Computer Engineering, Computer Networks and Communications, Electrical and Electronic Engineering, Artificial Intelligence
6
Scopus Publications
9
Scholar Citations
2
Scholar h-index
Scopus Publications
Comparative Analysis of C4.5 and Random Forest Algorithms for Teacher Certification Prediction Elang Prasakti Ghani, Nurhawa Nizar Siagian 2025 International Conference on Artificial Intelligence and Technological Solutions for Good Health Well Being and Sustainable Water Management in Support of Sdgs 3 6 and 9 Icaitech 2025 Proceeding, 2025 Teacher certification is a national policy in Indonesia designed to enhance teacher professionalism and ensure education quality. Accurate prediction of certification outcomes is crucial for supporting decision-making, optimizing resources, and guiding teacher development programs. This study presents a comparative analysis of two machine learning algorithms, C4.5 decision tree and Random Forest, for predicting teacher certification results. The dataset, obtained from an official education authority, contained 2,123 records with seven attributes including age, years of service, workload, rank, educational attainment, and functional position. Preprocessing steps such as feature engineering, categorical encoding, and duplication removal were applied to improve data quality before model development. Model performance was evaluated using accuracy, precision, recall, F 1 -score, and ROCAUC. Results show that C4.5 achieved an accuracy of 89%, precision of 90%, recall of 30.5%, and an AUC of 0.7451, highlighting weaknesses in handling class imbalance. In contrast, Random Forest with hyperparameter tuning demonstrated superior performance with an accuracy of 91%, precision of 92%, recall of 49%, and an AUC of 0.8110, indicating greater robustness. Feature importance analysis revealed rank and educational attainment as key predictors. Overall, Random Forest offers more balanced and reliable predictions, making it a valuable tool for policymakers in improving certification strategies.
AI-Driven Network Security: Detecting and Mitigating DDoS, Malware, and Backdoor Attacks with Isolation and Random Forest Algorithm Elang Prasakti Ghani, Aghus Sofwan, Maman Somantri 2025 International Conference on Smart Computing Iot and Machine Learning Siml 2025, 2025 Slot Backdoor attacks have become a growing cybersecurity threat in Indonesia, particularly exploiting vulnerabilities to inject unauthorized online gambling advertisements into university websites. These attacks alter website appearances, disrupt academic services, and negatively impact Webometrics rankings by reducing site accessibility and credibility. University XYZ experienced a severe decline in its Webometrics ranking, dropping from the top 5 to around 1000 due to repeated Slot Backdoor attacks. Following the deployment of the proposed machine learning-based mitigation system, the university successfully recovered and returned to the top 5 rankings. To address such threats, this study proposes an anomaly detection and prevention system at the network layer using machine learning. The system integrates Isolation Forest for anomaly detection and the Random Forest for attack classification. Isolation Forest identifies users with more than four failed login attempts within an hour, triggering a warning. If no further attempts follow in the next hour, the status returns to Normal; otherwise, access is Blocked to prevent brute-force and backdoor attacks. Random Forest then classifies network anomalies into Normal, Distributed Denial of Service (DDoS), and Malware/Backdoor threats. Evaluation metrics accuracy, precision, recall, F1-score, and confusion matrix confirm the system's effectiveness. The Random Forest classifier achieved 93 percent accuracy, with 88 percent precision for DDoS, 97 percent for Malware or Backdoor, and 100 percent for Normal traffic. Isolation Forest demonstrated 100 percent accuracy in DDoS and malware/backdoor mitigation with minimal false positives. By combining anomaly detection and threat classification, this approach significantly enhances cybersecurity resilience and offers a practical solution for protecting university networks like University XYZ.
