Claim Missing Document
Check
Articles

Found 7 Documents
Search

Computer-Aided Diagnosis (CAD) of Stroke in The Brain CT-Scan Images Using Integration of Grey Level Co-Occurrence Matrix (GLCM) Texture Feature Extraction And K-Nearest-Neighbour (KNN) Classification Casidi, Casidi; Syukur, Abdul; Soeleman, M. Arief; Nurhindarto, Aris
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 4 No. 3: NOVEMBER 2024
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v4i3.646

Abstract

This study presents an advanced and efficient computer-aided diagnosis (CAD) system for stroke detection using brain CT images, integrating Grey Level Co-Occurrence Matrix (GLCM) feature extraction and K-Nearest Neighbour (KNN) classification. The objective is to enhance stroke detection accuracy and efficiency in clinical settings. A dataset of 400 brain CT images, divided into 300 for training and 100 for testing with equal normal and stroke classes, was used to evaluate performance. The GLCM texture features significantly differentiated between normal and stroke images. The optimized KNN model demonstrated high performance, achieving 99% classification accuracy, 100% sensitivity, 98% specificity, 97% precision, a 99% F1 score, 100% positive predictive value, and 98% negative predictive value. The average computation time per image was 3.2 seconds, indicating feasibility for real-time application. In conclusion, the GLCM-KNN integrated CAD system proves to be an accurate and efficient method for stroke diagnosis on brain CT scans, offering a potential solution for early stroke detection in resource-limited healthcare facilities.
Predicting IT Incident Duration using Machine Learning: A Case Study in IT Service Management Caturkusuma, Resha Meiranadi; Alzami, Farrikh; Nurhindarto, Aris; Sulistiyono, MY Teguh; Irawan, Candra; Kusumawati, Yupie
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 1 (2025): Research Article, January 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i1.14310

Abstract

In the digital era, ensuring customer satisfaction with IT services is crucial for business success. However, the complexity of IT infrastructure makes it difficult to manage services, requiring companies to focus on improving efficiency and reducing operational costs. One of the strategies used is Information Technology Service Management (ITSM), the main component of which is incident management, which aims to minimize service disruptions. While various studies on ITSM exist, research focused on Machine Learning models for predicting incident resolution times is relatively limited. This research aims to develop an incident resolution duration prediction model using a Random Forest Regressor-based regression approach. The dataset used is an event log from the ServiceNow system containing data on 24,918 incidents. The model was evaluated using the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R2 metrics, where the model achieved a MAE of 14.33 hours, RMSE of 69.8 hours, and R2 of 0.98. These results show that the model can provide accurate predictions and support better decision-making in IT incident handling. Time-related features, such as sys_update_month and closed_month, proved to be the most influential factors in predicting incident resolution duration.
Clustering and Profiling Analysis for FIFA Football Player using K-Means Azzami, Salman Yuris Adila; Hadi, Heru Pramono; Alzami, Farrikh; Irawan, Candra; Nurhindarto, Aris; Sulistyono, MY Teguh
Jurnal Informatika: Jurnal Pengembangan IT Vol 10, No 1 (2025)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v10i1.7897

Abstract

The selection of football players is a complex process involving talent evaluation based on various performance indicators, combining objective measures with subjective assessments by coaches and scouts. This research aims to improve the football player selection process using the K-Means clustering method based on the attributes of transfer price, performance, body specifications, position, and player ability. The dataset used consists of 17.947 players taken from the FIFA 19 edition of the soFIFA.com platform, which includes complete information such as transfer price, performance, body specifications, position, and player ability. The data was processed using principal component analysis (PCA) to reduce the dimensions, followed by the Elbow Method to determine the optimal number of clusters. The clustering results show the distribution of players based on their on-field roles, such as center back, goalkeeper, striker, and left wing back. The profiling of players from each cluster is identified based on position, body type, dominant foot usage, transfer price, and rating. This research provides useful insights for coaches and scouts in selecting players that suit specific roles in the team using better analysis. The findings also highlight the importance of player clustering for data-driven decision-making, which can optimize team composition and overall performance.
Clustering IT Incidents Using K-Means: Improving Incident Response Time in Service Management Anggraeni, Rini; Alzami, Farrikh; Nurhindarto, Aris; Budi, Setyo; Megantara, Rama Aria; Rizqa, Ifan; Muslih, Muslih
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 2 (2025): Research Articles April 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i2.14822

