Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,456 Article Results

Leveraging image fusion and transfer learning for enhanced tumor diagnosis

10.11591/ijeecs.v37.i3.pp1804-1814
Nirmalajyothi Narisetty , Kunda Suresh Babu , Sneha Banala , Akash Reddy Kandi , Sreeja Nukarapu , Jagruthi Mekala
In India, the number of brain tumor cases are increasing rapidly. Compared to the current treatment approaches there is a need for efficient and advanced diagnostic approaches. Doctor primarily use magnetic resonance imaging (MRI) and computed tomography (CT) scans for diagnosis, each with its own set of advantages and limitations. Accurate diagnosis of brain tumors requires detailed information about the tumor’s type, size, location, and proliferation rate. But all this information must be estimated accurately and precisely. Even though MRI and CT provide anatomical information regarding tumors, they may not always correctly classify the tumor hence, often requiring the additional biopsy for more detailed analysis. This paper aims to demonstrate the fusion of MRI and CT scans by generating a fused image using transfer learning with convolution neural networks (CNN) that possesses all the important information from both modalities yields better results than using MRI and CT scans alone. This fused scan has the potential to highlight subtle details that may be overlooked on individual scans. This proposed system retains all the best possible functionalities for medical approaches to brain tumor detection. It paves the way to offer a much more impactful healthcare approach to patients by delivering accurate and reliable statistics, enhancing the diagnostic accuracy (96.43%) precedent to any single modality.
Volume: 37
Issue: 3
Page: 1804-1814
Publish at: 2025-03-01

Synergistic ensemble classification framework: utilizing a soft voting algorithm for enhanced prediction and diagnosis of diabetes mellitus

10.11591/ijeecs.v37.i3.pp1945-1953
Bhanu Prakash Lohani , Arvind Dagur , Dhirendra Kumar Shukla
Diabetes, a serious condition characterized by elevated blood glucose levels, can be effectively identified, and predicted early using machine learning (ML) algorithms. The research provides a comprehensive assessment of three ensemble ML models-stacking, soft voting, and hard voting-focused on enhancing diabetes diagnosis among Pima Indian women dataset taken from the National Institute of Diabetes and Digestive and Kidney Diseases, this study focuses on Pima Indian women aged 21 and older, with the dataset comprising critical diagnostic measurements. Two ensemble models were developed and evaluated on various evaluation parameters. The stacking model combines predictions from various classifiers using a meta-classifier, leveraging their strengths for final decision-making. In contrast, the voting model aggregates probability estimates from each classifier, providing nuanced predictions. Both models were rigorously evaluated on a validation dataset, emphasizing accuracy, specificity, sensitivity, and the receiver operating characteristic (ROC) area under the curve (AUC). Notably, the voting-based ensemble methods demonstrated superior performance in predicting diabetes for this cohort. However, their effectiveness heavily relies on preprocessing, base model selection, and hyperparameter optimization. This study underscores the potential of ensemble models in medical diagnostics, highlighting the critical role of data preprocessing, and configuration in enhancing predictive accuracy.
Volume: 37
Issue: 3
Page: 1945-1953
Publish at: 2025-03-01

Forecasting virtual machine resource utilization in cloud computing: a hybrid artificial intelligence approach

10.11591/ijeecs.v37.i3.pp1887-1898
Rim Doukha , Abderrahmane Ez-Zahout , Aristide Ndayikengurukiye
Cloud computing has transformed the management of IT infrastructures by providing scalable, flexible, and cost-effective solutions. However, efficient resource management in cloud environments remains a significant challenge, as over-provisioning or under-provisioning of resources can lead to unnecessary costs or degraded performance. Accurate forecasting of virtual machine (VM) resource utilization is crucial for optimizing resource allocation, reducing operational expenses, and ensuring compliance with service level agreements (SLAs). This study aims to address these challenges by developing a hybrid forecasting model that combines the strengths of auto regressive integrated moving average (ARIMA), linear regression (LR), and long short-term memory (LSTM) techniques. By integrating these methods, our model provides more accurate predictions and better adaptability to various workload patterns, helping cloud service providers and users to make informed decisions about resource allocation, ultimately reducing costs. The data was collected from multiple EC2 instances and processed using amazon web services (AWS) Glue with Spark. The experimental results demonstrate that the hybrid model outperforms individual models such as ARIMA, LR, and LSTM in terms of accuracy for forecasting memory, CPU, and disk utilization, offering a more effective solution for managing cloud resources efficiently.
Volume: 37
Issue: 3
Page: 1887-1898
Publish at: 2025-03-01

