Article Per Year (5 Year)
p-Index From 2020 - 2025
0.92
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Terpadu Journal of Intelligent Decision Support System (IDSS) JIKA (Jurnal Informatika) Transformasi
Kasmawaru, Kasmawaru
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Mathematics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Implementasi Metode Hybrid Filtering Technique pada Penentuan Rating Pestisida Ardimansyah, Ardimansyah; Husain, Husain; Herlinda, Herlinda; Kasmawaru, Kasmawaru; Nurdiansah, Nurdiansah; Marsa, Marsa
Jurnal Teknologi Terpadu Vol 10 No 1 (2024): Juli, 2024
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v10i1.1184

Abstract

Pesticides result from mixing organic chemicals that farmers use to protect their rice plants from disease. Farmers find it difficult to determine pesticide selection due to insufficient information.  So many pesticide products are available on the market, and their various advantages make it increasingly difficult for farmers to choose pesticides suitable for certain rice diseases. This research aims to provide farmers with recommendations on determining the best pesticide to eradicate rice diseases. The wrong choice of pesticide used can harm or reduce farmers' crop yields. This research used the Hybrid Filtering Technique combined with Content Based Filtering and Collaborative Filtering methods to search for weight values ​​and rating prediction values ​​using price criteria, pesticide ingredients, and form (liquid, solid, powder). The results of the calculation analysis of implementing the hybrid filtering technique method for each alternative criterion can simulate a ranking to recommend the best pesticide to eradicate the causes of rice disease. This research has concluded that the rating carried out by farmers who have used pesticides influences the determination of the rating value for each pesticide product. The system test results showed that the type of pesticide with the highest rating value was the enquity pesticide, with a value of 2,256.
SISTEM KENDALI CERDAS PEMBERIAN PAKAN DENGAN PENERAPAN INTERNET OF THINGS Kasmawaru, Kasmawaru; Husain, Husain; Herlinda, Herlinda; nurdiansah, nurdiansah; Ahmad, Ahmad; Asran, Asran
Jurnal Informatika Vol 8, No 3 (2024): JIKA (Jurnal Informatika)
Publisher : University of Muhammadiyah Tangerang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31000/jika.v8i3.10828

Abstract

Kucing merupakan hewan yang banyak dipelihara orang karena menggemaskan, cantik warna bulunya, memiliki tingkah laku yang lucu, dan bersahabat. Kucing juga dianggap bisa menghilangkan ataupun mengurangi stress setelah melakukan rutinitas pekerjaan di kantor. Permasalahan yang sering terjadi pada pemeliharaan kucing adalah proses pemberian makan minum, faktor inilah yang menjadi alasan penulis untuk membuat Kendali Cerdas sistem pemberian makan dan minum (Pakan) kucing dengan penerapan internet of Things. Tujuan pembuatan Kendali Cerdas ini adalah untuk menggantikan tugas pemilik kucing untuk memberikan pakan setiap harinya. Adapun metode yang digunakan yaitu menggunakan NodeMcu ESP8266 sebagai modul pengendali,  Sensor Ultrasonic, Sensor LoadCell, dan aplikasi android sebagai media penerima informasi dan mengontrolan manual sistem. Sistem ini akan mengendalikan pemberian pakan kucing dengan mengontrol stok pakan pada dispenser dan jumlah pakan pada wadah. Hasil pengujian yang telah dilakukan menunjukan nilai akurasi Sensor Ultrasonic 99,8% dan akurasi sensor  LoadCell  95,2% dalam melakukan pemantauan pada dispenser dan wadah pakan kucing.
Comparison of coronary heart disease prediction using basic model and ensemble learning Rachmat, Rachmat; Iskandar, Syamsul Bhahri; Kasmawaru, Kasmawaru; Suherwin, Suherwin
Journal of Intelligent Decision Support System (IDSS) Vol 8 No 2 (2025): June: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/idss.v8i2.298

