Article Per Year (5 Year)
p-Index From 2021 - 2026
4.242
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Teknologi dan Manajemen Informatika CommIT (Communication & Information Technology) Jurnal Edukasi dan Penelitian Informatika (JEPIN) International Journal of Advances in Intelligent Informatics Register: Jurnal Ilmiah Teknologi Sistem Informasi JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Jurnal Otomasi Kontrol dan Instrumentasi Jurnal Sisfokom (Sistem Informasi dan Komputer) INTECOMS: Journal of Information Technology and Computer Science Antivirus : Jurnal Ilmiah Teknik Informatika Journal of Information System,Graphics, Hospitality and Technology Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Journal of Electronics, Electromedical Engineering, and Medical Informatics Jurnal Teknologi Informasi dan Terapan (J-TIT) Buletin Ilmiah Sarjana Teknik Elektro Journal of Robotics and Control (JRC) Jurnal Teknika Teknika Insyst : Journal of Intelligent System and Computation JTECS : Jurnal Sistem Telekomunikasi Elektronika Sistem Kontrol Power Sistem dan Komputer International Journal of Robotics and Control Systems J-Intech (Journal of Information and Technology) Joutica : Journal of Informatic Unisla Jurnal Nasional Teknik Elektro dan Teknologi Informasi Jurnal Inovasi Teknologi dan Edukasi Teknik Journal of Information Technology
Yosi Kristian
Institut Sains Dan Teknologi Terpadu Surabaya
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Mechanical Engineering Other

Published : 45 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 45 Documents
Search

 1   2   3   4   5 
Single Objective Mayfly Algorithm with Balancing Parameter for Multiple Traveling Salesman Problem YOGA DWI WAHYU NUGRAHA; HENDRAWAN ARMANTO; YOSI KRISTIAN
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 5 No 3 (2023): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeemi.v5i3.299

Abstract

The Multiple Travelling Salesman Problem (MTSP) is a challenging combinatorial problem that involves multiple salesman visiting a set of cities, each exactly once, starting and ending at the same depot. The aim is to determine the optimal route with minimal cost and node cuts for each salesman while ensuring that at least one salesman visits each city. As the problem is NP-Hard, a single-objective metaheuristic algorithm, called the Mayfly Algorithm, inspired by the collective behavior of mayflies, is employed to solve the problem using the TSPlib95 test data. Since the Mayfly Algorithm employs a single fitness function, a balancing parameter is added to perform multiobjective optimization. Three balancing parameters in the optimization process: SumRoute represents the total cost of all salesmen travelling, StdRoute balances each salesman cost, and StdNodes balances the number of nodes for each salesman. The values of these parameters are determined based on the results of various tests, as they significantly impact the MTSP optimization process. With the appropriate parameter values, the single-objective Mayfly Algorithm can produce optimal solutions and avoid premature convergence. Overall, the Mayfly Algorithm shows promise as a practical approach to solving the MTSP problem. Using multiobjective optimization with balancing parameters enables the algorithm to achieve optimal results and avoid convergence issues. The TSPlib95 dataset provides a robust testing ground for evaluating the algorithm’s effectiveness, demonstrating its ability to solve MTSP effectively with multiple salesman.
Pemanfaatan Deep Learning pada Video Dash Cam untuk Deteksi Pengendara Sepeda Motor Stephen Ekaputra Limantoro; Yosi Kristian; Devi Dwi Purwanto
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 7 No 2: Mei 2018
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1738.3 KB)

Abstract

The number of motorcyclists in Indonesia was 105.15 million in 2016. It made the Indonesian government difficult to monitor motorcyclists on the highways. Dash cam could be used as the alternative tool to detect motorcyclists when given the intelligence. One of the typical drawbacks in detecting objects is complex and varied feature. A convolutional neural networks (CNN) that was capable of detecting motorcyclists was proposed. CNN successfully classified the ship object with f1-score of 0.94. Sliding window and heat map were used in thispaper to search the localization and region of motorcyclists. Two experiments had been done in this paper. The goal of this paper was to set the best combination of CNN architecture and parameter. The first experiment consisted of three trained weights while the second experiment consisted of one trained weight. Weight peformances against test data in experiment 1 and experiment 2 were measured using f1-score of 0.977, 0.988, 0.989, and 0.986, respectively. From the experimental results using the sliding window, experiment 2 had a lower error rate to predict motorcyclists than experiment 1 because the training data on experiment 1 contained more and various images.
Prediksi Timing Financial Distress Pada Bank Perkreditan Rakyat di Indonesia Menggunakan Machine Learning Maysas Yafi' Urrochman; Endang Setyati; Yosi Kristian
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 12, No 2: Agustus 2023
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v12i2.1219

