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

29,939 Article Results

Optimizing EfficientNet for imbalanced medical image classification using grey wolf optimization

10.11591/csit.v6i2.p112-121
Khusnul Khotimah , Sugiyarto Surono , Aris Thobirin
The advancement of deep learning in computer vision has result in substantial progress, particularly in image classification tasks. However, challenges arise when the model is applied to small and unbalanced datasets, such as X-ray data in medical applications. This study aims to improve the classification performance of fracture X-ray images using the EfficientNet architecture optimized with grey wolf optimization (GWO). EfficientNet was chosen for its efficiency in handling small datasets, while GWO was applied to optimize hyperparameters, including learning rate, weight decay, and dropout to improve model accuracy. Random cropping, rotation, flipping, color jittering, and random erasing, were used to expand the diversity of the dataset, and class weighting is applied to overcome class imbalance. The evaluation uses accuracy, precision, recall, and F1-score metrics. The combination of EfficientNetB0 and GWO resulted in an average 4.5% improvement in model performance over baseline methods. This approach provides benefits in developing deep learning methods for medical image classification, especially in dealing with small and imbalanced datasets.
Volume: 6
Issue: 2
Page: 112-121
Publish at: 2025-07-01

Blockchain technology for optimizing security and privacy in distributed systems

10.11591/csit.v6i2.p210-220
Wisnu Uriawan , Adrian Putra Pratama , Shafwan Mursyid
Blockchain technology is increasingly recognized as an effective solution for addressing security and privacy challenges in distributed systems. Blockchain ensures information security by validating data and defending against cyber threats, while guaranteeing data integrity through transaction validation and reliable storage. The research involves a literature study, problem identification, analysis of blockchain security and privacy, model development, testing, and analysis of trial results. Furthermore, blockchain enables user anonymity and fosters transparency by utilizing a distributed network, reducing the risk of fraudulent activities. Its decentralized nature ensures high reliability and accessibility, even in node failures. Blockchain enhances security and privacy by offering features like data immutability, provenance, and reduced reliance on trust. It decentralizes data storage, making tampering or deletion extremely challenging, and ensures the invalidation of subsequent blocks upon any changes. Blockchain finds applications in various domains, including supply chains, finance, healthcare, and government, enabling enhanced security by tracking data origin and ownership. Despite scalability and security challenges, the potential benefits of reduced costs, increased efficiency, and improved transparency position blockchain as a promising technology for the future. In summary, blockchain technology provides secure transaction recording and data storage, thus enhancing security, privacy, and the integrity of sensitive information in distributed systems.
Volume: 6
Issue: 2
Page: 210-220
Publish at: 2025-07-01

Optimizing social media analytics with the data quality enhancement and analytics framework for superior data quality

10.11591/ijres.v14.i2.pp472-480
B. Karthick , T. Meyyappan
his paper introduces the data quality enhancement and analytics (DQEA) framework to enhance data quality in social media analytics through machine learning (ML) algorithms. The efficacy of the framework is validated through features tested against human coders on Amazon Mechanical Turk, achieving an inter-coder reliability score of 0.85, indicating high agreement. Furthermore, two case studies with a large social media dataset from Tumblr were conducted to demonstrate the effectiveness of the proposed content features. In the first case study, the DQEA framework reduced data noise by 30% and bias by 25%, while increasing completeness by 20%. In the second case study, the framework improved data consistency by 35% and overall data quality score by 28%. Comparative analysis with state-of-the-art models, including random forest and support vector machines (SVM), showed significant improvements in data reliability and decision-making accuracy. Specifically, the DQEA framework outperformed the random forest model by 15% in accuracy and 20% in true positive rate, and the SVM model by 10% in error rate reduction and 18% in reliability. The results underscore the potential of advanced data analytics tools in transforming social media data into a valuable asset for organizations, highlighting the practical implications and future research directions in this domain.
Volume: 14
Issue: 2
Page: 472-480
Publish at: 2025-07-01

HepatoScan: Ensemble classification learning models for liver cancer disease detection

