Claim Missing Document
Check
Articles

Found 30 Documents
Search

Analysis of the Combination of Naïve Bayes and MHR (Mean of Horner’s Rule) for Classification of Keystroke Dynamic Authentication Zamah Sari; Didih Rizki Chandranegara; Rahayu Nurul Khasanah; Hardianto Wibowo; Wildan Suharso
JOIN (Jurnal Online Informatika) Vol 7 No 1 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i1.839

Abstract

Keystroke Dynamics Authentication (KDA) is a technique used to recognize somebody dependent on typing pattern or typing rhythm in a system. Everyone's typing behavior is considered unique. One of the numerous approaches to secure private information is by utilizing a password. The development of technology is trailed by the human requirement for security concerning information and protection since hacker ability of information burglary has gotten further developed (hack the password). So that hackers can use this information for their benefit and can disadvantage others. Hence, for better security, for example, fingerprint, retina scan, et cetera are enthusiastically suggested. But these techniques are considered costly. The advantage of KDA is the user would not realize that the system is using KDA. Accordingly, we proposed the combination of Naïve Bayes and MHR (Mean of Horner’s Rule) to classify the individual as an attacker or a nonattacker. We use Naïve Bayes because it is better for classification and simple to implement than another. Furthermore, MHR is better for KDA if combined with the classification method which is based on previous research. This research showed that False Acceptance Rate (FAR) and Accuracy are improving than the previous research.
Music Features Pada Bidang Ilmu Komputer Menggunakan Modularity Clustering Suharso, Wildan; Arifianto, Sofyan; Wibowo, Hardianto; Chandranegara, Didih Rizki; Syaifuddin, Syaifuddin
Jurnal Sistem Informasi, Teknologi Informatika dan Komputer Volume 13 No 1 Tahun 2022
Publisher : Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/justit.13.1.%p

Abstract

Music features menjadi bagian dari berbagai disiplin keilmuan sehingga sering terjadi bias saat dilakukan pencarian pada mesin pencari, music features dapat termasuk ke dalam ilmu komputer, teknik hingga psikologi. Music features pada bidang ilmu komputer juga terkelompok menjadi beberapa bagian jika ditinjau dari rujukan yang dilakukan oleh peneliti terutama yang berasal dari artikel internasional yang terindeks scopus, berbeda dengan artikel Indonesia yang terkelompok pada Sinta berdasarkan Jurnal yang menerbitkan artikel. Pada penelitian ini dilakukan clustering terhadap artikel yang tergolong dalam bidang ilmu komputer dan memiliki kata kunci music features sehingga diperoleh 448 artikel. Metode yang digunakan adalah modularity clustering dengan menggunakan tool VOSviewer dan menghasilkan 3 cluster berdasarkan topik dan 7 cluster jika ditinjau dari kuantitas penulis yang menjadi co-author
COMPARISON OF MACHINE LEARNING TECHNIQUES FOR CLASSIFICATION OF DISTRIBUTED DENIAL OF SERVICE ATTACKS BASED ON FEATURE ENGINEERING IN SDN-BASED NETWORKS Rizaldi, Muhammad Ikhwananda; Chandranegara, Didih Rizki; Akbi, Denar Regata
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 3 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i3.5262

Abstract

Distributed Denial-of-Service (DDoS) attacks present a noteworthy cybersecurity hazard to software-defined networks (SDNs). This investigation presents an approach that depends on feature engineering and machine learning to discern DDoS attacks in SDNs. Initially, the dataset acquired from Kaggle goes through cleansing and normalization procedures, and the optimal subset of features is determined by employing the Correlation-based Feature Selection (CFS) algorithm. Subsequently, the optimal subset of features is trained and evaluated utilizing diverse Machine Learning algorithms, specifically Random Forest (RF), Decision Tree, Adaptive Boosting (AdaBoost), K-Nearest Neighbor (k-NN), Gradient Boosting, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost). The outcomes demonstrate that XGBoost outperforms the other algorithms in various performance metrics (e.g., accuracy, precision, recall, F1, and AUC values). Furthermore, a comparative analysis was carried out among various models and algorithms, revealing that the technique proposed by the researchers yielded the most favourable outcomes and effectively detected and identified DDoS attacks in SDN. Consequently, this investigation provides a novel perspective and resolution for SDN security.
Diabetes Disease Detection Classification Using Light Gradient Boosting (LightGBM) With Hyperparameter Tuning Ramadanti, Elisa; Aprilya Dinathi, Devi; christianskaditya; Chandranegara, Didih Rizki
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 2 (2024): Article Research Volume 8 Issue 2, April 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i2.13530