Detection and Mitigation Effectiveness of Injection and Remote Service Attacks: A Machine Learning-Based Evaluation Elang Prasakti Ghani, R. Isnanto, Aris Triwiyatno 2025 5th International Symposium on Materials and Electrical Engineering Ismee 2025, 2025 Web applications and enterprise servers are frequent targets of injection attacks, including Structured Query Language (SQL) Injection, Cross-Site Scripting (XSS), and remote service exploits through Secure Shell (SSH), Telnet, and Simple Mail Transfer Protocol (SMTP). Exploits against HTTP, SMB, FTP, and MSSQL have also become common vectors for brute-force authentication, command injection, and malware distribution. Although FortiWeb and other Web Application Firewalls (WAFs) are widely deployed, their effectiveness remains uncertain without independent validation. To address this gap, a honeypot environment was deployed to capture attacker behavior, payloads, and malicious Internet Protocol (IP) addresses. The collected traces were redirected to a FortiWeb firewall for blocking, and the mitigation results were evaluated using machine learning classifiers. Random Forest (RF) and Support Vector Machine (SVM) were trained on more than 2,600 recorded attack sessions, with performance assessed through accuracy, confusion matrix, Receiver Operating Characteristic (ROC) curve, and Precision-Recall (PR) curve. Findings show that RF achieved 94 percent accuracy, 0.99 precision for malicious traffic, and an Area Under the Curve (AUC) of 0.94, outperforming SVM with 87 percent accuracy and an AUC of 0.81. Payload analysis further revealed SSH, Telnet, and SMTP brute-force attempts as dominant vectors, with additional exploitation on HTTP and SMB services.
Network-Layer Ransomware Protection for IoT in Resource-Constrained Environments Using Machine Learning Elang Prasakti Ghani, Adian Fatchur Rochim, Aghus Sofwan 2025 1st International Conference on Emerging Trends in Information Systems and Informatics Icetisi 2025, 2025 Network-layer ransomware attacks are on the rise with the rapid deployment of Internet of Things (IoT) devices, particularly in environments with limited CPU, memory, and energy resources. Conventional defenses are often too complex, allowing stealthy ransomware traffic to bypass protection and compromise service reliability. This paper introduces a lightweight hybrid framework using Network Simulator version 3 (NS-3), which combines simulation-based rule enforcement with machine learning analysis. The rule-based mechanisms include token-bucket rate limiting, circuit-breaker quarantine, authentication validation, replay protection, and Fair Queuing Controlled Delay (FQ-CoDel). These mechanisms reduce excessive packet injection, quarantine malicious nodes, and sustain fairness across IoT flows. However, some ransomware traffic still evades filtering. To improve resilience, supervised learning classifiers, Random Forest, Support Vector Machine, and K-Nearest Neighbors, are trained on controller node logs. Results show that FQ-CoDel stabilizes throughput at approximately 45 kilobytes per second and maintains an average drop rate of 52 %. Random Forest provides the best detection accuracy of 84 % with an area under the curve of 94 %, while K-Nearest Neighbors records 79 %, and Support Vector Machine achieves 77 %. These findings confirm that integrating lightweight rule-based controls with machine learning enhances ransomware protection in resource-constrained IoT system.
Performance Comparison of IEEE 802.11be and 802.11ax in Terms of Throughput Elang Prasakti Ghani, Bellia Dwi Cahya Putri, Adian Fatchur Rochim, Erwin Adriono, Delphi Hanggoro, Adnan Fauzi Icocseti 2025 International Conference on Computer Sciences Engineering and Technology Innovation Proceeding, 2025 IEEE 802.11be, the seventh-generation wireless protocol, will be released soon and will perform better than IEEE 802.11ax, the sixth-generation wireless technology. The performance of competing wireless protocols at the same operating frequency—5 GHz—is reviewed in this study. We use Network Simulator (NS-3) as a simulation tool that offers flexibility, shorter setup time, and makes it easy to experiment for any scenario we need to do. Furthermore, this paper focuses on analyzing and comparing the throughput of the IEEE 802.11be (Extremely High Throughput MCS) (EhtMcs) and 802.11ax (High Efficiency MCS) (HeMcs) protocols with different client counts and specific payload sizes. Spatial flow, channel width, Guard Interval (GI), Modulation and Coding Scheme (MCS), and simulation duration are among the other parameters that are set to certain values. Simulation results show that the IEEE 802.11be Modulation and Coding Scheme (MCS-13) protocol has better throughput performance than the IEEE 802.11ax Modulation and Coding Scheme (MCS-11) with many clients. In the simulation, the access point node is accessed from 2 to 128 clients. Simulation results show that in every situation, IEEE 802.11be performs better than IEEE 802.11ax. Wi-Fi 7 achieves up to 18 percent higher throughput for lower client counts and up to 35 percent higher throughput in scenarios with 64 to 128 clients, demonstrating its enhanced efficiency and reliability for high-density networks.
