cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
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
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Computer Science & IT
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
 55   56   57   58   59 
Optimasi Kombinasi Hyperparameter dan Augmentasi Korpus dalam Neural Machine Translation Bahasa Indonesia ke Bahasa Melayu Bengkulu Soyusiawaty, Dewi
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5369

Abstract

Neural Machine Translation (NMT) with attention mechanism has become an effective approach in improving the quality of cross-language translation. However, the application of NMT with attention to regional or minority languages still faces challenges, especially in the context of Bengkulu Malay Language, a variant of Malay Language used in the Bengkulu Province, Indonesia. This research aims to enhance the translation accuracy from Indonesian to Bengkulu Malay Language through optimization of hyperparameter combinations in NMT models with attention. The research method involves experiments with various hyperparameter combinations, such as batch size, dataset size, and dropout rate, applied to NMT models with attention. Evaluation is conducted using the BLEU metric to measure translation quality. Corpus augmentation is done to obtain a larger corpus.The experimental results indicate that translation accuracy improvement can be achieved by selecting optimal hyperparameter combinations. The use of a larger dataset yields better performance compared to a smaller dataset. A batch size of 16 yields better results than batch sizes of 32 and 64, especially when used with a larger dataset. Additionally, a dropout rate of 0.8 tends to perform better than dropout rates of 0.2 and 0.5. Regarding epoch values, the research shows that increasing epochs up to a certain point (approximately 30 epochs) enhances model performance, but further increases tend to cause overfitting on the training data. This research provides a significant contribution to the development of machine translation for Bengkulu Malay Language and other regional languages. It is hoped that the findings of this research can serve as a foundation for further development in the field of machine translation for minority languages, as well as improving information accessibility in diverse language communities in Indonesia.
Decision Support System for Determining the Quantity of Brick Production Using the Fuzzy Tsukamoto Method Nurpa, Murni Zaliah; Masrizal, Masrizal; Nasution, Marnis
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5497

Abstract

Maximum profits are obtained from maximum sales. Maximum sales are those that can meet existing demands. There is a determination of the planned production amount to meet production levels to meet planned sales levels or market demand levels. Factors that need to be considered in determining production quantities include: the amount of inventory and the amount of demand. The amount of demand and supply is an uncertainty. Fuzzy logic is a science that can analyze uncertainty. One of the fuzzy rule methods is Tsukamoto, which is a method that is often used to build a system whose reasoning resembles human intuition or feelings. The calculation process is quite complex so it takes a relatively long time, but this method provides results with quite high accuracy. Ratu Batubata Refinery is a factory that produces large quantities every day. Therefore, planning the amount of brick production is very important. In order to meet market demand appropriately and in appropriate quantities. By using this application, it is hoped that the company can make it easy for the company to predict production quantities based on the amount of demand and existing inventory data, in order to achieve maximum profits.
Rancang Bangun Alat Pendeteksi Zat Berbahaya Pada Makanan Berbasis Internet of Things (IoT) Edy, Rizma Ruqayyah; Nurdin, Ali; Suroso, Suroso
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5575

Abstract

As technology advances public awareness of food safety is increasing. Food safety is a crucial issue that requires special attention, especially regarding the use of hazardous substances in food. The misuse of these hazardous substances has led to many people suffering from food poisoning, which can cause serious health problems such as shortness of breath, diarrhea, allergies, kidney irritation, and even cancer. Despite many efforts to address this issue, the results have not been satisfactory. Therefore, the aim of this research is to use the Internet of Things (IoT) to design and build a device that can identify hazardous substances in food. This device detects potentially harmful substances using a TCS3200 sensor, which works by detecting the RGB (Red, Green, Blue) frequency values of food samples suspected of containing hazardous substances. The detection data is then sent to a server and the MIT App Inventor application via the internet, allowing real-time monitoring through Android devices. Testing results show that this detection device achieves an accuracy rate of 97.91% with an error margin of 2.09% and can display data in real-time on the Android application. The correlation between RGB values and the concentration of hazardous substances indicates that the higher the content of hazardous substances, the lower the detected RGB values, while higher RGB values indicate a darker color due to the presence of hazardous substances. This device is expected to help the public ensure food safety and raise awareness of the dangers of using hazardous substances. With this device, the public is expected to be more vigilant and protected from potential health risks due to consuming food containing hazardous substances. Additionally, this technology has the potential to be further developed to detect various other types of hazardous contaminants in the future.
Penerapan Algoritma Random Forest untuk Memprediksi Curah Hujan pada Masa Mendatang di Daerah Berpotensi Banjir Aswarisman, Novie Rahmadani; Handayani, Ade Silvia; Hadi, Irawan
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5593

