Article Per Year (5 Year)
p-Index From 2021 - 2026
4.915
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Techno.Com: Jurnal Teknologi Informasi TELKOMNIKA (Telecommunication Computing Electronics and Control) Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal Pengabdian UntukMu NegeRI CIRCUIT: Jurnal Ilmiah Pendidikan Teknik Elektro Seminar Nasional Teknologi Informasi Komunikasi dan Industri JITK (Jurnal Ilmu Pengetahuan dan Komputer) ALGORITMA : JURNAL ILMU KOMPUTER DAN INFORMATIKA JURNAL PENDIDIKAN TAMBUSAI IJISTECH (International Journal Of Information System & Technology) EDUMATIC: Jurnal Pendidikan Informatika Jurnal Pengabdian Kepada Masyarakat MEMBANGUN NEGERI Journal of Electronics, Electromedical Engineering, and Medical Informatics Indonesian Journal of Electrical Engineering and Computer Science Computer Science and Information Technologies Didaktik : Jurnal Ilmiah PGSD STKIP Subang Journal of Education Informatic Technology and Science Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) IJISTECH Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Computer Science and Information Technology (CoSciTech) Jurnal Pendidikan dan Teknologi Indonesia Journal of Software Engineering and Information System (SEIS) SATIN - Sains dan Teknologi Informasi Jurnal Pendidikan Dirgantara Jurnal Ilmu Komputer dan Teknik Informatika
Edi Ismanto
Universitas Muhammadiyah Riau
Religion Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Mathematics Social Sciences Other

Published : 53 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 53 Documents
Search

 1   2   3   4   5 
Pendekatan Machine Learning Dengan Menggunakan Algoritma Xgboost (Extreme Gradient Boosting) Untuk Peningkatan Kinerja Klasifikasi Serangan Syn Rahmad Gunawan Gunawan; Erik Suanda Handika; Edi Ismanto
Jurnal CoSciTech (Computer Science and Information Technology) Vol 3 No 3 (2022): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v3i3.4356

Abstract

Denial of Service (DoS) adalah salah satu serangan cyber populer yang ditargetkan pada situs web organisasi terkenal dan berpotensi memiliki biaya ekonomi dan waktu yang tinggi. Dalam makalah ini, beberapa metode pembelajaran mesin termasuk model ensemble dan pengklasifikasi deep learning berbasis autoencoder dibandingkan dan disetel menggunakan optimasi Bayesian. Kerangka autoencoder memungkinkan untuk mengekstrak fitur baru dengan memetakan input asli ke ruang baru. Metode tersebut dilatih dan diuji baik untuk klasifikasi biner dan multi-kelas pada kumpulan data Digiturk dan Labris, yang baru-baru ini diperkenalkan untuk mendeteksi berbagai jenis serangan DdoS. Semakin penting koneksi data melalui Internet membuat kebutuhan akan keamanan jaringan data semakin meningkat. Salah satu tools yang penting adalah Intrusion detection systems (IDS). Sistem Deteksi Intrusi (IDS) adalah proses pemantauan lalu lintas jaringan dalam sistem untuk mendeteksi pola dan aktivitas yang mencurigakan yang memungkinkan ada serangan dalam sistem itu. beberapa jenis serangan, yaitu Botnet, UDP, SYN, broadcast, sleep deprivation, dan serangan bertubi-tubi. klasifikasi pertama, hasilnya menunjukkan bahwa baik Precision (PR) dan Recall (RE) adalah 89% untuk Algoritma Random Forest. Akurasi rata-rata (AC) dari model yang kami usulkan adalah 89% yang luar biasa dan cukup baik. Pada klasifikasi kedua, hasilnya menunjukkan bahwa baik Precision (PR) dan Recall (RE)sekitar 90% untuk algoritma XGBoost. Akurasi rata-rata (AC) dari model yang kami sarankan adalah 90% pada dataset CICDDoS2019.
LSTM Network Hyperparameter Optimization for Stock Price Prediction Using the Optuna Framework Edi Ismanto; Vitriani Vitriani
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 9, No 1 (2023): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i1.24944

