Article Per Year (5 Year)
p-Index From 2021 - 2026
4.232
P-Index
This Author published in this journals
All Journal JUITA : Jurnal Informatika Jurnal Informatika dan Teknik Elektro Terapan Sinkron : Jurnal dan Penelitian Teknik Informatika Bina Insani ICT Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Pilar Nusa Mandiri Information System for Educators and Professionals : Journal of Information System JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Teknik Informatika UNIKA Santo Thomas Jurnal Riset Informatika Journal of Information System, Applied, Management, Accounting and Research JASIEK (Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer) JURSIMA (Jurnal Sistem Informasi dan Manajemen) Jurnal Sistem Informasi Jurnal AbdiMas Nusa Mandiri Jurnal ABDIMAS (Pengabdian kepada Masyarakat) UBJ HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Computer Science (CO-SCIENCE) Indonesian Journal of Networking and Security - IJNS Jurnal Teknik Informatika Unika Santo Thomas (JTIUST) Paradigma Jurnal Insan JURSIMA Jurnal Sistem Informasi dan Manajemen
Herlambang Brawijaya
Universitas Bina Sarana Informatika
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Physics Social Sciences Other

Published : 35 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 35 Documents
Search

 1   2   3   4 
PENGEMBANGAN APLIKASI ESTIMASI KALORI MAKANAN BERBASIS CITRA DENGAN PENDEKATAN DETEKSI OBJEK MENGGUNAKAN YOLO Supriyadi, Rizqy; Irfan, Muhamad; Hapijar, Rizki Dwi; Abubakar, Fadil; Saputra, Rendy; Supriyanto, Kus; Dwiantara, Raihan Putra; Nainggolan, Esron Rikardo; Brawijaya, Herlambang
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.8545

Abstract

Penelitian ini mengembangkan aplikasi estimasi kalori makanan berbasis citra untuk membantu pengguna memantau asupan energi secara praktis melalui foto ponsel. Sistem menggunakan deteksi objek YOLOv8n untuk mengenali makanan Indonesia dan memetakan tiap deteksi ke parameter nutrisi guna menghitung massa dan kalori. Dataset pelatihan berisi 3.772 citra pada 9 kelas makanan (dibagi 80% latih, 10% validasi, 10% uji). Model dilatih selama 100 epoch pada resolusi 640 piksel menggunakan optimizer AdamW dan early stopping. Backend FastAPI dalam lingkungan Docker menjalankan inferensi dan perhitungan kalori berdasarkan data nutrisi tiap kelas. Aplikasi mobile Flutter mengirim citra ke endpoint /predict dan menampilkan makanan terdeteksi beserta confidence, estimasi massa, dan total kalori. Hasil uji menunjukkan performa deteksi tinggi dengan mAP@0.5 0,975, sementara kesalahan terbesar terjadi pada kelas yang mirip secara visual atau minim data. Temuan ini menegaskan bahwa sistem end-to-end mampu mengestimasi kalori otomatis dari satu foto dan layak dikembangkan lebih lanjut dengan menambah kelas dan menyeimbangkan dataset.
PENERAPAN KECERDASAN BUATAN DALAM SISTEM PENGENALAN GERAK TANGAN UNTUK MENDUKUNG KOMUNIKASI PADA PENYANDANG TUNAWICARA: APPLICATION OF ARTIFICIAL INTELLIGENCE IN A HAND GESTURE RECOGNITION SYSTEM TO SUPPORT COMMUNICATION FOR PEOPLE WITH SPEECH IMPAIRMENTS Ardiansyah, Rija; Zamroni, Rio; Azhar, Muhammad; Mahesa, Kevin Indra; Reza, Syaiful Fan; Arkananta, Yudhistira; Nainggolan, Esron Richardo; Brawijaya, Herlambang
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 17 No. 1 (2026): Jurnal HOAQ - Teknologi Informasi
Publisher : STIKOM Uyelindo Kupang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol17no1.p53-61

