Search
504 articles for “model accuracy”
-
A Framework for Privacy-preserving AI Models in Cloud Computing: Challenges and Solutions
Abstract: The growing adoption of cloud computing for deploying artificial intelligence (AI) models has led to significant advancements in sectors such as healthcare, finance, and e-commerce. However, the integration of AI with cloud computing raises critical privacy concerns, particularly when handling sensitive data. This paper presents a comprehensive framework for implementing privacy-preserving AI models in cloud environments, addressing the unique challenges, and proposing effective solutions. The suggested framework employs advanced privacy-preserving …
Published in Journal of Operating Systems Development & Trends · Vol. 11, Issue 3, 2024 · pp. 1–12 Read article
-
A Reviewed Study On Cpu-Optimized Parameter-Efficient Fine- Tuning For Large Language Models To Increase Accuracy Using Lora
Abstract: The fast proliferation of Large Language Models (LLMs) has increased the need to optimize the process of fine-tuning but the existing workflows that require a GPU are still expensive, intensive, and unavailable to most researchers. This paper is driven by the desire to have a more cost-efficient and democratized version by examining a CPU-efficient implementation of Parameter-Efficient Fine-Tuning (PEFT) based on Low-Rank Adaptation (LoRA). The major purpose of the study …
Published in Recent Trends in Parallel Computing · Vol. 13, Issue 1, 2026 Read article
-
Modeling Dispersed Count Data: Evaluating the Conway–Maxwell–Poisson Regression with COVID-19 Mortality Data
Abstract: Count data are prevalent in diverse fields such as biology, healthcare, psychology, and marketing, characterized by non-negativity and inherent heteroskedasticity, often exhibiting overdispersion or underdispersion. Traditional Poisson regression, which assumes equal mean and variance, is inadequate for such dispersed data. To address this, various generalized linear models (GLMs) and their extensions, including negative binomial (NB) and Conway–Maxwell–Poisson (CMP) regressions, are utilized. This study evaluates the performance of CMP regression compared …
Published in Research & Reviews : Journal of Statistics · Vol. 13, Issue 3, 2024 · pp. 18–26 Read article
-
Performance-Based Wind Response Analysis of Tall RCC Iregular Structures Using Autodesk Revit and Robot Structural Analysis
Abstract: The increasing trend of vertical construction has made wind effects a critical consideration in the design of tall reinforced concrete (RCC) buildings. The response of such structures is largely governed by their geometric configuration, stiffness characteristics, and modelling accuracy under wind loading conditions Wind loads are evaluated based on standard provisions such as IS 875 (Part 3): 2015, which provide essential guidelines for structural safety This study focuses on evaluating …
Published in Journal of Structural Engineering and Management · Vol. 13, Issue 3, 2026 Read article
-
Enhancing Dimensional Accuracy of Affordable 3D-Printed Objects Via Solid Model Tuning For Industrial Manufacturing
Abstract: In the industrial applications of 3D printing (3DP) technologies, achieving precise dimensional accuracy and precision as well as improving surface quality are essential goals. With a focus on cost-effective engineering applications, this experimental research examines how solid model geometry tuning improves the internal and exterior dimensional accuracy of inexpensive 3DP technologies. Dimensional errors in the X, Y, and Z directions were meticulously measured on 3D parts made using Material Extrusion/Fused …
Published in Journal of Polymer & Composites · Vol. 13, Issue 3, 2025 · pp. 201–210 Read article
-
Harnessing Machine Learning for Stock Movement Prediction: A Review of Current Approaches
Abstract: Stock price prediction is a crucial task in financial analysis, aiding investors and traders in making informed decisions. This study investigates the use of deep learning methods, particularly Long Short-Term Memory (LSTM) networks, for predicting stock prices based on historical market data. The dataset, sourced from Yahoo Finance, consists of time-series stock price data, which is preprocessed, feature-engineered, and visualized to improve prediction accuracy. The model's performance is assessed using …
Published in Journal of Advances in Shell Programming · Vol. 12, Issue 2, 2025 · pp. 29–40 Read article
-
Comparison and Analysis of Facial Emotion Detection Using Various Deep Learning Neural Networks