Abstract

In recent years, the application of deep learning-based financial modeling tools has grown in popularity. Research on stock forecasting is crucial to understanding how a nation's economy is doing. The study of intrinsic value and stock market forecasting has significant theoretical implications and a broad range of potential applications. One of the trickiest challenges in projects involving deep learning and machine learning is hyperparameter search. In this paper, we evaluate and analyze the optimal hyperparameter search in the long short-term memory (LSTM) model developed to forecast stock prices using the Optuna framework. We examined a number of hyperparameters with several LSTM architectures, including optimizers (SGD, Adagrad, RMSprop, Nadam, Adamax, dan Adam), LSTM hidden units, dropout rates, epochs, batch size, and learning rate. The results of the experiment indicated that of the four LSTM models tested—model 1 single LSTM, model 2 single LSTM, model 1 LSTM stacked, and model 2 LSTM stacked—model 1 single LSTM was the most effective. Single LSTM version 1 offers the lowest losses when compared to other models and had the lowest root mean square error (RMSE) score of 7.21. When compared to manual hyperparameter tuning, automatic hyperparameter tuning has lower losses and is better.
Sistem Pendukung Keputusan Penerimaan Karyawan Dengan Metode Simple Additive Weighting (SAW) Edi Ismanto; Noverta Effendi
SATIN - Sains dan Teknologi Informasi Vol 3 No 1 (2017): SATIN - Sains dan Teknologi Informasi
Publisher : STMIK Amik Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (761.608 KB) | DOI: 10.33372/stn.v3i1.208

Abstract

Universitas Muhammadiyah Riau is really need the support of technology information in order to facilitate its activities. At  the time, there are usually find a case of an error of the recruitment  process in an institution. It is also possible at Universitas Muhammadiyah Riau. It is actually depend on parties the agency that will make or break its own admission employes. Actually, the process of selecting the employee in accordance with the intelectual capability in quantity and the ability to work in accordance with its quality controlled. There are several criteria assessment in process of making decision recruitment at Universitas Muhammadiyah Riau. There assessment are based on the criteria of education, work experience, performance, test, interview, age, status, and address. The objectives to be achieved is to create a system that can help decision makers to determine the process recruitment optimally by using method of SAW (Simple Additive Weighting). The result of this research is building decision support system for acceptance new employes, and finally it can be uses as supporting for process accepting new employes.
A comparative study of machine learning algorithms for virtual learning environment performance prediction Edi Ismanto; Hadhrami Ab. Ghani; Nurul Izrin Binti Md Saleh
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 12, No 4: December 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v12.i4.pp1677-1686

Abstract

Virtual learning environment is becoming an increasingly popular studyoption for students from diverse cultural and socioeconomic backgroundsaround the world. Although this learning environment is quite adaptable,improving student performance is difficult due to the online-only learningmethod. Therefore, it is essential to investigate students' participation andperformance in virtual learning in order to improve their performance. Usinga publicly available Open University learning analytics dataset, this studyexamines a variety of machine learning-based prediction algorithms todetermine the best method for predicting students' academic success, henceproviding additional alternatives for enhancing their academic achievement.Support vector machine, random forest, Nave Bayes, logical regression, anddecision trees are employed for the purpose of prediction using machinelearning methods. It is noticed that the random forest and logistic regressionapproach predict student performance with the highest average accuracyvalues compared to the alternatives. In a number of instances, the supportvector machine has been seen to outperform the other methods.
An LSTM-based prediction model for gradient-descending optimization in virtual learning environments Edi Ismanto; Noverta Effendi
Computer Science and Information Technologies Vol 4, No 3: November 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v4i3.p199-207

Abstract

A virtual learning environment (VLE) is an online learning platform that allows many students, even millions, to study according to their interests without being limited by space and time. Online learning environments have many benefits, but they also have some drawbacks, such as high dropout rates, low engagement, and students' self-regulated behavior. Evaluating and analyzing the students' data generated from online learning platforms can help instructors to understand and monitor students learning progress. In this study, we suggest a predictive model for assessing student success in online learning. We investigate the effect of hyperparameters on the prediction of student learning outcomes in VLEs by the long short-term memory (LSTM) model. A hyperparameter is a parameter that has an impact on prediction results. Two optimization algorithms, adaptive moment estimation (Adam) and Nesterov-accelerated adaptive moment estimation (Nadam), were used to modify the LSTM model's hyperparameters. Based on the findings of research done on the optimization of the LSTM model using the Adam and Nadam algorithm. The average accuracy of the LSTM model using Nadam optimization is 89%, with a maximum accuracy of 93%. The LSTM model with Nadam optimisation performs better than the model with Adam optimisation when predicting students in online learning.
Development of Microsoft Office Virtual Reality (VR) Application with Four-D (4D) Approach Ismanto, Edi; Al Rian, Rahmad; Septian Alza
Computer Science and Information Technology Vol 5 No 1 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i1.6816