Abstract

Diabetes is a condition caused by an imbalance between the need for insulin in the body and insufficient insulin production by the pancreas, causing an increase in blood sugar concentration. This study aims to find the best classification performance on diabetes datasets with the LightGBM method. The dataset used consists of 768 rows and 9 columns, with target values of 0 and 1. In this study, resampling is applied to overcome data imbalance using SMOTE and perform hyperparameter optimization. Model evaluation is performed using confusion matrix and various metrics such as accuracy, recall, precision and f1-score. This research conducted several tests. In hyperparameter optimization tests using GridSearchCV and RandomSearchCV, the LightGBM method showed good performance. In tests that apply data resampling, the LightGBM method achieves the highest accuracy, namely the LightGBM method with GridSearchCV optimization with the highest accuracy reaching 84%, while LightGBM with RandomSearchCV optimization reaches 82% accuracy.
IMPLEMENTASI METODE PERSONAL EXTREME PROGRAMMING DALAM PERACANGAN APLIKASI PEMESANAN RUANG RAPAT BERBASIS ANDROID DISKOMINFO JAWA TIMUR Akbar, Muhammad Sulthoni; Nuryasin, Ilyas; Chandranegara, Didih Rizki
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 6 No 1 (2024): March 2024
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v6i1.348

Abstract

The advancement of information technology greatly enhances human activities, including the introduction of information management and meeting room reservation systems. In the East Java Provincial Office of Communication and Informatics, manual room reservation processes pose challenges, especially when administrators are unavailable. To address this, a research project aims to develop an IT-based application for efficient meeting room management and reservation. This will simplify the process for employees, enabling systematic and effective room bookings. The application allows users to check room availability online in real-time, eliminating the need for direct interaction with administrators. This implementation is expected to significantly enhance the overall efficiency of the East Java Provincial Office of Communication and Informatics. The application development will follow Personal Extreme Programming (PXP), known for its adaptability in software development. PXP involves stages like requirements, planning, design, implementation, and testing, iterated as needed. Successful application of PXP relies on skilled developers, requiring clear requirement identification and accurate work estimation. This research builds upon prior studies demonstrating accelerated project completion using PXP. It aims to provide insights into applying PXP for flexible software development, emphasizing information technology's role in enhancing organizational efficiency.
Pengolahan Korpus Dataset Audio Bacaan Al-Qur’an Menggunakan Metode Wav2Vec 2.0 Aminudin, Aminudin; Nuryasin, Ilyas; Amien, Saiful; Wicaksono, Galih Wasis; Chandranegara, Didih Rizki; Thoifah, I'anatut; Rizky, Wahyu; Ferdiansyah, Danny; Azzahra, Kiara; Lathifah, Fildzah; Aulyah, Khairunnisa
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 10, No 1 (2024): Volume 10 No 1
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v10i1.71576

Abstract

Pengembangan sistem otomasi pengenalan ucapan (Automatic Speech Recognition/ASR) di dalam membaca Al-Qur'an dibutuhkan korpus data audio bacaan Al-Qur'an dan beranotasi dengan transkripsi tekstual agar dapat diproses oleh algoritma machine learning. Pemrosesan Korpus dataset ini dibangun mengingat belum adanya dataset beserta pemrosesanya menggunakan metode tertentu untuk keperluan riset di dalam pengembangan ASR. Paper ini menyajikan kumpulan corpus dataset dan pengolahannya menggunakan metode Wav2Vec 2.0 dengan total 24 ribuan dataset hasil dari rekaman dari 170 santri dengan jenjang umur 4 sampai dengan 16 tahun. Pemrosesan korpus dataset dibuat mengikuti standar metode Wav2Vec 2.0 agar dapat digunakan sebagai data latih pada pemrosesan machine learning. Wav2Vec merupakan model yang dapat mempelajari representasi vektor dari masukan sinyal suara dengan proses pembelajaran self-supervised learning. Wav2Vec juga mampu menangani perbedaan aksen dan karakteristik pembaca Al-Qur'an yang bervariasi dan lebih akurat karena menggunakan deep learning. Dari hasil pengujian menggunakan parameter Precision didapatkan hasil accuracy sebesar 65.52%, precision dengan nilai 0.83 Recall dengan nilai 0.66 dan F1-Score dengan nilai 0.73 serta Word Error Rate (WER) dengan nilai 0.5. Diharapkan dengan adanya pemrosesan korpus dataset ini dapat membantu pengembangan dan riset terkait automasi sistem bacaan Al-Qur'an dengan teknik deep learning dan meningkatkan minat generasi milenial untuk belajar Al-Qur'an dengan memanfaatkan teknologi terkini.
Classification of Dermoscopic Images Using CNN-SVM Minarno, Agus Eko; Fadhlan, Muhammad; Munarko, Yuda; Chandranegara, Didih Rizki
JOIV : International Journal on Informatics Visualization Vol 8, No 2 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.2.2153