Abstract

Perkembangan teknologi kecerdasan buatan (AI) telah mendorong peningkatan signifikan dalam interaksi antara manusia dan mesin, khususnya dalam menyediakan akses komunikasi yang lebih baik bagi individu dengan gangguan bicara. Penelitian ini mengusulkan sebuah sistem penerjemah Bahasa Isyarat Indonesia (BISINDO) berbasis computer vision yang mengintegrasikan deteksi landmark tangan secara real-time menggunakan MediaPipe dengan proses klasifikasi gestur berbasis Convolutional Neural Network (CNN). Sistem ini dirancang untuk mengenali pola gerakan tangan secara dinamis dan mengubahnya menjadi teks atau suara sintetis melalui modul Google Text-to-Speech (gTTS). Pendekatan yang digunakan menggabungkan analisis spasial dan temporal untuk menghasilkan interpretasi gestur yang akurat dan responsif terhadap konteks. Penelitian ini juga mengidentifikasi tantangan implementasi terkait kemampuan generalisasi model terhadap perbedaan pengguna, kondisi pencahayaan, dan lingkungan, serta menawarkan solusi melalui teknik augmentasi data dan optimalisasi arsitektur jaringan saraf. Dengan desain yang fleksibel dan adaptif, sistem ini memiliki potensi besar untuk menjadi dasar pengembangan teknologi bantuan komunikasi inklusif berbasis AI di Indonesia serta mendorong kolaborasi antara bidang visi komputer, bahasa isyarat, dan teknologi Internet of Things (IoT).   Advances in artificial intelligence (AI) technology have driven significant improvements in human–machine interaction, particularly in enhancing communication accessibility for individuals with speech impairments. This study proposes an Indonesian Sign Language (BISINDO) interpreter system based on computer vision, integrating real-time hand landmark detection using the MediaPipe framework with gesture classification powered by a Convolutional Neural Network (CNN). The system is designed to dynamically recognize hand gesture patterns and convert them into text or synthetic speech through the Google Text-to-Speech (gTTS) module. This approach combines spatial and temporal analysis to produce accurate and contextually responsive gesture interpretations. The study also identifies implementation challenges related to the model’s generalizability across different users, lighting conditions, and environments, while offering solutions through data augmentation techniques and neural network architecture optimization. With its flexible and adaptive design, the proposed system has strong potential to serve as a foundation for the development of AI-based inclusive communication technologies in Indonesia and to foster collaboration across the fields of computer vision, sign language, and Internet of Things (IoT) applications.
Hybrid Sampling untuk Meningkatkan Akurasi Deteksi Kanker Serviks pada Data Tidak Seimbang: Kajian Komparatif Slamet Widodo; Samudi; Herlambang Brawijaya
JASIEK (Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer) Vol. 7 No. 2 (2025): Desember 2025
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jasiek.v7i2.16134

Abstract

Cervical Cancer has a high mortality rate among women, driving the adoption of early detection systems based on machine learning. However, their implementation is hindered by class imbalance issues, as seen in the UCI Cervical Cancer Behavior Risk Dataset, where positive cases constitute only 5.8–7.3% of the data. This study proposes an evaluation of resampling techniques—including SMOTE, ADASYN, Random Undersampling, and Borderline-SMOTE—combined with classification algorithms such as RF, XGBoost, LR, GNB, and k-NN. Using Stratified K-Fold Cross Validation to preserve the original class distribution in each fold and ensuring resampling is applied only to the training data in each iteration, the results demonstrate that Borderline-SMOTE significantly improved model performance. Specifically, the Random Forest model achieved a Recall of 0.87 and an AUC-ROC of 0.94. These findings are expected to provide a foundation for future research focused on optimizing adaptive sampling methods
Implementation of PDDIKTI Neo Feeder Web Service in Recording of Independent Campus Activities Herlambang Brawijaya; Slamet Widodo; Samudi Samudi
Jurnal Riset Informatika Vol. 5 No. 2 (2023): March 2023
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v5i2.210