Empower BreastNet: breast cancer detection with transfer learning VGG Net-19

10.11591/ijeecs.v37.i3.pp1927-1935
Vaishali M. Joshi , Prajkta P. Dandavate , Rashmi Ramamurthy , Riddhi Mirajkar , Neeta N. Thune , Gitanjali R. Shinde
Breast cancer is a major cause of death among women globally, making early detection crucial for effective treatment. This study introduces a new deep learning (DL) method using transfer learning (TL) to automatically detect and diagnose breast cancer. TL improves performance on new tasks by using knowledge from previous tasks. In this study, we use pre-trained convolutional neural networks (CNNs) like AlexNet, ResNet50, visual geometry group (VGG)-16, and VGG-19 to extract features from the breast cancer wisconsin (BCW) diagnostic dataset. We measure the model's success with accuracy, sensitivity, specificity, precision, and F-score. The results show that the VGG-19 model, when applied with TL, performs best for diagnosing breast cancer, achieving an overall accuracy of 98.75%, sensitivity of 97.38%, specificity of 98.35%, precision of 97.35%, and an F-score of 97.66%.
Volume: 37
Issue: 3
Page: 1927-1935
Publish at: 2025-03-01

Development of newton dynamometer instrumentation integrated with smart counter applications based on Hooke's law

10.11591/ijeecs.v37.i3.pp1506-1514
Yulkifli Yulkifli , Alwi Nofriandi , Washilla Audia , Asrizal Asrizal , Yenni Darvina , Afdhal Muttaqin , Rosly Jaafar
This research presents the development of an instrumentation system that employs ultrasonic sensors for Newton dynamometer applications. A key parameter measured is the change in spring length before and after loading. The methodology implemented in this study is based on Hooke's Law, applied within the instrumentation devices. The length change data is transmitted to a smartphone via a Bluetooth module integrated into the instrument. This allows for flexible data usage and input through a calculator-based application created with MIT App Inventor, tailored to the relevant supporting parameters. Before implementation, the sensors underwent characterization to assess the linearity of their output compared to a standard measuring tool, specifically a ruler. The linearity test yielded a coefficient of 0.9998, indicating excellent performance for this application. Additionally, the system achieved an average accuracy of 94.12% and an average precision of 99.94%.
Volume: 37
Issue: 3
Page: 1506-1514
Publish at: 2025-03-01

A novel dataset and part-of-speech tagging approach for enhancing sentiment analysis in Kannada

10.11591/ijeecs.v37.i3.pp1661-1671
Sunil Mugalihalli Eshwarappa , Vinay Shivasubramanyan
The problem addressed in this research is the limited availability of labelled datasets and effective sentiment analysis tools for the Kannada language. Existing challenges include linguistic variations, cultural diversities, and the absence of comprehensive datasets designed specifically for sentiment analysis in Kannada. This research aims to enhance sentiment analysis capabilities for the Kannada language, addressing challenges posed by linguistic variations and limited labelled datasets. A novel Kannada dataset derived from SemEval 2014 task 4 was created using a conversion process. The dataset was processed using part-of-speech tagging, and a specialized model called K-BERT (Kannada bidirectional encoder representations from transformers) was introduced and implemented using Python within the Anaconda environment. Performance evaluation results showcased K-BERT's superiority over traditional machine learning (ML) algorithms and the BERT model, achieving an accuracy of 0.98, precision of 0.97, recall of 0.97, and F-score of 0.98 in sentiment classification for Kannada text data. This work contributes a unique Kannada dataset, introduces the K-BERT model specifically designed for Kannada sentiment analysis, and emphasizes the importance of collaborative efforts in advancing natural language processing (NLP) research for multilingual environments.
Volume: 37
Issue: 3
Page: 1661-1671
Publish at: 2025-03-01

Leveraging 3D convolutional networks for effective video feature extraction in video summarization