Abstract

There is no system that can provide early warning of financial problems that threaten the operations of Rural Banks (BPR), so it is necessary to predict the timing of financial distress in BPRs in Indonesia using a two-stage classification and regression technique. Researchers used BPR financial report data in Indonesia for 4 years as a research sample, with a total of 150 Financial Ratio Data, consisting of 50 bankrupt financial ratio data and 100 non-bankrupt BPRs. Data analysis was carried out 2 years before being declared bankrupt. The target classification is divided into 5 classes: very healthy, healthy, moderately healthy, less healthy, distressed. The results of the study concluded: a two-stage classification and regression technique can be used to predict the timing of financial distress. This is evidenced by the results of the MLP Classifier classification with an accuracy rate of f1-score of 87%. The results of the evaluation of timing predictions using Random Forest Regression showed a mean absolute error of 1.8 months and a mean absolute percentage error of 4%.Keywords: Rural Banks; Financial Distress; Random Forest Regression; Support Vector MachineAbstrakBelum ada suatu sistem yang dapat memberikan peringatan dini adanya permasalahan keuangan yang mengancam operasional Bank Perkreditan Rakyat (BPR), sehingga perlu memprediksi timing financial distress pada BPR di Indonesia menggunakan teknik dua tahap klasifikasi dan regresi. Peneliti menggunakan data laporan keuangan BPR di Indonesia selama 4 tahun sebagai sampel penelitian, dengan jumlah data 150 Data Rasio Keuangan, terdiri dari 50 Data rasio keuangan Pailit dan 100 BPR tidak pailit. Analisis Data dilakukan 2 tahun sebelum dinyatakan Pailit. Target klasifikasi dibagi menjadi 5 kelas: sangat sehat, sehat, cukup sehat, kurang sehat, distress. Hasil penelitian menyimpulkan: teknik dua tahap klasifikasi dan regresi dapat digunakan untuk memprediksi timing financial distress. Ini dibuktikan dengan hasil klasifikasi MLP Classifier dengan tingkat akurasi f1-score sebesar 87%. Hasil evaluasi prediksi timing menggunakan Random Forest Regression menunjukkan hasil mean absolute error sebesar 1,8 bulan dan hasil mean absolute percentage error sebesar 4%. 
A Multi Representation Deep Learning Approach for Epileptic Seizure Detection Hermawan, Arya Tandy; Zaeni, Ilham Ari Elbaith; Wibawa, Aji Prasetya; Gunawan, Gunawan; Hendrawan, William Hartanto; Kristian, Yosi
Journal of Robotics and Control (JRC) Vol 5, No 1 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i1.20870

Abstract

Epileptic seizures, unpredictable in nature and potentially dangerous during activities like driving, pose significant risks to individual and public safety. Traditional diagnostic methods, which involve labour-intensive manual feature extraction from Electroencephalography (EEG) data, are being supplanted by automated deep learning frameworks. This paper introduces an automated epileptic seizure detection framework utilizing deep learning to bypass manual feature extraction. Our framework incorporates detailed pre-processing techniques: normalization via L2 normalization, filtering with an 80 Hz and 0,5 Hz Butterworth low-pass and high-pass filter, and a 50 Hz IIR Notch filter, channel selection based on standard deviation calculations and Mutual Information algorithm, and frequency domain transformation using FFT or STFT with Hann windows and 50% hop. We evaluated on two datasets: the first comprising 4 canines and 8 patients with 2.299 ictal, 23.445 interictal, and 32.915 test data, 400-5000Hz sampling rate across 16-72 channels; the second dataset, intended for testing, 733 icatal, 4.314 interictal, and 1908 test data, each 10 minutes long, recorded at 400Hz across 16 channels. Three deep learning architectures were assessed: CNN, LSTM, and a hybrid CNN-LSTM model-stems from their demonstrated efficacy in handling the complex nature of EEG data. Each model offers unique strengths, with the CNN excelling in spatial feature extraction, LSTM in temporal dynamics, and the hybrid model combining these advantages.  The CNN model, comprising 31 layers, yielded highest accuracy, achieving 91% on the first dataset (precision 92%, recall 91%, F1-score 91%) and 82% on the second dataset using a 30-second threshold. This threshold was chosen for its clinical relevance. The research advances epileptic seizure detection using deep learning, indicating a promising direction for future medical technology. Future work will focus on expanding dataset diversity and refining methodologies to build upon these foundational results.
Deteksi Komentar Cyberbullying Pada YouTube Dengan Metode Convolutional Neural Network - Long Short-Term Memory Network (CNN-LSTM) Albertus Josef Andika; Yosi Kristian; Esther Irawati Setiawan
Teknika Vol 12 No 3 (2023): November 2023
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v12i3.677

