Garuda - Garba Rujukan Digital

Botnet Detection Using On-line Clustering with Pursuit Reinforcement Competitive Learning (PRCL) Mahardhika, Yesta Medya; Sudarsono, Amang; Barakbah, Ali Ridho
EMITTER International Journal of Engineering Technology Vol 6, No 1 (2018)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Botnet is a malicious software that often occurs at this time, and can perform malicious activities, such as DDoS, spamming, phishing, keylogging, clickfraud, steal personal information and important data. Botnets can replicate themselves without user consent. Several systems of botnet detection has been done by using classification methods. Classification methods have high precision, but it needs more effort to determine appropiate classification model. In this paper, we propose reinforcedÂ approach to detect botnet with On-line Clustering using Reinforcement Learning. Reinforcement Learning involving interaction with the environment and became new paradigm in machine learning. The reinforcement learning will be implemented with some rule detection, because botnet ISCX dataset is categorized as unbalanced dataset which have high range of each number of class. Therefore we implemented Reinforcement Learning to Detect Botnet using Pursuit Reinforcement Competitive Learning (PRCL) with additional rule detection which has reward and punisment rules to achieve the solution. Based on the experimental result, PRCL can detect botnet in real time with highÂ accuracy (100% for Neris, 99.9% for Rbot, 78% for SMTP_Spam, 80.9% for Nsis, 80.7% for Virut, and 96.0% for Zeus) and fast processing time up to 176 ms. Meanwhile the step of CPU and memory usage which are 78 % and 4.3 GBÂ for pre-processing, 34% and 3.18 GB for online clustering with PRCL, and Â 23% and 3.11 GB evaluation. The proposed method is one solution for network administrators to detect botnet which has unpredictable behavior in network traffic.

Botnet Detection Using On-line Clustering with Pursuit Reinforcement Competitive Learning (PRCL) Yesta Medya Mahardhika; Amang Sudarsono; Ali Ridho Barakbah
EMITTER International Journal of Engineering Technology Vol 6 No 1 (2018)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Botnet is a malicious software that often occurs at this time, and can perform malicious activities, such as DDoS, spamming, phishing, keylogging, clickfraud, steal personal information and important data. Botnets can replicate themselves without user consent. Several systems of botnet detection has been done by using classification methods. Classification methods have high precision, but it needs more effort to determine appropiate classification model. In this paper, we propose reinforcedÂ approach to detect botnet with On-line Clustering using Reinforcement Learning. Reinforcement Learning involving interaction with the environment and became new paradigm in machine learning. The reinforcement learning will be implemented with some rule detection, because botnet ISCX dataset is categorized as unbalanced dataset which have high range of each number of class. Therefore we implemented Reinforcement Learning to Detect Botnet using Pursuit Reinforcement Competitive Learning (PRCL) with additional rule detection which has reward and punisment rules to achieve the solution. Based on the experimental result, PRCL can detect botnet in real time with highÂ accuracy (100% for Neris, 99.9% for Rbot, 78% for SMTP_Spam, 80.9% for Nsis, 80.7% for Virut, and 96.0% for Zeus) and fast processing time up to 176 ms. Meanwhile the step of CPU and memory usage which are 78 % and 4.3 GBÂ for pre-processing, 34% and 3.18 GB for online clustering with PRCL, and Â 23% and 3.11 GB evaluation. The proposed method is one solution for network administrators to detect botnet which has unpredictable behavior in network traffic.

Implementation of Cyber Threat Intelligence on Intrusion Detection System using STIX Framework Mahardhika, Yesta Medya; Saputra, Ferry Astika; Syarif, Iwan; Wibowo, Prasetyo; Ardhani, Misbahul
Journal of Artificial Intelligence and Software Engineering Vol 5, No 1 (2025): March
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i1.6518

Cyber threats are complex and diverse issues. Various types of threats emerge daily on the internet. In this research, we proposed a new Cyber Threat Intelligence platform to deal with the challenges above, using Snort as a tool for detecting anonymous network traffic and STIX as a serialization format and standardization of Cyber Threat Intelligence data. As a result, a Cyber Threat Intelligence based on Snort contains Apache Spark as the processing engine, MongoDB as the database, and STIX as the serialization format and data standardization. We test our platform by using two data sources, the CIC-IDS2017 dataset, and the real traffic. We successfully converted the snort alerts to STIX format and visualized them into graph. The graph shows indication of network traffic suspicious, the country of attacker come from, attribute information and attack pattern. The experiment shows that converting Snort data to STIX requires considerable time if the amount of data processed is getting bigger, Real Traffic needs 16 seconds of data preprocessing and 3 minutes of conversion time, while PCAP needs 35 seconds of preprocessing time and 13 minutes of conversion time.

