cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 926 Documents
Implementasi Transfer Learning Menggunakan Convolutional Neural Network untuk Deteksi Jenis Kulit Wajah Septiani, Karlina Dwi; Subhiyakto, Egia Rosi
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6154

Abstract

In Indonesia, extreme tropical climate conditions with high humidity and sun exposure increase the risk of facial skin problems for the community. Facial skin that is not properly cared for is often prone to disorders, ranging from dry skin, oily skin, to acne. However, Indonesian people's awareness of the importance of maintaining healthy skin is still relatively low, which is exacerbated by limited time and access to consult a dermatologist. Most people may not know their skin type, even though each skin type requires different care to stay healthy and avoid more serious skin problems. To answer this problem, this study aims to develop an iOS-based application that is able to automatically detect facial skin types using transfer learning with a Convolutional Neural Network (CNN) architecture. The model was developed by training a dataset of facial images to classify skin types such as dry, oily, normal, and acne-prone, and integrated into an iOS application for real-time analysis through user facial images. The evaluation results showed a model accuracy of 87% and an application accuracy of 83.3% in identifying facial skin types. It is hoped that this application will help Indonesian people better understand their skin conditions and obtain appropriate treatment recommendations to maintain healthy skin in a tropical climate.
Development of AI-Based Presentation Application using Deep Learning for Individuals With Disabilities Hutagalung, Carli Apriansyah; Fitrianto, Adi; Akbar, Gebran
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6162

Abstract

This study addresses the challenges individuals with disabilities face in controlling presentation devices, particularly in noisy environments, by developing an AI-based application using a hybrid LSTM-GRU model. The primary objective is to improve voice command recognition accuracy for commonly used presentation commands, such as “next” and “back,” even under varying noise conditions. The research employs a hybrid deep learning architecture combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) with an attention mechanism to focus on the most relevant temporal features. The model was trained using the Speech Commands Dataset and further fine-tuned with noise-augmented data to simulate real-world environments. Results show that the LSTM-GRU model achieved high accuracy in clean environments and maintained reasonable performance in noisy conditions, outperforming traditional models like Hidden Markov Model (HMM) and Gaussian Mixture Model (GMM). The fine-tuned model, at its optimal epoch, demonstrated robust performance with a balanced precision and recall, making it suitable for deployment in real-world scenarios. The study concludes that while deep learning models offer significant improvements, further refinement is necessary to enhance noise resilience in practical applications
Implementasi Metode K-Means Clustering dalam Mengukur Tingkat Gizi Balita Berdasarkan Z-Score Desyanti, Desyanti; Desriyati, Welly; Mesran, Mesran
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6177

Abstract

Toddler health is very important as the basis for child development. Every child must receive good nutrition so that their development stages are not disrupted. This study aims to analyze the nutritional status of toddlers at Posyandu Currently, Posyandu Parents are given a Healthy Way Card (KMS) where the card only contains the child's age and weight. The data used includes the age, weight and body length of 20 toddlers. The analysis process involves determining the Z-Score for each parameter to group the data into three main clusters, namely overnutrition, obesity and risk of overnutrition. The research results showed that of the 20 toddlers, 6 were in the obese category, 13 were over-nourished, and 1 toddler was at risk of over-nutrition. This information can be a basis for evaluation for parents and Posyandu in increasing appropriate nutritional intake for children.
Penerapan Natural Language Processing dan Machine Learning untuk Prediksi Stres Siswa SMA Berdasarkan Analisis Teks sudrajat, Muhammad Rofiq; Zakariyah, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6180