Abstract

Pada era digital seperti sekarang cyberbullying kerapkali terjadi di berbagai belahan dunia termasuk di Indonesia, hal ini dapat terjadi pada siapa saja dan dimana saja terutama media sosial seperti YouTube melalui fitur komentar semua pengguna yang memiliki akun dapat dengan mudah terlibat cyberbullying hanya melalui berbalas komentar. Penelitian ini bertujuan untuk melakukan deteksi adanya cyberbullying melalui pengumpulan serta pengklasifikasian komentar negatif video pada kanal YouTube dengan konten tertentu berbasis bahasa Indonesia (serta bahasa-bahasa daerah tertentu, seperti Jawa dan Surabaya) melalui metode deep-learning Convolutional Neural Network — Long Short-Term Memory Network (CNN-LSTM). Dataset komentar yang dipakai dalam penelitian dikumpulkan dengan menggunakan Application Program Interface (API) yang telah disediakan oleh Youtube secara gratis dan berbatas kuota secara kumulatif. Terkumpul data komentar total sebanyak 26.918 komentar dengan perincian 9.834 komentar terklasifikasi cyberbullying dan 17.084 komentar terklasifikasi sebagai bukan cyberbullying. Setelah dataset dipakai dalam proses training pada model CNN-LSTM dan menghasilkan sebuah model dengan nilai F1-score sebesar 0,84, model tersebut dipakai dalam sebuah API sederhana yang menerima input beberapa kalimat yang akan dideteksi konten cyberbullying dan menghasilkan output berupa JSON yang berisi hasil klasifikasi dari setiap kalimat yang akan dideteksi.
Identifikasi Kerusakan Badan Kontainer Pada Waktu Pengiriman Berdasarkan Citra CCTV Memanfaatkan YOLO dan Deep Transfer Learning Fitra Hidayah; Yosi Kristian
Teknika Vol 13 No 1 (2024): Maret 2024
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v13i1.718

Abstract

Keamanan dalam operasional pelabuhan sangat ditentukan oleh kemampuan untuk mengawasi dan melindungi kontainer, yang meskipun berperan sebagai sarana utama perlindungan, masih rentan terhadap kerusakan. Rekaman CCTV di pelabuhan tidak dapat mengenali jenis kendaraan, seperti membedakan antara truk yang membawa kontainer dan yang tidak, serta tidak mampu mendeteksi kerusakan pada kontainer secara otomatis. Dalam mengatasi masalah ini, studi ini mengembangkan sebuah sistem untuk mendeteksi kontainer dan mengklasifikasikan jenis-jenis kerusakan seperti kerusakan struktural, korosi, depos, cacat pada cat, pembengkakan, serta masalah pada pintu kontainer, dengan memanfaatkan teknik machine learning. Menggunakan pendekatan Convolutional Neural Network (CNN) yang ditingkatkan dengan metode transferslearning dari DeepsConvolutional NeuralsNetworks(DCNN), penelitian ini memberikan solusi analitis untuk citra yang diperoleh. Dataset yang terdiri dari 3000 gambar kontainer sisi depan dan belakang dikategorikan secara manual melalui platform Roboflow. Model YOLOv7 yang terlatih pada dataset tersebut mampu mendeteksi kontainer dengan Skor F1 Terboboti mencapai 90%. Untuk tahap klasifikasi kerusakan kontainer, citra yang telah di-crop berdasarkan output YOLOv7 dianalisis kembali menggunakan model EfficientNetV2S dan ConvNeXtBase. Kedua model tersebut, dengan pemanfaatan transfer learning, menunjukkan performa yang dengan Weighted Average F1 Score berturut-turut sebesar 66% dan 72%. Penelitian ini membuka jalur baru untuk peningkatan keamanan dan pemeliharaan kontainer melalui penerapan model pengenalan gambar yang inovatif di lingkungan pelabuhan.
Detection of Porang Plant Diseases and Pests (Amorphophallus Muelleri) Based on Leaf Imagery Utilizing DCNN Transfer Learning Zuhan, Miftahuz; Kristian, Yosi
Jurnal Sistem Telekomunikasi Elektronika Sistem Kontrol Power Sistem dan Komputer Vol 3 No 2: JTECS Juli 2023
Publisher : FAKULTAS TEKNIK UNIVERSITAS ISLAM KADIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32503/jtecs.v3i2.3709