10.11591/csit.v6i2.p167-175
Tella Sumallika , Raavi Satya Prasad
Liver cancer is a dangerous disease that poses significant risks to human health. The complexity of early detection of liver cancer increases due to the unpredictable growth of cancer cells. This paper introduces HepatoScan, an ensemble classification to detect and diagnose liver cancer tumors from liver cancer datasets. The proposed HepatoScan is the integrated approach that classifies the three types of liver cancers: hepatocellular carcinoma, cholangiocarcinoma, and angiosarcoma. In the initial stage, liver cancer starts in the liver, while the second stage spreads from the liver to other parts of the body. Deep learning is an emerging domain that develops advanced learning models to detect and diagnose liver cancers in the early stages. We train the pre-trained model InceptionV3 on liver cancer datasets to identify advanced patterns associated with cancer tumors or cells. For accurate segmentation and classification of liver lesions in computed tomography (CT) scans, the ensemble multi-class classification (EMCC) combines U-Net and mask region-based convolutional network (R-CNN). In this context, researchers use the CT scan images from Kaggle to analyze the liver cancer tumors for experimental analysis. Finally, quantitative results show that the proposed approach obtained an improved disease detection rate with mean squared error (MSE)-11.34 and peak signal-to-noise ratio (PSNR)-10.34, which is high compared with existing models such as fuzzy C-means (FCM) and kernel fuzzy C-means (KFCM). The classification results obtained based on detection rate with accuracy-0.97%, specificity-0.99%, recall-0.99%, and F1S-0.97% are very high compared with other existing models.
Volume: 6
Issue: 2
Page: 167-175
Publish at: 2025-07-01

Bibliometric analysis and short survey in CT scan image segmentation: identifying ischemic stroke lesion areas

10.11591/csit.v6i2.p91-101
Wahabou K. Taba Chabi , Sèmèvo Arnaud R. M. Ahouandjinou , Manhougbé Probus A. F. Kiki , Adoté François-Xavier Ametepe
Ischemic stroke remains one of the leading causes of mortality and long-term disability worldwide. Accurate segmentation of brain lesions plays a crucial role in ensuring reliable diagnosis and effective treatment planning, both of which are essential for improving clinical outcomes. This paper presents a bibliometric analysis and a concise review of medical image segmentation techniques applied to ischemic stroke lesions, with a focus on tomographic imaging data. A total of 2,014 publications from the Scopus database (2013–2023) were analyzed. Sixty key studies were selected for in-depth examination: 59.9% were journal articles, 29.9% were conference proceedings, and 4.7% were conference reviews. The year 2023 marked the highest volume of publications, representing 17% of the total. The most active countries in this area of research are China, the United States, and India. "Image segmentation" emerged as the most frequently used keyword. The top-performing studies predominantly used pre-trained deep learning models such as U-Net, ResNet, and various convolutional neural networks (CNNs), achieving high accuracy. Overall, the findings show that image segmentation has been widely adopted in stroke research for early detection of clinical signs and post-stroke evaluation, delivering promising outcomes. This study provides an up-to-date synthesis of impactful research, highlighting global trends and recent advancements in ischemic stroke medical image segmentation.
Volume: 6
Issue: 2
Page: 91-101
Publish at: 2025-07-01

Effects of hyperparameter tuning on random forest regressor in the beef quality prediction model

10.11591/csit.v6i2.p159-166
Ridwan Raafi'udin , Yohanes Aris Purwanto , Imas Sukaesih Sitanggang , Dewi Apri Astuti
Prediction models for beef meat quality are necessary because production and consumption were significant and increasing yearly. This study aims to create a prediction model for beef freshness quality using the random forest regressor (RFR) algorithm and to improve the accuracy of the predictions using hyperparameter tuning. The use of near-infrared spectroscopy (NIRS) in predicting beef quality is an easy, cheap, and fast technique. This study used six meat quality parameters as prediction target variables for the test. The R² metric was used to evaluate the prediction results and compare the performance of the RFR with default parameters versus the RFR with hyperparameter tuning (RandomSearchCV). Using default parameters, the R-squared (R²) values for color (L*), drip loss (%), pH, storage time (hour), total plate colony (TPC in cfu/g), and water moisture (%) were 0.789, 0.839, 0.734, 0.909, 0.845, and 0.544, respectively. After applying hyperparameter tuning, these R² scores increased to 0.885, 0.931, 0.843, 0.957, 0.903, and 0.739, indicating an overall improvement in the model’s performance. The average performance increase for prediction results for all beef quality parameters is 0.0997 or 14% higher than the default parameters.
Volume: 6
Issue: 2
Page: 159-166
Publish at: 2025-07-01