Abstract

Virtual Reality (VR) technology has made significant advancements in recent decades. With its evolving potential, VR has the capability to transform the way we learn, work, play, and interact with the world around us. The development of VR applications for Microsoft Office training holds significant relevance, especially for students of Madrasah Tsanawiyah (MTs) Darul Hikmah Pekanbaru. Microsoft Office training is essential for MTs Darul Hikmah Pekanbaru students as it serves as a practical necessity in preparing them for academic and professional endeavors. One relevant challenge is how to integrate VR technology with appropriate learning methods, such as the Four D (4D) method, to make the training experience more effective and efficient. Therefore, this research aims to identify and address these issues, as well as explore the potential of VR applications with the 4D method to enhance users' practical and intuitive Microsoft Office skills. The development of VR applications for Microsoft Office training using the Four D (4D) method, comprising the Define, Design, Develop, and Disseminate stages, has yielded highly favorable results based on comparisons of measurements from subject matter experts, media experts, and participants. From the measurement and validation results, this VR application has received high feasibility ratings. Subject matter experts rated it 100%, while media experts rated it 91.83%, and participants rated it 96% from the VR application trial.
Pengembangan Media Pembelajaran Berbasis Game Edukasi Tema 4 Tentang Bangun Ruang Di Kelas 2 SD: PENGEMBANGAN MEDIA PEMBELAJARAN BERBASIS GAME EDUKASI TEMA 4 TENTANG BANGUN RUANG DI KELAS 2 SD Bella, Bella Fitria Sari; Melly Novalia; Edi Ismanto
Computer Science and Information Technology Vol 5 No 2 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v5i2.7529

Abstract

Learning media at SD Negeri 164 Pekanbaru City refers to blackboards and books that are already available, but do not yet have effective learning strategies. Lack of student interest in learning in the teaching and learning process which is not in accordance with the current development and needs of students. With increasingly advanced and rapid technological developments, humans can create various tools to carry out activities that support productivity. Like making educational game learning media. This research aims to produce a learning media product for the snakes and ladders educational game theme 4 about building space and to determine the feasibility test, practicality and effectiveness of the educational game snakes and ladders theme 4 about building spaces in class 2 of SD Negeri 164 Pekanbaru City. The research method used is the Research and Development (R&D) research method with the ADDIE (Analysis, Design, Development, Implementation, and Evaluation) development model. In the feasibility test, an assessment is carried out by two experts, namely a media expert and a material expert to determine the suitability of the product. Where the results of the feasibility test for media experts got a result of 82% in the "Very Good" category and for material experts a result of 93% in the "Very Good" category. In the practicality test, it was carried out by teachers and students, where the teacher got a practicality result of 93% in the "Very Practical" category and the students got a result of 80% in the "Practical" category. The effectiveness test was carried out by giving pretest and post-test questions, where the pretest got a result of 64% and the post-test got a result of 92.2%. So this learning media is feasible, practical and effective to use to support teaching and learning activities.
A Comparative Study of Improved Ensemble Learning Algorithms for Patient Severity Condition Classification Edi Ismanto; Abdul Fadlil; Anton Yudhana; Kitagawa, Kodai
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 6 No 3 (2024): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v6i3.452

Abstract

The evolution of Electronic Health Records (EHR) has facilitated comprehensive patient record-keeping, enhancing healthcare delivery and decision-making processes. Despite these advancements, analyzing EHR data using ensemble machine learning methods poses unique challenges. These challenges include data dimensionality, imbalanced class distributions, and the need for effective hyperparameter tuning to optimize model performance. The study conducted a thorough comparative analysis of various ensemble machine learning (EML) models using Electronic Health Record (EHR) datasets. After addressing data imbalance and reducing dimensionality, the accuracy of the EML models showed significant improvement. Notably, the Gradient Boosting Machine (GBM) and CatBoost models exhibited superior performance with an accuracy of 73%, achieved through experiments involving dimensionality reduction and handling of imbalanced data. Furthermore, optimization techniques such as Grid Search and Random Search were employed to enhance the EML models. The results of model optimization revealed that the GBM + Random Search model performed the best, achieving an accuracy of 74%, followed by the XGBoost + Grid Search model with an accuracy of 73%. The GBM model also excelled in distinguishing between positive and negative classes, boasting the highest Area under Curve (AUC) value of 0.78, indicative of its superior classification capabilities compared to other models. This study emphasizes the significance of incorporating cutting-edge EML techniques into clinical workflows and emphasizes the revolutionary potential of GBM in classification modeling for patient severity conditions. Future research should focus on deep learning (DL) applications and the integration of these models.
Pemanfaatan Digital Marketing untuk Memperluas Strategi Pemasaran Produk Furniture dari Bahan Kayu Rubber Ismanto, Edi; Januar Al Amien; Hammam Zaki; Eka Pandu Cynthia
Jurnal Pengabdian UntukMu NegeRI Vol. 8 No. 1 (2024): Pengabdian Untuk Mu negeRI
Publisher : LPPM UMRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jpumri.v8i1.5720