Abstract

Produk olahan dari umbi tanaman porang (Amorphophallus muelleri) selalu diminati di kawasan Asia: Jepang, China, Korea, serta negara kawasan Australia. Umbi tanaman porang dapat digunakan sebagai bahan baku industri kosmetik dan juga memiliki potensi untuk mencegah berbagai penyakit manusia, karena memiliki kandungan glaukoma yang tinggi. Untuk mendapatkan umbi porang yang berkualitas baik, banyak petani menghadapi berbagai penyakit seperti penyakit busuk daun, virus mozaik (mosaik konjac) dan serangan hama pada daun tanaman porang. Dalam studi ini, diajukan sebuah arsitektur deep learning untuk klasifikasi penyakit daun pada tanaman porang. Kinerja dari model CNN Custome dibandingkan dengan model deep learning lainnya. Semua model dilatih pada kumpulan data asli dan data augmentasi dari 1000 gambar. Pendekatan Transfer Learning digunakan untuk melatih semua model deep learning. Hasil pengujian dataset menunjukkan bahwa model arsitektur EfficientNetV2M mencapai skor tertinggi dibandingkan dengan model deep learning lainnya pada dataset augmentasi dengan akurasi sebesar 98,44%. Sedang ResNet50 pada dataset asli dengan nilai 97,66% pada dataset asli, sedangkan CNN Custome dengan akurasi sebesar 89,06% dan 85,94% untuk semua dataset.
EEG-Based Lie Detection Using Autoencoder Deep Learning with Muse II Brain Sensing Hermawan, Arya Tandy; Zaeni, Ilham Ari Elbaith; Wibawa, Aji Prasetya; Gunawan, Gunawan; Hartono, Nickolas; Kristian, Yosi
International Journal of Robotics and Control Systems Vol 4, No 3 (2024)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v4i3.1497

Abstract

Detecting deception has significant implications in fields like law enforcement and security. This research aims to develop an effective lie detection system using Electroencephalography (EEG), which measures the brain's electrical activity to capture neural patterns associated with deceptive behavior. Using the Muse II headband, we obtained EEG data across 5 channels from 34 participants aged 16-25, comprising 32 males and 2 females, with backgrounds as high school students, undergraduates, and employees. EEG data collection took place in a suitable environment, characterized by a comfortable and interference-free setting optimized for interviews. The research contribution is the creation of a lie detection dataset and the development of an autoencoder model for feature extraction and a deep neural network for classification. Data preparation involved several pre-processing steps: converting microvolts to volts, filtering with a band-pass filter (3-30Hz), STFT transformation with a 256 data window and 128 overlap, data normalization using z-score, and generating spectrograms from power density spectra below 60Hz. Feature extraction was performed using an autoencoder, followed by classification with a deep neural network. Methods included testing three autoencoder models with varying latent space sizes and two types of classifiers: three new deep neural network models, including LSTM, and six models using pre-trained ResNet50 and EfficientNetV2-S, some with attention layers. Data was split into 75% for training, 10% for validation, and 15% for testing. Results showed that the best model, using autoencoder with latent space size of 64x10x51 and classifier using the pre-trained EfficientNetV2-S, achieved 97% accuracy on the training set, 72% on the validation set, and 71% on the testing set. Testing data resulted in an F1-score of 0.73, accuracy of 0.71, precision of 0.68, and recall of 0.78. The novelty of this research includes the use of a cost-effective EEG reader with minimal electrodes, exploration of single and 3-dimensional autoencoders, and both non-pretrained classifiers (LSTM, 2D convolution, and fully connected layers) and pretrained models incorporating attention layers.
Pemanfaatan Mediapipe Body Pose Estimation dan Dynamic Time Warping untuk Pembelajaran Tari Remo Effendi, Yusuf; Kristian, Yosi; P.C.S.W, Lukman Zaman; Yutanto, Hariadi
Jurnal Teknologi dan Manajemen Informatika Vol. 9 No. 2 (2023): Desember 2023
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v9i2.10408

