Using Machine Learning and Big Data
Abstract: Climate change is now one of the biggest issues that affect the world today and studying its impacts for it is very significant in enabling the formulation of social policies. This paper also discusses how climate sciences, machine learning, and big data analytics can greatly help in the improvement of the current capacities in climate modeling. Explaining the methods of climate modeling, we look at how the big data offers …
Published in International Journal of Software Computing and Testing · Vol. 11, Issue 1, 2025 · pp. 6–11 Read article
-
Deep Learning for Smarter Farming: Innovations in Plant Disease Identification
Abstract: Agriculture is the backbone of global food security, yet plant diseases significantly impact crop yields and farmers' livelihoods. Traditional disease detection methods are often time-consuming and require expert intervention, making them less feasible for large-scale farming. Recent advancements in deep learning have revolutionized plant disease identification by offering automated, accurate, and efficient solutions. This article explores innovative deep learning techniques, including convolutional neural networks (CNNs) and transformer-based models, that enhance …
Published in International Journal of Microwave Engineering and Technology · Vol. 11, Issue 1, 2025 · pp. 27–32 Read article
-
Decision Trees in Intrusion Detection: A Comparative Analysis of Machine Learning Techniques
Abstract: Recent malware sophistication poses immense challenges in intrusion detection systems, making it imperative to develop highly sophisticated methodologies for detection of fast-evolving cyber threats. Traditional IDS typically employs a signature-based detection approach and has limitations in identifying unknown and obfuscated attacks, particularly zero-day vulnerabilities. This paper discusses the existing limitations of IDS based on ML techniques to further improve the detection capability of such systems. Machine learning algorithms, particularly decision …
Published in International Journal of Telecommunications & Emerging Technologies · Vol. 11, Issue 1, 2025 Read article
-
Decision Trees in Intrusion Detection: A Comparative Analysis of Machine Learning Techniques
Abstract: Recent malware sophistication poses immense challenges in intrusion detection systems, making it imperative to develop highly sophisticated methodologies for detection of fast-evolving cyber threats. Traditional IDS typically employs a signature-based detection approach and has limitations in identifying unknown and obfuscated attacks, particularly zero-day vulnerabilities. This paper discusses the existing limitations of IDS based on ML techniques to further improve the detection capability of such systems. Machine learning algorithms, particularly decision …
Published in International Journal of Telecommunications & Emerging Technologies · Vol. 11, Issue 1, 2025 Read article
-
Sensitive Spectrophotometric and Flame Photometric Methods for Determination of Diclofenac Sodium in Pharmaceuticals
Abstract: Diclofenac sodium (DFS) is a non-steroidal anti-inflammatory drug (NSAID). Two new analytical methods have been developed for the assay of DFS in its pure form, tablets and injections. Spectrophotometric method is based on the oxidation of drug with known excess of cerium(IV) and oxidation of methyl orange (MO) by residual oxidant and measurement of absorbance of unreacted MO at 470 nm. Flame photometric method is based on the measurement of …
Published in International Journal of Analytical and Applied Chemistry · Vol. 2, Issue 2, 2016 · pp. 1–10 Read article
-
Recognition and Detection of Content in Video Using OpenCV
Abstract: The emergence and continued reliance on the Internet and related technologies has resulted in massive amounts of data that can be analysed. Humans, on the other hand, do not have the cognitive abilities to comprehend such vast amounts of data. Machine learning (ML) is a mechanism that enables humans to process large amounts of data, gain insights into the data's behaviour, and make more informed decisions based on the analysis's …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 7, Issue 2, 2021 · pp. 42–47 Read article
-
Crop Disease Classification and Detection Using Deep Learning Approach
Abstract: Early diagnosis of plant diseases is essential because they have an effect on the evolution of their unique species. For the identification and classification of plant diseases, a variety of Machine Learning (ML) models have been employed, but with the advent of Deep Learning (DL), a subset of ML, this area of research now seems to offer substantial potential for increased accuracy. The 4th most common staple food consumed worldwide …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 9, Issue 1, 2023 · pp. 22–27 Read article
-
Breast Tumor Classification Using Machine Learning Algorithm
Abstract: Breast cancer is characterized by genetic mutations, periodic pain, changes in the length, color (redness) and texture of the breast skin. The categories of most types of breast cancer led the pathologist to a systematic and objective prognostic analysis. In general, the most common category is binary (benign/malignant). Today, Learning Gadget (ML) strategies are widely used in breast cancer classification problems. Offers extreme accuracy and powerful diagnostic technology. It kills …
Published in International Journal of Microwave Engineering and Technology · Vol. 8, Issue 1, 2022 · pp. 35–40 Read article
-
Asymmetrical Source Configuration of Multilevel Inverter on Solar PV System- A Review