Abstract: Facial emotion recognition employs Convolutional Neural Networks (CNNs), Residual Networks (ResNet), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNNs) to automatically identify various emotions, including disgust, anger, fear, happiness, sadness, surprise, and neutrality. This study utilizes transfer learning along with data preprocessing techniques such as rotation, flipping, brightness adjustment, and enhancement methods. Traditional machine learning models achieve an accuracy range of 45 to 50%. In contrast, our proposed …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 2, 2025 · pp. 37–42 Read article
-
An Analysis of Multimodal Fusion in Deepfake Detection for Video Samples
Abstract: In today’s rapidly evolving digital landscape, deepfake technology stands as both a marvel and a threat to privacy and security. Deepfakes, hyper-realistic synthetic media created using artificial intelligence (AI), can deceive and manipulate on an unprecedented scale, from political propaganda to compromising videos of public figures. This research navigates deepfake detection, focusing on two advanced methodologies: the vision transformers (ViT) image classifier and the Meso4 method. The ViT model utilizes …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 11, Issue 3, 2024 · pp. 19–27 Read article
-
A Comparative Analysis of Machine Learning Techniques for Fruit Defect Detection Systems
Abstract: With evolving technologies in machine learning, significant advancements have been made in the livestock industry, helping to reduce waste, increase yield, achieve cost savings, and improve competitiveness in the marketplace. Fruit defect detection models support precision agriculture by providing valuable data for decision-making and enhancing overall efficiency through automated inspection processes. This study implements and comparatively evaluates machine learning models including MobileNetV2, a custom-designed convolutional neural network (CNN) model, ResNet50, …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 11, Issue 3, 2024 · pp. 37–47 Read article
-
Parametric optimization and validation of novel 3D scanning approach for sustainable manufacturing of patient-specific orthodontic retainers
Abstract: The purpose of the proposed study is to identify the ideal procedure parameters for 3D scanning a denture in order to produce customised orthodontic retainers that can be produced sustainably. However, pilot investigations rarely explore parameters like scanning angle, light intensity, or scanning distance. In order to lower acquisition error, the suggested study examines a method for forecasting the ideal values of the previously indicated scanning parameters. Based on the …
Published in Journal of Polymer & Composites · Vol. 12, Issue 2, 2024 · pp. 265–278 Read article
-
Deep Learning-Based Pneumonia Diagnosis: A Comparative Review of Models and Metrics
Abstract: Pneumonia is a common viral infection that affects a large percentage of people worldwide. It is more common in developing and impoverished areas because of factors like poor sanitation, crowded living quarters, pollution in the environment, and restricted access to medical facilities. In order to improve survival chances and gain access to therapeutic therapies, pneumonia must be diagnosed as soon as possible. A type of artificial intelligence called deep learning …
Published in Research and Reviews : A Journal of Medical Science and Technology · Vol. 13, Issue 3, 2024 Read article
-
Fault Detection in Solar PV Systems Integrated with the Power Grid: Evaluating Logistic Regression through Confusion Matrix Analysis
Abstract: This paper proposes a method for failure detection in grid-integrated solar photovoltaic (PV) systems using logistic regression and real-time sensor data. The approach effectively classifies and identifies seven distinct fault types. The developed model demonstrates a high fault identification accuracy, ranging from 93% to 96.5% across various fault types and operational conditions. By leveraging logistic regression, the system utilizes key independent variables that significantly influence the classification process. Additionally, the …
Published in Journal of Power Electronics and Power Systems · Vol. 15, Issue 2, 2025 · pp. 45–52 Read article
-
Comparative Analysis of Kinetic Models for Simulation of Biogas Production from Cow Dung and Fruit Waste via Anaerobic Digestion
Abstract: This study investigates the optimization of biogas and biofertilizer production from cow dung and fruit waste through anaerobic digestion, utilizing various microbial growth kinetic models. Simulations were conducted using the Monod, Moser, Contois, and Tessier models to predict biogas yield and assess model accuracy. Results indicated that the Tessier model provided the closest fit to experimental data, with a biogas yield of 0.45 m³/kg VS, while the Monod model overestimated …
Published in International Journal of Membranes · Vol. 2, Issue 1, 2025 · pp. 47–63 Read article
-
Accelerating Unsupervised Feature Learning: Parallelized Training of Denoising Autoencoders
