Article Per Year (5 Year)
p-Index From 2021 - 2026
3.939
P-Index
This Author published in this journals
All Journal JSI: Jurnal Sistem Informasi (E-Journal) Sinkron : Jurnal dan Penelitian Teknik Informatika JITK (Jurnal Ilmu Pengetahuan dan Komputer) Techno Nusa Mandiri : Journal of Computing and Information Technology Jurnal Nasional Komputasi dan Teknologi Informasi Jurnal Riset Informatika JISICOM (Journal of Information System, Infomatics and Computing) Jurnal Mantik JATI (Jurnal Mahasiswa Teknik Informatika) Jurnal Scientia Computer Science (CO-SCIENCE) PROSISKO : Jurnal Pengembangan Riset dan observasi Rekayasa Sistem Komputer Innovative: Journal Of Social Science Research Jurnal Multidisiplin Sahombu Jurnal Pengabdian Masyarakat dan Riset Pendidikan
Desmulyati, Desmulyati
Universitas Bina Sarana Informatika
Aerospace Engineering Arts Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Mechanical Engineering Neuroscience Public Health Transportation Other

Published : 33 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 33 Documents
Search

 1   2   3   4 
Classification of Payment Patterns for Toyota Car Sales Using the Decision Tree Algorithm Siregar, Martua Hami; Saiyar, Hafdiarsya; Desmulyati, Desmulyati; Noviansyah, Mohammad
Jurnal Multidisiplin Sahombu Vol. 5 No. 04 (2025): Jurnal Multidisiplin Sahombu, May - Juny (2025)
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Car sales represent a business sector highly dependent on the implementation of appropriate payment strategies to enhance customer satisfaction and operational efficiency. This study aims to classify payment patterns in Toyota car sales using the Decision Tree algorithm. Historical sales data were utilized to identify various attributes influencing payment methods, such as cash, credit, or leasing.Through processes of preprocessing, feature selection, and model training, the Decision Tree algorithm successfully established clear classification patterns based on variables such as payment type, gender, car type, and car category. The research findings indicate that the Decision Tree method not only provides a high level of accuracy in classifying payment patterns but also produces models that are easily interpretable by business decision-makers. Thus, the implementation of this classification technique is expected to assist companies in designing more effective and targeted sales and promotional strategies.
Identification E-SIM for Motorcycle Security Using Atmega 8 Microcontroller Saiyar, Hafdiarsya; Desmulyati, Desmulyati
Jurnal Riset Informatika Vol. 5 No. 1 (2022): December 2022
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v5i1.182

Abstract

Motorcycle theft is getting more disturbing, so it encourages the author to make security devices on motorbikes. This study has created a security system that can secure motorcycles using an e-SIM based on the Atmega-8 Microcontroller. Where the e-SIM has a chip, the chip itself has 7 bytes. In this case, the authors take advantage of the 7-byte chip in the e-SIM. The e-SIM will replace the motorcycle ignition key. Not only that, but the e-SIM will also give orders to the motor starter to start the motorcycle. Thus, only the owner of the e-SIM who already has a sim can give the motorcycle ON and OFF orders. The research method used is direct observation of the selected object, namely the author's home environment, and conducting literature studies related to the Atmega-8 microcontroller. This study aims to create a security system for motorcycle vehicles to avoid theft and the use of motorcycles for children without driving licenses.
Sistem Pengendali Pintu Garasi Mobil Menggunakan Sensor Reed Switch dan RFID Berbasis Mikrokontroler ATMega Saiyar, Hafdiarsya; Noviansyah, Mohammad; Desmulyati, Desmulyati; Siregar, Martua Hami
Innovative: Journal Of Social Science Research Vol. 4 No. 2 (2024): Innovative: Journal Of Social Science Research
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/innovative.v4i2.10345

Abstract

Dalam kehidupan, banyak hal dilakukan di dalam dan di luar ruangan, bahkan kegiatan tersebut tidak terlepas dari keberadaan pintu dimana kita harus membuka atau menutup pintu yang membuat kita merasa enggan melakukannya, secara berulang masuk dan keluar pintu dengan menarik atau mendorong pintu. Melihat kondisi bahwa sebagian besar proses operasi pintu garasi mobil masih dilakukan secara manual di mana intervensi manusia masih terlibat secara langsung, maka akan lebih praktis dan efisien jika pintu garasi dapat membuka sendiri. Oleh karena itu, semakin kompleks proses yang harus diatasi, semakin penting penggunaan sistem minimum ATMega16 untuk memfasilitasi proses tersebut, oleh karena itu penulis terinspirasi untuk membuat Merancang dan Membangun Pengendalian Pintu Mobil Menggunakan Sensor Reed Switch dan Mikrokontroler Berbasis RFID ATMega16. Alat ini berfungsi untuk secara otomatis membuka dan menutup pagar dengan input sensor yang terperinci. Jika kendaraan memiliki pengirim, secara otomatis sistem minimum akan menerima gangguan dari sensor dan akan memberi perintah atau melanjutkan membuka pagar secara otomatis.
Implementasi DeepFace dan OpenCV untuk Prediksi Umur dan Jenis Kelamin Berdasarkan Citra Wajah: Penelitian GF, M. Iqbal; Khadafi, Amar; Satrio W, Aryo; Fani, Dzattho Key; Budiawan, Imam; Desmulyati, Desmulyati
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4956

