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

Smart brake pad early warning system: enhancing vehicle safety through real-time monitoring

10.11591/csit.v6i2.p122-135
Afif Syam Fauzi , Giva Andriana Mutiara , Muhammad Rizqy Alfarisi , Tedi Gunawan , Muhammad Aulia Rifqi Zain
A contributing factor to traffic accidents is brake pad failure, which diminishes braking system performance and extends braking distance. This work develops a prototype utilizing internet of things (IoT) to measure brake pad thickness, hence enhancing driver awareness through real-time monitoring. The system establishes the thickness detection threshold at 75% (3-4 mm) and 50% (5–6 mm) as a cautionary parameter. The thickness parameter employs an American wire gauge (AWG) 18 cable to connect to the ESP32 microcontroller. The web-based IoT monitoring interface employs Laravel. This method enables drivers to get prompt notifications regarding the decrease in brake pad thickness, hence permitting urgent preventative maintenance to mitigate the risk of accidents. The system underwent testing through friction at a rotational speed of 600 to 6,000 rpm. The test findings indicated that the sensor precisely measured the brake pad thickness with a prototype response time of a second. This system is suitable for implementation on old model vehicles that do not have an early warning system. The installation of this technology is anticipated to enhance driver knowledge of the state of the brake pads, hence potentially diminishing the danger of brake system failure caused by unmonitored pad wear.
Volume: 6
Issue: 2
Page: 122-135
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

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 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

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

FPGA-based implementation of a substitution box cryptographic co-processor for high-performance applications

10.11591/ijres.v14.i2.pp587-596
Moulai Khatir Ahmed Nassim , Ziani Zakarya
The increasing demand for reliable cryptographic operations for securing current systems has given birth to well-advanced and developed hardware solutions, in this paper we consider issues within the traditional symmetric advanced encryption standard (AES) cryptographic system as major challenges. Additionally, problems such as throughput limitations, reliability, and unified key management are also discussed and tackled through appropriate hierarchical transformation techniques. To overcome these challenges, this paper presents the design and field programmable gate array (FPGA)-based implementation of a cryptographic coprocessor optimized for substitution box (S-Box) operation which is considered as a key component in many cryptographic algorithms such as AES. The architecture of the co-processor proposed in this article is based on the advanced characteristics of FPGAs to accelerate the S-Box transformation, improve throughput and reduce latency compared to software implementations. We discussed carefully the design considerations along with resource utilization, speed optimization, and energy efficiency. The obtained experimental results present significant performance improvements, the FPGA-based implementation ensured higher throughput and lower execution time compared to traditional central processing unit (CPU)-based methods. We presented in this work the effectiveness of using FPGAs for the acceleration of cryptographic operations in secure applications which will therefore be a robust solution for the next generation of secure systems.
Volume: 14
Issue: 2
Page: 587-596
Publish at: 2025-07-01

Development of a web-based application for real-time eye disease classification system using artificial intelligence

10.11591/ijres.v14.i2.pp558-574
Kennedy Okokpujie , Adekoya Tolulope , Abidemi Orimogunje , Joshua Sokowonci Mommoh , Adaora Princess Ijeh , Mary Oluwafeyisayo Ogundele
The incorporation of artificial intelligence (AI) into the field of medicine has created new strategies in enhancing the detection of disease, with a focus on the identification of eye diseases such as glaucoma, diabetic retinopathy, and macular degeneration associated with age, which can lead to blindness if not detected and treated early enough. Driven by the need to combat blindness, which affects approximately 39 million people globally, according to the World Health Organization (WHO). This research offers a web-based, real time approach to classifying eye diseases from fundus images due to user friendliness. Three pre-trained convolutional neural network (CNN) models are adopted, namely ResNet-50, Inception-v3, and MobileNetV3. The models were trained on a dataset of 8000 fundus images subdivided into four classes: cataract, glaucoma, diabetic retinopathy, and normal eyes. The performance of the models was evaluated in 3-way (normal eye and two diseases) and 4-way (normal eye and three diseases). ResNet-50 had higher performances, with 98% and 97% accuracy in the respective classifications, compared to InceptionV3 and MobileNetV3. Consequently, ResNet-50 was used in an online application that made real-time diagnoses. This research findings reveal the potential of CNNs in the healthcare industry, particularly in reducing over-reliance on specialists and increasing access to quality diagnostic technologies. Especially in critical areas such as this with limited healthcare resources, where the technology can create significant gaps in disease detection and control.
Volume: 14
Issue: 2
Page: 558-574
Publish at: 2025-07-01

