Article Per Year (5 Year)
p-Index From 2021 - 2026
7.974
P-Index
This Author published in this journals
All Journal International Journal of Advances in Applied Sciences IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Pendidikan Fisika Undiksha Jurnal Pendidikan Teknologi dan Kejuruan Prosiding Seminar Nasional MIPA Wahana Matematika dan Sains Jurnal Sains dan Teknologi Jurnal Simetris Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Sistem dan Informatika Mimbar Pendidikan: Jurnal Indonesia untuk Kajian Pendidikan KLIK (Kumpulan jurnaL Ilmu Komputer) (e-Journal) Sinkron : Jurnal dan Penelitian Teknik Informatika JUTIK : Jurnal Teknologi Informasi dan Komputer JITK (Jurnal Ilmu Pengetahuan dan Komputer) JOURNAL OF APPLIED INFORMATICS AND COMPUTING PROCESSOR Jurnal Ilmiah Sistem Informasi, Teknologi Informasi dan Sistem Komputer SINTECH (Science and Information Technology) Journal Jurnal Teknik Informatika UNIKA Santo Thomas Jurnal Serambi Engineering Jurnal RESISTOR (Rekayasa Sistem Komputer) International Journal of Community Service Learning Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Riset Informatika Jurnal Ilmiah Sinus Jurnal Teknologi Informasi dan Pendidikan Jurnal Mantik Jurnal Teknologi Informasi dan Terapan (J-TIT) JURNAL ILMU KOMPUTER INDONESIA Jurnal Teknologi Informasi dan Multimedia Bali Medika Jurnal Indonesian Journal of Electrical Engineering and Computer Science INFOKUM Journal of Computer Networks, Architecture and High Performance Computing Jurnal Teknik Informatika (JUTIF) J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Info Sains : Informatika dan Sains Jurnal Teknik Informatika Unika Santo Thomas (JTIUST) Malcom: Indonesian Journal of Machine Learning and Computer Science INOVTEK Polbeng - Seri Informatika
I Gede Aris Gunadi
Universitas Pendidikan Ganesha
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Nursing Physics Public Health Social Sciences Other

Published : 84 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 84 Documents
Search

 4   5   6   7   8 
Analisis Hyperparameter Pada Klasifikasi Jenis Daging Menggunakan Algoritma Convolutional Neural Network Dinata, I Made Anom Mahartha; Gunadi, I Gede Aris; Sunarya, I Made Gede
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 8, No 1 (2024): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v8i1.763

Abstract

In the context of food and economy, meat plays a vital role in fulfilling the nutritional needs of society and serves as a strategic economic commodity. However, the difficulty in distinguishing between beef and pork often leads to fraud by meat traders. Particularly in Indonesia, where the consumption of beef and pork is high, this confusion raises significant concerns, especially since pork is prohibited in the Islamic religion. This research aims to address this issue by applying Artificial Intelligence technology, specifically the Convolutional Neural Network (CNN) deep learning method in classifying images of beef, pork, and mixed meat. The study utilizes a dataset of 410 samples, with 70% used for training and 30% for testing. Testing is conducted using a basic CNN model with hyperparameter analysis such as image size, number of epochs, and batch size. Additionally, the dataset is tested using a comparative architecture, namely the ResNet-50 architecture. The best accuracy rate of the CNN model is 82.20%, achieved with an image size of 75 x 75 pixels, 100 epochs, and a batch size of 64. Testing with the ResNet-50 architecture yields the highest accuracy of 76.14%. Evaluation is performed using a confusion matrix with four categories: Accuracy, Precision, Recall, and F1 Score.
Kombinasi Oversampling dan Undersampling dalam Menangani Class Imbalanced dan Overlapping pada Klasifikasi Data Bank Marketing Erlangga, Anak Agung Gde Wahyu Sukma; Gunadi, I Gede Aris; Sunarya, I Made Gede
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol. 7 No. 1 (2024): Jurnal RESISTOR Edisi April 2024
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/jurnalresistor.v7i1.1515

