Article Per Year (5 Year)
p-Index From 2021 - 2026
2.735
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Informasi Jurnal Presipitasi : Media Komunikasi dan Pengembangan Teknik Lingkungan Journal of ICT Research and Applications Indonesia Symposium on Computing Indonesian Journal on Computing (Indo-JC) IJoICT (International Journal on Information and Communication Technology) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JURNAL MEDIA INFORMATIKA BUDIDARMA Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control JITTER (Jurnal Ilmiah Teknologi Informasi Terapan) Zero : Jurnal Sains, Matematika, dan Terapan eProceedings of Engineering Bulletin of Social Informatics Theory and Application LOGIC: Jurnal Penelitian Informatika IJoICT (International Journal on Information and Communication Technology)
Kemas Rahmat Saleh Wiharja
Universitas Telkom
Agriculture, Biological Sciences & Forestry Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Library & Information Science Mathematics Mechanical Engineering Physics Social Sciences

Published : 40 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 40 Documents
Search

 1   2   3   4 
Prediksi Diagnosis Hepatitis B Virus Menggunakan Gated Graph Neural Network Wisnu Ramadhan, Fadhil; Saleh Wiharja , Kemas Rahmat
eProceedings of Engineering Vol. 12 No. 1 (2025): Februari 2025
Publisher : eProceedings of Engineering

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

Abstract

Abstrak— Hepatitis merupakan infeksi virus pada hati dan dapat menyebabkan komplikasi terhadap penyakit lain yang dialami oleh pasien. Diagnosis dini dan penanganan yang tepat sangat penting untuk mencegah progresi penyakit dan komplikasi lebih lanjut.Diperlukan sebuah sistem prediksi diagnosis hepatitis yang akurat untuk menangani dan mengatasi kemungkinan terjangkitnya seseorang akan hepatitis. Penelitian ini melakukan prediksi model Gated Graph Neural Network terhadap pilihan data Hepatitis UCI Machine Learning Repository. Pada penelitian ini dilakukan pemodelan dan penelitian model dengan dua model graph neural network lainnya dan menghasilkan evaluasi yang baik pada prediksi klasifikasi node Hepatitis, dengan menggunakan Gated Graph Neural Network model menunjukan nilai yang superior terhadap 2 metode lain yaitu GAT dan GCN. Dimana GGNN mendapatkan nilai Accuracy, Precision, dan Recall diatas 90%. Kata Kunci: Hepatitis, Gated Graph Neural Network, Prediksi.
Sistem Tanya Jawab menggunakan Knowledge Graph mengenai Sistem Tata Surya Muhammad, Jaish; Saleh Wiharja, Kemas Rahmat
eProceedings of Engineering Vol. 12 No. 1 (2025): Februari 2025
Publisher : eProceedings of Engineering

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

Abstract

Abstrak - Manfaat dari Knowledge Graph (KG) bisa kita amati langsung, seperti optimalisasi search engine query Google, yang mempermudah dalam mencari sesuatu di internet. Diatas KG bisa juga dibangun sebuah Question Answering System (QA). Penelitian ini menggunakan artikel-artikel mengenai sistem tata surya dari halaman web NASA. Dengan menggunakan NLTK, artikel-artikel yang didapatkan dari halaman web NASA dipecah ke dalam bentuk triple. Triple tersebut kemudian diubah ke dalam bentuk Knowledge Graph yang disimpan di dalam Neo4j, kemudian dibangun QA System diatasnya. Proses validasi hasil sistem melibatkan ahli di bidang Astronomi. Hasil dari sistem ini adalah sistem yang menjawab query pertanyaan mengenai sistem tata surya. Performansi sistem diukur menggunakan akurasi, precision, recall, f1 score, dan mean reciprocal rank, yang mana didapatkan Akurasi = 0.78, Precision = 0.5, Recall = 1, F1 Score = 0.67, dan MRR = 0.2112955621. Kata kunci - Knowledge Graph, Question Answering system, NASA, triple, sistem tata surya.
Utilizing GP 2 for Restaurant Recommendation Nitamayega; Gia Septiana Wulandari; Kemas Rahmat Saleh Wiharja
Indonesian Journal on Computing (Indo-JC) Vol. 9 No. 1 (2024): April, 2024
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2024.9.1.907

Abstract

The increasing diversity of food and beverage providers poses a challenge for people to find a restaurant that aligns with their preferences. Restaurant recommendation systems can address this problem by providing accurate and relevant suggestions. Although there are many previous studies have explored various recommendation methodologies, the utilization of knowledge graph implemented with GP 2 is still limited. Knowledge graphs can represent complex information in a structured way, while GP 2 is a graph-specific programming language that has a simple syntax. This research focuses on the implementation of a knowledge graph-based restaurant recommendation system with GP 2. The recommendation scheme built can provide the best accuracy, reaching 84.97%. This shows that the knowledge graph-based restaurant recommendation system with GP 2 can demonstrate the effectiveness of the system in providing accurate and relevant recommendations, showing the potential of knowledge graph and GP 2 for the development of recommendation systems in the future and being an effective solution to overcome recommendation problems.
SAFE NUSANTARA: A semi-automatic framework for engineering and populating a Nusantara Food Ontology Wiharja, Kemas Rahmat Saleh; Barawi, Mohamad Hardyman; Romadhony, Ade; Atastina, Imelda; Dharayani, Ramanti; Othman, Mohd Kamal
International Journal on Information and Communication Technology (IJoICT) Vol. 10 No. 2 (2024): Vol.10 No. 2 Dec 2024
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v10i2.1042

Abstract

Constructing a comprehensive food ontology, particularly for culturally diverse cuisines like Southeast East Asian (Nusantara), is hindered by the variability of online recipes and the scarcity of structured data. This research introduces SAFE Nusantara, a novel semi-automated system designed to build and populate a Nusantara food ontology by extracting relevant terms from diverse online sources in Indonesian and Malaysian languages. By leveraging a combination of techniques, including topic modelling, natural language processing, and knowledge graph techniques, SAFE Nusantara addresses the challenges of data format diversity and language specificity. The system has demonstrated significant improvements in the accuracy of food classification and has the potential to enhance food recommendation systems and cultural heritage preservation efforts.
Visualisasi Al- Qur’an Berbasis Knowledge graph dengan Ayat Sebagai Vertex Ayuningtyas, Shinta Cyntia; Wiharja, Kemas Rahmat Saleh; Nhita, Fhira
eProceedings of Engineering Vol. 10 No. 3 (2023): Juni 2023
Publisher : eProceedings of Engineering

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

Abstract

Abstrak-Al- Qur’an merupakan sumber utama ajaran agama islam yang memiliki derajat keterkaitan yang sangat tinggi diantara ayat-ayatnya. Cara yang paling natural untuk menyajikan keterkaitan antara ayat ini adalah dengan menyajikan Al-Qur’an dalam format knowledge graph. Penelitianini akan mencoba menyajikan Al-Qur’an dalam format Knowledge graph dengan setiap ayat yang akan dijadikan sebagai node dan hubungan antar setiap ayat yang dijadikan relasi (busur) pada Knowledge graph. Sebelumnya sudah ada penelitian yang menyajikan Al- Qur’an dalam bentuk Knowledge graph dengan menggunakan Neo4j yang berjudul ‘Visualisasi Tematik Al- Qur’an berbasis Knowledge Graph’. Berbeda dengan penelitian sebelumnya pada penelitian ini akan digunakan TigerGraph untuk proses penyajian knowledge graph. Pada proses pengujian dilakukan 2 tahap yaitu membandingkan antara penelitian ini dengan penelitian sebelumnya dalam hal kelengkapan keterhubungan ayat yang dihasilkan. dan melibatkan penguji (ahli Al - Qur’an) untuk menguji kelengkapan keterhubungan ayat yang dihasilkan. Hasil yang didapatkan dari penelitian ini adalah pada pengujian tipe pertama data yang dapat dimunculkan oleh sistem ini memiliki hasil tema yang lebih lengkap daripada penelitian sebelumnya karena menggunakan dataset yang berbeda. Pada pengujian tipe kedua memiliki hasil keterkaitan yang berbeda saat divalidasi oleh penguji dikarenakan data yang dihasilkan sesuai dengan data yang berasal dari sumber dataset, perbedaan hasil keterkaitan ini dikarenakan adanya beberapa perbedaan pendefinisian kata atau kalimat tertentu dari pengertian bahasa arab saat diterjemahkan kedalambahasa indonesia.Kata kunci -Al – Qur’an , knowledge graph , visualisasi tematik ,tigergraph.
Prediksi Diagnosis Hepatitis B Virus Menggunakan Gated Graph Neural Network Fadhil Wisnu Ramadhan; Wiharja, Kemas Rahmat Saleh
LOGIC: Jurnal Penelitian Informatika Vol. 3 No. 1 (2025): September 2025
Publisher : Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/logic.v3i1.9855

Abstract

Hepatitis merupakan infeksi virus pada hati dan dapat menyebabkan komplikasi terhadap penyakit lain yang dialami oleh pasien. Diagnosis dini dan penanganan yang tepat sangat penting untuk mencegah progresi penyakit dan komplikasi lebih lanjut. Diperlukan sebuah sistem prediksi diagnosis hepatitis yang akurat untuk menangani dan mengatasi kemungkinan terjangkitnya seseorang akan hepatitis. Penelitian ini melakukan prediksi model Gated Graph Neural Network terhadap pilihan data Hepatitis UCI Machine Learning Repository. Pada penelitian ini dilakukan pemodelan dan penelitian model dengan dua model graph neural network lainnya dan menghasilkan evaluasi yang baik pada prediksi klasifikasi node Hepatitis, dengan menggunakan Gated Graph Neural Network model menunjukan nilai yang superior terhadap 2 metode lain yaitu GAT dan GCN. Dimana GGNN mendapatkan nilai Accuracy, Precision, dan Recall diatas 90%.
Automated Social Media Advertising Poster Design Using a Multi-Agent AI Framework Christiana Naida Putri; Kemas Rahmat Saleh Wiharja
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 3 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i3.27563

Abstract

This study proposes an automated system for social media advertising poster generation using a role-based multi-agent architecture implemented with CrewAI. The system decomposes the design task into three sequential agents responsible for text generation, visual asset recommendation, and grid-based layout optimization. A formal 12×12 discrete layout model is employed to represent spatial constraints, enabling consistent and structured poster composition. System performance was evaluated through user testing involving five respondents using a five-point Likert scale. The results show mean scores of 3.2 for content completeness, 3.6 for layout consistency, 3.8 for text relevance, and an overall performance mean of 3.4 (SD = 0.15), indicating satisfactory usability. From an applied mathematics perspective, this work contributes a computational layout formulation using grid discretization and rule-based optimization, as well as a quantitative evaluation of multi-agent coordination efficiency. The proposed framework demonstrates that agentic AI can effectively support structured visual content generation while maintaining user-controlled refinement.
QURANIC KNOWLEDGE GRAPH: A MULTIDISCIPLINARY APPROACH TO MAPPING SEMANTIC NETWORKS IN THE QURAN Kemas Saleh Rahmat Wiharja; Muhammad Arif Bijaksana; Kemas Muslim Lhaksmana; Hafizh Putra Ardhana; Muhammad Aqil Ghazali Anhein
IJoICT (International Journal on Information and Communication Technology) Vol. 12 No. 1 (2026): Vol.12 No.1 Jun 2026
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/ijoict.v12i1.10653

Abstract

Understanding the Al-Quran is the eternal goal of every Muslim, wherever they are. Before the emergence of the Knowledge Graph, readers of the Al-Quran needed to move from the Al-Quran to Tafsir, Hadith, scholar opinions or other resources in order to grasp the full meaning of a verse or a chapter in the Al-Quran. To help the readers of the Al- Quran in pondering the meaning of the Al-Quran and linking the verses to the meaning of the word or the interpretation of the verse in a tafsir book, we propose the first multi-layer Quranic Knowledge Graph that uses the property graph format. We also add a chatbot on top of our Quranic Knowledge Graph. And to save cost in using a Large Language Model, we deploy a vector database to memorize the previously answered user queries and their corresponding Cypher translations. We evaluate our approach using three point of views: large language model, knowledge graph, and chatbot. The result of evaluation shows that our Quranic Knowledge Graph achieves 100% correctness and 90% accuracy, despite only covering 9 parts of the Al-Quran. For the interested readers, please access https://zentilax.github.io/quranic-chatbot-UI/ for exploring the quranic knowledge graph
PM2.5 Temporal Pattern in Jambi City: Meteorological Drivers and Air Mass Trajectory Analysis Benedy Fajar; Muhammad Damris; Kemas Rahmat Saleh Wiharja; Elma Mutmainnah; Noorlin Mohamad; Rizki Andre Handika
Jurnal Presipitasi : Media Komunikasi dan Pengembangan Teknik Lingkungan Vol 23, No 2 (2026): July 2026
Publisher : Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/presipitasi.v23i2.402-413

Abstract

Air pollution, particularly particles with a diameter of less or equal than 2.5 micrometers (PM2.5), has become an important global health and environmental problem. Jambi City in Sumatra is highly susceptible to this issue, both locally and particularly influenced by forest fires. As early studies were conducted over a short period, this study examined the meteorological factors that influenced PM2.5 levels and estimated the pollutant transport pathways over two years in the post-COVID-19 period (2023-2024). The methods employed were time-series analysis, scatter-plot evaluation, multiple linear regression analysis, and backward trajectory modeling using HYSPLIT. The results show that the average PM2.5 concentration in 2023 (30.53 µg/m³) was higher than in 2024 (25.36 µg/m³), with night-time levels generally exceeding day-time levels. 3.69% of the days exceeded Indonesia’s daily air quality standard, while 90.83% surpassed the stricter WHO guideline. Meteorological factors explained only 23–38% of PM2.5, with temperature positively correlated, wind speed showing mixed effects, and humidity and rainfall negatively correlated.. The major PM₂.₅ sources influenced by the southeast–South Sumatra, particularly South Sumatra, highlighting the strong stimulus of transboundary emissions alongside local sources. In the future, studies focusing on chemistry-based source apportionment are needed to accurately separate each contributing source.
DETR-CLIP-BLIP Integrated Framework for Context-Guided Multimodal Knowledge Graph Retrieval Raihan Atsal Hafizh; Kemas Rahmat Saleh Wiharja
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 5 (2026): October 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i5.7647

Abstract

Image search systems that rely on metadata tags or basic captions often miss the semantic relationships and visual details needed for complex queries. This study presents a multimodal knowledge graph framework that combines DETR for object detection, CLIP for attribute classification across 188 dimensions, and BLIP for caption generation. On the COCO 2017 validation set (5,000 images), the pipeline processed 4,906 images successfully, of which 4,243 contained the multiple objects required for relationship extraction. The resulting knowledge graph reached 99.98% relational coverage among multi-object images and 2.94 relationships per image, with 117 of the 188 attributes appearing in the data. Retrieval was evaluated under a self-consistency protocol relevance defined by the system's own top-ranked matches yielding an MRR of 0.96 for keyword-based queries and 0.29 for relationship-based queries, with Recall@50 of 88% for the latter. The framework runs on pretrained models without task-specific training and produces both structured triples and human-readable descriptions, supporting applications such as visual question answering, scene understanding, and context-aware image retrieval.
Co-Authors A. Nurul Istiqamah Ade Romadhony Adiwijaya Ahmad Ridwan Rezani Akbar Gozali Akbar Gozali Alfian Akbar Gozali Anisa Herdiani Aufa Bil Ahdi P Ayuningtyas, Shinta Cyntia Barawi, Mohamad Hardyman Benedy Fajar Christiana Naida Putri Damris Muhammad Dana Sulistiyo Kusumo Danang Triantoro Murdiansyah Defrianda Rizky Pranata Donny Faturrachman Elma Mutmainnah Emir Septian Sori Dongoran Fadhil Wisnu Ramadhan Fauzi Aulia Rahman Fauzi Aulia Rahman Fhira Nhita Fikriansyah, Muhammad Arya Fitriyani Fitriyani Gede Agung Ary Wisudiawan Gia Septiana Wulandari Hadyan Arif Hafizh Putra Ardhana Hafizh, Raihan Atsal Harris Febryantony Z Hegar Aryo Dewandaru Hegar Aryo Dewandaru I Gusti Bagus Ady Sutrisna Ibnu Asror Ilham Kamil Noviandi Imelda Atastina Irvan Nur Aziz Isjhar Kautsar Kemas Muslim Lhaksmana Ludovica Gorganusa Lukman Arie Susanto Mira Kania Sabariah Mochammad Fitrah Eka Pramudita Mohamad Fauzy Mohammad Fauzy Muhammad Aqil Ghazali Anhein Muhammad Arif Bijaksana Muhammad Ramadhan Gandidi Muhammad Zakiyullah Romdlony Muhammad, Jaish Nitamayega Nitamayega Noorlin Mohamad Nungki Selviandro Nunit Prihatoni Siregar Nurzakiah, Azmi othman, mohd kamal Raihan Atsal Hafizh Ramadhanti, Aisyah Dliya Ramanti Dharayani Riche Julianti Wibowo Rizki Andre Handika Shaufiah . Shinta Yulia Puspitasari Taufiqurrahman Taufiqurrahman Tiwa Ramdhani Wijaya, Dewa Made Wisnu Ramadhan, Fadhil Wisnu Riyan Pratama Putra Yustiawan, Yoga