Investigating the recall efficiency in abstractive summarization: an experimental based comparative study

10.11591/ijeecs.v39.i1.pp446-454
Surabhi Anuradha , Martha Sheshikala
This study explores text summarization, a critical component of natural language processing (NLP), specifically targeting scientific documents. Traditional extractive summarization, which relies on the original wording, often results in disjointed sequences of sentences and fails to convey key ideas concisely. To address these issues and ensure comprehensive inclusion of relevant details, our research aims to improve the coherence and completeness of summaries. We employed 25 different large language models (LLMs) to evaluate their performance in generating abstractive summaries of scholarly scientific documents. A recall-oriented evaluation of the generated summaries revealed that LLMs such as 'Claude v2.1,' 'PPLX 70B Online,' and 'Mistral 7B Instruct' demonstrated exceptional performance with ROUGE-1 scores of 0.92, 0.88, and 0.85, respectively, supported by high precision and recall values from bidirectional encoder representations from transformers (BERT) scores (0.902, 0.894, and 0.888). These findings offer valuable insights for NLP researchers, laying the foundation for future advancements in LLMs for summarization. The study highlights potential improvements in text summarization techniques, benefiting various NLP applications.
Volume: 39
Issue: 1
Page: 446-454
Publish at: 2025-07-01

Advanced cervical cancer classification: enhancing pap smear images with hybrid PMD filter-CLAHE

10.11591/ijeecs.v39.i1.pp644-655
Ach Khozaimi , Isnani Darti , Syaiful Anam , Wuryansari Muharini Kusumawinahyu
Cervical cancer remains a significant health problem, especially in developing countries. Early detection is critical for effective treatment. Convolutional neural networks (CNN) have shown promise in automated cervical cancer screening, but their performance depends on pap smear image quality. This study investigates the impact of various image preprocessing techniques on CNN performance for cervical cancer classification using the SIPaKMeD dataset. Three preprocessing techniques were evaluated: PeronaMalik diffusion (PMD) filter for noise reduction, contrast-limited adaptive histogram equalization (CLAHE) for image contrast enhancement, and the proposed hybrid PMD filter-CLAHE approach. The enhanced image datasets were evaluated on pretrained models, such as ResNet-34, ResNet-50, SqueezeNet-1.0, MobileNet-V2, EfficientNet-B0, EfficientNet-B1, DenseNet121, and DenseNet-201. The results show that hybrid preprocessing PMD filter-CLAHE can improve the pap smear image quality and CNN architecture performance compared to the original images. The maximum metric improvements are 13.62% for accuracy, 10.04% for precision, 13.08% for recall, and 14.34% for F1-score. The proposed hybrid PMD filter-CLAHE technique offers a new perspective in improving cervical cancer classification performance using CNN architectures.
Volume: 39
Issue: 1
Page: 644-655
Publish at: 2025-07-01

Core methodological classes of text extraction and localization-a snapshot of approaches