Pelatihan pemanfaatan panel surya untuk teknologi di SMP Negeri 3 Kediri Endriantono, Dafit Ody; Mahardhika, Yesta Medya; Habibi, Muhammad Nizar
SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan Vol 9, No 5 (2025): September
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jpmb.v9i5.33750

Abstrak Rendahnya literasi energi terbarukan di tingkat sekolah menjadi tantangan dalam mendukung transisi energi nasional. Kegiatan pengabdian ini bertujuan untuk memperkenalkan teknologi fotovoltaik kepada siswa dan guru SMP Negeri 3 Kediri, meningkatkan pemahaman konseptual dan minat mereka terhadap energi terbarukan, serta memberikan keterampilan praktis awal dalam rekayasa teknologi sederhana. Metode yang digunakan adalah sosialisasi, demonstrasi perakitan langsung mobil tenaga surya sederhana, dan diskusi interaktif yang dilaksanakan dalam satu hari sebagai bagian dari Projek Penguatan Profil Pelajar Pancasila (P5). Hasil kegiatan menunjukkan antusiasme dan partisipasi aktif yang sangat tinggi dari siswa dan guru. Metode demonstrasi terbukti efektif dalam mengubah konsep abstrak menjadi pengalaman belajar yang konkret dan memotivasi. Adanya komitmen dari guru untuk mereplikasi proyek secara mandiri menunjukkan potensi keberlanjutan program. Kegiatan ini menjadi model intervensi edukatif yang efisien dan dapat direplikasi untuk menumbuhkan budaya inovasi energi berkelanjutan sejak dini. Kata kunci: energi terbarukan; panel surya; literasi energi; projek penguatan profil pelajar pancasila; edukasi teknologi. Abstract Low renewable energy literacy at the school level poses a significant challenge to supporting the national energy transition. This community service activity aimed to introduce photovoltaic technology to the students and teachers of SMP Negeri 3 Kediri, enhance their conceptual understanding and interest in renewable energy, and provide foundational practical skills in simple technological engineering. The methodology involved an introductory session, a live assembly demonstration of a simple solar-powered car, and an interactive discussion, conducted as a part of the Pancasila Student Profile Reinforcement Project (P5). The results showed exceptionally high enthusiasm and active participation from both students and teachers. The demonstration method proved effective in transforming abstract concepts into a tangible and motivating learning experience. Furthermore, the commitment shown by teachers to independently replicate the project indicates the program's potential for sustainability. This activity serves as an efficient and replicable educational intervention model for fostering a culture of sustainable energy innovation from an early age. Keywords: renewable energy; solar technology; energy literacy; pancasila student character development; technology-based learning.

Pembuatan Perangkat Portabel untuk Penanggulangan Banjir dengan Monitoring Real-Time Ketinggian Air Sungai Berbasis IoT Endriantono, Dafit Ody; Syakirudin, Thofail; Rifat, Ahmad Miftahur; Novaliyanto, Zanuar Dwi; Kemal Pasya, Moch Raihan; Zaky, Asyraf Sulthan; Mahardhika, Yesta Medya; Habibi, Muhammad Nizar
ROTASI Vol 27, No 3 (2025): VOLUME 27, NOMOR 3, OKTOBER 2025
Publisher : Departemen Teknik Mesin, Fakultas Teknik, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/rotasi.27.3.%p

Bencana banjir merupakan tantangan hidrometeorologi paling signifikan di Indonesia, menyebabkan kerugian sosial-ekonomi yang besar dan mengancam keselamatan jiwa. Sistem peringatan dini yang ada seringkali terkendala oleh keterlambatan informasi, jangkauan terbatas, dan ketergantungan pada infrastruktur konvensional. Penelitian ini bertujuan merancang, membangun, dan menguji "FLOPRO", sebuah sistem peringatan dini banjir yang portabel, mandiri energi, dan berbasis Internet of Things (IoT). Metodologi pengembangan sistem ini mengintegrasikan mikrokontroler ESP32 sebagai unit pemrosesan utama, sensor ultrasonik HC-SR04 untuk pengukuran ketinggian air secara non-kontak, dan sistem catu daya mandiri yang terdiri dari panel surya 5V, modul pengisi daya TP4056, serta baterai LiPo. Data pengukuran ditransmisikan secara real-time ke cloud server melalui protokol Message Queuing Telemetry Transport (MQTT) yang ringan dan efisien. Sistem ini menyediakan mekanisme peringatan melalui peringatan suara lokal melalui modul ISD1820 untuk respons komunitas yang cepat. Hasil pengujian prototipe dalam lingkungan laboratorium terkontrol menunjukkan kinerja yang sangat andal. Validasi sensor HC-SR04 menghasilkan tingkat kesalahan rata-rata di bawah 3%. Transmisi data melalui MQTT menunjukkan latensi end-to-end yang rendah dengan keandalan pengiriman pesan yang tinggi. Sistem catu daya surya terbukti mampu menjaga operasional perangkat secara kontinu. Dapat disimpulkan bahwa perangkat FLOPRO berhasil divalidasi sebagai solusi EWS banjir yang efektif, portabel, dan efisien energi, dengan potensi besar untuk meningkatkan kesiapsiagaan masyarakat terhadap bencana banjir.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search