Claim Missing Document
Check
Articles

Found 38 Documents
Search

Mengoptimalkan Kinerja Naïve Bayes Pada Ancaman Modern Dengan Menggunakan PCA Pada Data Intrusion Detection System (IDS) Kevin Salsabil Arlandy; Ahmad Faqih; Ade Rizki Rinaldi
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 8, No 1 (2025): Januari
Publisher : Akademi Ilmu Komputer Ternate

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v8i1.303

Abstract

Abstrak: Intrusion Detection System (IDS) digunakan untuk mendeteksi serangan atau aktivitas mencurigakan dalam jaringan. Dengan meningkatnya ancaman siber modern, penelitian ini mengusulkan kombinasi metode Naïve Bayes dan Principal Component Analysis (PCA) untuk meningkatkan akurasi dan efisiensi deteksi. Metode tambahan PCA dapet mereduksi dimensi dataset menjadi 30 komponen utama tanpa kehilangan informasi penting, menggunakan dataset UNSW-NB15. Proses melibatkan standarisasi data dengan StandardScaler, reduksi dimensi menggunakan PCA, serta evaluasi model Naïve Bayes pada dataset dengan dan tanpa PCA. Analisis ini menggunakan program Python yang di eksekusi dengan Google Collab, dengan hasil menunjukkan bahwa model dengan PCA mencapai akurasi sebesar 96.65% dengan recall 1.00 untuk kelas ancaman, meskipun presisi masih rendah (0.49). Sebaliknya, tanpa PCA, akurasi hanya mencapai 92.72% dengan presisi 0.31 untuk kelas yang sama. Selain itu, penggunaan PCA berhasil mengurangi waktu komputasi dari 1 menit menjadi 30 detik. Kombinasi dengan teknik reduksi dimensi Principal Component Analysis (PCA) menunjukkan kinerja yang lebih baik dalam mengklasifikasikan data pada sistem Intrusion Detection System (IDS). PCA dan Naïve Bayes terbukti menjanjikan dalam mendeteksi ancaman modern, meskipun masih diperlukan perbaikan untuk mencapai kinerja yang lebih optimal.Kata kunci: Intrusion Detection System, Naïve Bayes, PCA, Keamanan JaringanAbstract:An Intrusion Detection System (IDS) is used to detect attacks or suspicious activities in the network. With the increase of modern cyber threats, this research proposes a combination of Naïve Bayes and Principal Component Analysis (PCA) methods to improve detection accuracy and efficiency. The additional PCA method can reduce the dataset dimension to 30 principal components without losing important information, using the UNSW-NB15 dataset. The process involves data standardization with Standard-Scaler, dimensionality reduction using PCA, and Naïve Bayes model evaluation on the dataset with and without PCA. This analysis used a Python program executed with Google Collab, with the results showing that the model with PCA achieved an accuracy of 96.65% with a recall of 1.00 for the threat class. However, the precision was still low (0.49). In contrast, without PCA, the accuracy only reached 92.72% with a precision of 0.31 for the same class. In addition, the use of PCA successfully reduced the computation time from 1 minute to 30 seconds combination with the Principal Component Analysis (PCA) dimension reduction technique shows better performance in classifying data in the Intrusion Detection System (IDS). PCA and Naïve Bayes proved promising in detecting modern threats, although improvements are still needed to achieve more optimal performance.Keywords: Intrusion Detection System, Naïve Bayes, PCA, Network Security
Diversifikasi Produk Dan Strategi Digital Marketing Bagi UMKM Oemah Singkong Untuk Daya Saing Berkelanjutan Ade Rizki Rinaldi; Sandy Eka Permana; Ahmad Najib Yahya; Luthfi Adianto
AMMA : Jurnal Pengabdian Masyarakat Vol. 3 No. 2 : Maret (2024): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

Abstract

This community service program aims to enhance the competencies of vocational high school (SMK) students in web development through Junior Web Developer training. The activities were carried out at several SMKs in Cirebon Regency and Cirebon City as an effort to bridge the gap between school curricula and industry needs. The implementation methods included preparation and planning, training execution, monitoring and evaluation, as well as dissemination of results. The outcomes of this program showed a significant improvement in students’ understanding and skills in web development technologies, particularly in the use of HTML, CSS, JavaScript, and modern frameworks. In addition, the participating teachers also benefited from workshops designed to enhance their ability to teach industry-based materials. This program successfully produced several outputs such as learning modules, student web projects, and collaborations with industry partners to open job opportunities for graduates. Through this program, it is expected that vocational students will be better prepared to face the workforce and the digital industry. The sustainability of this program can be expanded by increasing the number of industry partners and broadening the scope of training participants.
Pelatihan Operator Komputer Madya Untuk Meningkatkan Keterampilan Teknologi Tenaga Pendidik Pondok Pesantren Di Kabupaten Cirebon Ade Irma Purnama Sari; Ade Rizki Rinaldi; Ahmad Najib Yahya; Ainun Nisa Sari
AMMA : Jurnal Pengabdian Masyarakat Vol. 2 No. 2 (2023): AMMA : Jurnal Pengabdian Masyarakat (INPRESS)
Publisher : CV. Multi Kreasi Media