10.11591/ijeecs.v39.i1.pp455-465
Dayananda Kodala Jayaram , Puttegowda Devegowda
The motivation to work on text extraction and localization is quite a substantial that potentially influences a larger area of application right from business intelligence to advanced data analytics. At present, there are massive archives of literatures addressing varying ranges of problems associated with text extraction and localization with an effective realization of respective contribution as well as on-going issues. However, problem statement is that all these massive implementation studies are further required to converge down in order to realize the core classes of methodologies involved in text extraction. Hence, this manuscript uses desk research methodology to address this issue by presenting a compact insight of core methodological classes where all the recent implementation work are converged down to understand its strength and weakness. The research outcome contributes towards facilitating information of current research trend and identified research gap. The proposed review study assists in undertaking decision of suitable approach of text extraction, localization, detection, recognition, and classification.
Volume: 39
Issue: 1
Page: 455-465
Publish at: 2025-07-01

Optimizing stress resistance in MEMS inertial sensors through material and thickness variations

10.11591/ijeecs.v39.i1.pp110-117
Miladina Rizka Aziza , Onny Setyawati , Jumiadi Jumiadi
Stress on the micro-electromechnical system (MEMS) sensors significantly decreases sensor accuracy. Thermomechanical stresses induced by the packaging assembly process and external loads during operation induce a shift in the output signal (offset) of MEMS sensors. To achieve high precision in accelerometers, gyroscopes, and other MEMS devices, it is crucial to employ advanced modeling and simulation techniques to mitigate stress-induced offset drift. Therefore, this paper aims to explore and simulate stress on inertial sensors by designing a gyroscope tuning fork with a perforated proof mass to reduce the damping effect. Our findings provide insights for decreasing stress by varying the material and thickness of the inertial sensor. The least stress was obtained from an inertial silicon sensor with 5 and 20 mm thicknesses.
Volume: 39
Issue: 1
Page: 110-117
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

The impact of coordinator failures on the performance of Zigbee networks in various topologies

10.11591/ijeecs.v39.i1.pp235-246
Daulet Naubetov , Mubarak Yakubova , Bahodir Yakubov , Nurzhigit Smailov
Zigbee, a key technology in the field of wireless networks for the Internet of Things, plays a significant role in the development of modern wireless network technologies. In this study, the analysis of coordinator failures in ZigBee networks with different topologies (“star”, “tree”, “mesh”) was carried out using the OPNET Modeler software tool. The problems related to the reliability and efficiency of systems using Zigbee technology are considered. Simulation of successive coordinator failures allowed us to compare the performance of topologies, revealing that the tree topology provides high traffic speed and bandwidth, but suffers from significant packet loss and delays. In turn, the star topology demonstrates minimal latency and high speed, and the mesh topology has better reliability with less packet loss, but the lowest speed and bandwidth. The findings emphasize the importance of choosing the optimal topology to ensure the efficiency and reliability of Zigbee networks in a volatile environment and increased load.
Volume: 39
Issue: 1
Page: 235-246
Publish at: 2025-07-01

Attack detection in internet of things networks with deep learning using deep transfer learning method

10.11591/csit.v6i2.p202-213
Riki Abdillah Hasanuddin , Muhammad Subali
Cybersecurity becomes a crucial part within the information management framework of internet of things (IoT) device networks. The large-scale distribution of IoT networks and the complexity of communication protocols used are contributing factors to the widespread vulnerabilities of IoT devices. The implementation of transfer learning models in deep learning can achieve optimal performance faster than traditional machine learning models, as they leverage knowledge from previous models that already understand these features. Base model was built using the 1-dimension convolutional neural network (1D-CNN) method, using training and test data from the source domain dataset. Model 1 was constructed using the same method as base model. The test and training data used for model 1 were from the target domain dataset. This model successfully detected known attacks at a rate of 99.352%, but did not perform well in detecting unknown attacks, with an accuracy of 84.645%. Model 2 is an enhancement of model 1, incorporating transfer learning from the base model. Its results significantly improved compared to model 1 testing. Model 2 has an accuracy and precision rate of 98.86% and 99.17 %, respectively, allowing it to detect previously unknown attacks. Even with a slight decrease in normal detection, most attacks can still be detected.
Volume: 6
Issue: 2
Page: 202-213
Publish at: 2025-07-01
1 2 3
...
1995 1996
Show 168 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