Machine learning methods for energy sector in internet of things

10.11591/ijres.v14.i2.pp538-545
Reyhane Hafezifard , Soodeh Hosseini
This research paper focuses on exploring machine learning studies and conducting a comparative analysis of their advantages, disadvantages, implementation environments, and algorithms. A key aspect of the study involves evaluating the energy efficiency using machine learning algorithms to predict energy consumption. Additionally, a feature selection algorithm is employed to rank the features, with the highest-ranking feature identified as one of the most significant. The experimentation is conducted using the Weka tool, incorporating several machine learning algorithms such as linear regression, k-nearest neighbors, decision stump, radial basis function (RBF) network, and isotonic regression. The RBF algorithm, which relies on RBF, shares similarities with neural network algorithms. Results indicate a minimum error value of 1.546 for cooling load and 1.364 for heating load. The random forest algorithm emerges as the most suitable choice within the context of this study.
Volume: 14
Issue: 2
Page: 538-545
Publish at: 2025-07-01

IoT-based smart agriculture system using fuzzy logic: case study in Vietnam

10.11591/ijres.v14.i2.pp440-451
Le Phuong Truong , Le Nam Thoi
This paper presents an internet of things (IoT)-based smart agriculture system using fuzzy logic. This system automatically supervise and regulate pivotal parameters like temperature, humidity, pH, nutrients (NPK), and electrical conductivity (Ec) for vegetables. Data from the cultivation environment is gathered by sensors system and processed by fuzzy logic algorithms to make appropriate control decisions, ensuring optimal crop growth conditions. Additionally, a web application was developed to monitor temperature, humidity, Ec, pH, and NPK content. Moreover, when any of the NPK, Ec, pH, temperature or humidity indices fall outside allowed ranges, the system send warning notifications through the web application. Furthermore, an IP camera was installed to take images of the garden and send them to users via this web app. Experimental results demonstrate the system's reliability with a pH root mean square error (RMSE) of 0.22 and temperature RMSE of 0.93, corresponding to low errors of 0.034% and 0.056% respectively. Concurrently, this system optimizes resource utilization including water and electricity to assist in reducing production costs.
Volume: 14
Issue: 2
Page: 440-451
Publish at: 2025-07-01

Blockchain-based decentralized voting system with SHA-256 algorithm and facial recognition

10.11591/ijres.v14.i2.pp481-489
BJD Kalyani , Jaya Krishna Modadugu , Sarabu Neelima
Blockchain technology has completely changed the way data is stored and transactions are verified. It provides a dependable, transparent, and safe medium for communication and transaction validation. In order to solve the drawbacks of conventional electronic voting systems, the goal of this research project is to design a decentralized voting system based on blockchain technology. The suggested method offers an immutable and safe way to record and validate votes by utilizing the security and transparency capabilities of blockchain technology. The suggested approach provides an immutable and safe way to record and validate votes by utilizing the security and transparency capabilities of blockchain technology. This paper aims to provide a comprehensive process for digital identity authentication, create a voter interface that is compatible with Ethereum wallets, and apply smart contracts on the Ethereum network to speed up voter registration, ballot preparation, voting, and result tabulation. Additionally, this paper proposes to build up a multi-factor authentication system for election managers and validators to offer them safe and approved power over the voting process. By carefully examining the existing methods, this research highlights the flaws and weaknesses of traditional electronic voting systems and stresses the need for more trustworthy and secure voting technology. The proposed blockchain-based voting system offers an innovative solution to problems with voter fraud and election manipulation because of its irreversible blockchain record, which gives a high degree of transparency and integrity.
Volume: 14
Issue: 2
Page: 481-489
Publish at: 2025-07-01

Enhancing scalability and efficiency in technological transaction utilizing dual-layer blockchain approach