Abstract

Coronary heart disease (CHD) remains one of the leading causes of death worldwide, highlighting the urgent need for accurate early detection. This study aims to compare the performance of various machine learning models—including Decision Tree, K-Nearest Neighbor (KNN), Logistic Regression, Random Forest, XGBoost, and Stacking Ensemble—in predicting CHD using the UCI Heart Disease Dataset. The models were evaluated using five metrics: accuracy, precision, recall, F1-score, and AUC. The results indicate that Stacking and Logistic Regression achieved the highest AUC scores (0.80), while XGBoost obtained the best F1-score (0.40). Simpler models such as Decision Tree and KNN showed relatively lower performance. In addition, feature importance analysis using permutation methods revealed that features like number of major vessels (ca), thalassemia (thal), ST depression (oldpeak), and age play a critical role in prediction accuracy. These findings demonstrate that ensemble learning approaches, especially Stacking and XGBoost, can effectively improve diagnostic performance and offer strong potential for clinical decision support systems (CDSS) in the early detection of coronary heart disease.
SISTEM MONITORING GARDU INDUK PLN DENGAN PENERAPAN INTERNET OF THINGS Ahmad, Ahmad; T, Husain; Herlinda, Herlinda; Kasmawaru, Kasmawaru
Jurnal Informatika Vol 9, No 3 (2025): JIKA (Jurnal Informatika)
Publisher : University of Muhammadiyah Tangerang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31000/jika.v9i3.14294

Abstract

The area surrounding power transformers at substations must remain free from wild animals, as their presence can disrupt the flow of electricity, potentially causing equipment damage and reducing the reliability of the electrical system. This study aims to design and implement an automated monitoring system based on the Internet of Things (IoT) to detect the presence of animals near high-voltage equipment (150 kV) at the Tallasa substation. The proposed system integrates Passive Infrared (PIR) and ultrasonic sensors with an ESP32-CAM microcontroller to detect animal movement in real time. Detection data is transmitted to an IoT platform via WiFi or cellular networks, and real-time alerts are sent through the Telegram application to enable a prompt response by personnel. Test results indicate that the system demonstrates high accuracy in detecting animals under both daylight and low-light conditions. Furthermore, real-time notifications enhance monitoring responsiveness and enable early intervention to prevent potential disruptions. With its reliable and consistent performance, the system presents an effective and sustainable solution for maintaining the operational integrity of transformer protection systems and perimeter barriers.
ANALISIS PERILAKU PEMBELIAN AUDIENS TIKTOK MELALUI KLASTERISASI PREFERENSI KONTEN DENGAN ALGORITMA K-MEANS Irmawati, Irmawati; T, Husain; Santi, Santi; nurdiansah, nurdiansah; herlinda, herlinda; kasmawaru, kasmawaru
TRANSFORMASI Vol 21, No 1 (2025): TRANSFORMASI
Publisher : STMIK BINA PATRIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56357/jt.v21i1.432

Abstract

The rapid growth of TikTok as a digital marketing platform has created a need to understand how content variation influences user purchasing behavior. This study is motivated by the lack of information regarding audience responses to live streaming content, particularly in the context of purchase decision-making. The objective of this research is to identify audience segmentation patterns on TikTok based on content preferences and how these relate to purchasing decisions, using the account @takiboutique as a case study. A quantitative research approach was employed, utilizing an online survey distributed to 99 randomly selected respondents. Data were analyzed using the K-Means clustering algorithm to group respondents based on dominant factors influencing their buying decisions. The clustering results revealed three main audience segments. The first cluster (53%) prioritizes creative and interactive marketing strategies. The second cluster (34%) considers price as the most influential factor in purchasing decisions. The third cluster (12%) highlights product quality as the primary consideration. These findings indicate that audience preferences for promotional content are diverse, requiring marketing communication strategies to be tailored to the characteristics of each segment. The application of the K-Means algorithm has proven effective in profiling consumers to support more adaptive and targeted digital marketing strategies.
Co-Authors Ahmad Ahmad Ardimansyah Ardimansyah Asran, Asran Herlinda Herlinda, Herlinda Husain Husain Irmawati Irmawati Iskandar, Syamsul Bhahri Marsa, Marsa Nurdiansah, Nurdiansah RACHMAT RACHMAT Santi Santi Suherwin, Suherwin T, Husain