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

30,411 Article Results

Word embedding and imbalanced learning impact on Indonesian Quran ontology population

10.11591/ijeecs.v39.i1.pp603-613
Fandy Setyo Utomo , Yuli Purwati , Mohd Sanusi Azmi , Lulu Shafira , Nikmah Trinarsih
This research addresses limitations in Quranic instance classification, exceptionally high dimensionality, lack of semantic relationships in the term frequency-inverse document frequency (TF-IDF) technique, and imbalanced data distribution, which reduce prediction accuracy for minority classes. This study investigates the impact of word embedding and imbalance learning techniques on instance classification frameworks using Indonesian Quran translation and Tafsir datasets to handle previous research limitations. Four classification frameworks were built and evaluated using accuracy and hamming loss metrics. The results show that the synthetic minority oversampling technique (SMOTE) technique, TF-IDF model, and logistic regression classifier provide the best accuracy results of 62.74% and a hamming loss score of 0.3726 on the Quraish Shihab Tafsir dataset. This is better than the performance of previous classifiers backpropagation neural network (BPNN) and support vector machine (SVM) used in the previous framework, with accuracies of 59.91% and 62.26%, respectively. Logistic regression can also provide the best classification results with an accuracy of 67.92% and a hamming loss of 0.3208 using the previous framework. These results are better than the performance of the previous classifiers BPNN and SVM used in the previous framework, with accuracies of 62.26% and 66.98%, respectively. TF-IDF feature extraction outperforms word2vec in instance classification results due to its superior support under limited dataset conditions.
Volume: 39
Issue: 1
Page: 603-613
Publish at: 2025-07-01

Influences of the Sm3+ -Eu3+ codoped Ba2Gd(BO3)2Cl phosphors on the commercial white light emitting diodes

10.11591/ijeecs.v39.i1.pp62-69
Luu Hong Quan , My Hanh Nguyen Thi
The color quality of current commercial white light emitting diodes (wLEDs) suffers low performance owing to the lack of the red-emission component. Developing quality and stable red-emission phosphors is feasible among various approaches to obtain the red spectral supplement for the w-LEDs in the pursuit of color quality improvement. In this paper, the Sm3+-Eu3+ codoped Ba2Gd(BO¬3)2Cl (BGBC:Sm-Eu) red phosphor was proposed for using in commercial w-LEDs. Its luminescence and influences on w-LED properties were simulated and presented. The solid-phase method was utilized for the fabrication of the phosphor. The results indicated that the phosphor emitted the strong emission in orange-red region with a peak centering at 593 nm. It can be caused by the proficient power shift between Sm3+ and Eu3+. In the w-LED package, the presence of BGBC:Sm-Eu phosphor stimulated the scattering efficiency to promote the blue-light conversion and extraction. The orange emission spectrum of the w-LED increased with the higher BGBC:Sm-Eu doping amount. The luminous strength of the w-LED was enhanced and so was the color temperature uniformity. The color rendering properties declined with high BGBC:Sm-Eu phosphor concentration owing to the red-light dominance over the light spectrum. The BGBC:Sm-Eu phosphor is a promising red phosphor for improving commercial w-LED color-temperature stability and luminosity. It also helps to obtain full-spectrum w-LED with high color rendition when combined with other blue-to-green luminescent materials.
Volume: 39
Issue: 1
Page: 62-69
Publish at: 2025-07-01

EMG-based hand gesture classification using Myo Armband with feedforward neural network

10.11591/ijeecs.v39.i1.pp159-166
Sofea Anastasia Mohd Said , Norashikin M. Thamrin , Megat Syahirul Amin Megat Ali , Mohamad Fahmi Hussin , Roslina Mohamad
This paper presents the development of an electromyography (EMG)-based hand gesture identification system for remote-controlled applications. Even though the Myo Armband is no longer commercially supported, the research discusses its use in EMG data collecting. Open-source libraries were utilized to capture EMG data from this device to solve this problem. Using the developed data acquisition platform, data was collected from 30 participants who performed three (3) gestures - a fist, an open hand, and a pinch. The energy spectral density (ESD) and power ratio (pRatio) were extracted to describe gesture-specific patterns. A feedforward neural network (FFNN) was implemented for classification, initially configured with 10 hidden neurons and later optimized to 40 neurons to improve the performance. The box plot analysis showed channels CH1, CH4, CH5, and CH7 as the most significant for enhancing classification accuracy. The optimized FFNN achieved 80% and 70% for the training and testing accuracies, respectively. However, the results suggest that implementing a systematic protocol during data acquisition to reduce signal overlap between movements could improve classification accuracy. In conclusion, the study successfully developed an open-source EMG data acquisition platform for MYO Armband and demonstrated acceptable hand gesture recognition using an optimized FFNN.
Volume: 39
Issue: 1
Page: 159-166
Publish at: 2025-07-01

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

Artificial intelligence-powered robotics across domains: challenges and future trajectories