10.11591/ijres.v14.i2.pp452-462
T. Kanimozhi , M. Inbavalli
The leather industry encounters significant challenges in integrating blockchain technology and smart contracts into its complex supply networks. Despite technological advancements, existing supply chain management systems suffer from inefficiencies, opacity, and vulnerabilities to fraud. Blockchain offers promising solutions such as immutable ledgers, decentralized governance, and smart contract automation. However, scalability limitations hinder the efficient handling of high transaction volumes, impacting procurement, production, inventory management, and distribution processes, leading to delays and increased costs. This research aims to address these challenges by exploring innovative approaches, including dual-layer blockchain architectures incorporating sharding and state channels, tailored to the unique needs of the leather industry. By overcoming scalability barriers, the research seeks to unlock the transformative potential of blockchain technology and smart contracts, enhancing transparency, traceability, and efficiency in leather supply chains while ensuring global interoperability and regulatory compliance. Through empirical validation and comparative analysis, this study provides understandings into the practical implementation of blockchain solutions within the leather industry, offering strategic guidance for sustainable supply chain management practices.
Volume: 14
Issue: 2
Page: 452-462
Publish at: 2025-07-01

Blockchain technology for optimizing security and privacy in distributed systems

10.11591/csit.v6i2.p214-224
Wisnu Uriawan , Adrian Putra Pratama , Shafwan Mursyid
Blockchain technology is increasingly recognized as an effective solution for addressing security and privacy challenges in distributed systems. Blockchain ensures information security by validating data and defending against cyber threats, while guaranteeing data integrity through transaction validation and reliable storage. The research involves a literature study, problem identification, analysis of blockchain security and privacy, model development, testing, and analysis of trial results. Furthermore, blockchain enables user anonymity and fosters transparency by utilizing a distributed network, reducing the risk of fraudulent activities. Its decentralized nature ensures high reliability and accessibility, even in node failures. Blockchain enhances security and privacy by offering features like data immutability, provenance, and reduced reliance on trust. It decentralizes data storage, making tampering or deletion extremely challenging, and ensures the invalidation of subsequent blocks upon any changes. Blockchain finds applications in various domains, including supply chains, finance, healthcare, and government, enabling enhanced security by tracking data origin and ownership. Despite scalability and security challenges, the potential benefits of reduced costs, increased efficiency, and improved transparency position blockchain as a promising technology for the future. In summary, blockchain technology provides secure transaction recording and data storage, thus enhancing security, privacy, and the integrity of sensitive information in distributed systems.
Volume: 6
Issue: 2
Page: 214-224
Publish at: 2025-07-01

HepatoScan: Ensemble classification learning models for liver cancer disease detection

10.11591/csit.v6i2.p169-177
Tella Sumallika , Raavi Satya Prasad
Liver cancer is a dangerous disease that poses significant risks to human health. The complexity of early detection of liver cancer increases due to the unpredictable growth of cancer cells. This paper introduces HepatoScan, an ensemble classification to detect and diagnose liver cancer tumors from liver cancer datasets. The proposed HepatoScan is the integrated approach that classifies the three types of liver cancers: hepatocellular carcinoma, cholangiocarcinoma, and angiosarcoma. In the initial stage, liver cancer starts in the liver, while the second stage spreads from the liver to other parts of the body. Deep learning is an emerging domain that develops advanced learning models to detect and diagnose liver cancers in the early stages. We train the pre-trained model InceptionV3 on liver cancer datasets to identify advanced patterns associated with cancer tumors or cells. For accurate segmentation and classification of liver lesions in computed tomography (CT) scans, the ensemble multi-class classification (EMCC) combines U-Net and mask region-based convolutional network (R-CNN). In this context, researchers use the CT scan images from Kaggle to analyze the liver cancer tumors for experimental analysis. Finally, quantitative results show that the proposed approach obtained an improved disease detection rate with mean squared error (MSE)-11.34 and peak signal-to-noise ratio (PSNR)-10.34, which is high compared with existing models such as fuzzy C-means (FCM) and kernel fuzzy C-means (KFCM). The classification results obtained based on detection rate with accuracy-0.97%, specificity-0.99%, recall-0.99%, and F1S-0.97% are very high compared with other existing models.
Volume: 6
Issue: 2
Page: 169-177
Publish at: 2025-07-01

Arowana cultivation water quality forecasting with multivariate fuzzy timeseries and internet of things