10.11591/ijeecs.v37.i3.pp1616-1625
Bhakti Deepak Kadam , Ashwini Mangesh Deshpande
Video feature extraction is pivotal in video processing, as it encompasses the extraction of pertinent information from video data. This process enables a more streamlined representation, analysis, and comprehension of video content. Given its advantages, feature extraction has become a crucial step in numerous video understanding tasks. This study investigates the generation of video representations utilizing three-dimensional (3D) convolutional neural networks (CNNs) for the task of video summarization. The feature vectors are extracted from the video sequences using pretrained two-dimensional (2D) networks such as GoogleNet and ResNet, along with 3D networks like 3D Convolutional Network (C3D) and Two-Stream Inflated 3D Convolutional Network (I3D). To assess the effectiveness of video representations, F1-scores are computed with the generated 2D and 3D video representations for chosen generic and query-focused video summarization techniques. The experimental results show that using feature vectors from 3D networks improves F1-scores, highlighting the effectiveness of 3D networks in video representation. It is demonstrated that 3D networks, unlike 2D ones, incorporate the time dimension to capture spatiotemporal features, providing better temporal processing and offering comprehensive video representation.
Volume: 37
Issue: 3
Page: 1616-1625
Publish at: 2025-03-01

Tomato leaf disease detection using Taguchi-based Pareto optimized lightweight CNN

10.11591/ijeecs.v37.i3.pp1772-1784
Bappaditya Das , C. S. Raghuvanshi
The prospect of food security becoming a global danger by 2050 due to the exponential growth of the world population. An increase in production is indispensable to satisfy the escalating demand for food. Considering the scarcity of arable land, safeguarding crops against disease is the best alternative to maximize agricultural output. The conventional method of visually detecting agricultural diseases by skilled farmers is time-consuming and vulnerable to inaccuracies. Technology-driven agriculture is an integral strategy for effectively addressing this matter. However, orthodox lightweight convolutional neural network (CNN) models for early crop disease detection require fine-tuning to enhance the precision and robustness of the models. Discovering the optimal combination of several hyperparameters might be an exhaustive process. Most researchers use trial and error to set hyperparameters in deep learning (DL) networks. This study introduces a new systematic approach for developing a less sensitive CNN for crop leaf disease detection by hyperparameter tuning in DL networks. Hyperparameter tuning using a Taguchi-based orthogonal array (OA) emphasizes the S/N ratio as a performance metric primarily dependent on the model’s accuracy. The multi-objective Pareto optimization technique accomplished the selection of a robust model. The experimental results demonstrated that the suggested approach achieved a high level of accuracy of 99.846% for tomato leaf disease detection. This approach can generate a set of optimal CNN models’ configurations to classify leaf disease with limited resources accurately.
Volume: 37
Issue: 3
Page: 1772-1784
Publish at: 2025-03-01

A hybrid approach for hotspot problem using load balancing and advanced ant colony algorithm

10.11591/ijeecs.v37.i3.pp1865-1873
Padmini Mysuru Srikantha , Sampath Kuzhalvaimozhi , Susheela Shimoga Balasubramanya , Sklita Buthello , Sadana Hulugundi Jagadish , Spandana Mallegowdanakoppalu Thammanna
Wireless sensor networks (WSNs) are crucial in various applications such as environmental surveillance, military operations, transportation monitoring, and healthcare. However, due to a finite set of sensor nodes' resources concerning energy, memory, disk, and CPU processing, nodes in WSNs often face hotspot issues. The sensor nodes that are located near the base station, are responsible for relaying data not only from themselves but also from neighboring nodes. This leads to hotspot issues, where nodes near the base station experience higher traffic loads and faster energy depletion. This paper mainly focuses on mitigating hotspot issues in heterogeneous WSNs using unequal clustering, load balancing, and an advanced ant colony algorithm. This approach involves devising strategies for selecting cluster heads, determining clusters optimal number and formation, and optimizing data transmission processes. Central to the methodology is utilizing load balancing mechanisms and an advanced ant colony algorithm to distribute the workload among sensor nodes more evenly and find the optimum routing path. The proposed algorithm shows promise in alleviating traffic congestion and energy depletion and provides an innovative approach to enhance network performance and prolong the lifespan of sensor nodes.
Volume: 37
Issue: 3
Page: 1865-1873
Publish at: 2025-03-01