Abstract

Palembang, as one of the largest cities in Indonesia, regularly experiences severe flooding problems every year. Flooding not only disrupts the daily activities of residents, but also causes significant economic losses and social impacts. To solve this problem, it is crucial to have an in-depth understanding of flooding patterns and some of the factors that influence them. The purpose of this research is to apply highly efficient Machine Learning (ML) technology for the prediction analysis of future flood-prone areas. The integration of ML can help in identifying patterns, predicting risks, and making more accurate decisions in flood mitigation. In an effort to achieve this goal, the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology will be applied to ensure the research is conducted systematically and comprehensively. Therefore, research on the analysis of mapping flood-prone areas in Palembang using ML is essential to provide a fairly effective and efficient solution to the long-standing flooding problem. With the CRISP-DM approach, it is expected that this research can produce an accurate and reliable prediction model by integrating the Random Forest algorithm as a regression model, and provide long-term benefits for flood risk management in Palembang and several other cities in Indonesia that experience similar problems.
Modification of the Grey Relational Analysis Method in Determining the Best Mechanic Arshad, Muhammad Waqas; Sulistiani, Heni; Maryana, Sufiatul; Palupiningsih, Pritasari; Rahmanto, Yuri; Setiawansyah, Setiawansyah
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.v6i3.5678

Abstract

Determining the best mechanics in the industry has an important role to ensure the quality and reliability of the products and services offered. Competent and experienced mechanics are able to diagnose and repair accurately and efficiently, thereby minimizing operational downtime and increasing productivity. Without a structured system, mechanical performance appraisals tend to be subjective and inconsistent, which can lead to dissatisfaction among employees and customers. Mechanics may not get clear and constructive feedback on their performance, thus hindering skill development and professionalism. The purpose of the research of the modified Grey Relational Analysis (GRA) using standard deviation is to improve the accuracy and reliability of the decision-making process in situations where the data has a high degree of variability or significant uncertainty. By integrating standard deviations into the GRA, the study aims to account for variations and fluctuations in the data, which allows for more accurate and representative assessment of the criteria. This modification is expected to overcome the weaknesses of traditional GRAs that may not adequately consider data uncertainty, as well as produce more robust and realistic alternative rankings. The results of the best ranking of mechanics, Mechanic FR ranks first with a value of 0.11, followed by Mechanic HS with a value of 0.104. The third place was occupied by Mechanic AY with a score of 0.099.
Modifikasi Metode Simple Additive Weighting Dalam Rekomendasi Restoran Terbaik Berdasarkan Ulasan Pengunjung Prastowo, Kukuh Adi; Sulistiani, Heni; Setiawansyah, Setiawansyah
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.v6i3.5679