Abstract

Incident management is one of the critical processes in Information Technology service management that aims to manage disruptions and minimize the impact of unexpected incidents on business services. This study applies the K-Means algorithm to cluster IT service incidents, aiming to enhance company operational efficiency. Utilizing a dataset from the UCI Machine Learning Repository comprising 141,712 events related to 24,918 incidents, this research analyzes incident patterns and characteristics for optimized handling. The data was analyzed through a series of preprocessing stages, and the elbow and silhouette methods were used to determine the optimal number of clusters. From the results, it was successfully grouped into 4 (four) clusters with a distortion score value of 964264294.569 and 0.52 silhouette score based on incident characteristics, such as urgency, priority, and number of reassignments. From this, the clustering results show that the K-Means algorithm effectively identifies incidents that require further handling, such as those with high urgency and priority, as well as helping the company focus resources to resolve incidents that have the most impact on the business sector. This research provides a data-driven solution to improve incident management and Service Level Agreement (SLA) fulfillment, while offering a framework for more effective and efficient IT incident analysis and resource allocation.
Peningkatan Performa Ensemble Learning pada Segmentasi Semantik Gambar dengan Teknik Oversampling untuk Class Imbalance Nugroho, Arie; Soeleman, M. Arief; Pramunendar, Ricardus Anggi; Affandy, Affandy; Nurhindarto, Aris
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 4: Agustus 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2024106831

Abstract

Perkembangan teknologi dan gaya hidup manusia yang semakin tinggi menghasilkan data-data yang berlimpah. Data-data tersebut dapat berbentuk data yang terstruktur dan tidak terstruktur. Data gambar termasuk dalam data yang tidak terstruktur. Aktifitas dan objek yang terekam dalam suatu gambar beraneka ragam. Secara normal, mata manusia dapat dengan mudah membedakan antara foreground dan background dari suatu gambar, tetapi komputer membutuhkan pembelajaran dalam membedakan keduanya. Segmentasi gambar adalah salah satu bidang dalam computer vision yang membahas bagaimana cara komputer mempelajari dan mengenali segmen dari suatu gambar sesuai label yang ditentukan. Dalam kenyataannya banyak data yang mempunyai class atau label yang tidak seimbang, tentunya akan mempengaruhi tingkat akurasi dari suatu prediksi. Dalam riset ini membahas bagaimana meningkatkan akurasi segmentasi semantik gambar pada metode ensemble learning untuk menangani masalah data yang tidak seimbang dalam segmentasi gambar. Teknik yang digunakan adalah sintetis oversampling sehingga menghasilkan data yang seimbang dan akurasi yang tinggi. Metode ensemble learning yang digunakan adalah Random Forest dan Light Gradien Boosting Machine (LGBM). Dengan menggunakan dataset Penn-Fudan Database for Pedestrian yang mengandung imbalanced class. Penggunaan teknik sintetis oversampling dapat memperbaikki tingkat akurasi pada class minoritas. Pada algoritma random forest mengalami peningkatan akurasi sebesar 37 % sedangkan pada algoritma LGBM meningkat sebesar 41 %. AbstractThe development of technology and the increasingly high lifestyle of humans produce abundant data. These data can be in the form of structured and unstructured data. Image data is included in unstructured data. The activities and objects recorded in a picture are varied. Normally, the human eye can easily distinguish between the foreground and background of an image, but computers need learning to distinguish between the two. Image segmentation is one of the fields in computer vision that discusses how computers learn and recognize segments of an image according to specified labels. In reality, a lot of data has unbalanced classes or labels, of course, it will affect the accuracy of a prediction. This research discusses how to improve the accuracy of image semantic segmentation in the ensemble learning method to deal with the problem of unbalanced data in image segmentation. The technique used is synthetic oversampling so as to produce balanced data and high accuracy. The ensemble learning methods used are Random Forest and Light Gradient Boosting Machine (LGBM). By using the Penn-Fudan Database for Pedestrian dataset which contains a imbalanced class. The use of synthetic oversampling techniques can improve the level of accuracy in minority classes. The random forest algorithm experienced an increase in accuracy by 37% while the LGBM algorithm increased by 41%.
A Decision Support System is Developed to Determine the Optimal Criteria for Selecting Exceptional Lecturers Based on Their Lecturer Performance Index Nurhindarto, Aris; Sari, Wellia Shinta; Hendriyanto , Novi; Sulistyono, MY Teguh
TEPIAN Vol. 5 No. 2 (2024): June 2024
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v5i2.1783