Quantitation of new arbitrary view dynamic human action recognition framework

10.11591/ijeecs.v37.i3.pp1797-1803
Anh-Dung Ho , Huong-Giang Doan
Dynamic action recognition has attracted many researchers due to its applications. Nevertheless, it is still a challenging problem because the diversity of camera setups in the training phases are not similar to the testing phases, and/or the arbitrary view actions are captured from multiple viewpoints of cameras. In fact, some recent dynamic gesture approaches focus on multiview action recognition, but they are not resolved in novel viewpoints. In this research, we propose a novel end-to-end framework for dynamic gesture recognition from an unknown viewpoint. It consists of three main components: (i) a synthetic video generation with generative adversarial network (GAN)-based architecture named ArVi-MoCoGAN model; (i) a feature extractor part which is evaluated and compared by various 3D CNN backbones; and (iii) a channel and spatial attention module. The ArVi-MoCoGAN generates the synthetic videos at multiple fixed viewpoints from a real dynamic gesture at an arbitrary viewpoint. These synthetic videos will be extracted in the next component by various three-dimensional (3D) convolutional neural network (CNN) models. These feature vectors are then processed in the final part to focus on the attention features of dynamic actions. Our proposed framework is compared to the SOTA approaches in accuracy that is extensively discussed and evaluated on four standard dynamic action datasets. The experimental results of our proposed method are higher than the recent solutions, from 0.01% to 9.59% for arbitrary view action recognition.
Volume: 37
Issue: 3
Page: 1797-1803
Publish at: 2025-03-01

Visual treatment with AR for children with dysphasia

10.11591/ijeecs.v37.i3.pp1702-1711
Misael Lazo Amado , Meyluz Monica Paico Campos
The language disorder known as dysphasia significantly affects the ability to communicate effectively, presenting challenges in both comprehension and expression of language. To address this issue, the development of a visual treatment using augmented reality (AR) specifically designed for children with dysphasia has been proposed. The methodology selected for this project is analysis, design, development, implementation, and evaluation (ADDIE), an innovative methodology that encompasses analysis, design, development, implementation and evaluation. This methodology is perfectly adapted to the needs of the project, allowing a systematic and complete approach at all stages of the process of creating the visual treatment. The results obtained show that the visual treatment with AR has been positively evaluated by development experts and dysphasia specialists. Its innovative capacity to assist children with this disorder in health and educational settings is highlighted. This approach provides an effective tool to improve the communication and language development of children affected by dysphasia, offering new opportunities for their learning and growth. Its implementation in healthcare and educational settings could have a significant impact on the quality of life and development of these children.
Volume: 37
Issue: 3
Page: 1702-1711
Publish at: 2025-03-01

Sustainable supply chain modeling: a review based on the application of the system dynamics approach

10.11591/ijeecs.v37.i3.pp1637-1649
Julia Kurniasih , Zuraida Abal Abas , Siti Azirah Asmai , Agung Budhi Wibowo
Sustainable supply chains, evolving with supply chain 5.0 revolution, are crucial for achieving sustainable development goals (SDGs) by balancing economic growth, environmental protection, and social responsibility. They help reduce environmental impacts, promote ethical labor practices, and ensure financial viability. Sustainable supply chains involve complex interactions and external influences. The system dynamics approach effectively captures these intricate interactions through feedback loops and non-linear relationships. This review seeks to identify issues in modeling sustainable supply chains using system dynamics and offer insights for developing sustainable, flexible, responsive, and resilient models. This paper reviews literature from 2020 to 2023 using thematic analysis. It examines dynamics, behaviors, management, sustainability strategies, decision-making, and future directions for sustainable supply chain modeling. The findings suggest that a comprehensive framework can enhance management practices, support policymaking, and promote sustainability. Integrated risk management is essential for resilient, adaptable supply chains, while financial viability and scalability are essential for the widespread adoption of sustainability practices. Understanding the roles of various actors and integrating supply chain components can improve support systems, and exploring green energy, technology adoption, and consumer behavior can advance sustainability goals. Future research should also better integrate sustainability aspects and explore a broader range of literature for deeper insights.
Volume: 37
Issue: 3
Page: 1637-1649
Publish at: 2025-03-01

Optimized dense convolutional network with conditional autoregressive value-at-risk for chronic kidney disease detection through group-based search