Abstract

Simple Additive Weighting (SAW) is a method in DSS that is used to solve multi-criteria problems by adding up the value weights of each alternative. The weakness of SAW is its sensitivity to weight determination and value which can significantly affect the final result. If the weight or value of the criteria is not determined correctly or does not reflect reality well, the results of the decision can be less accurate. The purpose of this study is to modify the SAW method with the name SAW-C to be more effective in providing the best restaurant recommendations based on visitor reviews. SAW modification using a change driven approach not only improves accuracy in decision-making, but also improves adaptability and responsiveness to dynamic and complex environments. The SAW-C method not only improves decision-making accuracy, but also improves adaptability and responsiveness to dynamic and complex environments. SAW-C integrates flexibility and adaptability in managing changes in visitor preferences or the weighting of relevant criteria, which often change over time. With this approach, the recommendation system can dynamically update restaurant ratings based on recent reviews and changing visitor preferences, providing more personalized and relevant recommendations. The results of the ranking of the best restaurants using the SAW-C method show that the results of rank 1 with a final score of 0.92135 are obtained by Flamboyant Restaurant, rank 2 with a final score of 0.70548 obtained by Zozo Garden, and rank 3 with a final score of 0.70312 obtained by Square Restaurant.
Sistem Pendukung Keputusan Pemilihan Aplikasi Jasa Angkut Barang Menggunakan PIPRECIA-S dan Composite Performance Index Sinlae, Alfry Aristo Jansen; Jamaludin, Jamaludin; Nugroho, Nurhasan; Badaruddin, Muliati
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.v6i3.5698

Abstract

Freight service applications play a crucial role in supporting logistics efficiency and goods mobility. However, with the multitude of available applications, users often face difficulties in determining which application best suits their needs. The manual process of selecting these applications requires users to search and compare information from various sources, which demands considerable time and effort and is prone to subjectivity. This study aims to develop a Decision Support System (DSS) that is quick and accurate in determining the best freight service application using the Simplified Pivot Pairwise Relative Criteria Importance Assessment (PIPRECIA-S) method and the Composite Performance Index (CPI). The PIPRECIA-S method is used to objectively and systematically determine the criteria weights, while the CPI method is employed to identify the best alternative by integrating various performance aspects into a single, easily understood composite measure. In the conducted case study, the best alternative identified was Lalamove (A2), with a composite index score of 122.55, followed by Deliveree (A3) with a score of 114.39, Lion Parcel (A1) with a score of 109.24, GoBox (A4) with a score of 102.04, and The Lorry (A5) with a score of 99.04. The DSS calculations were consistent with the manual calculations, demonstrating its validity and reliability. Usability testing showed an average score of 90%, indicating that the developed DSS possesses the necessary functionality with an intuitive and user-friendly interface.
Analisis Perbandingan Metode AdaBoost, Gradient Boosting, dan XGBoost Untuk Kalsifikasi Status Gizi Pada Balita Erkamim, Moh.; Tanniewa, Adam M; AP, Irfan; Nurhayati, Nurhayati
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.v6i3.5717

Abstract

Nutritional issues in toddlers are a crucial issue that significantly impacts the health and development of children in Indonesia. Malnutrition can lead to various long-term health problems. Therefore, detecting and classifying the nutritional status of toddlers is very important. This study aims to analyze and compare boosting techniques to classify the nutritional status of toddlers, focusing on three boosting techniques: AdaBoost, Gradient Boosting, and XGBoost. This is done because boosting techniques work by sequentially building models, where each new model attempts to correct the prediction errors of the previous model. The results show that the XGBoost model provides the best performance with a precision of 0.9849, recall of 0.9848, accuracy of 0.9848, F1 score of 0.9848, and ROC-AUC of 0.9994 at an 80:20 data split ratio. Conversely, the AdaBoost model shows the lowest results with a precision of 0.6294, recall of 0.6292, accuracy of 0.6292, F1 score of 0.6291, and ROC-AUC of 0.7581 at a 90:10 data split ratio, caused by its sensitivity to outliers and noise in the data. These findings indicate that XGBoost is the best boosting model for classifying the nutritional status of toddlers, followed by Gradient Boosting, with AdaBoost in the last position. The outstanding performance of XGBoost is due to the use of regularization techniques, effective handling of missing values, and efficient and fast boosting algorithms through parallel processing techniques.
Combination Multilayer Fuzzy Inference System with K-means for Classification of Dental Diseases Prandana, Randy; Mawengkang, Herman; Suwilo, Saib
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5737