10.11591/csit.v6i2.p136-146
Alauddin Maulana Hirzan , April Firman Daru , Lenny Margaretta Huizen
Water quality plays a crucial role in the growth and survival of arowana fish, with imbalances in key parameters (pH, temperature, turbidity, dissolved oxygen, and conductivity) leading to increased mortality rates. While previous studies have introduced various monitoring models using Arduino IDE and intrinsic approaches, they lack predictive capabilities, leaving cultivators unable to take proactive measures. To address this gap, this study develops a predictive model integrating the internet of things (IoT) with a fuzzy time series (FTS) algorithm. Through rigorous evaluation and validation, the proposed FTS-multivariate T2 model demonstrated superior performance, achieving an exceptionally low error rate of 0.01704%, outperforming decision tree (0.13410%), FTS-multivariate T1 (0.88397%), and linear regression (20.91791%). These findings confirm that FTS-multivariate T2 not only accurately predicts water quality but also significantly reduces the mean absolute percentage error, providing a robust solution for sustainable arowana aquaculture.
Volume: 6
Issue: 2
Page: 136-146
Publish at: 2025-07-01

Advancements in gas leakage detection and risk assessment: a comprehensive survey

10.11591/ijeecs.v39.i1.pp614-624
Y. Bhavani , Sanjusree Vodapally , Dinesh Bokka , Harshitha Varma Muddasani , Deepika Kasturi
Gas leakage is the main problem that harms the environment, infrastructure and public safety. Technology is increasing rapidly nowadays. So, there must be advancements in the methods used. Many methods have been come across to solve this problem. This survey paper explores various methods and technology used to solve the problem. Many methodologies have been suggested to reduce the risk of gas leaks and improve detection systems. It investigates cutting-edge models for estimating the effects of liquefied natured gas (LNG) leakage accidents, comprehensive wireless sensor network (WSN) is set up for detecting gas leaks in advance, and neural network and Kalman filter-based gas leakage early warning systems. Current developments include factors like point of interest (PoI), human data movement and gas pipelines. As technology increases, there would be major threat of authentication. So, it also looks on methods for user authentication based on different patterns to mobile applications. Especially in smart home environments, there is a need to improve security. This survey provides complete understanding of present and future directions for the researchers in gas leakage detection and risk management through various methods and their evaluation.
Volume: 39
Issue: 1
Page: 614-624
Publish at: 2025-07-01

PRDTinyML: deep learning-based TinyML-based pedestrian detection model in autonomous vehicles for smart cities

10.11591/ijeecs.v39.i1.pp283-309
Norah N. Alajlan , Abeer I. Alhujaylan , Dina M. Ibrahim
Detecting pedestrians and cars in smart cities is a major task for autonomous vehicles (AV) to prevent accidents. Occlusion, distortion, and multi-instance pictures make pedestrian and rider detection difficult. Recently, deep learning (DL) systems have shown promise for AV pedestrian identification. The restricted resources of internet of things (IoT) devices have made it difficult to integrate DL with pedestrian detection. Tiny machine learning (TinyML) was used to recognize pedestrians and cyclists in the EuroCity persons (ECP) dataset. After preliminary testing, we propose five microcontroller-deployable lightweight DL models in this study. We applied SqueezeNet, AlexNet, and convolution neural network (CNN) DL models. We also use two pre-trained models, MobileNet-V2 and MobileNet-V3, to determine the optimal size and accuracy model. Quantization aware training (QAT), full integer quantization (FIQ), and dynamic range quantization (DRQ) were used. The CNN model had the shortest size with 0.07 MB using the DRQ approach, followed by SqueezeNet, AlexNet, MobileNet-V2, and MobileNet-V2 with 0.161 MB, 0.69 MB, 1.824 MB, and 1.95 MB, respectively. The MobileNet-V3 model’s DRQ accuracy after optimization was 99.60% for day photos and 98.86% for night images, outperforming other models. The MobileNet-V2 model followed with DRQ accuracy of 99.27% and 98.24% for day and night images.
Volume: 39
Issue: 1
Page: 283-309
Publish at: 2025-07-01
1 2 3
...
1995 1996
Show 167 of 1996

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