Abstract: Unsupervised representation learning has become a cornerstone of contemporary machine learning, enabling algorithms to extract informative features from un-labelled, high-dimensional data. This work investigates the efficacy of stacked denoising autoencoders (SDAEs) trained via parallelized stochastic gradient descent (SGD) as a scalable approach to feature extraction. By strategically leveraging multi-threaded computation, our study systematically examines the trade-offs between increased parallelism, training efficiency, and the preservation of model accuracy. Experiments on the …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 3, 2025 · pp. 56–64 Read article
-
Revolutionizing Plant Disease Detection: A Comprehensive Review
Abstract: Rise in population demands more food production but the diseases in plants contribute to loss. The advancement in agricultural field has a remarkable effect in detecting plant diseases. These diseases will have a major impact on the quality of plant and yield and hence can destroy the entire plant if they are not controlled on time. To reduce disease-related losses, it is necessary to identify different types of diseases and …
Published in International Journal of Advance in Molecular Engineering · Vol. 1, Issue 2, 2023 · pp. 44–55 Read article
-
Generative AI for VR: Creating Physically Realistic Models
Abstract: Virtual Reality has revolutionized the traditional learning system by creating and interactive and engaging environment. However, its ability to show precise real-world experiences is limited due to lack of physical realism. This study investigates the potential of Generative Adversarial Network (GAN) in creating physically realistic 3D models. Proposed system incorporates deep learning techniques along with physics-based constraints to enhance model’s accuracy and usability. To achieve this, experiments were conducted on …
Published in Journal of Advancements in Robotics · Vol. 12, Issue 3, 2025 · pp. 14–22 Read article
-
Atmospheric Modeling: A Comprehensive Review of Numerical Approaches and Applications
Abstract: Atmospheric modeling plays a crucial role in understanding and predicting atmospheric processes, weather patterns, and climate variability. This review synthesizes current methodologies and applications across several types of atmospheric models, including numerical weather prediction (NWP), climate models, air quality models, and chemical transport models. We explore the intricacies of data assimilation, model evaluation, parameterization, and the importance of high-performance computing in advancing model accuracy and efficiency. Special emphasis is placed …
Published in International Journal of Atmosphere · Vol. 1, Issue 2, 2024 · pp. 16–21 Read article
-
Hybrid Techniques in Mango Leaf Disease Identification: Evaluating Neural Networks and Support Vector Machines
Abstract: Mango leaf diseases pose a significant threat to mango production, impacting both yield and fruit quality. Early and accurate detection of these diseases is crucial for effective management. This paper evaluates the use of hybrid techniques, specifically the integration of neural networks (NNs) and support vector machines (SVM), in the identification and classification of mango leaf diseases. NN excel in extracting complex features from images, while SVMs are robust classifiers, …
Published in Trends in Opto-electro & Optical Communication · Vol. 14, Issue 3, 2024 · pp. 19–27 Read article
-
Data-driven Approaches to Mineral Resource Management Using AI: A Brief Review
Abstract: The role of Artificial Intelligence (AI) in the mineral resource sector has become increasingly significant over the past few years, as industries seek to optimize and modernize their operations. AI encompasses a variety of technologies and techniques, such as machine learning, deep learning, and expert systems, that are now widely used in mineral exploration, resource estimation, and mine management. These AI-driven approaches have brought about a transformative shift, enhancing efficiency, …
Published in International Journal of Minerals · Vol. 2, Issue 1, 2025 · pp. 25–29 Read article
-
Algorithm for the prediction of cardiovascular disease (CVD)
Abstract: cardiovascular diseases (CVD) still claim a significant number of deaths globally and remain the number one killer with an annual death toll of nearly 17.9 million. While several medical advancements have been made, an early diagnosis is still hard to obtain, which often leads to worsening conditions and intricate treatment options. With the advancement of modern technology, Machine learning has demonstrated to be a miraculous tool which can greatly impact …
Published in Research and Reviews : A Journal of Immunology · Vol. 15, Issue 2, 2025 Read article