Garuda - Garba Rujukan Digital

Gaussian Based-SMOTE Method for Handling Imbalanced Small Datasets Muhammad Misdram; Edi Noersasongko; Purwanto Purwanto; Muljono Muljono; Fandi Yulian Pamuji
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 9, No 4 (2023): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i4.26881

The problem of dataset imbalance needs special handling, because it often creates obstacles to the classification process. A very important problem in classification is to overcome a decrease in classification performance. There have been many published researches on the topic of overcoming dataset imbalances, but the results are still unsatisfactory. This is proven by the results of the average accuracy increase which is still not significant. There are several common methods that can be used to deal with dataset imbalances. For example, oversampling, undersampling, Synthetic Minority Oversampling Technique (SMOTE), Borderline-SMOTE, Adasyn, Cluster-SMOTE methods. These methods in testing the results of the classification accuracy average are still relatively low. In this research the selected dataset is a medical dataset which is classified as a small dataset of less than 200 records. The proposed method is Gaussian Based-SMOTE which is expected to work in a normal distribution and can determine excess samples for minority classes. The Gaussian Based-SMOTE method is a contribution of this research and can produce better accuracy than the previous research. The way the Gaussian Based-SMOTE method works is to start by determining the random location of synthesis candidates, determining the Gaussian distribution. The results of these two methods are substituted to produce perfect synthetic values. Generated synthetic values are combined with SMOTE sampling of the majority data from the training data, produce balanced data. The result of the balanced data classification trial from the influence of the Gaussian Based SMOTE result in a significant increase in accuracy values of 3% on average.

Customer Segmentation with RFM Model using Fuzzy C-Means and Genetic Programming Anas Syaifudin; Purwanto Purwanto; Heribertus Himawan; M. Arief Soeleman
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 22 No. 2 (2023)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v22i2.2408

One of the strategies a company uses to retain its customers is Customer Relationship Management (CRM). CRM manages interactions and supports business strategies to build mutually beneficial relationships between companies and customers. The utilization of information technology, such as data mining used to manage the data, is critical in order to be able to find out patterns made by customers when processing transactions. Clustering techniques are possible in data mining to find out the patterns generated from customer transaction data. Fuzzy C-Means (FCM) is one of the best-known and most widely used fuzzy grouping methods. The iteration process is carried out to determine which data is in the right cluster based on the objective function. The local minimum is the condition where the resulting value is not the lowest value from the solution set. This research aims to solve the minimum local problem in the FCM algorithm using Genetic Programming (GP), which is one of the evolution-based algorithms to produce better data clusters. The result of the research is to compare the application of fuzzy c-means (FCM) and genetic programming fuzzy c-means (GP-FCM) for customer segmentation applied to the Cahaya Estetika clinic dataset. The test results of the GP-FCM yielded an objective function of 20.3091, while for the FCM algorithm, it was 32.44741. Furthermore, evaluating cluster validity using Partition Coefficient (PC), Classification Entropy (CE), and Silhouette Index proves that the results of cluster quality from gp-fcm are more optimal than fcm. The results of this study indicate that the application of genetic programming in the fuzzy c-means algorithm produces more optimal cluster quality than the fuzzy c-means algorithm.

Optimizing Chronic Kidney Disease Diagnosis Using the C4.5 Algorithm and Missing Value Imputation Strategies Ahmad Riyanto; Purwanto Purwanto; Farrikh Al Zami; Ridodio Andreuw Meda
Jurnal Penelitian Pendidikan IPA Vol 11 No 9 (2025): September
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v11i9.12456

The occurrence of missing values in data mining is a significant challenge that can hinder the knowledge extraction process. Incomplete data not only reduces efficiency in data management and analysis, but also has the potential to bias decision-making. This study aims to improve the performance of the C4.5 algorithm in dealing with missing value problems through the application of imputation techniques and GridSearchCV optimization. In this study, we propose an approach to handling missing values by combining several imputation methods, including minimum, maximum, mean-mode, median, and k-Nearest Neighbors (k-NN). These methods are applied to the Chronic Kidney Disease dataset obtained from the UCI Repository. After the imputation process, we performed hyperparameter optimization using GridSearchCV to find the best parameter combination for the C4.5 algorithm. Experimental results show that the application of imputation techniques and GridSearchCV optimization significantly improves the classification accuracy of the C4.5 algorithm. The comparison results show that the application of missing value handling, combined with GridSearchCV optimization, successfully improves the accuracy of the model by 2.25% compared to without using missing values. This proves that handling missing values along with proper GridSearchCV optimization can improve the prediction quality of the model.