Abstract

This research explores the application of Natural Language Processing (NLP) and Machine Learning in predicting stress among high school students. As stress in students often goes unnoticed, there is a need for effective methods to identify it early. To address this issue, this research develops a text-based stress prediction model using NLP for feature extraction and Machine Learning for classification. Core NLP techniques include data cleaning, stopword removal, tokenization, and lemmatization to process text data, while feature extraction is achieved through methods such as Bag Of Words (BOW), Term Frequency-Inverse Document Frequency (TF-IDF), and N-grams (Unigram, Bigram, Trigram). The Machine Learning models tested include Logistic Regression, Naive Bayes, Random Forest, and Support Vector Machine (SVM). Results from the experiments showed that the Naive Bayes model using Bigram features achieved the highest accuracy of 95.6%, with the other models achieving around 93%. Despite the strong performance of the models, errors such as False Positive and False Negative were still found, indicating room for improvement. This research shows that NLP combined with Machine Learning provides an effective approach to identifying student stress, with promising potential for mental health interventions in educational settings.
Analisis Sentimen Tanggapan Publik di Twitter Terkait Program Kerja Makan Siang Gratis Prabowo–Gibran Menggunakan Algoritma Naïve Bayes Classifier dan Support Vector Machine Ramadhani, Annisa; Permana, Inggih; Afdal, M; Fronita, Mona
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6188

Abstract

Indonesia faces a serious challenge related to stunting, with rates reaching 21% in 2024, although this represents a decrease from 24% in 2021. In response, the government has launched various programs to address this issue, including nutrition education, health check-ups for pregnant women, and supplementary food provisions. Amid these efforts, the proposed free lunch program aims to improve nutritional quality for children and pregnant women. However, this program has sparked controversy over the required budget, estimated at IDR 450 trillion, which could impact the national budget balance and lead to inflation.This study analyzes public sentiment toward the free lunch program using the Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM) algorithms. An analysis of 1,028 tweets revealed that negative sentiment predominates at 44.84%, followed by positive sentiment (32.39%) and neutral sentiment (22.76%). SVM outperformed NBC with an accuracy of 75.39%, compared to NBC's 68.97%. The findings provide important insights into public perceptions of the program and highlight the need for further research to improve sentiment analysis methodologies.
Enchancing K-NN Performance With SMOTE for Sentiment Analysis of Streaming App Reviews Patrycia Dewi, Ni Putu Eka; Yanti, Christina Purnama; Yusa, I Made Marthana
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6190

Abstract

This research aims to analyze the sentiment of user reviews for a popular streaming app on both the Play Store and App Store using the K-Nearest Neighbor (K-NN) method. As the user base expands, reviews increasingly influence app development, guiding improvements and optimizing user experience. However, the large volume of reviews renders manual analysis inefficient and prone to inconsistencies, underscoring the necessity of sentiment analysis to quickly and accurately capture user perceptions. Review data were collected from both platforms, with preprocessing steps such as data cleaning, tokenization, and normalization applied to ensure data consistency. The Synthetic Minority Over-sampling Technique (SMOTE) was used to address class imbalance, enhancing the reliability of classification results. Findings indicate that SMOTE improved model accuracy, raising it from 74% to 82.9% for Play Store data and from 79% to 84.1% for App Store data. Furthermore, a notable difference in sentiment dominance was observed, with positive sentiment prevailing on the Play Store, while negative sentiment was more prevalent on the App Store. These insights reveal that, overall, the app is well received, although certain areas highlighted in negative reviews require further attention to improve user satisfaction.
Clusterisasi Tingkat Pengangguran Terbuka Menurut Provinsi di Indonesia Menggunakan Algoritma K-Medoids Karim, Abdul; Esabella, Shinta; Kusmanto, Kusmanto; Suryadi, Sudi; Mardinata, Erwin
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6198

Abstract

The Open Unemployment Rate (OER) in Indonesia decreased in February 2024 to 4.82%, showing an improvement compared to February 2023. Despite the decline in TPT, there are still regions with TPT reaching 7.02%, which could potentially lead to negative consequences such as increased crime. Efforts to address TPT include increasing economic growth, developing the quality of education and training. This research utilises clustering in data mining. The number of clusters formed was 3 clusters with a DBI value of -1.685. This study uses K-Medoids clustering to group 38 provinces based on TPT. Of the 38 data, there is incomplete data so preprocessing is done using the "filter example" operator in rapidminer to eliminate incomplete data so that there are 34 data that will be used in this study (after preprocessing). The results show 4 provinces with the highest TPT (Riau Islands, DKI Jakarta, West Java, and Banten) with a percentage of 11.76%.
Analisis Perbandingan Algoritma Klasifikasi Data Mining Untuk Penentuan Bibit Unggul Sugito, Bambang; Iqbal, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6199

