Claim Missing Document
Check
Articles

Found 14 Documents
Search

Optimalisasi Feature Selection Untuk Mendeteksi Penyakit Diabetes Mellitus Menggunakan Metode Decision Tree Pameka, Aplea; Heriansyah, Rudi; Widya Astuti, Lastri
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 16 No 2 (2024): Jurnal Penelitian Ilmu dan Teknologi Komputer (JUPITER)
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.13283676

Abstract

Diabetes mellitus type 2 is a health problem with a high prevalence rate throughout the world. The International Diabetes Federation (IDF) in the West Asia Pacific region consists of 20 countries, of which Indonesia is a member. In the world, 536.6 million people have diabetes and 206 million in the West Asia Pacific region. Until 2045, this number will continue to increase to 260 million in the West Asia Pacific Region and as many as 783.7 million diabetes sufferers worldwide. An unhealthy lifestyle causes diabetes, so it is found that people with diabetes no longer come from older people. Machine learning has been widely used to recognize several disease patterns as an initial detection effort. The machine learning accuracy matrix can be improved using a decision tree algorithm by adding improvements to the feature selection process using information gain. This research uses several attributes that are thought to have information on detecting diabetes mellitus. Five features with the highest scores were obtained using the Information Gain method in the feature subset selection process. Next, the Decision Tree classification algorithm is applied to a subset of selected features, and applying the Decision Tree algorithm using information gain increases accuracy by 96.25%. It is hoped that the results of this research can reduce the number of people with diabetes.   Keywords— Detection, Diabetes Mellitus, Feature Selection, Information Gain, Decision Tree
PEMBINAAN DAN PENINGKATAN SKALA USAHA IRT-UM MELALUI PEMANFAATAN PEWARNA ALAM BENANG, KAIN DAN PURUN PADA KELOMPOK USAHA PERAJIN DI DESA BURAI, KECAMATAN TANJUNG BATU, KABUPATEN OGAN ILIR, SUMATERA SELATAN Setiawan, Herri; Viatra, Aji Windu; Dhamayanti; Febriyanti, Doris; Heriansyah, Rudi; Setiawan, Budi; Lestari, Sylvia Dwi
Jurnal Abdimas Mandiri Vol. 9 No. 1
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jam.v9i1.5307

Abstract

Penguatan usaha Industri Rumah Tangga Usaha Mikro (IRT-UM) menjadi bagian strategis dalam membangun ekonomi rakyat yang berdaya saing dan berkelanjutan. Keberhasilan usaha tersebut sangat bergantung pada keterampilan dan pengetahuan para pelaku usaha. Program Pembinaan Industri Rumah Tangga Usaha Mikro berbasis Kemitraan ini bertujuan untuk meningkatkan kapasitas usaha mitra IRT-UM Burai Indah dan Purun Warna Warni (Purwani) di Desa Burai, Tanjung Batu, Ogan Ilir, melalui pelatihan di berbagai aspek, seperti tata kelola kelembagaan, manajemen keuangan, digital marketing, branding, packaging produk, fotografi produk, serta produksi pewarna alami. Program ini melibatkan 40 peserta perajin kain songket dan purun dengan metode kombinasi penyampaian materi dan praktik langsung. Hasil program menunjukkan bahwa, baik dalam Pelatihan Digital Marketing, Tata Kelola Kelembagaan dan Manajemen Keuangan, maupun Branding dan Packaging yang dilaksanakan terhadap Mitra Burai Indah dan Purwani di Desa Burai menunjukkan hasil yang signifikan dalam meningkatkan kapasitas pengetahuan dan keterampilan peserta. Evaluasi kuisioner sebelum dan sesudah pelatihan memperlihatkan adanya peningkatan yang konsisten pada berbagai aspek, seperti tata kelola kelembagaan, manajemen keuangan, digital marketing, branding, packaging, serta fotografi produk, dimana pada masing-masing pelatihan memiliki hasil kuesioner yang secara konsisten menunjukan hasil skala diatas 4,0 (Sangat Memahami), baik pada Mitra Burai maupun Perwani. Dengan peningkatan skala produksi dan efisiensi biaya, produk mitra memiliki potensi untuk menjangkau pasar yang lebih luas, termasuk pasar global, sehingga berdampak positif terhadap perekonomian lokal serta keberlanjutan lingkungan.
Similarity Identification Model of Thesis Titles with Mahalanobis Distance Approach Fajri Munawar, Muhammad; Heriansyah, Rudi; Irfani, Muhammad Hafiz; Jambak, Muhammad Ikhwan; Ferano, Dwi Asa
Jurnal Software Engineering and Computational Intelligence Vol 3 No 01 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i01.5413