Abstract

This study was conducted to solve the problem of classifying dental diseases such as pulpitis, gingivitis, periodontitis and advanced periodontitis. The method in this study uses a combination of algorithms with a multilayer system where in the first layer a fuzzy inference will be carried out whether a patient is suffering from pulpitis. Early symptoms of pulpitis are characterized by pain with varying levels. Meanwhile, in the second layer a fuzzy inference process will also be carried out to identify other types of dental diseases, but in this second layer the centroid value calculation process is carried out using the K-means algorithm for all input variables. Then the inference process will run to determine the type of disease suffered by the patient following the fuzzy set of other types of diseases. This study is expected to contribute to helping the initial screening process for dental diseases so that it is easier for dentists to carry out further examinations. The results of this study have been proven to be able to help doctors in conducting initial screening to determine dental disease. In this study, the multilayer system is intended to differentiate the results of dental disease classification because pulpitis does not have a relationship between input variables and other types of dental disease. Meanwhile, the use of the fuzzy inference system method in this study showed good results because the FIS method can map the level of pain suffered by a patient with mild, moderate and severe levels into a numeric value that can be classified where the level of pain is a feeling that cannot be calculated, by using the fuzzy method, the linguistic value can be defined into a conclusion. Grouping input values by finding the means value in the second layer and combined with the fuzzy method has been proven to provide good results for determining the type of dental disease.
Clustering-Based Stock Return Prediction using K-Medoids and Long Short-Term Memory (LSTM) Sofyan, Denny; Saepudin, Deni
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.v6i3.5744

Abstract

This research focuses on predicting stock returns using the K-Medoids clustering method and the Long Short-Term Memory (LSTM) model. The primary challenge lies in forecasting stock prices, which are then converted into return predictions. Clustering is performed to group stocks with similar price movements, facilitating the preparation of data for training the LSTM model within each cluster. This issue is crucial for aiding investors in making more informed investment decisions by leveraging predictions within specific stock clusters. Through clustering with K-Medoids, based on average returns and return standard deviation, the LSTM model is trained to predict daily returns for each stock within different clusters using the average stock price in each cluster. The data is divided into training (2013-2019) and testing (2020-2022) datasets, with model evaluation conducted using Root Mean Square Error (RMSE). The implementation results indicate prediction performance measured by RMSE for each cluster, with Cluster 3 showing the best performance with a testing RMSE of 0.0300, while Cluster 4 exhibited the worst performance with an RMSE of 0.3995. In the formation of an equal weight portfolio, tested from May 2020 to January 2023, the portfolio value grew from 1 to 2.50, with an average return of 0.0014 and a return standard deviation of 0.0158, indicating potential gains with lower risk compared to the LQ45 index.

Page 57 of 93 | Total Record : 926

 55   56   57   58   59 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 3 (2025): December 2025 Vol 7 No 2 (2025): September 2025 Vol 7 No 1 (2025): June (2025) Vol 6 No 4 (2025): March 2025 Vol 6 No 3 (2024): December 2024 Vol 6 No 2 (2024): September 2024 Vol 6 No 1 (2024): June 2024 Vol 5 No 4 (2024): March 2024 Vol 5 No 3 (2023): December 2023 Vol 5 No 2 (2023): September 2023 Vol 5 No 1 (2023): June 2023 Vol 4 No 4 (2023): March 2023 Vol 4 No 3 (2022): December 2022 Vol 4 No 2 (2022): September 2022 Vol 4 No 1 (2022): June 2022 Vol 3 No 4 (2022): March 2022 Vol 3 No 3 (2021): December 2021 Vol 3 No 2 (2021): September 2021 Vol 3 No 1 (2021): June 2021 Vol 2 No 2 (2020): December 2020 Vol 2 No 1 (2020): June 2020 Vol 1 No 2 (2019): December 2019 Vol 1 No 1 (2019): June 2019 Vol 1 No 1 (2019): Edisi Juni More Issue