Article Per Year (5 Year)
p-Index From 2021 - 2026
1.168
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika JOURNAL OF SCIENCE AND SOCIAL RESEARCH PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Jurnal Ilmiah Teknik Informatika dan Komunikasi Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK)
Pratama, Andre
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Economics, Econometrics & Finance Education Electrical & Electronics Engineering Law, Crime, Criminology & Criminal Justice Public Health Social Sciences

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
PERBANDINGAN PREDIKSI POLUSI UDARA MENGGUNAKAN LSTM DAN BILSTM Pratama, Andre; Sembiring, Asha; Nababan, Junerdi; Zarkasyi, Muhammad Imam; Rahayu, Novriza
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 3 (2025): August 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i3.3596

Abstract

Abstract: Air pollution has become a serious problem in densely populated urban areas such as DKI Jakarta. To mitigate its negative impacts, an accurate air pollution prediction system is necessary. This study compares the performance of two deep learning models, Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM), in predicting PM10 concentration using air quality data from DKI Jakarta between 2016 and 2019. The research process includes data collection and preprocessing, model training, and model evaluation. Both models were tested with various parameters such as the number of hidden neurons, dropout rate, epochs, and batch size. The results consistently show that BiLSTM outperforms LSTM, achieving lower Root Mean Square Error (RMSE) values across 54 testing scenarios. The best BiLSTM configuration, with 64 hidden neurons, 0.2 dropout rate, 50 epochs, and batch size 16, yielded an RMSE of 9.311401. Meanwhile, the best LSTM configuration, with 128 hidden neurons, 0.1 dropout rate, 100 epochs, and batch size 16, produced an RMSE of 9.330554. The advantage of BiLSTM lies in its ability to process data bidirectionally, making it more effective in capturing temporal patterns for air pollution prediction compared to LSTM. Keywords: air pollution prediction, pollutant, deep learning, LSTM, BiLSTM Abstrak: Pencemaran udara menjadi masalah serius di wilayah perkotaan padat seperti DKI Jakarta. Untuk mengurangi dampak negatifnya, diperlukan sistem prediksi polusi udara yang akurat. Penelitian ini membandingkan performa dua model deep learning, Long Short-Term Memory (LSTM) dan Bidirectional Long Short-Term Memory (BiLSTM), dalam memprediksi konsentrasi PM10 menggunakan data kualitas udara DKI Jakarta tahun 2016-2019. Proses penelitian mencakup pengumpulan dan praproses data, pelatihan model, serta evaluasi model. Kedua model diuji dengan berbagai parameter seperti jumlah hidden neuron, dropout rate, epoch, dan batch size. Hasil menunjukkan BiLSTM lebih unggul secara konsisten dengan nilai Root Mean Square Error (RMSE) lebih rendah melalui 54 skenario pengujian. Konfigurasi terbaik BiLSTM menggunakan 64 hidden neuron, dropout rate 0.2, 50 epoch, dan batch size 16 menghasilkan RMSE 9.311401. Sedangkan konfigurasi LSTM terbaik pada 128 hidden neuron, dropout rate 0.1, 100 epoch, dan batch size 16 menghasilkan RMSE 9.330554. Keunggulan BiLSTM terletak pada kemampuannya memproses data dua arah, sehingga lebih efektif dalam menangkap pola temporal untuk prediksi polusi udara dibandingkan LSTM.  Kata kunci: prediksi polusi udara, polutan, deep learning, LSTM, BiLSTM
Pelatihan Media Sosial Bilingual untuk Promosi Berkelanjutan: Studi Kasus Karang Taruna Dwikora Medan: Bilingual Social Media Training for Sustainable Promotion: A Community Service Program for Karang Taruna Dwikora Medan Ananda, Zhafran Fatih; Aurlani, Febry; Pratama, Andre
PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Vol. 10 No. 9 (2025): PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
Publisher : Institute for Research and Community Services Universitas Muhammadiyah Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33084/pengabdianmu.v10i9.9596