Abstract

This study aims to identify the similarity of thesis titles by applying the Mahalanobis Distance method which is known to be effective in measuring the distance between vectors by considering data distribution and correlation between variables. In its implementation, each thesis title is represented in vector form using the TF-IDF scheme before calculating the level of similarity using Mahalanobis Distance. The test results show that this method is able to produce similarity values between titles, but its performance has not shown optimal effectiveness in the context of similarity classification. The highest precision value obtained of 1.0 indicates that this method is quite reliable in identifying pairs of titles that are truly similar. However, the low recall value of only 0.5 indicates that there are many pairs of similar titles that fail to be detected, resulting in an F1-score value of only 0.638. This shows an imbalance between the system's ability to detect similarity and its classification accuracy. Although the accuracy value is relatively high, ranging from 0.958 to 0.988, these results do not necessarily reflect the overall effectiveness of the method in handling minor classification errors. Testing of the threshold parameters also shows that a value of 0.1 provides the best performance compared to other threshold values because it is able to maintain a balance between precision, recall, F1-score, and accuracy.
ANALISIS PREDIKSI TERHADAP PENINGKATAN TINDAK PIDANA DENGAN METODE NAIVE BAYES BERDASARKAN LAPORAN KRIMINALITAS Dwi Kurniawan, Budi; Heriansyah, Rudi; Romegar Mair, Zaid
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 3 (2025): JATI Vol. 9 No. 3
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i3.13620

Abstract

Kriminalitas merupakan permasalahan sosial yang terus berkembang dan memerlukan analisis mendalam untuk memahami pola serta faktor yang memengaruhinya. Polres PALI Polda Sumsel menghadapi tantangan dalam mengidentifikasi tren kriminalitas guna merancang strategi pencegahan yang lebih efektif. Penelitian ini menerapkan metode Naïve Bayes, yang dikenal dalam klasifikasi berbasis probabilistik, untuk menganalisis serta memprediksi peningkatan tindak pidana. Data laporan kriminalitas dari Polres PALI digunakan untuk mengklasifikasikan angka kriminalitas berdasarkan faktor utama, seperti jumlah kasus dan tingkat pengangguran. Evaluasi model dilakukan menggunakan classification report, mencakup akurasi, precision, recall, dan F1-score. Hasil analisis menunjukkan bahwa wilayah dengan tingkat pengangguran tinggi cenderung mengalami peningkatan kriminalitas. Model Naïve Bayes terbukti efektif dalam mendeteksi pola kriminalitas, terutama dalam kategori pencurian berat, dengan akurasi mencapai 90%. Model ini memiliki recall 1.00 dalam mendeteksi peningkatan kriminalitas, tetapi kurang akurat dalam mengklasifikasikan penurunan angka kejahatan (recall 0.67). Metode ini dapat digunakan sebagai alat bantu dalam analisis prediksi angka kriminalitas, karena memiliki kecepatan dan efisiensi tinggi.
Performance Evaluation of YOLOv10 and YOLOv11 on Blood Cell Object Detection Dataset Džakula, Nebojša Bačanin; Heriansyah, Rudi; Fadly, Fadly
International Journal of Advances in Artificial Intelligence and Machine Learning Vol. 2 No. 2 (2025): International Journal of Advances in Artificial Intelligence and Machine Learni
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/ijaaiml.v2i2.434