Abstract

The development of Artificial Intelligence technology in the field of facial image processing has encouraged the emergence of various methods for automatically analyzing human attributes. This study implements the DeepFace and OpenCV libraries to detect faces and predict age and gender based on human facial images. DeepFace provides integration with various pre-trained models such as VGG-Face, OpenFace, and DeepID so that the analysis process can be carried out without retraining. This study uses several stages starting from image upload, face detection, facial attribute analysis, and visualization of the prediction results. From the tests conducted, the system successfully identified faces stably and provided relatively accurate age and gender estimates, especially in images with sufficient lighting and frontal facial poses. The results of this study indicate that DeepFace can be used as a practical solution in the development of facial image-based biometric systems.
Analisa Prediksi Kelulusan Mahasiswa Menggunakan Metode Machine Learning: Penelitian Walya, Abdul Khalik; Sulistyo, Hasbi Rizki; Pratama, Ibnu Agustian; Akmal, Sifatul; Budiawan, Imam; Desmulyati, Desmulyati
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4959

Abstract

Student graduation prediction is an important issue in higher education as it is closely related to the evaluation of academic success. Various machine learning algorithms have been applied to predict student graduation based on academic data. This study conducts a comparative analysis of three classification algorithms, namely Logistic Regression, Random Forest, and K-Nearest Neighbor, using a simulated dataset consisting of 200 student records with attributes including age, department, GPA, and graduation year. The research stages include data preprocessing, data splitting, model training, and performance evaluation using classification metrics. Experimental results indicate that Logistic Regression and Random Forest achieve the best performance with an accuracy of 100%, while the K-Nearest Neighbor algorithm attains an accuracy of 80%. These findings highlight that data characteristics and algorithm selection significantly affect the accuracy of student graduation prediction.
CLAHE-Enhanced YOLOv8: Deteksi Pelanggaran Helm Real-Time pada Citra CCTV Low-Light: Penelitian Wijaya, Devin Nurman; Ariyanto, Dedy; Bintang S.N, Prasetyo; Cecilia P, Levina; Budiawan, Imam; Desmulyati, Desmulyati
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4964

Abstract

Low lighting conditions in CCTV images cause a decrease in the accuracy of the Electronic Traffic Law Enforcement (E-TLE) system, especially in detecting helmet use among motorcyclists. Dark images with low contrast and high noise hinder the feature extraction process, so that deep learning-based detection models often produce False Negatives. This study proposes the integration of the Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing method with the YOLOv8 architecture to improve the performance of helmet violation detection in low-light environments. The Helmet Detection dataset is used with the addition of synthetic low-light augmentation to simulate variations in nighttime lighting intensity. Tests show that the use of CLAHE can significantly improve the quality of visual features, as evidenced by the increase in Mean Average Precision (mAP@0.5) from 72.4% in raw images to 89.1% after preprocessing. In addition, the system is still able to operate in real-time with an average speed of 35–37 FPS on a Tesla T4 GPU. These results indicate that the integration of CLAHE and YOLOv8 is effective in improving the reliability of helmet violation detection in low-light conditions and is feasible to be implemented in computer vision-based traffic surveillance systems.
Analisa Komparasi Kinerja Algoritma K-Nearest Neighbor (K-NN) dan Decision Tree dalam Klasifikasi Situs Web Phising: Penelitian Prasetyo, Fajar Dwi; Maulana, Muhammad; Ramadhan, Faris; Setiabudi, Ananda Lutfi; Budiawan, Imam; Desmulyati, Desmulyati
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4965

Abstract

Phishing attacks represent a significant cybersecurity threat aimed at stealing sensitive user information through psychological manipulation using fake websites. Conventional detection methods relying on blacklists are considered ineffective in recognizing zero-day attacks or newly published phishing sites. This study aims to develop an automated detection model using a Machine Learning approach by comparing the performance of two Supervised Learning algorithms: K-Nearest Neighbor (K-NN) and Decision Tree. The dataset used is sourced from the UCI Machine Learning Repository, consisting of 11,055 records with 30 URL characteristic features. Performance evaluation was conducted using Accuracy metrics and Confusion Matrix analysis. Experimental results indicate that the Decision Tree algorithm significantly outperforms K-NN with an accuracy of 95.21%, while K-NN achieved an accuracy of only 60.11%. Furthermore, Decision Tree demonstrated a very low False Negative rate, making it a more recommended model for real-time cybersecurity system implementation.
Analisis Pengelompokan Pola Pembayaran UKT Mahasiswa Menggunakan Algoritma K-Means Clustering: Penelitian Desmulyati, Desmulyati; Budiawan, Imam; Andrianto, Feri; Canavaro, Reafael Andrian; Nugroho, Muhammad Haikal; Saputra, Sofiyan Aris
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4967