Abstract

Independent Learning-Independent Campus Program (MBKM) is a policy of granting the right for students to be able to take study activities outside the study program as many as three semesters with the division of two semesters of study outside the college and one semester in different study programs in one college. As well as teaching and learning activities, universities must report Independent Learning-Independent Campus activities to DIKTI every semester through the Neo Feeder PDDIKTI application. The Neo Feeder PDDIKTI application has a feature to enter the activities the operator will carry out. The operator enters this data individually on the Neo Feeder PDDIKTI application. This is a significant problem because the data entry process will take quite a lot of time, even though PDDIKTI has provided web service access to universities to optimize the data reporting process using the Neo Feeder PDDIKTI application. Building an application that can be used for recording MBKM activities by utilizing web services provided by PDDIKTI is the primary purpose of this study. The development of an application certainly requires a method as a framework or guide in facilitating the manufacturing process. The extreme Programming (XP) method becomes essential for applications with variable or non-fixed needs. This method has four working elements: planning, designing, coding, testing and software increment. The output generated by this study is an application for recording MBKM activities that use web service restful API technology so that data entry can be done en masse and not one by one.
Optimasi Naïve Bayes Untuk Analisa Sentimen Pengguna Transportasi Online Menggunakan TF-IDF Brawijaya, Herlambang; Samudi; Widodo, Slamet
Jurnal INSAN Journal of Information System Management Innovation Vol. 6 No. 1 (2026): Juni 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/j-insan.v6i1.12707

Abstract

Perkembangan layanan transportasi online mendorong meningkatnya jumlah ulasan pengguna pada media sosial yang dapat dimanfaatkan untuk mengetahui tingkat kepuasan pelanggan. Penelitian ini bertujuan untuk mengoptimalkan algoritma Naïve Bayes pada analisis sentimen pengguna transportasi online menggunakan teknik seleksi fitur Term Frequency–Inverse Document Frequency (TF-IDF). Dataset penelitian diperoleh dari Facebook, Twitter, dan Instagram dengan total 2.019 ulasan pengguna. Tahapan penelitian meliputi data harvesting, preprocessing teks berupa data cleaning, case folding, tokenization, stopword removal, stemming, serta pembobotan kata menggunakan TF-IDF. Selanjutnya, proses klasifikasi dilakukan menggunakan algoritma Naïve Bayes untuk mengelompokkan sentimen ke dalam kategori positif, netral, dan negatif. Hasil penelitian menunjukkan bahwa sentimen negatif mendominasi sebesar 84,77%, sedangkan sentimen positif dan netral masing-masing sebesar 9,28% dan 5,78%. Penerapan TF-IDF mampu meningkatkan kualitas fitur teks sehingga proses klasifikasi menjadi lebih optimal pada data tidak terstruktur. Penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan metode analisis sentimen serta menjadi bahan evaluasi bagi transportasi online dalam meningkatkan kualitas layanan kepada pengguna
Co-Authors - UBSI, Slamet Abubakar, Fadil Ardiansyah, Rija Arkananta, Yudhistira Doni Andriansyah Dwiantara, Raihan Putra Elly Mufida, Elly Endang Retnoningsih Eni Pudjiarti Eva Rahmawati Hapijar, Rizki Dwi Hikmah, Noer Hylenarti Hertyana Indah Ariyati Irfan, Muhamad Lala Nilawati Mahesa, Kevin Indra Muhammad Azhar Nainggolan, Esron Richardo Nainggolan, Esron Rikardo Noer Hikmah Rendy Saputra Reza, Syaiful Fan Rudianto, Biktra samudi Samudi Siti Faizah Slamet Widodo Slamet Widodo Slamet Widodo Supriyadi, Rizqy Supriyanto, Kus Toto Haryanto Verry Riyanto Zamroni, Rio