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

Abstract

This Community Service Program aims to improve the technological skills of educators at Islamic boarding schools (Pondok Pesantren) in Cirebon Regency through Intermediate Computer Operator Training. The main problem faced by educators is the limited knowledge and skills in operating computers, particularly in using office applications such as Microsoft Word, Excel, and PowerPoint. This condition affects the efficiency of pesantren administration and limits the utilization of technology in the learning process. This program was carried out through several stages, including needs identification, preparation of training materials, hands-on practice, evaluation, and mentoring. The materials provided covered basic computer operation, document management, data processing, digital presentation creation, and digital data management of students. The results of the training showed a significant improvement in participants' skills, especially in using office applications and managing digital-based administration. Several pesantren have started to implement digital systems for recording student data, finances, and lesson schedules. In addition, educators are now able to create more attractive and interactive technology-based learning materials. The outputs of this activity include digital training modules, tutorial videos, evaluation reports, and the formation of a technology-based educator community. This program is expected to continue to develop so that educators in Islamic boarding schools are increasingly ready to face the challenges of digitalization in education and are able to improve the quality of administrative management and learning processes within the pesantren environment.
Peningkatan Literasi Digital Guru Sekolah Dasar Dalam Menghadapi Pembelajaran Daring Ade Rizki Rinaldi; Agus Bahtiar; Arga Esa Putra; Arunika Wijaya
AMMA : Jurnal Pengabdian Masyarakat Vol. 2 No. 2 (2023): AMMA : Jurnal Pengabdian Masyarakat (INPRESS)
Publisher : CV. Multi Kreasi Media

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

Abstract

This Community Service Program aims to improve digital literacy for elementary school teachers in facing the challenges of online learning in the digital era. The rapid development of information and communication technology has brought significant changes to learning methods, including demands for teachers to master various digital platforms. However, in reality, many elementary school teachers still face limitations in using technology, both in terms of skills, access to devices, and strategies for delivering learning materials online. This program was implemented through a series of activities, including training, workshops, mentoring, and evaluation. The training materials focused on the use of online learning platforms such as Google Classroom, Zoom, Canva, and the creation of engaging and interactive digital learning materials. In addition, participants received guidance in overcoming technical obstacles and strategies for building effective communication with students in online learning. The results of this program showed a significant improvement in teachers' understanding and skills in operating educational technology. Teachers became more confident in designing and delivering digital-based learning, online classroom management improved, and student participation in the learning process increased. The outputs of this activity included a digital literacy guide module, tutorial videos on the use of online learning platforms, program activity reports, and the establishment of a knowledge-sharing community among teachers. This program is expected to support the transformation of technology-based education, improve the quality of online learning, and create educators who are more adaptive and creative in facing future technological developments.
Peningkatan Kompetensi Digital Guru Madrasah Melalui Pelatihan Aplikasi Perkantoran Berbasis Microsoft Office Ade Irma Purnama Sari; Ade Rizki Rinaldi; Ahmad Syaeful Ma’arief; Alfi Rizqi Falih
AMMA : Jurnal Pengabdian Masyarakat Vol. 1 No. 03 (2022): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

Abstract

This community service program aims to enhance the digital competence of teachers at Madrasah Tsanawiyah (MTs) in Cirebon City through office application training. Preliminary surveys revealed that the majority of educators lacked optimal skills in using office software such as Microsoft Word, Excel, PowerPoint, and Google Workspace, which negatively impacted administrative efficiency and the quality of digital-based learning. This issue prompted the implementation of an intensive training program using a learning by doing approach, featuring hands-on practice, case studies, and simulations based on real educational needs. The training was conducted in several structured modules, covering basic application use, academic data management, and the development of digital teaching materials. Participants completed assignments and were evaluated through pre-tests and post-tests. Results showed a significant improvement in digital skills, with 80% of participants demonstrating technical progress and 92% expressing satisfaction and finding the training highly beneficial. Furthermore, several madrasahs began adopting digital-based administrative systems, indicating a tangible impact on digital transformation within educational institutions. Program outcomes include digital training modules, ready-to-use administrative document templates, and improved teacher capacity in data management and the development of engaging learning content. This initiative also fostered greater awareness of the importance of digital literacy among educators and opened up opportunities for sustained professional development through follow-up mentoring and advanced training sessions. Overall, the program successfully contributed to improving educational quality and teacher efficiency in the digital era.
Peningkatan Literasi Digital UMKM melalui Pelatihan Pemasaran Digital dan E-Commerce di Kota Cirebon Ade Rizki Rinaldi; Agus Bahtiar; Aziz Chairul Imam; Bima Anurgraha Djajnegara
AMMA : Jurnal Pengabdian Masyarakat Vol. 1 No. 03 (2022): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