Abstract

Single Tuition Fee (UKT) plays a crucial role in financing higher education, but late and arrear payments are often difficult to analyze manually. This study aims to classify student UKT payment patterns using the K-Means algorithm based on per capita income, UKT amount, lateness, lateness category, and total arrears. The data used were 300 cleaned and standardized students. The number of clusters was determined using the Elbow and Silhouette Score methods, with the best results at k = 3 (SSE = 524.06; Silhouette Score = 0.5609). The three clusters include high-income students with regular payments, low-income students with minor delays, and high-risk students with large delays and arrears. These results help universities map UKT payment risks and develop more targeted collection and relief policies.
Analisa Prediksi Mahasiswa Penerima KIP-K menggunakan Algoritma Naive Bayes: Penelitian Desmulyati, Desmulyati; Mulyono, Muhammad Jadetz; Maulana, Amriandry; Raihan, Muhammad Ibnu; Sumitra, Ridwan Sholeh; Mukhtar, Ali
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4969

Abstract

The Indonesia Pintar–Kuliah card (KIP-K) program is a government-funded educational assistance initiative aimed at supporting financially disadvantaged students. The selection process requires accurate data analysis to ensure that the assistance is distributed appropriately. This study aims to develop a classification model for predicting KIP-K recipients using the Naive Bayes algorithm based on several attributes, including family income, number of dependents, housing condition, parents’ occupation, social assistance status, GPA, attendance, and income per capita. A dataset of 200 student records was preprocessed and encoded before the model was trained using an 80:20 train–test split. The model’s performance was evaluated through accuracy, precision, recall, and F1-score metrics. The results indicate that the Naive Bayes algorithm achieves satisfactory classification performance, with an accuracy score of (insert your model accuracy). These findings highlight the potential of machine learning techniques to support a more objective and efficient selection process for KIP-K recipients.
Analisis Kepuasan Pelanggan terhadap Beberapa Produk yang di Jual di E-Commerce Menggunakan Metode Naïve Bayes dan Logistic Regression: Penelitian Alam, Java Diovanka; Ramdhan, Musyaffa; Rafael, Muhammad Yuzakki Raja; Hamka, Muhammad Faiz; Desmulyati, Desmulyati; Budiawan, Imam
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 3 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 3 (Januari 202
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i3.4970

Abstract

Customer satisfaction is a crucial element that plays a significant role in the sustainability of businesses in the e-commerce sector. Reviews provided by consumers serve as an important source of information to assess how satisfied they are with the products they purchased. This study aims to evaluate customer satisfaction levels using product review data through two classification methods: Multinomial Naive Bayes and Logistic Regression. The data used comes from a real Indonesian-language dataset that includes review texts and buyer ratings. The research process consists of several stages, starting from text preprocessing, feature extraction using the TF-IDF method, satisfaction label grouping, model training, and evaluation using metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The findings of this study indicate that both methods can predict customer satisfaction with competitive accuracy. Logistic Regression demonstrates more consistent results compared to Naive Bayes in the context of Indonesian-language text. These results can be utilized by e-commerce companies to monitor product quality and continuously improve services for consumers.
Co-Authors Agus Irawan Akmal, Sifatul Alam, Java Diovanka Andi Taufik ARIYANTO, DEDY Balqis, Aisyah Shinta Bintang S.N, Prasetyo Budiman, Ade Surya Canavaro, Reafael Andrian Cecilia P, Levina Chaerullah Fadli Fadlil, Galih Min Fahrani, Deny Wahyu Fahrizal Fahrizal Fani, Dzattho Key Febriyanto Febriyanto Feri Andrianto Fitria Purwaningsih GF, M. Iqbal Hafdiarsya Saiyar Hafdiarsya Saiyar Hafdiarsya Saiyar, Hafdiarsya Hafid, Shabrina Auliya Zahra Hamka, Muhammad Faiz Imam Budiawan Imam Sujarwo Khadafi, Amar Martua Hami Siregar Maulana, Amriandry Maulidia, Nahya Faulya Mohammad Noviansyah Muhammad Ihsan Muhammad Maulana Mukhtar, Ali Mulyono, Muhammad Jadetz Nico Hadipratama Nugroho, Muhammad Haikal Perdana Putra, Muhammad Rizki Prasetyo, Fajar Dwi Pratama, Ibnu Agustian Rafael, Muhammad Yuzakki Raja Raihan, Muhammad Ibnu Ramadhan, Faris Ramadhina Fajriani, Rieka Ramdhan, Musyaffa Rizky Apriansyah Hadi Rizky Fauzi Salsabila, Khalisa Saputra, Sofiyan Aris Satrio W, Aryo Setiabudi, Ananda Lutfi Sulistyo, Hasbi Rizki Sumitra, Ridwan Sholeh Syahrul Suci Romadhon Try Budi Septiandoko Wahyudi Wahyudi Walya, Abdul Khalik Wardhana, Ade Ikhsanudin Setiawan Wijaya, Devin Nurman Wirahman, Raihan Putra