Abstract

Class imbalance can occur in various types of datasets, one of which is bank marketing datasets. The class imbalance can cause classification problems. To handle the problem, the SMOTE method can be used. However, the application of SMOTE can cause class overlapping and interfere with classification performance. Therefore, this research will try to handle it by combining the SMOTE method with undersampling methods consisting of ENN, NCL, and TomekLink. The classification algorithm used is Logistic Regression and the performance evaluation uses sensitivity, specificity, and g-means of the model. The results show that the SMOTE-ENN combination produces the most optimal results with sensitivity, specificity, and g-means of 94.05%, 83.22%, and 88.47% respectively on bank marketing datasets, while on credit card fraud datasets it has almost uniform results with sensitivity, specificity, and g-means ranging from 88.62%, 97.59%, and 93.00%. Finally, on cerebral stroke datasets, SMOTE-ENN produces the highest sensitivity at 80.1%, the highest specificity on SMOTE-NCL at 75.62%, and the highest g-means on SMOTE at 77.03%.
Analisis Hyperparameter Pada Klasifikasi Jenis Daging Menggunakan Algoritma Convolutional Neural Network Dinata, I Made Anom Mahartha; Gunadi, I Gede Aris; Sunarya, I Made Gede
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 8, No 1 (2024): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v8i1.763

Abstract

In the context of food and economy, meat plays a vital role in fulfilling the nutritional needs of society and serves as a strategic economic commodity. However, the difficulty in distinguishing between beef and pork often leads to fraud by meat traders. Particularly in Indonesia, where the consumption of beef and pork is high, this confusion raises significant concerns, especially since pork is prohibited in the Islamic religion. This research aims to address this issue by applying Artificial Intelligence technology, specifically the Convolutional Neural Network (CNN) deep learning method in classifying images of beef, pork, and mixed meat. The study utilizes a dataset of 410 samples, with 70% used for training and 30% for testing. Testing is conducted using a basic CNN model with hyperparameter analysis such as image size, number of epochs, and batch size. Additionally, the dataset is tested using a comparative architecture, namely the ResNet-50 architecture. The best accuracy rate of the CNN model is 82.20%, achieved with an image size of 75 x 75 pixels, 100 epochs, and a batch size of 64. Testing with the ResNet-50 architecture yields the highest accuracy of 76.14%. Evaluation is performed using a confusion matrix with four categories: Accuracy, Precision, Recall, and F1 Score.
Klasifikasi Kualitas Biji Kopi Robusta Dengan Metode Naive Bayes berdasarkan Ukuran Biji, Tekstur, dan Warna Putra, I Kadek Nurcahyo; Gunadi, I Gede Aris; Sunarya, I Made Gede
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 15, No 1 (2024): JURNAL SIMETRIS VOLUME 15 NO 1 TAHUN 2024
Publisher : Fakultas Teknik Universitas Muria Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24176/simet.v15i1.10790

Abstract

Kopi merupakan salah satu komoditas terpenting di dunia, lebih dari dua juta gelas kopi di konsumsi setiap hari. Kualitas kopi bergantung pada serangkaian proses, dan sortasi merupakan proses yang sangat penting untuk mensegmentasi biji kopi sesuai kualitas. Biji kopi yang tercampur menyebabkan rusaknya rasa, menurunkan kualitas, dan harga. Sortasi biji dengan cara manual rentan mengalami kesalahan disebabkan turunnya konsentrasi serta subjektivitas manusia. Pada penelitian ini penulis mengimplementasi algoritma Naive Bayes untuk membangun model klasifikasi kualitas biji kopi robusta berdasarkan fitur warna RGB, fitur tekstur dengan metode GLCM, dan fitur ukuran biji kopi robusta. Biji kopi robusta diperoleh dari CV. Kaki Lima Solid sejumlah 300 gram untuk setiap kualitas. Biji kopi difoto untuk menghasilkan citra biji kopi. Citra biji kopi di pre-proses selanjutnya di lakukan ekstraksi fitur warna, tekstur, dan ukuran biji. Dataset hasil ekstraksi fitur di bagi menjadi dua bagian, 480 data digunakan untuk melatih algoritma Naive Bayes. Pengujian model klasifikasi dengan 120 data uji memperoleh hasil akurasi 87.5%. Komparasi fitur dan metode klasifikasi lain pada masa depan dapat dilakukan untuk memperoleh hasil yang lebih baik.
Perbandingan Metode Analisis Sentimen Pelayanan Daring di Fakultas Teknik dan Kejuruan Universitas Pendidikan Ganesha Menggunakan Algoritma Naïve Bayes dan LSTM: Sentiment Analysis of Online Services at the Engineering and Vocational Faculty of Ganesha Education University Using Naïve Bayes and LSTM Algorithms Saputri, Ni Kadek Tesya Ari; Gunadi, I Gede Aris; Sunarya, I Made Gede
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 3 (2024): MALCOM July 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i3.1336