Abstract

Social media has become a strategic medium in modern communication, including for the sustainable promotion of products and services. Recognizing the importance of practical communication skills on digital platforms, this community service activity aimed to provide training for the Karang Taruna Dwikora Medan on socialization of using English and Indonesian for sustainable promotion on social media. The training was conducted over two days using a participatory approach, involving presentations, discussions, and hands-on practice. The materials covered include using social media as a promotional tool, techniques for creating sustainable content, and language strategies such as code-switching, bilingual hashtags, and content adaptation based on the platform. This activity showed a significant increase in participants' understanding and ability to design engaging and relevant promotional content for local and international audiences, with an 85% improvement in knowledge based on pretest and posttest evaluations. The participants' enthusiasm and active participation demonstrated this program's success in raising awareness of the importance of adaptive and inclusive communication strategies in the digital age. This activity made a real contribution to youth empowerment by mastering digital communication skills oriented toward sustainability.
Applying BERT Model for Early Detection of Mental Disorders Based on Text Input Jimmy Sunjaya; Jefferson Ong; Rezky Firmansyah Ziliwu; Henny Risni; Andre Pratama
Jurnal Ilmiah Teknik Informatika dan Komunikasi Vol. 5 No. 2 (2025): Juli: Jurnal Ilmiah Teknik Informatika dan Komunikasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juitik.v5i2.1251

Abstract

In today's digital era, awareness of mental health issues is growing significantly. Many individuals are now more open about sharing their psychological conditions through written texts on social media, forums, and surveys. This phenomenon presents an opportunity to leverage technology for the automatic detection of mental disorders through text analysis. This study aims to implement the Bidirectional Encoder Representations from Transformers(BERT) model to identify mental health conditions such as depression, bipolar disorder, anxiety, suicidal tendencies, and others. The dataset was sourced from Kaggle and underwent several preprocessing stages, including data cleaning, tokenization, and text classification model training. This BERT model achieved strong performance, with an accuracy of 91% and an average F1-Score of 0.91. These results demonstrate the model's effectiveness in identifying various psychological expressions. The findings highlight the potential for developing early detection systems that are faster, more objective, and widely accessible. However, this study acknowledges limitations in dataset diversity, suggesting future work to incorporate more varied data sources and explore other NLP models to enhance detection accuracy and coverage.
Analisis Sentimen terhadap Terorisme pada Platform Twitter menggunakan Support Vector Machine Rahayu, Novriza; Indri Yani, Sylvia; Marwah, Marwah; Pratama, Andre
Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK) Vol 4 No 1 (2025): Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK)
Publisher : STMIK Amika Soppeng

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70247/jumistik.v4i1.152

Abstract

This research aims to classify public sentiment regarding terrorism issues using the Support Vector Machine (SVM) algorithm. This topic is important because text-based sentiment analysis plays a significant role in understanding public opinion on critical issues. Initial data in the form of Indonesian text was processed through preprocessing stages, translated into English, and labeled using VADER. Data imbalance was addressed using Random Over Sampling methods, while numerical data representation was obtained through feature extraction using TF-IDF. The SVM model was evaluated using confusion matrix with accuracy, precision, recall, and F1-score metrics. The results show that the model achieved 98.02% accuracy, 98.09% precision, 98.02% recall, and 98.01% f1-score, demonstrating excellent performance in classifying sentiment into negative, neutral, and positive categories. Some prediction errors were still found in the negative and positive categories. This research demonstrates that the combination of preprocessing methods, data balancing, and TF-IDF feature extraction effectively produces an accurate sentiment classification model. This research contributes significantly to the development of text-based sentiment analysis technology to support decision making. Keywords: Sentiment Analysis, Support Vector Machine, Terrorism, Twitter Penelitian ini bertujuan mengelompokkan sentimen masyarakat terkait isu terorisme menggunakan algoritma Support Vector Machine (SVM). Topik ini penting karena analisis sentimen berbasis teks berperan signifikan dalam memahami opini publik terhadap isu-isu kritis. Data awal berupa teks berbahasa Indonesia diproses melalui tahap preprocessing, diterjemahkan ke bahasa Inggris, dan dilabeli menggunakan VADER. Ketidakseimbangan data diatasi dengan metode Random Over Sampling, sementara representasi data numerik diperoleh melalui ekstraksi fitur TF-IDF. Model SVM dievaluasi menggunakan confusion matrix dengan metrik accuracy, precision, recall, dan f1-score. Hasilnya, model mencapai akurasi 98,02%, precision 98,09%, recall 98,02%, dan F1-score 98,01%, menunjukkan performa sangat baik dalam mengklasifikasikan sentimen ke dalam kategori negatif, netral, dan positif. Beberapa kesalahan prediksi masih ditemukan pada kategori negatif dan positif. Penelitian ini menunjukkan bahwa kombinasi metode preprocessing, penyeimbangan data, dan ekstraksi fitur TF-IDF efektif menghasilkan model klasifikasi sentimen yang akurat. Penelitian ini berkontribusi secara signifikan terhadap pengembangan teknologi analisis sentimen berbasis teks untuk mendukung pengambilan keputusan. Kata kunci: Analisis Sentimen, Support Vector Machine, Terorisme, Twitter
Sistem Deteksi Berita Hoaks berbasis Algoritma Natural Language Processing (NLP) menggunakan BERT Fardhina, Azura; Siregar, Ramadhan Mustaqim; Sibarani, Mika Ria Waty Br; Ginting, Irsya Chlara Br; Pratama, Andre
Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK) Vol 4 No 1 (2025): Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK)
Publisher : STMIK Amika Soppeng