Abstract

Cocoa is one of the leading commodity crops from the growing plantation sub-sector, mostly cultivated by farmers in the form of community plantations. Cultivation is carried out so that it can continue to produce seeds and trees independently for the sustainability of the commodity. The process currently carried out in the selection of superior seeds is carried out by staff who are specifically assigned to that section. The process of selecting superior cocoa plant seeds should have been recorded and stored. Data mining is a process that uses statistical techniques, mathematics, artificial intelligence, and machine learning to extract and identify useful information and related knowledge from various large databases. Based on this problem, the C5.0 and K-Nearest Neighbor algorithms are applied to carry out the comparison process in predicting the need for superior seeds to be used. It will be able to provide accurate information and can be used as a consideration in the stock of superior cocoa seed needs. The process using the C5.0 and K-Nearest Neighbor algorithms has been successfully carried out, from the testing process carried out that the C5.0 algorithm has a better performance result of 87.50% compared to the K-Nearest Neighbor algorithm of 62.50%.
Kombinasi Inisialisasi Hyperparameter dan Algoritma Adam untuk Optimasi Model Gated Recurrent Unit dalam Meramalkan Harga Penutupan Saham Pasca Isu Boikot Labibah, Bintu; Guntara, Rangga Gelar; Maesaroh, Syti Sarah
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6202

Abstract

This research aims to enhance the accuracy of daily closing price forecasting for PT Unilever Indonesia Tbk shares by optimizing a Gated Recurrent Unit (GRU) model, a deep learning architecture. The study focuses on the impact of boycott issues on company performance and explores the effectiveness of hyperparameter tuning and the Adam optimization algorithm. Utilizing a five-year historical dataset, time series analysis was employed. The results demonstrate that the GRU model with a configuration of 50 epochs, batch size 8, hidden state 64, and default Adam parameters achieved the lowest Mean Absolute Percentage Error (MAPE) of 1.59% and Root Mean Squared Error (RMSE) of 71.51 among the 81 configurations tested. While higher Adam parameter settings also yielded satisfactory results, this specific configuration exhibited superior performance. The findings highlight the sensitivity of model accuracy to sharp price fluctuations, suggesting that shorter forecast horizons may be more appropriate. This research contributes significantly to the advancement of accurate and reliable stock price forecasting models.
Analisis Sentimen Opini Publik Tentang Gempa Megathrust di Indonesia Menggunakan Metode Support Vector Machine dan Naïve Bayes Kurniawan, Dicky; Satria, Muhhammad Najib Dwi
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6213

Abstract

Indonesia is a country prone to natural disasters, especially earthquakes. One of the biggest threats is the potential for megathrust earthquakes that can cause severe damage and loss of life, especially in the Jakarta area. In the digital era, information about the potential for megathrust earthquakes is widely disseminated through social media platforms such as YouTube, which then triggers various opinions and comments from the public. A video titled "MEGATHRUST EARTHQUAKE!! JAKARTA RESIDENTS MUST BE PREPARED FOR THE COLLAPSE OF BUILDINGS?" uploaded by the Kamar Jeri YouTube channel has attracted public attention and sparked discussions about community preparedness for this potential disaster. This study aims to analyze public opinion sentiment towards the video using two machine learning methods, namely Naive Bayes and Support Vector Machine (SVM). To overcome the imbalance of data between sentiment classes, the Synthetic Minority Over-sampling Technique (SMOTE) technique was applied. The results showed that SMOTE was effective in improving the performance of both models, but the improvement in SVM was more significant. SVM performed better than Naive Bayes in classifying public opinion sentiment