Abstract

The COVID-19 pandemic, which has affected Indonesia for the past three years, has had a significant negative impact on a number of industries, including the Micro, Medium, and Small Enterprises (MSME) sector, which has been particularly hard hit. Pekanbaru City has 105,445 MSMEs, with data indicating that there are as many as 1,034 MSMEs, which produce a range of goods used by the community, including furniture products and various wood-based office and home furnishings. Of course, if development is carried out for MSME wood craftsmen, this is a potential aspect for the City of Pekanbaru. UMKM Furniqa Woodcraft as a raw material to create furniture items like chairs, tables, cabinets, and various other handicraft products uses rubber wood. However, there has been a significant drop in sales since the Covid-19 pandemic, so a solution must be found. In an effort to increase product marketing, service activities performed include training and assisting with managing Digital Marketing. This activity is implemented using a variety of approaches, including the Interview and Discussion Method, the Training Method, and the Evaluation Method. The evaluation of the implementation of digital marketing training and mentoring showed that employees at Furniqa Woodcraft had increased knowledge competence by 75.875%.
Analisis Perbandingan Model Fully Connected Neural Networks (FCNN) dan TabNet Untuk Klasifikasi Perawatan Pasien Pada Data Tabular Ismanto, Edi; Abdul Fadlil; Anton Yudhana
Computer Science and Information Technology Vol 5 No 3 (2024): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

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

Abstract

Electronic Health Records (EHR) store tabular data that is rich in information and play a critical role in supporting decision-making within the healthcare field, particularly for patient care classification. This study evaluates the performance of two artificial intelligence models, Fully Connected Neural Networks (FCNN) and TabNet, in processing tabular data for patient care classification tasks. The findings reveal that both models demonstrate strong performance, with TabNet showing a slight advantage. TabNet achieves an accuracy of 0.74, marginally surpassing FCNN's 0.73. Furthermore, TabNet excels in precision (0.74 vs. 0.72), recall (0.72 vs. 0.71), and F1-Score (0.73 vs. 0.71), highlighting its greater reliability in minimizing false positives and accurately detecting positive cases with a better balance between precision and recall. With its architecture specifically tailored for tabular data and its capacity for direct interpretability, TabNet offers enhanced efficiency and ease of implementation compared to FCNN, which demands more complex data preprocessing. For future research, it is suggested to employ larger and more diverse datasets, explore data with higher feature complexity, and conduct comprehensive hyperparameter tuning to further improve the performance of both models.
Co-Authors Abdul Fadlil Adam Ramadhan Afandi Alsyar Agus Satria Ahmad Gunawan Dalimunthe Ajeng Safitri Al Rian, Rahmad Ambiyar, Ambiyar Amelia Agustina Amran, Hasanatul Fu'adah Anton Yudhana Azzahra Chairunnisa Bella, Bella Fitria Sari Celvin Arafat Chintya, Indri Davie Rizky Akbar Delopinli, Crystian Deprizon, Deprizon Diah Eka Ratna Diva Arifal Adha Dwi Sanggar Wati, Anisa Effendi, Noverta Eka Pandu Cynthia Eka Pandu Cynthia Erik Suanda Handika Fadli Rahmad Hidayatullah Fatihul Ihsan, Tengku Fawwaz Fauza Addinunnisa Fikri Abdul Jafar Gunawan, Rahmad Habil Maulana Hadhrami Ab Ghani Hadhrami Ab. Ghani Hammam Zaki Harun Mukhtar Hendra, Zana Vania Herdani, Inka friska Herlandy, Pratama Benny Herman Ilham Ramadhan Januar Al Amien Januar Al Amien Januar Al Amien Khairul Anshari Kitagawa, Kodai Lisman, Muhammad Maulana, M.Rizky Melly Novalia Melly Novalia Melly Novalia, Melly Mohamad, Mohd Saberi Muhammad Cavin Ramadhan Muhammad Iqbal Muhammad Ridwansyah Nuraeni, Eneng Nurul Izrin Binti Md Saleh Nurul Izrin Md Saleh Nurul Safira, Natasya Oriana, Larisa Patlan Putra Humala Harahap Pramudya, Muhammad Rayenra Azthi Pratama Benny Herlandi Pratama Benny Herlandy Putri Ramahdani, Anggi Rahmad Al Rian Rahmad Al Rian Rahmad Alrian Rahmad Gunawan Gunawan Rahmadani, Delia Syaf Rahmatullah, Yuvi Ramadani, Tasya Ramadhani, Monica Alya Remli, Muhammad Akmal Renita Rahmadani Resmi Darni Ridhollah, Farhan Riski Amin Putra Rohima Zalti, Ulfani Rose Darmakusuma, Dinda Safitri, Ajeng Septian Alza Septiawan, Raffi Siti Niah Soni Sri Fitria Retnawaty Sunanto Sunanto Suryadila, Lusi Tri Wahono Vitriani Vitriani Vitriani Vitrian Vitriani, Vitriani Wan Salihin Wong, Khairul Nizar Syazwan Wandi Syahfutra Winson Ardhika Ramadhani Yeeri Badrun