Optimizing Stacked KNN, Naive Bayes, and LDA Models Using Random Forest as a Meta-Learner for Diabetes Classification Ridodio Andreuw Meda; Purwanto Purwanto; Farrikh Al Zami; Ahmad Riyanto
Jurnal Penelitian Pendidikan IPA Vol 11 No 10 (2025): October
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v11i10.12546

Diabetes is one of the chronic diseases with a high mortality rate that requires proper treatment and early detection. This study proposes a stacking model approach with a combination of K-Nearest Neighbor (KNN), Naive Bayes, and Linear Discriminant Analysis (LDA) as the base-learner, and Random Forest as the meta-learner. The main objective of this study is to improve the classification accuracy of diabetes datasets that have an unbalanced class distribution. The experiment was conducted on the Pima Indians Diabetes dataset from the UCI Machine Learning Repository. The test results showed that the proposed stacking model was able to achieve an accuracy of 96.30%, True Positive Rate (TPR) of 88.89%, True Negative Rate (TNR) of 100%, and G-Mean of 94.28%. This performance is significantly better than the previous single classifier model and stacking approach. Thus, the proposed stacking model can be used as an effective solution in the classification of diabetic diseases under conditions of unbalanced class distribution.

Quantum Cryptography – Principles, Protocols, and Future Directions: A Review Dian Arif Rachman; Muhamad Akrom; Didik Hermanto; Moch. Anjas Aprihartha; Khafiizh Hastuti; Ayu Pertiwi; Purwanto
Journal of Multiscale Materials Informatics Vol. 3 No. 1 (2026): April
Publisher : Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/jimat.v3i1.15959

The rapid advancement of quantum computing poses a significant threat to classical cryptographic systems that rely on the computational hardness of mathematical problems such as integer factorization and discrete logarithm problems. In this context, quantum cryptography has emerged as a promising paradigm for secure communication based on the fundamental principles of quantum mechanics rather than on computational assumptions. This paper presents a comprehensive review of quantum cryptography, with a particular focus on Quantum Key Distribution (QKD), the most mature application. The study discusses the theoretical foundations of quantum security, including superposition, entanglement, and the No-cloning theorem, which collectively enable eavesdropping detection and guarantee information-theoretic security. Furthermore, the review examines major QKD protocols, such as BB84 and E91, as well as their advanced variants designed to address practical vulnerabilities and enhance performance. Recent progress in real-world implementations, including fiber-optic networks, free-space communication, and satellite-based systems such as the Micius satellite, is also analyzed. In addition, the paper highlights critical challenges related to scalability, hardware limitations, and security loopholes arising from imperfect devices. Finally, emerging research directions, including hybrid cryptographic frameworks that integrate quantum and post-quantum approaches, are discussed to provide insights into the future of secure communication. This review aims to provide a structured, up-to-date understanding of quantum cryptography, bridging the gap between theoretical developments and practical implementations, and emphasizing its crucial role in shaping next-generation cybersecurity systems.

Gaussian Based-SMOTE Method for Handling Imbalanced Small Datasets Muhammad Misdram; Edi Noersasongko; Purwanto Purwanto; Muljono Muljono; Fandi Yulian Pamuji
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 4 (2023): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i4.26881

The problem of dataset imbalance needs special handling, because it often creates obstacles to the classification process. A very important problem in classification is to overcome a decrease in classification performance. There have been many published researches on the topic of overcoming dataset imbalances, but the results are still unsatisfactory. This is proven by the results of the average accuracy increase which is still not significant. There are several common methods that can be used to deal with dataset imbalances. For example, oversampling, undersampling, Synthetic Minority Oversampling Technique (SMOTE), Borderline-SMOTE, Adasyn, Cluster-SMOTE methods. These methods in testing the results of the classification accuracy average are still relatively low. In this research the selected dataset is a medical dataset which is classified as a small dataset of less than 200 records. The proposed method is Gaussian Based-SMOTE which is expected to work in a normal distribution and can determine excess samples for minority classes. The Gaussian Based-SMOTE method is a contribution of this research and can produce better accuracy than the previous research. The way the Gaussian Based-SMOTE method works is to start by determining the random location of synthesis candidates, determining the Gaussian distribution. The results of these two methods are substituted to produce perfect synthetic values. Generated synthetic values are combined with SMOTE sampling of the majority data from the training data, produce balanced data. The result of the balanced data classification trial from the influence of the Gaussian Based SMOTE result in a significant increase in accuracy values of 3% on average.