10.11591/csit.v6i2.p176-199
Tole Sutikno , Hendril Satrian Purnama , Laksana Talenta Ahmad
The rise of artificial intelligence (AI) in robotic systems raises both challenges and opportunities. This technological change necessitates rethinking workforce skills, resulting in new qualifications and potentially outdated jobs. Advancements in AI-based robots have made operations more efficient and precise, but they also raise ethical issues such as job loss and responsibility for robot decisions. This study explores AI-powered robotics in both of their challenges and future trajectories. As AI in robotics continues to grow, it will be crucial to tackle these issues through strong rules and ethical standards to ensure safe and fair progress. Collaborative robots in manufacturing improve safety and increase productivity by working alongside human employees. Autonomous robots reduce human mistakes during checks, leading to better product quality and lower operational expenses. In healthcare, robotic helpers improve patient care and medical staff performance by managing routine tasks. Future research should focus on improving efficiency and accuracy, boosting productivity, and creating safe environments for humans and robots to work safely together. Strong rules and ethical guidelines will be vital for integrating AI-powered robotics into different areas, ensuring technology development aligns with societal values and needs.
Volume: 6
Issue: 2
Page: 176-199
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

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

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

An ensemble learning approach for diabetes prediction using the stacking method

10.11591/csit.v6i2.p102-111
Elliot Kojo Attipoe , Alimatu Saadia Yussiff , Maame Gyamfua Asante-Mensah , Emmanuel Dortey Tetteh , Regina Esi Turkson
Diabetes is a severe illness characterized by high blood glucose levels. Machine learning algorithms, with their ability to detect and predict diabetes in its early stages, offer a promising avenue for research. This study sought to enhance the accuracy of predicting diabetes mellitus by employing the stacking method. The stacking method was chosen because it integrates predictions from various base models, resulting in a more precise final prediction. The stacking method enhances accuracy and generalization by utilizing the varied strengths of multiple base models. The Pima Indians diabetes dataset, a widely used benchmark dataset, was utilized in the study. The machine learning models used for the studies were logistic regression (LR), naïve Bayes (NB), extreme gradient boost (XGBoost), K-nearest neighbor (KNN), decision tree (DT), and support vector machine (SVM). LR, KNN, and SVM were the best-performing models based on accuracy, F1-score, precision, and area under the curve (AUC) score, and were consequently used as the base model for the stacking method. The LR model was utilized for the meta-model. The proposed ensemble approach using the stacking method demonstrated a high accuracy of 82.4%, better than the individual models and other ensemble techniques such as bagging or boosting. This study advances diabetes prediction by developing a more accurate early-stage detection model, thereby improving clinical management of the disease.
Volume: 6
Issue: 2
Page: 102-111
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

Non-contact breathing rate monitoring using infrared thermography and machine learning

10.11591/ijeecs.v39.i1.pp669-680
Anadya Ghina Salsabila , Rachmad Setiawan , Nada Fitrieyatul Hikmah , Zain Budi Syulthoni
Monitoring vital physiological parameters such as breathing rate (BR) is crucial for assessing patient health. However, current contact-based measurement methods often cause discomfort, particularly in infants or burn patients. This study aims to develop a non-contact system for monitoring BR using infrared thermography (IRT). This approach permits to detects and tracks the nose from thermal video, extracts temperature variations into a breathing signal, and processes this signal to estimate BR. The estimated BR is then classified into three health categories (bradypnea/normal/tachypnea) using k-nearest neighbors (k-NN). To evaluate system accuracy and robustness, experiments were conducted under three conditions: (i) stationary breathing, (ii) breathing with head movements, and (iii) specific breathing patterns. Results demonstrated high consistency with contact-based photoplethysmography (PPG) measurements, achieving complement of the absolute normalized difference (CAND) index values of 94.57%, 93.71%, and 96.06% across the three conditions and mean absolute BR errors of 1.045 bpm, 1.259 bpm, and 0.607 bpm. The k-NN classifier demonstrated high performance with training, validation, and testing accuracies of 100%, 100%, and 99.2%, respectively. Sensitivity, specificity, precision, and F-measure results confirm system reliability for non-contact BR monitoring in clinical and practical settings.
Volume: 39
Issue: 1
Page: 669-680
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

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

10.11591/csit.v6i2.p159-168
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: 159-168
Publish at: 2025-07-01

Artificial intelligence-powered robotics across domains: challenges and future trajectories

10.11591/csit.v6i2.p178-201
Tole Sutikno , Hendril Satrian Purnama , Laksana Talenta Ahmad
The rise of artificial intelligence (AI) in robotic systems raises both challenges and opportunities. This technological change necessitates rethinking workforce skills, resulting in new qualifications and potentially outdated jobs. Advancements in AI-based robots have made operations more efficient and precise, but they also raise ethical issues such as job loss and responsibility for robot decisions. This study explores AI-powered robotics in both of their challenges and future trajectories. As AI in robotics continues to grow, it will be crucial to tackle these issues through strong rules and ethical standards to ensure safe and fair progress. Collaborative robots in manufacturing improve safety and increase productivity by working alongside human employees. Autonomous robots reduce human mistakes during checks, leading to better product quality and lower operational expenses. In healthcare, robotic helpers improve patient care and medical staff performance by managing routine tasks. Future research should focus on improving efficiency and accuracy, boosting productivity, and creating safe environments for humans and robots to work safely together. Strong rules and ethical guidelines will be vital for integrating AI-powered robotics into different areas, ensuring technology development aligns with societal values and needs.
Volume: 6
Issue: 2
Page: 178-201
Publish at: 2025-07-01
1 2 3
...
2027 2028
Show 199 of 2028

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