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70247/jumistik.v4i1.156

Abstract

The advancement of digital technology brings both benefits and challenges, one of which is the increasing spread of hoaxes that can trigger conflicts in various sectors such as social, cultural, political, and economic. Hoaxes are unverifiable and often provocative information that spreads rapidly across digital platforms. Indonesian society remains vulnerable to unverified information. Therefore, an artificial intelligence (AI)-based system is needed to automatically detect hoaxes. This study employs the BERT model for its ability to understand word context and perform effective semantic classification through tokenization and transformer architecture. The dataset, sourced from Kaggle, consists of 730 articles: 425 labeled as hoax and 305 as non-hoax. After preprocessing and tokenization, the data was input into the model. BERT was chosen for its strong word representation capabilities trained on a large-scale corpus. Evaluation results show that BERT achieved 98% accuracy, outperforming the previous KNN model which reached 93.33%. These findings demonstrate the effectiveness of the BERT-based approach in detecting digital disinformation.
Analysis of Factors Causing Toddler’s Malnutrition in Medan City Using the Random Forest Method Simamora, Windi Saputri; Harahap, Siti Sarah; Pratama, Andre
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15380

Abstract

Malnutrition and severe malnutrition in toddlers remain critical public health concerns that impair physical growth, cognitive development, and long-term productivity. Deficiencies in essential nutrients increase the risks of stunting, weakened immunity, and developmental delays. Although interventions such as supplementation and routine anthropometric monitoring are implemented, comprehensive identification of multidimensional causal factors is still limited, reducing the effectiveness of targeted policies. This study aims to predict toddler nutritional status using a quantitative data mining approach. A dataset consisting of 328 samples and 17 features was collected from health facilities in Medan City, including Puskesmas, the Health Office, and Posyandu. A Random Forest Classifier was developed with missing-value handling, feature engineering, and feature importance analysis to identify dominant predictors of nutritional outcomes. The model achieved an overall accuracy of 92.42 percent and showed strong performance in identifying the “Normal” class, although predictive sensitivity for minority classes such as “Gizi Kurang” and “Gizi Buruk” remained comparatively lower. Feature importance analysis indicated that complete immunization and health insurance ownership were the most influential determinants of nutritional status. This research provides a machine learning–based tool for early nutritional risk prediction and offers data-driven insights to support more precise malnutrition interventions. Future enhancement may include expanding feature diversity and applying advanced interpretability techniques to strengthen model reliability. The findings reinforce the importance of evidence-based nutrition policy strategies that prioritize early prevention and improved child health outcomes.
Klasifikasi Jenis Kelamin Berdasarkan Citra Mata Menggunakan Fitur HSV dan HOG Dengan Algoritma SVM Rahayu, Novriza; Silitonga, Marta Tabita Anggi; Jordan, Dimas; Nabila, Salwa; Pratama, Andre
Jurnal Ilmiah ILKOMINFO - Ilmu Komputer & Informatika Vol 9, No 1 (2026): Januari
Publisher : Akademi Ilmu Komputer Ternate

