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
Analisis Perbandingan Algoritma Naive Bayes dan Support Vector Machine dengan Pendekatan TF-IDF Sebagai Klasifikasi Perintah Suara Syarifuddin, Faisal; Kusumaningsih, Dewi
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7160

Abstract

This study evaluates the performance of two classification algorithms, namely Naive Bayes and Support Vector Machine (SVM), in identifying voice commands in financial applications for the blind. The data used has gone through a preprocessing process including tokenization, stemming, and stopword removal, and was extracted using the TF-IDF method. The models were trained using a data sharing scheme of 80% for training and 20% for testing, then evaluated based on accuracy, precision, recall, and F1-score. The test results show that both models achieve a very high level of accuracy, with Naive Bayes achieving an accuracy of 98.6% and SVM reaching 98.4%. Both show high precision, recall, and F1-score in each voice command category, with the highest value in the "QRIS Payment" category which achieved a precision and recall of 1.00. Confusion matrix analysis shows that classification errors occur in minimal amounts. This study also shows that TF-IDF as a feature extraction technique is effective in improving speech recognition accuracy by giving more weight to relevant and rarely appearing words in the dataset, which helps the model to focus more on the most important information. With these results, both algorithms are proven to be effective in recognizing voice commands. However, Naive Bayes is slightly superior in accuracy, so it is more recommended for voice-based applications in digital financial systems. These findings support the development of more inclusive and accessible technology for the visually impaired.
Perbandingan Algoritma Naïve Bayes, Random Forest, dan SVM Untuk Analisis Sentiment Aplikasi PLN Mobile Pada Google Play Store Sari, Cici Nurita Kumala; Suryono, Ryan Randy
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7164

Abstract

PLN Mobile is a digital innovation developed by PT PLN (Persero) to provide electricity services through mobile devices. Many users submit their complaints and reviews on the Google Play Store. This study aims to analyze user sentiment towards the PLN Mobile application using three classification methods: Naïve Bayes, Random Forest, and Support Vector Machine (SVM). A total of 19,870 reviews that have gone through the preprocessing stage were analyzed in this study. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The SMOTE technique was applied to address the imbalance of sentiment classes. The results showed that before the implementation of SMOTE, SVM had the best performance with an accuracy of 92%, followed by Random Forest 79%, and Naïve Bayes 62%. After the implementation of SMOTE, SVM performance increased to 95%, Random Forest to 85%, while Naïve Bayes remained at 62%. Other evaluation metrics such as recall and F1-score also showed significant improvements after the implementation of SMOTE, especially for negative and neutral sentiments. These results show that SMOTE is able to improve the accuracy and balance of model performance, as well as provide important insights into public perception of the PLN Mobile application.
Perbandingan Performa Algoritma SVR, LSTM, dan SARIMA dalam Peramalan Produksi Kelapa Sawit Hendri, Desvita; Permana, Inggih; Salisah, Febi Nur; Afdal, M; Megawati, Megawati; Saputra, Eki
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7170

Abstract

Oil palm production in Indonesia fluctuates significantly due to various factors such as weather, soil fertility, and fruit bunch condition. These changes These changes have an impact on price stability, supply and planning for the palm oil industry. industry planning. Therefore, to improve decision-making in this industry, an accurate forecasting method is required to improve decision-making regarding distribution. appropriate decision-making regarding distribution. This study aims to compare the performance of three machine learning-based forecasting methods, namely Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Seasonal Autoregressive Integrated Moving Average (SARIMA), in predicting palm oil production based on historical data for the last 10 years obtained from PTPN V Riau. The evaluation results show that the SVR model with a linear kernel provides the best performance with an MSE value of 4.1718. with MSE 4.1718, RMSE 0.0020, MAE 0.0018, MAPE 0.2014% and R2 0.9988. The SVR model provides superior prediction results compared to LSTM and SARIMA. with LSTM and SARIMA in forecasting palm oil production. This research is expected to make a real contribution in the development of a more reliable prediction system, thus supporting operational efficiency and stability of the palm oil industry in Indonesia. stability of the palm oil industry in Indonesia.
Sistem Pendukung Keputusan Penerimaan Karyawan Menggunakan Kombinasi Gray Relational Analysis dan G2M Weighting Santika, Aisyara Zulaika Anteng; Ardiansah, Temi
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7189