Abstract

Traditional machine learning methods like GLCM and ABCD rules have long been employed for image classification tasks. However, they come with inherent limitations, primarily the need for manual feature extraction. This manual feature extraction process is time-consuming and relies on expert domain knowledge, making it challenging for non-experts to use effectively. Deep learning methods, specifically Convolutional Neural Networks (CNN), have revolutionized image classification by automating the feature extraction. CNNs can learn hierarchical features directly from the raw pixel values, eliminating the need for manual feature engineering. Despite their powerful capabilities, CNNs have limitations, mainly when working with small image datasets. They may overfit the data or struggle to generalize effectively. In light of these considerations, this study adopts a hybrid approach that leverages the strengths of both deep learning and traditional machine learning. CNNs are automatic feature extractors, allowing the model to capture meaningful image patterns. These extracted features are then fed into a Support Vector Machine (SVM) classifier, known for its efficiency and effectiveness in handling small datasets. The results of this study are encouraging, with an accuracy of 0.94 and an AUC score of 0.94. Notably, these metrics outperform Abbas' previous research by a significant margin, underscoring the effectiveness of the hybrid CNN-SVM approach. This research reinforces that SVM classifiers are well-suited for tasks involving limited image data, yielding improved classification accuracy and highlighting the potential for broader applications in image analysis.
Implementation of Generative Adversarial Network (GAN) Method for Pneumonia Dataset Augmentation Chandranegara, Didih Rizki; Sari, Zamah; Dewantoro, Muhammad Bagas; Wibowo, Hardianto; Suharso, Wildan
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 8, No. 2, May 2023
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v8i2.1675

Abstract

As a communicable disease, the majority of pneumonia cases are brought on by bacteria or viruses, which cause the lungs' alveoli to swell with fluid or mucus. Pneumonia may arise from this and further making breathing challenging since the lungs' air sacs are unable to contain enough oxygen for the body. Pneumonia may generally be diagnosed clinically (by a physician based on physical symptoms) as well as through a photo chest radiograph, CT scan, and MRI. In this case, the lower cost of a chest radiograph examination making it as one of the most popular medical imaging tests. However, chest radiograph photo readings have a disadvantage, where it takes a long time for medical staff or physicians to identify the patient's illness since it is difficult to detect the condition. Therefore, an identification of chest radiograph imagery into various forms using machine learning becomes one way to address this issue. This research focuses on building a deep neural network model using techniques from the Generative Adversarial Network algorithm. GAN is a category of machine learning techniques using two models to be trained simultaneously, one is a generator model to generated fake data and the other is a discriminator model used to separate the raw data from the real data set images. The dataset used is Chest X-Ray images obtained from repo GitHub and repo Kaggle totaling 5,863 with normal data 1583 images and pneumonia data 4273 imagesThe results showed that the use of the Generative Adevrsarial Network method as augmentation data proved to be more effective in improving the generalization of neural networks, this can be seen from the results the result of the accuracy value obtained is 97%.
Comparison of Transfer Learning Models in Classification Dental and Tongue Disease Images Azhar, Yufis; Setiono, Fauzan Adrivano; Chandranegara, Didih Rizki
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 1 (2025): January
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i1.487

Abstract

According to the Global Burden of Disease Study, dental caries is the most prevalent oral health ailment, affecting around 3.5 billion individuals globally. According to the Ministry of Health of the Republic of Indonesia, 93% of children in the country suffer from oral health issues, making poor oral health a serious public health concern. The tongue and teeth in the mouth are particularly vulnerable to a wide range of illnesses, and the condition of the mouth is a key sign of the health of the body as a whole. The CNN algorithm has been utilized in numerous studies to classify disorders of the tongue and teeth. Nevertheless, no study has classified tongue and dental diseases using merged datasets as of yet. This research addresses this gap by focusing on the classification of dental and tongue diseases using transfer learning techniques with CNN architecture models VGG16, VGG19, and ResNet50. The primary aim is to compare these three models to identify the one with the most optimal performance in handling related cases. Based on the results, the best accuracy was achieved with data augmentation and models trained for 75 epochs. The VGG16 model attained 94% accuracy, VGG19 achieved 93% accuracy, and ResNet50 also reached 94% accuracy. These findings suggest that transfer learning with CNN architectures can effectively classify dental and tongue diseases. The implications are significant for developing automated diagnostic tools that can aid in the early detection and treatment of oral health issues globally.
Stroke Prediction with Enhanced Gradient Boosting Classifier and Strategic Hyperparameter Setyarini, Dela Ananda; Gayatri, Agnes Ayu Maharani Dyah; Aditya, Christian Sri Kusuma; Chandranegara, Didih Rizki
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3555

Abstract

A stroke is a medical condition that occurs when the blood supply to the brain is interrupted. Stroke can cause damage to the brain that can potentially affect a person's function and ability to move, speak, think, and feel normally. The effect of stroke on health emphasizes the importance of stroke detection, so an effective model is needed in predicting stroke. This research aimed to find a new approach that can improve the performance of stroke prediction by comparing four derivative algorithms from Gradient Boosting by adding hyperparameters tuning. The addition of hyperparameters was used to find the best combination of parameter values that can improve the model accuracy. The methods used in this research were Categorical Boosting, Histogram Gradient Boosting, Light Gradient Boosting, and Extreme Gradient Boosting. The research involved retrieving, cleaning, and analyzing data and then the model performance was evaluated with a confusion matrix and execution time. The results obtained were Light Gradient Boosting with Hyperparameter RandomSearchCV achieved the highest accuracy at 95% among the algorithms tested, while also being the fastest in execution. The contribution of this research to the medical field can help doctors and patients predict the occurrence of stroke early and reduce serious consequences.