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47324/ilkominfo.v9i1.423

Abstract

Abstrak: Identifikasi jenis kelamin melalui analisis citra mata menjadi pendekatan yang relevan dalam aplikasi forensik dan keamanan, khususnya dalam situasi ketika identifikasi wajah tidak dapat dilakukan. Penelitian ini mengembangkan sistem klasifikasi jenis kelamin berdasarkan citra mata menggunakan kombinasi fitur HSV dan HOG dengan algoritma Support Vector Machine (SVM). Permasalahan yang diangkat adalah bagaimana mengekstraksi fitur citra mata secara representatif dan mengoptimalkan akurasi klasifikasi jenis kelamin melalui pendekatan metode yang tepat. Metode penelitian ini mencakup tahap pengumpulan data, pra-pemrosesan citra, ekstraksi fitur dengan memanfaatkan HSV untuk memperoleh karakteristik warna serta HOG untuk mengidentifikasi karakteristik bentuk, penerapan SVM sebagai algoritma klasifikasi, serta evaluasi model guna menilai performa sistem secara keseluruhan. Dataset penelitian terdiri dari citra mata dari subjek laki-laki dan perempuan dengan berbagai kondisi. Sistem klasifikasi yang dikembangkan berhasil mencapai accuracy sebesar 90,24%, precision 90,26%, recall 90,24%, dan F1-score 90,22%. Hasil penelitian menunjukkan bahwa kombinasi fitur HSV dan HOG dengan algoritma SVM mampu memberikan tingkat akurasi yang konsisten dan reliabel dalam mengklasifikasi jenis kelamin berbasis citra mata. Pendekatan ini dapat diterapkan sebagai solusi alternatif dalam sistem keamanan, analisis forensik, dan layanan personalisasi yang membutuhkan estimasi jenis kelamin ketika hanya bagian mata yang dapat diamati.Kata kunci: Citra Mata, HOG, HSV, Jenis Kelamin, Support Vector MachineAbstract: Identifying gender through eye image analysis is a relevant approach in forensic and security applications, especially in situations where facial identification is not possible. This study develops a gender classification system based on eye images using a combination of HSV and HOG features with the Support Vector Machine (SVM) algorithm. The problem addressed is how to extract representative eye image features and optimize gender classification accuracy through the appropriate methodological approach. Research method includes data collection, image preprocessing, feature extraction using HSV to obtain color characteristics and HOG to identify shape characteristics, application of SVM as a classification algorithm, and model evaluation to assess the overall system performance. The research dataset consists of eye images from male and female subjects under various conditions. The developed classification system achieved an accuracy of 90.24%, precision of 90.26%, recall of 90.24%, and an F1-score of 90.22%. The results show that the combination of HSV and HOG features with the SVM algorithm is capable of providing consistent and reliable accuracy in classifying gender based on eye images. This approach can be applied as an alternative solution in security systems, forensic analysis, and personalized services that require gender estimation when only the eyes are observable.Keywords: Eye Image, Gender , HOG, HSV, Support Vector Machine
Co-Authors Ananda, Zhafran Fatih Aurlani, Febry Fardhina, Azura Ginting, Irsya Chlara Br Henny Risni Indri Yani, Sylvia Jefferson Ong Jimmy Sunjaya Jordan, Dimas Marwah Marwah Nababan, Junerdi Nabila, Salwa Rahayu, Novriza Rezky Firmansyah Ziliwu Sembiring, Asha Sibarani, Mika Ria Waty Br Silitonga, Marta Tabita Anggi Simamora, Windi Saputri Siregar, Ramadhan Mustaqim Siti Sarah Harahap Zarkasyi, Muhammad Imam