Abstract

An effective and efficient employee recruitment process is crucial for companies to ensure that selected candidates align with organizational needs and culture. However, the complexity of evaluation criteria often leads to subjectivity in decision-making. This study aims to develop a decision support system (DSS) for employee recruitment by integrating the Gray Relational Analysis (GRA) method and G2M Weighting. The GRA method is utilized to evaluate the relative relationships among criteria under conditions of incomplete data, while G2M Weighting provides objective weighting of criteria using a combination of gray system analysis and geometric mean. This combination of methods is designed to yield a more accurate, objective, and comprehensive ranking of candidates. The research stages include data collection for employee selection, determination of criteria weights using G2M Weighting, and candidate ranking analysis with GRA. The results of the employee recruitment selection ranking research show that for rank 1 with a final GRA value of 0.918 obtained by employee Pipit, rank 2 with a final GRA value of 0.903 obtained by employee Iswara, rank 3 with a final GRA value of 0.805 obtained by employee Riska, rank 4 with a final GRA value of 0.733 obtained by employee Andri, rank 5 with a final GRA value of 0.697 obtained by employee Ikhsan, rank 6 with a final GRA value of 0.595 obtained by employee Ani, and rank 7 with a final GRA value of 0.553 obtained by employee Estu. Which shows this approach is able to increase objectivity and efficiency in the selection process. By considering various dimensions of assessment in a balanced manner, developed system provides recommendations for the best candidates based on highest scores. The implementation this method can help companies in reducing subjective bias, improving decision quality, and minimizing the risk of recruitment errors. This research makes a significant contribution in the field of decision support systems, especially for the employee selection process, by offering innovative solutions that are adaptive to changing needs of the company.
Penerapan Kombinasi Multi Objective Optimization on the basis of Ration Analysis dan Metode Pembobotan RECA Untuk Pemilihan Sales Berprestasi Sari, Putri Mayang; Ardiansyah, Temi
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7190

Abstract

This research proposes the application of a combination of Multi-Objective Optimization by Ratio Analysis (MOORA) and Respond to Criteria Weighting (RECA) methods for a more objective and transparent sales performance assessment system. MOORA is used to evaluate alternatives based on various criteria through a ratio normalization process, while RECA determines the weight of criteria proportionally by considering the contribution level of each criterion. The combination of these two methods is designed to reduce subjectivity in the evaluation process and produce a systematic and measurable ranking of salespeople. The results show that the integration of MOORA and RECA is able to provide an accurate solution in determining sales achievers, by considering various performance indicators such as sales volume, customer satisfaction, and the ability to build long-term relationships. The results of the study show that the combination of these two methods can produce transparent rankings. With the following ranking results, the first rank with a total final score of 0.514 by Sample, the second rank with a total final score of 0.314 by Jinilianty, the third rank with a total final score of 0.308 by Rudi Hartono. The system not only increases salesperson motivation to achieve targets, but also provides structured feedback for self-development. With a transparent and accountable approach, the company is able to improve. The system not only increases salespeople's motivation to achieve targets, but also provides structured feedback for self-development. With a transparent and accountable approach, the company can increase sales team loyalty, customer satisfaction, and overall profitability. The results of this study can also serve as a reference for other companies in developing a more effective sales performance evaluation system.
Pengelompokkan Perguruan Tinggi di Indonesia Menggunakan Algoritma BIRCH Husna, Nur Alfa; Mustakim, Mustakim; Afdal, M; Rahmawita, Medyantiwi
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7234

Abstract

Accreditation is currently the main focus for all universities. Each institution strives to get superior accreditation. The evaluation and assessment process carried out by BAN-PT is based on data reported by universities to PDDikti. This research aims to assist universities in achieving superior accreditation, by providing recommendations regarding the most influential attributes and clustering to find patterns or data structures from PDDikti. This research uses two feature selection methods AHP and Chi-Square are used separately to identify the most influential attributes. The results of each method were used as input features for the clustering process using the BIRCH algorithm. The purpose of this approach is to evaluate the effect of feature selection from both methods on the quality of clustering results. The evaluation is done using the Davies-Bouldin Index (DBI) metric. The results showed that the Lecturer attribute has the highest eigenvalue in AHP which is 0.379, indicating its significant role in accreditation assessment. Meanwhile, the Year of Establishment Decree attribute has the highest Chi-Square value of 290.625 which indicates a strong correlation with accreditation results. In addition, based on the cluster DBI value, it shows that AHP is superior to chi-square, so AHP is considered more effective in this context. With the best Davies Bouldin Index (DBI) value of 0.73603 in cluster 7 with a threshold of 0.05 and a branching factor of 50.
Optimasi Prediksi Harga Sawit Menggunakan Teknik Stacking Algoritma Machine Learning dan Deep Learning dengan SMOTE Karim, Abdul; Bangun, Budianto; Prayetno, Sugeng; Afrendi, Mohammad
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7239