Abstract

Salah satu fakultas di Univesitas Pendidikan Ganesha yaitu Fakultas Teknik dan Kejuruan (FTK) yang menerapkan pelayanan daring di masa pandemi COVID-19. Berbagai komentar muncul saat dilakukan pelayanan daring ini sehingga perlu dilakukannya sebuah analisis. Mahasiswa memberikan pendapat positif dan negatif. Untuk menganalisis komentar mahasiswa menggunakan metode Naive Bayes dan Long Short-Term Memory (LSTM). Data yang digunakan merupakan informasi yang diperoleh dari penyebaran angket yang diisi oleh mahasiswa FTK. Evaluasi matriks konfusi termasuk akurasi, presisi, recall, dan f-measure. Penelitian ini bertujuan untuk membandingkan kedua metode Naive Bayes dan LSTM serta mendeteksi kata-kata yang sering muncul pada pelayanan daring FTK dengan membandingkan stopword yang dikumpulkan pada saat pemrosesan kuesioner. Menguji keakuratan metode klasifikasi Naïve Bayes dan hasilnya adalah 83,69%. Hasil klasifikasi metode LSTM mencapai akurasi sebesar 53,12%. Nilai akurasi LSTM yang dihasilkan sangat rendah. Mungkin alasan utamanya adalah hanya komentar positif yang terbaca saat mencoba metode LSTM. Penyebab lainnya yaitu dataset yang juga dapat mempengaruhi. Dengan membandingkan kinerja Naive Bayes dan LSTM, diperoleh hasil yang menunjukkan metode Naïve Bayes lebih unggu untuk menganalisis komentar mahasiswa FTK Undiksha.
Improving k-nearest neighbor performance using permutation feature importance to predict student success in study Jana Satvika, Gd. Aditya; Sukajaya, I. N.; Gunadi, I Gede Aris
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i3.pp1835-1844

Abstract

The timely graduation of students is a critical indicator of academic quality assessment. Therefore, universities should use effective predictive systems to identify earlier potential lateness of graduation. This study aimed to improve the K-nearest neighbor (K-NN) algorithm’s ability to predict student on-time graduation. It evaluated K-NN algorithm performance with and without the permutation feature importance (PFI) technique, using a dataset of 460 student graduation records from 2014 to 2017. The training data was oversampled, adjusting the ratio of minority class samples from 13% to 100% of the majority class samples. The result shows that integrating PFI into the K-NN model improved K-NN performance by 10 iterations of the PFI process, N-shuffle varying from 10 to 100 for each iteration, and a minority class sample ratio of 25%. The accuracy score improved from 90.22% to 92.39%, precision from 50.00% to 62.50%, F1-score from 52.63% to 58.82%, while recall remained consistent at 55.56%. The PFI analysis showed that achievement index for the 1st semester or IPS 1 had the least impact on the model. The study suggested using a comprehensive approach to determine the n-shuffle of PFI based on the number of test data for a more accurate feature contribution pattern.
Analysis of the implementation of the scheduling and tracking project application at CV. Emporio architect Pathni, Ida Ayu Wisma Anggaritha; Gunadi, I Gede Aris; Sunarya, I Made Gede
Jurnal Info Sains : Informatika dan Sains Vol. 14 No. 01 (2024): Informatika dan Sains , Edition March 2024
Publisher : SEAN Institute