Abstract

Background of study:  Blood cell analysis is vital for diagnosing medical conditions, but traditional manual methods are laborious and error-prone. Deep learning, especially YOLO models, offers automated solutions for medical image analysis. However, the real-world effectiveness of the latest YOLOv11 in blood cell detection is not thoroughly investigated, as general object detection improvements may not translate to biomedical images due to their unique characteristics.Aims and scope of paper: This study systematically compares YOLOv10 and YOLOv11 on a public blood cell detection dataset to assess if YOLOv11's advancements provide tangible benefits for blood cell classification. The goal is to identify the most effective model for accurate and efficient detection in microscopic images, guiding AI-driven diagnostic tool selection.Methods: Both models were trained and tested under identical conditions using the Kaggle Blood Cell Detection Dataset (RBCs, WBCs, Platelets). Images were resized to 640x640 pixels. Performance metrics included mAP (mAP@50 and mAP@50–95), Precision, Recall, F1-score, speed, model complexity, and training time.Result: YOLOv11n consistently showed higher accuracy (mAP50: 0.9279 vs. 0.9120; mAP50-95: 0.6524 vs. 0.6347), particularly for RBCs and WBCs. However, YOLOv11n had longer inference (11.35 ms/image) and postprocessing times (8.64 ms/image) compared to YOLOv10n (7.00 ms/image and 0.90 ms/image). YOLOv11n trained faster (0.311 hours vs. 0.375 hours), with a smaller model size (5.5 MB vs. 5.8 MB), fewer parameters, and reduced computational complexity.Conclusion: YOLOv11n offers superior accuracy and improved training efficiency, making it suitable for medical image object detection where precision is paramount. The increased inference and postprocessing times indicate a performance-speed trade-off. Model selection should balance these factors based on deployment context.
Pengenalan Pola Huruf Bahasa Isyarat Menggunakan Framework You Only Look Once (YOLO) JABAR, Tri Ahmad Jabar; Heriansyah, Rudi; Purnamasari, Evi
JURNAL FASILKOM Vol. 15 No. 2 (2025): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v15i2.10018

Abstract

Bahasa isyarat merupakan bentuk komunikasi visual yang penting bagi penyandang disabilitas rungu wicara. Namun, masih banyak masyarakat yang belum memahami Sistem Isyarat Bahasa Indonesia (SIBI), sehingga menimbulkan hambatan komunikasi. Penelitian ini bertujuan untuk mengembangkan sistem pengenalan huruf bahasa isyarat SIBI menggunakan framework You Only Look Once (YOLO). Data citra huruf dikumpulkan dari tangan penulis, dianotasi menggunakan Roboflow, dan dilatih dengan algoritma YOLOv11. Hasil deteksi huruf tidak hanya dikenali secara individu, tetapi juga disusun menjadi kalimat secara real-time melalui input kamera menggunakan pemrosesan sekuens huruf. Model terbaik menunjukkan nilai precision sebesar 0,835, recall 0,928, serta mean Average Precision (mAP) dengan mAP@50 (IoU 50%) sebesar 0,968 dan mAP@50–95 (rata-rata pada berbagai ambang IoU) sebesar 0,774. Sistem juga mencapai akurasi rata-rata 0,831 dan F1-score sebesar 0,865 dalam pengenalan huruf. Pada pengujian real-time, sistem berhasil menyusun kalimat sederhana “VINA SEDANG MAKAN” dengan akurasi 86,6%. Hasil ini membuktikan bahwa sistem tidak hanya mampu mendeteksi huruf, tetapi juga dapat merangkai huruf menjadi kalimat bermakna. Penelitian ini diharapkan dapat memberikan kontribusi nyata dalam pengembangan teknologi inklusif yang dapat menjembatani komunikasi antara penyandang disabilitas rungu wicara dengan masyarakat umum, serta berpotensi diimplementasikan dalam bidang pendidikan, pelayanan publik, maupun aplikasi sehari-hari
Detection of Palembang Jumputan Cloth Motifs Using Canny Edge Detection Method and Rule-Based Classifier Remustin, Rivky; Heriansyah, Rudi; Mair, Zaid Romegar
Golden Ratio of Mapping Idea and Literature Format Vol. 6 No. 1 (2026): July - January
Publisher : Manunggal Halim Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52970/grmilf.v6i1.1701

Abstract

Palembang jumputan cloth has a distinctive motif, which is part of the heritage culture of Indonesia. However, process identification motif is still done manually, requiring high accuracy and being prone to errors. This study aims to build an automatic detection system for Jumputan fabric motifs using the Canny Edge Detection method to extract borders and a Rule-Based Classifier for motif classification based on the number, area, and contour density features. This study uses 750 fabric images from five types of motifs: Tiga Negeri, Titik Tujuh, Tabur, Lereng, and Ecoprint. The images are processed through grayscale conversion, histogram smoothing, and Canny edge detection. The results of feature extraction are used to classify motifs using logical rules. Based range, mark each feature. Evaluation done with a confusion matrix and produces an accuracy rate of 54%, which shows that this method is quite Good as an approach, beginning, however, still needs improvement so that More accurate classification results. The system has also been implemented in a GUI interface for practical use.
Perbandingan Algoritma Decision Tree dan Support Vector Machine Dalam Pemilihan Calon Mahasiswa Penerima KIP-K Kanaka, Nayaka Al Syahreal; Heriansyah, Rudi; Puspasari, Shinta
TIN: Terapan Informatika Nusantara Vol 4 No 9 (2024): February 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v4i9.4902