Abstract

Video can be used as a learning medium for various purposes. In this research, the object of study is the movements of the traditional dance "remo." Thus, as a substitute for an absent coach or instructor, videos can take on the role of a dance instructor. However, video communication is one-way between the coach and the learners. Without movement correction, individuals trying to learn remo dance may find it challenging to determine if they are performing the movements correctly. Therefore, the author aims to create a system to assist coaches in correcting the dance movements of their learners. Using the MediaPipe module and the Dynamic Time Warping algorithm, the author developed a system to correct the learners' dance movements. This system can detect deviations from the coach's instructional video and provide notifications about which body angles do not match the coach's video instructions. The system operates by having users upload a video of their dance movements, and then it identifies which movements deviate from the correct remo dance. The accuracy is measured by comparing the angle distances between the master's movements and the test data. If the angle exceeds a predetermined threshold, the movement is considered incorrect. The system's output is validated by the coach, and it achieves 90% accuracy in identifying movement errors in videos. With this accuracy, the system can assist coaches in evaluating their learners' remo dance movements.
Utilization of MLP and LSTM Methods in Hero Selection Recommendations for the Game of Mobile Legends: Bang Bang Yulianto, Masrizal Eka; Kristian, Yosi
Teknika Vol. 14 No. 1 (2025): March 2025
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v14i1.1201

Abstract

Mobile Legends is one of the popular MOBA games played in real-time. The game begins with each player selecting one hero in the draft pick phase. Choosing the right hero is very important because it can affect the chances of winning. This study uses datasets from rank mode matches conducted by streamers, top global heroes, and top leaderboards in Indonesia to compare the accuracy of the MLP and LSTM methods in recommending the fifth hero for one's team. The Concatenate Layer is used in model development. Modifying the dataset was also done by reducing the number of target classes and performing data augmentation to increase data variation. The results show that LSTM excels in top-1 recommendations with an accuracy of up to 59%. Meanwhile, MLP outperforms in top-3 and top-5 recommendations, indicating that this model is more flexible in providing multiple hero alternatives. The conclusion is that players can use the LSTM method if they only want to select the best single hero. However, if players prefer a broader range of hero recommendations, the MLP method is more suitable.
Co-Authors Adriel Ferdianto Ajeng Restu Kusumastuti Aji Prasetya Wibawa Aji Wibawa Alamgunawan, Suriani Albertus Josef Andika Alwi, Luthfi Andy Hermawan Anggay Luri Pramana Anik Nur Handayani Arya Tandy Hermawan Ayyub Chastine Fatichah Citra Mahaputri Damayanti, Elok Darlis Herumurti Devi Dwi Purwanto Dhaniswara, Erwin Edwin Pramana Effendy Hadi Sutanto Eha Renwi Astuti Eka Rahayu Setyaningsih Endang Setyati Endang Setyati Esa Prakasa Esther Irawati Setiawan Fitra Hidayah Gunawan Gunawan Gunawan Gunawan Gunawan Gunawan, Riko Hariadi Yutanto Hartono, Nickolas Hatem Alsadeg Ali Salim Hendrawan Armanto Hendrawan, William Hartanto Hermawan Andika Heru Wahyu Herwanto I Ketut Eddy Purnama Irawati Setiawan, Esther Joan Santoso Kenny Vincent Kms Yusuf Effendi Kurniawan S, Putu Widiarsa Kusuma Susanto, Evan Lukman Zaman M. Najamudin Ridha Masrur Anwar Mauridhi Hery Purnomo Maysas Yafi' Urrochman Muhammad Harris Syafa'at Nafi'iyah, Nur Nur Nafi’iyah Putra, Bayu Anggara Putra, Ramadhan Hardani Putu Widiarsa Kurniawan S Retno Wardhani Sandhopi Santoso, Elkana Lewi Setiono, Kevin Setyaningsih, Eka Rahayu Shandy Darmawan Stephen Ekaputra Limantoro Surya Sumpeno Wahyu Sakti Gunawan Irianto Wahyu Widodo Wikjatmiko, Zhulfi Bajra William Sugiarto YOGA DWI WAHYU NUGRAHA Yuliana Melita Pranoto Yulianto, Masrizal Eka Yunan Kholilul Fatah Zaeni, Ilham Ari Elbaith Zuhan, Miftahuz