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

Abstract

CV. Emporio Architect make a Scheduling and Tracking Project application is created to help employee performance in scheduling a project. However, the implementation in the field had not met expectations, where each division made its own schedule and kept it individually, so that there was no transparency in the performance of the inter-divisional relay teams. This was because many divisions did not use the applications provided by the company. From the background description above, it is necessary to identify the factors that influence the use of Scheduling and Project Tracking applications on CV. Emporio Architect. The aim of this research is to analyze the implementation of the Scheduling and Tracking Project application by identifying factors that influence the use of the application using the TOE Framework research model and quantitative methods with data collection techniques through questionnaires, interviews and observation. The population in this study consisted of 58 respondents, and the data analysis was conducted using validity tests, reliability tests, multiple linear regression analysis, and hypothesis testing. The data testing was processed with the help of  SPSS software. The research results identified that the variables of technology and organization did not significantly affect the implementation of the application, leading to the ineffectiveness of the application implementation at CV. Emporio Architect, as expected. However, the environmental variable had a significant influence according to the conditions at CV. Emporio Architect. The suggested recommendation is that the company improves from both technological and organizational aspects so it can be better at preparing for implementing scheduling and project tracking applications at CV. Emporio Architect.
ANALYSIS OF WEBQUAL 4.0 AND COGNITIVE WALKTHROUGH METHODS ON CTI GOVIDEO SPARK HIRE ONLINE INTERVIEW APPLICATION Apriyanthi, Ni Putu Eka; Gunadi, I Gede Aris; Sunarya, I Made Gede
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024 - SENIKO
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2198

Abstract

This study aims to analyze the user experience quality of the CTI GoVideo Spark Hire online interview application, focusing on Safaga Indonesia institution. The research methodology employs Webqual 4.0 analysis and Cognitive Walkthrough as frameworks for evaluating application quality. Respondents were selected using Simple Random Sampling, and data were analyzed using reliability and internal consistency tests. The findings from the Webqual 4.0 analysis indicate that the majority of respondents rated the application positively, with 73% considering its quality to be good and 27% rating it as excellent. Internal consistency tests revealed overall high reliability, although the interaction variable showed relatively low values. Analysis using the Cognitive Walkthrough method revealed that 8 respondents were able to complete approximately 92.8% of the total 7 given task scenarios, with an average completion time of around 446 seconds or 7 minutes 26 seconds for all tasks. This evaluation holds significant relevance to Safaga Indonesia's need to enhance recruitment process efficiency.
COMPARISON OF PROFILE MATCHING AND MOORA METHODS IN DETERMINING LOAN ELIGIBILITY Wayan Eka Ariawan; Gede Indrawan; I Gede Aris Gunadi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 2 (2024): JITK Issue November 2024
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i2.5608

Abstract

The objective of this research is to analyze the comparison between the profileimatching method and MOORA in supporting decision-making for loan approvals at the Widya Dharma Student Cooperative (KOPMA). The criteria used in this research include basic salary, length of service, loan duration, membership status, loan amount, and number of dependents. These two methods are compared based on their accuracy levels. The accuracy levels are obtained through testing with the Mean Average Precision (MAP) technique, which measures the accuracy in ranking. The testing is conducted by comparing the ranking results from the method calculations with the rankings from the KOPMA chairman. The analysis results show that the Profile Matching method has a higher accuracy rate, which is 67.83%, compared to the MOORA method, which has an accuracy rate of 45.46%. Besides method testing, system testing was also conducted using the User Acceptance Test (UAT) technique. The UAT results indicate that the developed system aligns with the business processes in determining loan eligibility, the menu layout and contents within the system are well-organized, the system features function properly and are easy to understand, and the system meets expectations.
A Comparative Study on the Impact of Feature Selection and Dataset Resampling on the Performance of the K-Nearest Neighbors (KNN) Classification Algorithm Gunadi, I Gede Aris; Rachmawati, Dewi Oktofa
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol. 13 No. 2 (2024)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v13i2.82174