An integration of quantum systems using BB84 for enhanced security in aeroponic smart farming Christy Atika Sari; Purwanto Purwanto; Eko Hari Rachmawanto; Abdul Syukur
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 6: December 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i6.26450

Modern aeroponic systems leverage internet of things (IoT) technology for automated control of climate, lighting, and nutrient delivery, rendering them susceptible to unauthorized access and network attacks. Such disruptions can lead to financial losses and impair agricultural productivity by altering essential growth conditions. To mitigate these risks, robust security measures including encryption and firewalls are essential, alongside continuous monitoring and updates to combat evolving threats. Addressing cyber threats in urban aeroponic systems, implementing quantum encryption emerges as a promising solution. Quantum key distribution (QKD) ensures highly secure encryption keys using quantum states that change upon eavesdropping, thereby thwarting intrusion attempts effectively. Integrating quantum encryption in aeroponic control systems safeguards data integrity and operational continuity against cyber threats, bolstering urban agriculture resilience. Our findings demonstrate the efficacy of quantum BB84 protocol integrated with API for Eve’s security. Quantum bit error rate (QBER) measurements revealed minimal interference (0.015) for Alice and Bob, contrasting with higher initial QBER (up to 1.0) for Eve, indicative of intrusion attempts. Histogram analysis further underscored quantum security’s effectiveness in identifying and mitigating breaches. For future research, enhancing quantum encryption protocols and integrating advanced detection mechanisms will be essential.

An image encryption based on Fibonacci sequence and fusion of advanced encryption standard-least significant bit method Purwanto Purwanto; Aris Marjuni; Erna Zuni Astuti; Christy Atika Sari; Nova Rijati; Pulung Nurtantio Andono; Md Kamruzzaman Sarker
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 6: December 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i6.26078

Image encryption is a vital field ensuring the secure transmission of digital images. In this study, encryption is the core process, employing complex mathematical algorithms and cryptographic keys to transform the original image into a secure format, shielding visual data from unauthorized access during transmission. To enhance security, the research integrates Fibonacci and advanced encryption standard (AES)–least significant bit (LSB) methodologies for a complex key generation system. This mechanism introduces intricate transformations within the image data, creating patterns challenging for potential attackers to decipher. Evaluation of the algorithm’s performance reveals efficiency in terms of mean squared error (MSE) and peak signal-to-noise ratio (PSNR). The RGB cover image achieves the lowest MSE of 0.0001 and the highest PSNR values ranging from 44.31 to 49.27. Integration of the Fibonacci sequence notably improves visual quality, enhancing both MSE and PSNR metrics. Unified average changing intensity (UACI) and normalized pixel change rate (NPCR) assessments consistently show the effectiveness of the algorithm, with the RGB cover image presenting the highest UACI and NPCR values. Future research directions involve exploring advanced encryption algorithms, optimizing techniques for high-dimensional datasets, and addressing ethical implications in image encryption, contributing to the development of adaptable and secure solutions.

An optimation of advanced encryption standard key expansion using genetic algorithm and least significant bit integration Aris Marjuni; Nova Rijati; Ajib Susanto; Daurat Sinaga; Purwanto Purwanto; Zainal Arifin Hasibuan; Noorayisahbe Mohd. Yaacob
Bulletin of Electrical Engineering and Informatics Vol 13, No 6: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i6.8367

Ensuring data security in todayâ€™s digital landscape is of paramount importance, driving the exploration of advanced techniques for safeguarding confidential information. This study introduces a robust approach that combines advanced encryption standard (AES) encryption with key expansion, genetic algorithms (GA), and least significant bit (LSB) embedding to achieve secure data concealment within digital images. Motivated by the pressing need for enhanced data protection, our work addresses the critical challenge of securing sensitive information from unauthorized access. Specifically, we present a systematic methodology that integrates AES encryption for robust data security, GA for optimization, and LSB embedding for subtle information concealment. Through comprehensive experimentation, involving images such as â€˜Lena.jpg,â€™ â€˜Peppers.jpg,â€™ and â€˜Baboon.jpg,â€™ we demonstrate the efficacy of our approach. The imperceptible modification rates mean squared error (MSE) of 0.199, 0.101, and 0.105, coupled with high peak signal-to-noise ratios (PSNR) of 10.04 dB, 9.95 dB, and 9.79 dB respectively, underscore the fidelity and subtlety of the embedded information. This study contributes to the ongoing discourse on data security by offering a comprehensive and innovative approach that addresses the evolving challenges in safeguarding digital information.

Title

Found 19 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 19 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 19 Documents
Search