10.11591/ijeecs.v37.i3.pp2009-2020
Chetan Nimba Aher , Archana Rajesh Date , Shridevi S. Vasekar , Priyanka Tupe-Waghmare , Amrapali Shivajirao Chavan
Chronic kidney disease (CKD) is the gradual decrease in renal functionality that leads to kidney failure or damage. This disease is the most severe worldwide health condition that kills numerous people every year as an outcome of hereditary factors and worse lifestyles. As CKD progresses, it becomes difficult to diagnose. Utilizing regular doctor consultation data for evaluating diverse phases of CKD can assist in earlier detection and timely inference. Furthermore, effectual detection methods are vital owing to an increased count of patients with CKD. Here, group search conditional autoregressive value-at-risk based dense convolutional network (GSCAViaR-DenseNet) is introduced for CKD detection. Firstly, chronic data is acquired from the dataset and Min-Max normalization is utilized to pre-process considered chronic kidney data. Thereafter, feature selection (FS) is performed based on Topsoe similarity. Lastly, CKD detection is executed by dense convolutional network (DenseNet) and group search conditional autoregressive value-at-risk (GSCAViaR) is employed to train DenseNet. However, GSCAViaR is designed by incorporating a group search optimizer (GSO) with a conditional autoregressive value-at-risk (CAViaR) model. Additionally, GSCAViaR-DenseNet acquired a maximal accuracy of about 91.5%, sensitivity of about 92.8% and specificity of about 90.7%.
Volume: 37
Issue: 3
Page: 2009-2020
Publish at: 2025-03-01

Multifaceted approach for anticipating learner performance using parameter weightage and ensemble algorithm fusion

10.11591/ijeecs.v37.i3.pp2032-2043
Shabnam Ara S Jahagirdar , Tanuja Ramachandraiah
Anticipating student performance has garnered significant attention in education research for offering early insights that enable timely interventions and personalized support, ultimately improving student success and retention rates. This research focuses on enhancing the accuracy and efficiency of student performance prediction models by employing a hybrid ensemble framework that integrates weighted feature selection with meta-learner-based approaches. A weighted feature selection method was employed to prioritize the most influential of the 23 parameters in the dataset, enhancing prediction accuracy while reducing the computational burden. These parameters were then used to build a hybrid ensemble model by combining base learners with meta-learners, systematically tuned using hyperparameter optimization. This approach aimed to further improve prediction accuracy by fusing multiple base learners, leveraging the strengths of different algorithms for more accurate predictions. The proposed hybrid model was validated across different features selected based on feature importance using random forest (RF). An accuracy of 98.38% was achieved when all 23 features were considered and an accuracy of 97.13 % was achieved when the top 10 features were used. The research highlights the significance of early prediction for prompt intervention and demonstrates how feature weighting can boost model efficacy.
Volume: 37
Issue: 3
Page: 2032-2043
Publish at: 2025-03-01

Analysis of cryptographic methods for ensuring security in the field of internet of things

10.11591/ijeecs.v37.i3.pp1596-1606
Temirbekova Zhanerke Erlanovna , Abdiakhmetova Zukhra Muratovna , Tynymbayev Sakhybay
The number of internet of things (IoT) devices continues to grow, and so do the associated concerns regarding their security and privacy. Evaluating the efficacy of cryptographic solutions within IoT systems emerges as a crucial endeavor to uphold the integrity and reliability of these systems. Amidst the rapid evolution of IoT technology, safeguarding the confidentiality, integrity, and availability of data emerges as a top priority. This article underscores the significance of deploying robust cryptographic algorithms to fortify IoT devices against a myriad of potential threats. Effective evaluation of cryptographic solutions within IoT systems entails a comprehensive analysis and comparison of diverse algorithms, coupled with an assessment of their performance, resilience against attacks, and resource utilization. Central to evaluating the effectiveness of cryptographic solutions within IoT systems is a consideration of various factors including computational complexity, power consumption of devices, ease of implementation, and compatibility with existing infrastructures. This article reviews a number of cryptographic solutions including Rivest–Shamir–Adleman (RSA), El-Gamal, Paillier. These algorithms are implemented on the ATmega2560 microcontroller, which allows for a comprehensive assessment of key parameters such as efficiency in terms of encryption and decryption time, power consumption, and memory usage of IoT devices.
Volume: 37
Issue: 3
Page: 1596-1606
Publish at: 2025-03-01
1 2 3
...
2097 2098
Show 343 of 2098

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration