Article Per Year (5 Year)
p-Index From 2021 - 2026
5.486
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) MEDIA ELEKTRIKA Transmisi: Jurnal Ilmiah Teknik Elektro JURNAL SISTEM INFORMASI BISNIS Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Journal of Telematics and Informatics Jurnal Transformatika Proceeding of the Electrical Engineering Computer Science and Informatics TRANSISTOR Elektro dan Informatika AKSIOLOGIYA : Jurnal Pengabdian Kepada Masyarakat Indonesian Journal of Community Services Abdi: Jurnal Pengabdian dan Pemberdayaan Masyarakat Jurnal Pengabdian kepada Masyarakat Nusantara Community Empowerment JAST Prosiding University Research Colloquium Prosiding Seminar Riset Mahasiswa Jurnal Ilmiah Sultan Agung Jurnal Rekayasa Sistem Informasi dan Teknologi Journal of Data Analytics, Information, and Computer Science (JDAICS) JuTISI (Jurnal Teknik Informatika dan Sistem Informasi) Inventa: Journal of Science, Technology, and Innovation Journal of Software Engineering and Multimedia (JASMED)
Sam Farisa Chaerul Haviana
Universitas Islam Sultan Agung
Religion Arts Humanities Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Public Health Social Sciences Other

Published : 58 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 58 Documents
Search

 2   3   4   5   6 
Generasi Desain Pakaian Muslimwear Berbasis Multimodal (Teks dan Gambar) Menggunakan Stable Diffusion v1.5 Assyfa Febriwanti; Sam Farisa Chaerul Haviana
Journal of Science, Technology, and Innovation Vol 1 No 3 (2026): : April: Inventa: Journal of Science, Technology, and Innovation
Publisher : CV SCRIPTA INTELEKTUAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65310/abf5c845

Abstract

The rapid advancement of Generative Artificial Intelligence has accelerated the adoption of diffusion models in fashion design applications. However, conventional text-to-image approaches often encounter limitations in maintaining visual consistency and controllability during image generation. This study proposes a multimodal Muslimwear design generation system based on Stable Diffusion v1.5 by integrating textual prompts and reference images through a cross-attention fusion mechanism. The training dataset combines DeepFashion1 and a curated Muslimwear dataset, which were preprocessed through image normalization, resolution standardization, and automated caption generation using BLIP. Domain adaptation was performed using the Low-Rank Adaptation (LoRA) technique to enable computationally efficient fine-tuning. Performance evaluation employed Fréchet Inception Distance (FID) and Structural Similarity Index Measure (SSIM) to assess visual quality and structural consistency. Experimental results indicate that the female model achieved a FID score of 176.77 and an SSIM score of 0.311, outperforming the male model with a FID score of 256.22 and an SSIM score of 0.275. The findings demonstrate that multimodal conditioning enhances visual distribution learning and structural preservation, supporting the development of controllable and efficient AI-assisted fashion design systems.
DESIGN OF AN AUTOMATED CLASSIFICATION SYSTEM USING INDOBERT TRANSFORMERS AND LOCAL NEWS TEXT SUMMARIZATION WITH LLAMA 3 ON RADARTEGAL.COM Keisya Anazwa Octa Reviandy; Sam Farisa Chaerul Haviana
Journal of Data Analytics, Information, and Computer Science Vol. 3 No. 3 (2026): Juli
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jdaics.v3i3.3659

Abstract

In the digital news production process, editorial teams face challenges in manually categorizing news articles and generating summaries, which are time-consuming, inefficient, and prone to inconsistencies that affect content management quality and Search Engine Optimization (SEO). This study aims to design and develop an automated system for news classification and summarization on the radartegal.com platform using the Transformer-based IndoBERT model for automatic news category classification and the Large Language Model (LLM) LLaMA 3 for abstractive text summarization. The research methodology consisted of problem identification, literature review, dataset collection, text preprocessing, IndoBERT fine-tuning, LLaMA 3 implementation, pipeline integration, and system evaluation. Classification performance was evaluated using accuracy, precision, recall, and F1-score, while summarization quality was evaluated using ROUGE metrics. Experimental results showed that the IndoBERT model achieved an accuracy of 84.00%, precision of 84.58%, recall of 84.00%, and F1-score of 83.95%. Meanwhile, the LLaMA 3 summarization module achieved ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.4672, 0.2732, and 0.4122, respectively. The integrated system successfully automated editorial workflows, improved categorization consistency, generated informative summaries, and supported SEO optimization. These findings demonstrate that the proposed system can improve editorial efficiency while maintaining content quality in local digital news publishing.
Detection of Nutrition Deficiency in Iceberg Lettuce Plants Using Autoencoder and Multilayer Perceptron Methods Sadra Din Azizi Muhammad; Sam Farisa Chaerul Haviana
Journal of Software Engineering and Multimedia (JASMED) Vol. 3 No. 2 (2025): Journal of Software Engineering and Multimedia (JASMED)
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/jasmed.v3i2.10130

Abstract

Iceberg lettuce was selected as the research object because its leaves show clear visual responses to nutrient deficiencies, while visual inspection methods commonly used by small- and medium-scale growers remain subjective. This study aims to develop an automated detection system for nutrient deficiency using an autoencoder combined with a Multilayer Perceptron (MLP). The dataset was sourced from Kaggle and categorized into four classes: Nitrogen, Phosphorus, Potassium, and Healthy. The preprocessing stage included converting images from BGR to HSV, resizing to 128×128 pixels, normalizing to 0–1, and applying an 80:20 train–test split. Feature extraction was performed using the autoencoder (encoder, bottleneck, decoder), while classification was carried out using the MLP (input, hidden, and output layers). Evaluation using a confusion matrix showed an accuracy of 86%, precision of 89%, recall of 87%, and an F1-score of 88%. The system has been implemented in a user-friendly web application that allows users to upload images and obtain detection results instantly. In conclusion, integrating autoencoder and MLP proved effective for automated nutrient deficiency detection in iceberg lettuce, providing a more objective alternative to conventional visual diagnosis.
Song Lyric Meaning Generator Using Transformer (Case Study: Drake's Song Lyrics) Tubagus Alwasi'i; Sam Farisa Chaerul Haviana
Journal of Software Engineering and Multimedia (JASMED) Vol. 3 No. 1 (2025): Journal of Software Engineering and Multimedia (JASMED)
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/jasmed.v3i1.10132

Abstract

The limited availability of structured and credible sources that interpret Drake’s song lyrics makes it difficult for listeners to fully grasp the meaning and emotional depth within his music. This study aims to develop a web-based lyric meaning generator capable of automatically interpreting Drake’s lyrics using the Transformer architecture. The system employs the LLaMA 3 model, which is fine-tuned through Low-Rank Adaptation (LoRA) to improve training efficiency while maintaining high semantic accuracy. The curated dataset consists of Drake’s song lyrics, their corresponding interpretations, and metadata such as album and reference sources. Data preprocessing and supervised fine-tuning were conducted using the Hugging Face framework in Google Colab. A  gradio-based web application was implemented with a Retrieval-Augmented Generation (RAG) mechanism to enhance contextual relevance during inference. Evaluation metrics, including Semantic Similarity and ROUGE-L, were applied to measure the model’s ability to produce coherent and contextually aligned interpretations. The results demonstrate that the fine-tuned LLaMA 3 model effectively generates accurate lyric meanings while reducing computational cost. Overall, this study highlights the potential of Transformer-based models to bridge the gap between music and natural language understanding, particularly in analyzing metaphorical and emotion-rich song lyrics.
Deep neural network classification in chatbot system family health counseling services Andi Riansyah; Sam Farisa Chaerul Haviana; Ratna Supradewi; Muhammad Ainul Wahib
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i2.pp1211-1218

Abstract

Mental health problems affect many aspects of life, including physical well being, work productivity, social functioning, and suicide risk. In Indonesia, access to professional mental health services remains very limited: only a small proportion of people with depression receive treatment and the number of mental health professionals per population is far below international recommendations, creating an urgent service gap. This study proposes an artificial intelligence–based chatbot to support family mental health counseling services in Indonesia. The chatbot uses a deep neural network (DNN) to classify user questions into counseling intent categories and to provide appropriate responses. Psychologists compiled and verified a dataset of Indonesian counseling questions and responses, which was then pre processed using standard text processing techniques and encoded with a bag of words (BoW) representation. A fully connected DNN with one input layer, two hidden layers of eight neurons each, and a SoftMax output layer was trained using the Adam optimizer (learning rate 0.01) on 80% of the data and evaluated on the remaining 20%. The best configuration achieved a training accuracy of 96%, with test results of 93% accuracy, 92% precision, 93% recall, and 92% F1-score. These findings indicate that proposed DNN based chatbot can accurately classify counseling intents and generate contextually appropriate responses, suggesting its potential as complementary tool to support initial family mental health counseling in Indonesia.
IMPLEMENTASI MODEL INDOBERT UNTUK ANALISIS SENTIMEN PUBLIK TERHADAP ISU DUGAAN IJAZAH PALSU PRESIDEN JOKO WIDODO DALAM PERCAKAPAN DI PLATFORM X (TWITTER) Naufal Rafif Ramadhani; Sam Farisa Chaerul Haviana
Jurnal Ilmiah Penelitian Mahasiswa Vol 5, No 1 (2026): MARET 2026
Publisher : Jurnal Ilmiah Sultan Agung

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

Abstract

Penelitian ini membahas implementasi model IndoBERT untuk analisis sentimen publik terhadap isu dugaan ijazah palsu Presiden Joko Widodo di Platform X (Twitter). Tujuan penelitian ini adalah mengklasifikasikan opini publik menjadi tiga kategori sentimen, yakni positif, netral, serta negatif, untuk mengetahui kecenderungan opini masyarakat terhadap isu yang tengah berkembang. Metode yang dipergunakan yakni pendekatan kuantitatif dengan eksperimen model IndoBERT-base-p1 yang di-fine-tune menggunakan dataset berbahasa Indonesia. Data dikumpulkan melalui Twitter API v2 dengan kata kunci terkait isu tersebut, kemudian melalui tahapan preprocessing meliputi cleaning, case folding, normalisasi, tokenisasi, filtering, serta stemming. Sebanyak 2.113 tweet digunakan dan diklasifikasikan ke dalam data latih serta data uji dengan perbandingan 70:30. Model dilatih mempergunakan algoritma AdamW optimizer dengan fungsi Cross-Entropy Loss dan dievaluasi mempergunakan metrik accuracy, precision, recall, serta F1-score. Hasil uji memperlihatkan bahwasanya model IndoBERT memiliki akurasi sebesar 91,13% dengan nilai F1-score sejumlah 0,91, menandakan performa klasifikasi yang sangat baik serta stabil. Distribusi hasil analisis memperlihatkan dominasi sentimen negatif sejumlah 61%, disusul sentimen positif sejumlah 23% serta netral sejumlah 16%. Model ini diimplementasikan ke dalam aplikasi web berbasis Streamlit yang memungkinkan pengguna melaksanakan analisis sentimen secara langsung dan menampilkan hasil dalam bentuk visualisasi interaktif berupa pie chart, bar chart, dan wordcloud. Temuan studi ini menunjukkan bahwa IndoBERT mampu memahami konteks opini publik dalam Bahasa Indonesia secara efektif dan dapat dijadikan dasar pengembangan sistem analisis opini publik yang informatif dan aplikatif.Kata Kunci: Analisis Sentimen, IndoBERT, Opini Publik, Media Sosial, Platform X
PREDIKSI KECEPATAN RATA-RATA BERSEPEDA BERDASARKAN KONDISI TOPOGRAFI DAN FAKTOR CUACA MENGGUNAKAN XGBOOST DARI DATA STRAVA Rifqy Ramdhani Hakim; Sam Farisa Chaerul Haviana
Jurnal Rekayasa Sistem Informasi dan Teknologi Vol. 3 No. 2 (2025): November
Publisher : Yayasan Nuraini Ibrahim Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70248/jrsit.v3i2.3143

Abstract

Meningkatnya minat bersepeda dan penggunaan aplikasi perekam data seperti Strava menuntut pemahaman mendalam mengenai faktor yang memengaruhi performa. Kecepatan rata-rata sangat dipengaruhi oleh variabel non-linear seperti kondisi topografi dan cuaca, sehingga memerlukan model prediksi yang akurat. Tujuan penelitian ini adalah mengimplementasikan Extreme Gradient Boosting (XGBoost) untuk membangun model prediksi kecepatan rata-rata bersepeda. Penelitian berfokus memodelkan hubungan antara data historis aktivitas Strava dengan variabel lingkungan. Metode penelitian dimulai dari pengumpulan data aktivitas pribadi (Juni 2024 - Agustus 2025) , mencakup fitur jarak, elevasi, cuaca, dan waktu tidur. Data mentah melalui pra-pemrosesan, termasuk normalisasi Min-Max Scaler. Data dibagi menjadi 80% data latih dan 20% data uji. Model XGBRegressor dilatih dengan hyperparameter seperti n_estimators=300 dan learning_rate=0.2. Kinerja model dievaluasi menggunakan Root Mean Squared Error (RMSE) dan R-squared (R²). Hasilnya, model XGBoost mampu memberikan estimasi kecepatan dengan akurasi cukup baik. Model mencapai skor RMSE 1.240 km/jam , yang mengindikasikan rata-rata kesalahan prediksi. Selain itu, model memperoleh nilai R² sebesar 0.800. Nilai R² ini berarti model mampu menjelaskan 80% variasi data kecepatan. Kesimpulannya, model XGBoost terbukti representatif
Implementasi Algoritma Cosine Similarity pada sistem arsip dokumen di Universitas Islam Sultan Agung Dedy Kurniadi; Sam Farisa Chaerul Haviana; Andika Novianto
Jurnal Transformatika Vol. 17 No. 2 (2020): January 2020
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v17i2.1613

Abstract

Archiving in University that have not been well organized will cause a problems, the documents need for structuring and archives properly in the systems for the good standard a universities. The most importance of ease in finding the required archives is an important reason why it is necessary to develop an archive search system that can facilitate and improve the process of searching the archived document. Apllying cosine similarity algorithm in Information Systems is a solution for University to organizing archived documents, results from this reserach is the systems can show the relavant document from database list with precision 88.8% and recall 76.1%   from all the data in database.  
Co-Authors A Asyhari Achya Puji Sari Adhi, Anjas Restu Mulia Akhsinatul Laeliyah Andika Novianto Arief Budiman Ariyanto, Bagas Afza Joko Assyfa Febriwanti Asyhari Asyhari Asyhari Asyhari, Asyhari Asyhari, A Azizah, Eka Nurul Badie'ah, Badie'ah Badieah Assegaf Badie’ah, Badie’ah Dedy Kurniadi Dedy Kurniadi Dedy Kurniadi Dedy Kurniadi Ellisa Mu'alifah Fadhilah, Achmad Naufal Fahmi Arif Dewoputro Fatimah, Akmalia Ghozi Fidaul Haq Hermawan, Hildan Mulyo Huda, Rizky Miftachul Ilham Pradipta, Muhammad Ilhamsyah, Muhamad Reynaldi Imam Much Ibnu Subroto Keisya Anazwa Octa Reviandy Komsiyah Afri Maryuliana Maryuliana Milasanti, Denina Moch Taufik Muhammad Ainul Wahib Muhammad Nur Gofinda Muhammad Taufik Munir, Abdulloh Nada, Anita Soffiyun Naufal Rafif Ramadhani Nur Fatahna Nurinayah, Alfiyatu Nurnasikha, Kusuma Nurwidiana Nurwidiana Nurwidiana, N Poetro, Bagus Satrio Waluyo Putra, Ardan Nur Chaiya Putra, Yustian Dikma Eka Ratna Supradewi Riansyah, Andi Rifqy Ramdhani Hakim Riziq, Alvin Yusuf Sadra Din Azizi Muhammad Salwa Ahla Amania Sigit Ardianto Sri Mulyono Sri Mulyono Sri Mulyono Sulaiman, Noor Suhana Suryani Alifah Taufik, Muhammad Tubagus Alwasi'i Ushuludin, Mohammad Wicaksono, Yusuf Arief Widhya Nugroho Satrioajie Wiwiek Fatmawati Yacob, Azliza Yasni, Loura Yusuf Arief Wicaksono Yusuf Arief Wicaksono