Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Jurnal Mantik Jurnal Teknoinfo
Deny Kurniawan
Universitas Bina Sarana Informatika
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
OPTIMIZATION OF THE NUMBER OF CLUSTERS ON K-MEDOIDS USING CHEBYCHEV AND MANHATTAN ON GOLD SELLING GROUPING Dedi Triyanto; Deny Kurniawan; Mochamad Wahyudi
Jurnal Mantik Vol. 5 No. 3 (2021): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

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

Abstract

Gold is a type of precious metal that can maintain value and can be used for exchange. Gold has attractive properties, so many people like to buy gold for jewelry and also for investments that can be resold when they need money quickly. During the COVID-19 pandemic, some sales sectors experienced a decline but gold was still selling well. M. Siregar Gold Shop serves gold jewelry sales. Gold jewelery sales transactions at the M. Siregar gold shop are stored in the database. Every day the transaction data is increasing, so the data is getting more and more. From the mountains of data we can dig up information or generate knowledge. M. Siregar's gold shop has difficulty in knowing the type of gold that is selling well, making it difficult for gold shop owners to determine the right gold supply. This study aims to classify gold sales at the M. Sisregar gold shop so that it is known which types of gold are selling well. This grouping uses the K-Medoids method with the calculation of the distance between the Chebychec distance and the Manhanttan distance. The data is taken from the sales of gold at the M. Siregar store from November 2021 to March 2022. To produce an optimal grouping, this grouping is tested with several number of clusters by calculating the distance between Chebycev distance and Manhattan distance by calculating the DBI value of each number of clusters. . The result of the optimal grouping of gold sales is the K-Medoids method with the calculation of the Chebycev distance with the number of clusters = 2 with DBI value = 0.024.ns.
COMPARISON OF EUCLIDEAN DISTANCE, CAMBERRA DISTANCE, AND CHEBYCHEV DISTANCE IN K-MEANS ALGORITHM BASED ON DBI EVALUATION Deny Kurniawan; Dedi Triyanto; Mochamad Wahyudi
Jurnal Mantik Vol. 5 No. 4 (2022): February: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

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

Abstract

During the COVID-19 pandemic, almost all businesses experienced difficulties. But not all businesses experience difficulties. Cosmetics is a product category that still exists during the pandemic. Many customers buy cosmetics through online sales. Devi Cosmetics is a trading business which is engaged in selling cosmetics. Due to the large number of sales transactions recorded in the neglected database, it is difficult for business managers to find out which cosmetic products are in high demand by customers and make it difficult for business managers to determine the inventory of cosmetic goods correctly. Determination of the incorrect supply of cosmetics resulted in the loss of the store manager, namely many customers who canceled buying cosmetics due to empty supplies. This study uses the K-Means algorithm to classify sales of cosmetic goods. To find out the best grouping results, it is necessary to compare several distance calculation methods. The distance calculation method here uses three methods, namely Euclidean Distance, Camberra Distance, and Chebychev Distance by finding the DBI value of the three methods. The smallest DBI value is the chebychev distance calculation method with a DBI value = 0.254.
SISTEM PERINGATAN DINI KANTUK PENGEMUDI MENGGUNAKAN MODEL YOLOV11N BERBASIS CITRA WAJAH Adi Supriyatna; Deny Kurniawan; Mochamad Wahyudi; Lise Pujiastuti; Sumanto Sumanto; Dedi Triyanto
Jurnal Teknoinfo Vol. 19 No. 2 (2025): July 2025 Period
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/teknoinfo.v19i2.732

Abstract

Kecelakaan lalu lintas akibat kantuk saat mengemudi merupakan salah satu penyebab utama kematian di jalan raya dan menjadi isu keselamatan yang krusial. Studi menunjukkan bahwa 20–30% kecelakaan disebabkan oleh pengemudi yang mengantuk, sehingga diperlukan sistem peringatan dini yang mampu mendeteksi kondisi ini secara akurat dan real-time. Penelitian ini bertujuan untuk mengembangkan model deteksi kantuk berbasis visi komputer menggunakan algoritma YOLOv11n, yang dikenal sebagai varian ringan dan cepat dari keluarga YOLO. Model dilatih menggunakan dataset citra wajah yang telah diproses dan diaugmentasi melalui platform Roboflow, dengan tujuan untuk mendeteksi tanda-tanda kantuk secara visual. Hasil evaluasi model menunjukkan performa yang sangat baik, dengan nilai mAP50 sebesar 0,9710 dan mAP50-95 sebesar 0,6796. Selain itu, precision mencapai 0,9382 dan recall sebesar 0,9280, yang mengindikasikan kemampuan deteksi yang tinggi serta tingkat kesalahan yang rendah. Temuan ini membuktikan bahwa YOLOv11n dapat diimplementasikan secara efektif dalam sistem peringatan dini untuk meningkatkan keselamatan pengemudi, bahkan pada perangkat dengan sumber daya terbatas. Penelitian ini tidak hanya menjawab tantangan efisiensi dan akurasi deteksi kantuk, tetapi juga memberikan kontribusi nyata bagi pengembangan sistem keselamatan kendaraan berbasis kecerdasan buatan. Ke depan, pengembangan sistem deteksi multimodal yang menggabungkan citra wajah dengan data fisiologis seperti EOG dan detak kepala disarankan untuk meningkatkan keandalan sistem dalam kondisi nyata.
KOMPARASI ALGORITMA K-NEAREST NEIGHBOR, SUPPORT VECTOR MACHINE, DAN NEURAL NETWORK UNTUK KLASIFIKASI PENYAKIT DAUN JERUK Deny Kurniawan; Dedi Triyanto; Mochamad Wahyudi; Lise Pujiastuti; Sumanto Sumanto; indra Chaidir
Jurnal Teknoinfo Vol. 19 No. 2 (2025): July 2025 Period
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/teknoinfo.v19i2.751

Abstract

Jeruk merupakan salah satu buah tropis yang banyak dikonsumsi masyarakat karena kandungan nutrisinya yang tinggi, khususnya vitamin C. Namun, produksi jeruk kerap mengalami penurunan akibat serangan penyakit, terutama pada bagian daun. Identifikasi penyakit secara manual dinilai kurang efisien dan rawan kesalahan, sehingga diperlukan sistem otomatis berbasis machine learning untuk membantu proses deteksi secara cepat dan akurat. Penelitian ini bertujuan untuk membandingkan tiga algoritma klasifikasi K-Nearest Neighbor (KNN), Support Vector Machine (SVM), dan Neural Network (NN) dalam mengidentifikasi penyakit daun jeruk berdasarkan fitur tekstur. Dataset yang digunakan terdiri dari lima kategori: Black Spot, Canker, Greening, Melanose, dan Healthy, dengan total 609 citra daun yang dibagi secara proporsional untuk pelatihan dan pengujian. Hasil evaluasi menunjukkan bahwa model Neural Network memberikan performa terbaik dengan akurasi 87,5%, diikuti oleh SVM sebesar 82,4%, dan KNN sebesar 77,5%. Penelitian ini menunjukkan bahwa pendekatan machine learning, khususnya Neural Network, efektif dalam klasifikasi penyakit daun jeruk dan berpotensi untuk diimplementasikan lebih lanjut dalam bentuk aplikasi praktis bagi petani.
Co-Authors Adi Supriyatna Dedi Triyanto Dedi Triyanto Indra Chaidir, Indra Lise Pujiastuti Lise Pujiastuti Mochamad Wahyudi Sumanto, Sumanto