Abstract

This study aims to evaluate the impact of dataset balancing and feature selection on the performance of the K-Nearest Neighbors (KNN) classification algorithm. The primary objective is to determine the effect of different training data balance ratios on classification performance. Additionally, the study analyzes the contribution of feature selection methods and data balancing to the overall performance of the classification algorithm. Three datasets (Titanic, Wine Quality, and Heart Diseases) sourced from Kaggle, were utilized in this research. Following the preprocessing stage, the datasets were subjected to three resampling scenarios with balance ratios of 0.3, 0.6, and 0.9. Feature selection was performed by combining correlation test values and information gain values, each weighted at 50%. The selected features were those with positive combined values of summation, correlation, and information gain. The KNN classification algorithm was then applied to datasets with and without feature selection. The results indicate that achieving a perfectly balanced ratio (ratio = 1) is not essential for improving classification performance. A balance ratio of 0.6 yielded results comparable to those of a perfect balance ratio. Furthermore, the findings demonstrate that feature selection has a more significant impact on classification performance than data balancing. Specifically, data with a balance ratio of 0.3 and feature selection outperformed data with a balance ratio of 0.6 but without feature selection.
Co-Authors ., Ketut Suma ., Putu Sonia Virgawati Pratiwi Adi Sista, Dewa Nyoman Agus Ariwanta, I Putu Yesha Agus Gunawan Agus Harjoko Agus Harjoko Agus Harjoko Ahmad Asroni Ahmad Asroni, Ahmad Anandita, Ida Bagus Gede Andiny T T Arditaloka, I Wayan Angga Ariasa, Komang Ariyani, Putu Wendy Artama, Made Bella Eka Wahyuningtias Cipta, I Putu Agus Eka Yatna Cokorda Oka Birawidya David Juli Ariyadi Dewa Gede Hendra Divayana, Dewa Gede Hendra Dewi Oktofa Rachmawati Dharmana, I Wayan Diatmika, I Ketut Agus Indra Dinata, I Made Anom Mahartha Erlangga, Anak Agung Gde Wahyu Sukma Fauzi, Muhammad Rizki Galih Cahyaningsih, Agung Ukki Gede Indrawan Hajrin, M. Heryanto, I Wayan Agus I Ketut Paramarta I Made Candiasa I Made Gede Sunarya I Made Pradipta I Nyoman Sukajaya I Nyoman Wahyu Semeru Putra I Putu Agus Eka Yatna Cipta I Putu Aris Sanjaya I Putu Aris Sanjaya, I Putu Aris I Putu Dody Suarnatha I Putu Putra Damana I Wayan Agus Heryanto I Wayan Gede Suweca Antara I Wayan Pio Pratama I Wayan Rosiana I Wayan Sadia I Wayan Santyasa I Wayan Sukra Ida Ayu Mirah Cahya Dewi Jana Satvika, Gd. Aditya Kadek Yota Ernanda Aryanto Ketut Suma Ketut Suma . Ketut Suma . Komang Ariasa Komang Setemen Luh Joni Erawati Dewi Luh Putu Budi Yasmini Luh Rumni Oktaria M. Hajrin M.Cs S.Kom I Made Agus Wirawan . Made Artama Made Wahyu Aditya Arta Made Windu Antara Kesiman Made Windu Segara Mahendra, I Gusti Agung Putu Matius Ivan Bimasena Mimin Yeli Sholekah Moh. Heri Setiawan MS Prof. Dr. Ketut Suma . N Dinda Maharani Ni ketut Lisa Maheni Ni Komang Rai Mirayanti NI LUH PUTU MANIK WIDIYANTI Ni Made Yeni Dwi Rahayu Ni Putu Eka Apriyanthi Nugraha, I Gede Pradipta Adi Nugraha, I Gusti Agung Satria Oktaria, Luh Rumni Pathni, Ida Ayu Wisma Anggaritha pramana, i gede pramana ade saputra Prof. Dr. Ketut Suma, MS . Putra, I Kadek Nurcahyo Putra, I Made Arya Adinata Dwija Putra, I Nyoman Wahyu Semeru Putra, I Putu Arya Putu Eka Parianthana Putu Sonia Virgawati Pratiwi . Rai Sujanem Risha, Nurfa Sandhiyasa, I Made Subrata Saputri, Ni Kadek Tesya Ari Sariyasa Sariyasa Sariyasa Sariyasa Sawitri D U Segara, Made Windu Sidik, Purnama Sisilia Fhelly Djun Sonia Dewi Parna.T Sri Hartati Suputra, I Putu Arsana Suryawan, I Made Yuda Sutarno, Erwan Sutarno, Erwan Suweca Antara, I Wayan Gede T, Andiny T U, Sawitri D Wardana, I Komang Tri Edi Wayan Eka Ariawan Yogi Duwi Antara