Abstract

The prediction of palm oil prices plays a strategic role in decision-making within the agribusiness sector, particularly in addressing market volatility and imbalanced historical data distribution. This study aims to optimize the accuracy of palm oil price prediction by applying a stacking approach that combines machine learning and deep learning algorithms, while integrating the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance issues. Three main models were employed in this study: Random Forest, Long Short-Term Memory (LSTM), and a model enhanced with SMOTE. The evaluation was conducted using accuracy, precision, recall, and F1-score metrics, supported by confusion matrix analysis. The results indicate that the model integrated with SMOTE outperforms the others, achieving an accuracy of 0.5447, precision of 0.5512, recall of 0.5447, and F1-score of 0.5462. This model also demonstrates a more balanced classification performance compared to the LSTM and Random Forest models. These findings confirm that the application of oversampling techniques such as SMOTE, when combined with appropriate algorithms, can significantly enhance predictive performance in imbalanced datasets. The study contributes to the development of predictive models for commodity prices based on historical data and opens opportunities for further exploration of more adaptive hybrid methods in future research.
Perbandingan Metode TF-IDF dan Bag of Words dalam Analisis Sentimen Diet Kopi Americano di Media Sosial Twitter Menggunakan Naïve Bayes Suryanti, Rahmatika; Prasetyaningrum, Putri
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7244

Abstract

The popularity of diet coffee, particularly the Americano variant, has risen alongside the growing trend of healthy lifestyles in society. This phenomenon has led to various public opinions circulating on social media, which need to be analyzed to better understand consumer perceptions. This study compares two commonly used text feature representation methods, Term Frequency-Inverse Document Frequency (TF-IDF) and Bag of Words (BoW), in sentiment analysis using the Naïve Bayes algorithm. Using relevant keywords, data were collected from Twitter and underwent preprocessing stages including case folding, cleansing, tokenizing, stopword removal, and stemming. Sentiment labeling was conducted manually based on keyword indicators, and the data were classified into positive, negative, and neutral categories. The evaluation results show that the TF-IDF model achieved an accuracy of 85%, outperforming BoW which obtained 64%. This performance gap indicates that the choice of feature representation method plays a crucial role in the success of sentiment classification. This research is expected to serve as a reference for optimizing text representation techniques to analyze public opinion on social media, particularly concerning diet products and low-calorie beverages.
Pemanfaatan Deep Learning untuk Klasifikasi Kanker Kulit Menggunakan Few-shot Learning Berbasis Prototypical Networks dan Backbone EfficientNet-B0 Setianingsih, Wahyu; Setyaningsih, Putry Wahyu
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7245

Abstract

The utilization of Artificial Intelligence in the current era of technological development is increasingly popular, especially in the field of health. The increasing number of skin cancer cases globally is of particular concern today. Therefore, a classification model utilizing deep learning was developed to assist in the effective diagnosis process. However, data limitations and imbalances are often an issue in training skin cancer classification models. This research develops a skin cancer classification model using the Few-shot Learning approach with Prototypical Networks architecture and EfficientNet-B0 backbone. The research aims to develop an image-based skin cancer classification model and evaluate how effectively the model performs in classifying various types of skin lesions. Experimental results show that increasing k-shots has a positive impact on model accuracy. The best results were obtained in the 10-shot 15-query scheme with an accuracy value of 86.73% and supported by an ROC AUC value of 94%. This study proves that the few-shot learning approach with Prototypical Networks architecture and EfficientNet-B0 backbone is effective for skin cancer classification under limited dataset conditions. This model also has the potential to be an early diagnosis tool.
Analisis Perbandingan Model ARIMA dan Exponential Smoothing dalam Meramalkan Harga Penutupan Saham Abdul Aziz, Arif Rahman; Taqwa Prasetyaningrum, Putri
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7246

Abstract

The stock market is one of the most sought-after investment instruments due to its high profit potential. However, significant fluctuations in stock prices also bring considerable risks, which are influenced by various factors such as macroeconomic conditions, government policies, company financial reports, and market sentiment. Therefore, stock price analysis and forecasting have become important aspects for investors and market participants in making more accurate investment decisions. This research focuses on the stock of PT Indosat Ooredoo Hutchison Tbk (ISAT), which shows high volatility, particularly following a sharp decline in stock prices in late February 2025, which was suspected to be triggered by discrepancies between financial reports and analysts' expectations.The main objective of this study is to compare two commonly used time series forecasting methods, namely Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing, in predicting the closing price of ISAT stock. This research uses daily stock price data from October 28, 2022 to March 27, 2025, which is then analyzed to identify patterns in the movement of stock prices. Based on the analysis, it was found that both forecasting methods have their respective strengths and limitations. The ARIMA method is more accurate in handling stationary data, while Exponential Smoothing is more adaptive to fluctuating stock prices.The results of this study are expected to provide insights for investors in selecting the appropriate method to predict stock price movements with high volatility and help make smarter investment decisions as well as more effective risk management strategies.