Abstract

KIP Kuliah is tuition assistance from the government for high school / equivalent graduates who have good academic potential but have economic limitations. There are many things that should be considered by universities before selecting prospective students who receive KIP Lecture so that selection can be done using machine learning and classification algorithms. In this research, two machine learning algorithms will be used including: Decision Tree and Support Vector Machine (SVM). Furthermore, these two algorithms will be tested and compared the final results. Both algorithms have different results. The highest level of accuracy, precision, recall, and F1 score is 100%. This value can be achieved by the Decision Tree algorithm because the dataset used is suitable for it to solve. Therefore, the Decision Tree algorithm is recommended to be used in selecting KIP College student candidates.
Penjadwalan Mata Pelajaran Menggunakan Metode Dynamic Programming (Studi Kasus SD Negeri 1 Babat Toman) Riyanti, Rizki; Heriansyah, Rudi; Ramadhan, Mustafa
Jurnal Pengembangan Sistem Informasi dan Informatika Vol. 5 No. 1 (2024): Jurnal Pengembangan Sistem Informasi dan Informatika
Publisher : Training & Research Institute - Jeramba Ilmu Sukses

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47747/jpsii.v5i1.1730

Abstract

Student subject scheduling is the process of selecting the optimal schedule for each student based on the availability of teacher Student subject scheduling is selecting the optimal schedule for each student based on the availability of teacher schedules, teacher teaching hours, and subjects adjusted to grade levels. Many methods, including the Dynamic Programming method, can be used to solve this problem. Dynamic Programming is an optimization method that solves problems into smaller sub-problems and saves sub-problem solutions to avoid resolving. In scheduling student subjects, this method can select the optimal schedule by solving problems into smaller subproblems. Using Dynamic Programming allows scheduling student subjects to be done more efficiently and quickly. Overall, using dynamic programming to schedule student subjects provides a better and more efficient solution than other methods. Therefore, this method benefits schools or educational institutions that want to create an optimal lesson schedule for their students.  
Pemanfaatan Canva untuk Guru Sekolah Dasar sebagai Media Penyusunan Materi. Permatasari, Indah; Sartika, Dewi; Heriansyah, Rudi; Saluza, Imelda
Reswara: Jurnal Pengabdian Kepada Masyarakat Vol 5, No 2 (2024)
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/rjpkm.v5i2.4347

Abstract

Di sekolah, saat ini telah memanfaatkan teknologi untuk menyampaikan informasi pembelajaran kepada peserta didik. Selain faktor infrastuktur dan pemahaman penggunaan internet, peningkatan pada kemampuan para pendidik dalam memberikan materi juga perlu diperhatikan. Pengembangan materi yang menyesuaikan pemanfaatan teknologi dirasa akan menjadi modal penting untuk tetap menarik perhatian peserta didik agar tetap berminat belajar secara mandiri. Modal materi inilah yang saat ini sering dibuat bervariasi karena harus bersaing dengan era generasi peserta didik yang lebih tertarik dengan teknologi. Dengan tujuan untuk memberikan pemahaman kepada para pendidik/Guru agar dapat membuat materi dengan tampilan yang lebih menarik hanya dengan memanfaatkan aplikasi Canva, tim PkM mengusulkan diperlukan kegiatan pelatihan. Metode workshop dipilih sebagai solusi agar dapat berinteraksi langsung dengan para pendidik selain pemberian pelatihan. Hasil dari kegiatan menunjukkan sebanyak 13 peserta belum pernah menggunakan aplikasi Canva serta sebanyak 22 peserta merasa tertarik dengan aplikasi Canva. kegiatan workshop ini sebagai bagian dari pengabdian masyarakat (PkM) telah diselesaikan dengan baik dan dapat disimpulkan bahwa saat ini kegiatan dianggap penting dilakukan karena masih rendahnya jangkauan pemahaman peserta/Guru terkait beberapa aplikasi pendukung penyusunan materi pembelajaran