Abstract

This community service program aims to improve digital literacy among Micro, Small, and Medium Enterprises (MSMEs) through training in online marketing and e-commerce. The background of this program stems from the low level of understanding and skills among MSME actors in utilizing digital technology to support business marketing and management online. The problems faced by MSME partners include limited use of social media, suboptimal management of online marketplaces, and a lack of digital branding strategies to expand market reach. To address these issues, the program offers a solution in the form of digital literacy training, which includes online marketing strategies, social media optimization, marketplace account management, and digital-based transaction management. The implementation method of this program involves several stages: identifying partner needs, preparing training materials and modules, conducting workshops, providing intensive mentoring, and evaluating the development of the partners. The results of this program show that participants experienced a significant increase in their understanding and skills in online marketing. Most participants were able to create and manage social media and marketplace accounts for their businesses and apply digital marketing strategies to promote their products. In addition, this program produced several outputs, including training modules, digital guide templates, activity documentation, and the formation of a digital-based MSME community. With this program, it is expected that MSMEs can become more adaptive to technological developments, expand their market reach, increase their revenue, and strengthen their competitiveness in an ever-evolving digital era. The program also recommends ongoing mentoring so that MSMEs can continuously develop their digital skills in a sustainable manner.
OPTIMIZING VGG-16 CONVOLUTIONAL NEURAL NETWORK FOR PAP SMEAR IMAGE CLASSIFICATION IN CERVICAL CANCER DETECTION Odi Nurdiawan; Heliyanti Susana; Ade Rizki Rinaldi; Ahmad Asyraful Hijrah; Indah Diniarti
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.7131

Abstract

Early detection of cervical cancer through Pap smear image analysis plays a crucial role in reducing mortality rates associated with this disease. This study aims to optimize the VGG16 architecture to improve the classification accuracy of Pap smear images. The proposed method employs transfer learning with pre-trained ImageNet weights, customization of fully connected layers, and data augmentation techniques to enhance the diversity of training images. Experimental results demonstrate a significant improvement in training accuracy, reaching 98.50%, while validation accuracy remained stable at 88.24%, indicating potential overfitting. Performance testing on unseen data yielded an accuracy of 80%, with high precision for the negative class but low recall for the positive class, suggesting a bias toward the majority class. These findings highlight the need for additional strategies, such as data balancing and hybrid method integration, to improve sensitivity to positive cases. This research contributes to the development of adaptive deep learning-based classification models that support clinical decision-making in cervical cancer screening and opens opportunities for further research on model optimization and dataset expansion.
SOLAR-POWERED IOT-BASED BEHAVIORAL VALIDATION SYSTEM FOR SUSTAINABLE RAT PEST CONTROL IN RURAL RICEFIELDS Willy Prihartono; Ade Rizki Rinaldi; Cep Lukman Rohmat; Odi Nurdiawan
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 4 (2026): JITK Issue May 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i4.7247

Abstract

Rice-field rats (Rattus argentiventer) continue to cause substantial rice yield losses in Indonesia, reaching up to 30% per season. This study presents a solar-powered IoT-based ultrasonic deterrent system designed for autonomous operation in off-grid rural environments. The system integrates PIR motion detection, PWM-controlled ultrasonic emission (16–20 kHz; 85–95 dB), and a solar-battery energy subsystem to ensure continuous nocturnal functionality. Field validation involving 21 rats demonstrated measurable short-term behavioral disruption, with 42.9% avoidance and 33.3% panic responses. Electrical testing confirmed stable night-time performance, with an average power output of 26.8 W during peak rodent activity. Statistical analysis showed χ²(2, N = 21) = 2.38, p = 0.30. While statistical significance was not achieved, the observed effect size (Cramer’s V = 0.24) indicates a moderate behavioral association, supporting practical deterrent potential under field conditions. Unlike prior studies that evaluate sensing or energy components separately, this research integrates renewable energy autonomy, real-field behavioral validation, and IoT-based automation within a single operational framework. The findings establish a foundation for adaptive, machine-learning-driven pest control systems to enhance sustainable rice-field management