Abstract: Solar energy is the best clean alternative energy resource. During shading condition arrays can be treated as an asymmetrical DC source for multilevel inverter, based on insulation level, sets of PV panels are formed to act as DC source. During shading condition, based on insulation level sets of PV panels are allocated to multilevel inverter to as asymmetric source. With the growing research in multilevel inverter there are many topologies …
Published in International Journal of Power Electronics Controllers and Converters · Vol. 2, Issue 1, 2016 · pp. 1–6 Read article
-
Deep Learning Techniques for Optimizing Resource Allocation and Sustainability in the Next Generation of 6G Wireless Networks
Abstract: The upcoming sixth generation (6G) of wireless communication networks aims to meet challenging requirements such as ultra-reliable low-latency services, massive connectivity for billions of smart devices, and intelligent automation across highly diverse environments. Along with these goals, the issues of energy efficiency and environmental sustainability are becoming equally important, as the rising number of users and traffic volumes will directly increase power demand and carbon emissions. To lower total energy …
Published in International Journal of Broadband Cellular Communication · Vol. 11, Issue 2, 2026 Read article
-
Integrating Machine Learning with Edge Computing for Real Time Data Analytics
Abstract: Smart devices such as mobile phones, sensors, cameras, etc., are producing a huge amount of data every second. This data is normally sent to cloud servers for processing. This approach is normally slow and expensive, and it also raises a lot of privacy issues as data is sent over the internet, which takes a lot of time to return with results. This study aims to address the issue through the …
Published in International Journal of Distributed Computing and Technology · Vol. 12, Issue 2, 2026 Read article
-
Predicting Traffic Congestion in Mumbai Using Artificial Intelligence
Abstract: Abstract — Mumbai's ongoing traffic problems are brought on by the city's fast urbanization, population expansion, and growing reliance on private automobiles. The majority of traffic management technologies in use today are reactive, frequently reacting only after congestion has already arisen. Using information from a variety of sources, such as commuter surveys, weather reports, and traffic incident logs, this study explores the application of artificial intelligence (AI) and machine learning …
Published in International Journal of Transportation Engineering and Traffic System · Vol. 12, Issue 2, 2026 Read article
-
Evaluation of Kinetic Parameters of Crude Oil Remediation Using Bio-Stimuant of Mint Leaf (Mentha piperita)
Abstract: Kinetic parameters of crude oil degradation as related to total petroleum hydrocarbon (TPH) were evaluated. The experiment was set-up using crude oil, loamy soil polluted and addition of bio-stimulant (nutrient based substance). The depletion of the pollutant was monitored within the contact time of 7 to 35 days. At intervals of 7 days samples were collected and analyzed to determine the TPH concentration at each bioreactor set-up, through subjecting the …
Published in International Journal of Chemical Engineering and Processing · Vol. 12, Issue 1, 2026 · pp. 62–71 Read article
-
An Overview on Metal Processing using Machine Learning
Abstract: Metalworking, which is an important part of modern industry, includes a wide range of steps, such as shaping and casting the metal, machining it, and riveting it. The industry has always relied on trial and error and other empirical methods, but machine learning (ML) is now causing a big change. It is expected that this change will lead to higher production, better product quality, and better use of resources. The …
Published in International Journal of Manufacturing and Materials Processing · Vol. 12, Issue 1, 2026 · pp. 43–53 Read article
-
A Study on Machine-Learning-Driven Insight into theThermal Behavior of Polymers and Composite Materials
Abstract: The thermal performance of polymeric and composite systems underpins their suitability for aerospace, electronics, and energy‑storage applications, yet reliable prediction of temperature‑dependent properties remains a formidable challenge. In this work we present a data‑driven framework that harnesses modern machine‑learning (ML) techniques to forecast key thermal metrics – glass‑transition temperature (Tg), melting point (Tm), thermal conductivity (k), and decomposition onset (Td) – from a chemically informed descriptor space. A curated database …
Published in International Journal of Polymer Science and Engineering · Vol. 12, Issue 1, 2026 · pp. 1–11 Read article
-
Synthesis and Evaluation of Antifungal Properties of 2-((4-((6phenylimidazo[2,1-b][1,3,4]thiadiazole-2-yl)methoxy)phenoxy)methyl)-6-phenylimidazo[2,1-b][1,3,4] thiadiazole Derived from Hydroquinone
Abstract: Thiadiazole, a heterocyclic core, has garnered significant interest from chemists seeking novel therapeutic agents. The synthetic route for the target compounds is depicted in Scheme 1. The compounds were synthesized with favorable yields through the condensation of hydroquinone with various organic reagents. They underwent physical characterization and were analyzed using spectroscopic methods, including infrared (FTIR) and NMR (1H, 13C) spectroscopy. The FT-IR spectrum of the product exhibited a ν(C=N) absorption …
Published in International Journal of Environmental Chemistry · Vol. 12, Issue 1, 2026 · pp. 76–82 Read article