Abstract

Decision Support Systems (DSS) are computer systems that analyze data and convert it into actionable information for decision-making. The prior application mainly emphasized design analysis in web development, neglecting the use of decision-making knowledge as a responsibility within the Tri Dharma of Higher Education.  Analyzing data to transform it into information is a complex task involving decision-making. The process of decision-making has a significant impact on the information generated for recommendation purposes.   Suggestions in a decision-making process only sometimes serve as a standard for leaders to implement immediately. However, it is essential to acknowledge that multiple suggestions are required to make a final decision since they provide a basis for comparison with earlier recommendations.  The Decision Support System (DSS) utilized in this research focuses on selecting the optimal criteria from several criteria. The research employed the Analytical Hierarchy Process (AHP) technique, which consists of six stages : Criteria Alternative Determination, Pairwise Matrix Comparison, Criteria And Making Matrix, Square of Pairwise Matrix, Normalisation, and Alternative Ranking.   All six steps must be sequentially executed without skipping any stage, ensuring each stage complements the others and generates accountable information.   The research concludes by proposing a Decision Support System for Determining the Best Criteria for Lecturer Selection. This system utilizes the Lecturer Performance Index to provide recommendations to parties seeking information on selecting criteria for assessing lecturer performance. The system aims to enhance accountability in the performance of the Tri Dharma of Higher Education.
Decision Tree Classification for Reducing Alert Fatigue in Patient Monitoring Systems Herfiani, Kheisya Talitha; Nurhindarto, Aris; Alzami, Farrikh; Budi, Setyo; Megantara, Rama Aria; Soeleman, M Arief; Handoko, L Budi; Rofiani, Rofiani
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8414

Abstract

The development of information technology in healthcare opens new opportunities to improve continuous patient monitoring. A major challenge is alert fatigue, where medical personnel are overwhelmed by excessive notifications, reducing concentration, work efficiency, and potentially compromising patient safety. This study presents a proof-of-concept application of the Decision Tree algorithm to analyze alert triggering factors in patient monitoring systems. The dataset is a synthetic health monitoring dataset from Kaggle, containing 10,000 entries with vital parameters including blood pressure, heart rate, oxygen saturation, and glucose levels, designed with deterministic logical relationships between threshold indicators and alert outcomes. The imbalanced dataset (73.67% alert triggered, 26.33% no alert) was intentionally not processed using imbalanced learning techniques to demonstrate Decision Tree's capability in processing structured health data and producing interpretable classifications. The research methodology included data preprocessing, exploratory data analysis, data splitting (90% training, 10% testing), GridSearchCV optimization, and performance evaluation. Results showed perfect metrics (100% accuracy, precision, recall, F1-score), reflecting the deterministic nature of the synthetic dataset rather than real-world clinical complexity. Feature importance analysis identified blood pressure as the most dominant variable, followed by heart rate and glucose levels. This study demonstrates Decision Tree's interpretability and feature importance analysis capabilities in health data contexts, establishing a methodological framework that requires validation on real clinical Electronic Health Record (EHR) data for practical application in reducing alert fatigue and supporting informed clinical decisions.