Design and Development of Serial Hub as a Monitoring System at Networking Practice Course using Raspberry Pi Adnan Fauzi, Elang Prasakti Ghani, Muhammad Amri Hakim, Darul Fahri, Dania Eridani, Adian Fatchur Rochim Eecsi 2025 Proceedings 2025 12th International Conference on Electrical Engineering Computer Science and Informatics, 2025 The networked laboratory is a place for doing computer networking practical activities on campus. However, significant damage to equipment, including network cables, switch ports, and routers often happens. Therefore, this research aims to develop a web-based monitoring system application for network devices using Raspberry Pi. The development process follows Agile Methodology and utilizes the Hypertext Preprocessor (PHP) and JavaScript languages with Hypertext Markup Language (HTML) and Cascading Style Sheet (CSS) as the elements. The application will be hosted on a server connected to the internet, allowing public access via Raspberry Pi. Subsequently, Raspberry Pi will connect to network devices such as switches and routers. Testing will involve functional testing to ensure that the application functions as intended. Leveraging Raspberry Pi, an open-source tool adaptable to user requirements, the application uses Raspbian Operating System (OS) features, particularly Secure Shell (SSH). Users can remotely access network devices through Raspberry Pi, facilitating assistants and practitioners in their computer network practicum activities while minimizing potential damage to network devices, network cables, switch ports, and routers.
RECENT SCHOLAR PUBLICATIONS
Network-Layer Ransomware Protection for IoT in Resource-Constrained Environments Using Machine Learning EP Ghani, AF Rochim, A Sofwan 2025 1st International Conference on Emerging Trends in Information Systems … , 2025 2025
Comparative Analysis of C4. 5 and Random Forest Algorithms for Teacher Certification Prediction EP Ghani, NN Siagian 2025 International Conference on Artificial Intelligence and Technological … , 2025 2025
Detection and Mitigation Effectiveness of Injection and Remote Service Attacks: A Machine Learning-Based Evaluation EP Ghani, R Isnanto, A Triwiyatno 2025 5th International Symposium on Materials and Electrical Engineering … , 2025 2025
Design and Development of Serial Hub as a Monitoring System at Networking Practice Course using Raspberry Pi A Fauzi, EP Ghani, MA Hakim, D Fahri, D Eridani, AF Rochim 2025 12th International Conference on Electrical Engineering, Computer … , 2025 2025
AI-Driven Network Security: Detecting and Mitigating DDoS, Malware, and Backdoor Attacks with Isolation and Random Forest Algorithm EP Ghani, A Sofwan, M Somantri 2025 International Conference on Smart Computing, IoT and Machine Learning … , 2025 2025 Citations: 6
Performance Comparison of IEEE 802.11 be and 802.11 ax in Terms of Throughput EP Ghani, BDC Putri, AF Rochim, E Adriono, D Hanggoro, A Fauzi 2025 International Conference on Computer Sciences, Engineering, and … , 2025 2025 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
AI-Driven Network Security: Detecting and Mitigating DDoS, Malware, and Backdoor Attacks with Isolation and Random Forest Algorithm EP Ghani, A Sofwan, M Somantri 2025 International Conference on Smart Computing, IoT and Machine Learning … , 2025 2025 Citations: 6
Performance Comparison of IEEE 802.11 be and 802.11 ax in Terms of Throughput EP Ghani, BDC Putri, AF Rochim, E Adriono, D Hanggoro, A Fauzi 2025 International Conference on Computer Sciences, Engineering, and … , 2025 2025 Citations: 3
Network-Layer Ransomware Protection for IoT in Resource-Constrained Environments Using Machine Learning EP Ghani, AF Rochim, A Sofwan 2025 1st International Conference on Emerging Trends in Information Systems … , 2025 2025
Comparative Analysis of C4. 5 and Random Forest Algorithms for Teacher Certification Prediction EP Ghani, NN Siagian 2025 International Conference on Artificial Intelligence and Technological … , 2025 2025
Detection and Mitigation Effectiveness of Injection and Remote Service Attacks: A Machine Learning-Based Evaluation EP Ghani, R Isnanto, A Triwiyatno 2025 5th International Symposium on Materials and Electrical Engineering … , 2025 2025
Design and Development of Serial Hub as a Monitoring System at Networking Practice Course using Raspberry Pi A Fauzi, EP Ghani, MA Hakim, D Fahri, D Eridani, AF Rochim 2025 12th International Conference on Electrical Engineering, Computer … , 2025 2025
