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 889 Documents
Analisis Potensi Bencana Tanah Longsor di Kabupaten Banjarnegara Menggunakan Interpolasi Inverse Distance Weigthed (IDW) Supit, Christanti Ekkelsia; Prasetyo, Sri Yulianto Joko
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5187

Abstract

Landslides are a common disaster in Indonesia, especially in Banjarnegara Regency, caused by geomorphology and tropical climate. This is triggered by several factors, namely high rainfall and slope steepness, impacting communities and resulting in losses and even fatalities. According to data obtained from the BNPB website for the period of 2018-2023, there were 51 landslide disasters. Based on this background, the research problem formulates an analysis of landslide-prone areas using rainfall data, classification, and overlay techniques. The research objective is to produce mapping of areas potentially prone to landslides. The study discusses the analysis of rainfall data and slope classification, followed by overlay techniques to produce mapping. The research is supported by the Inverse Distance Weighted (IDW) method and overlay technique. The results obtained from the study include rainfall maps, slope maps, and landslide-prone maps from overlay results. Thus, based on the research findings, the conclusion is drawn that out of a total of 20 districts, there are 7 districts with a very high potential for experiencing landslides, namely Susukan, Mandarija, Madukara, Pagedongan, Sigalu, Pandanarum, and Pagetan
Applying Data Mining Techniques to Investigate the Impact of Smoking Prevalence on Life Expectancy in Indonesia: Insights from Random Forest Models Dalimunthe, Abdul Hakim; Samsir, Samsir; Subagio, Selamat; Siagian, Taufiqqurrahman Nur; Watrianthos, Ronal
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5201

Abstract

This study investigates the relationship between smoking prevalence and life expectancy in Indonesian provinces using data mining techniques, specifically focusing on the application of random forests. The primary objective is to quantify the potential impact of reducing smoking prevalence on population health outcomes. Data were sourced from the Indonesian Central Bureau of Statistics, which included life expectancy and smoking prevalence data from 2021 to 2023. The methodology involved aggregating life expectancy data from the district to the province level, followed by the application of a random forest model to predict life expectancy based on smoking prevalence and other socioeconomic indicators. Key findings indicate a weak to moderate negative correlation between smoking prevalence and life expectancy, with higher smoking rates associated with lower life expectancies. Predictive modeling suggests that a reduction in smoking prevalence could lead to significant improvements in life expectancy. For example, a 5% reduction in smoking rates could increase the average life expectancy by approximately 0.3 years, while a 15% reduction could result in an increase of about 0.9 years by 2025. These results underscore the detrimental impact of smoking on population health and highlight the importance of effective tobacco control measures. The predictive models developed in this study provide valuable information for policymakers, enabling targeted public health strategies and resource allocation. This research contributes to the field by demonstrating the utility of data mining techniques in public health and offering a comprehensive analysis of the relationship between smoking and life expectancy in Indonesia. The findings advocate for the urgent implementation of smoking cessation programs to enhance life expectancy and improve public health outcomes
Implementation of Data Mining for Interpretation of KSE Scholarship Applicant Number Data using Naive Bayes Algorithm Purnama, Riyan Hidayah; Ikhwan, Ali
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5203

Abstract

The purpose of this study is to interpret the large number of KSE scholarship applicant data, which is expected to provide a positive contribution in developing the KSE scholarship branding strategy, optimizing resource allocation and increasing the attractiveness of companies to allocate their CSR funds to the Karya Salemba Empat Foundation using data analysis techniques. The problem currently experienced is that the Karya Salemba Empat Foundation has been selecting KSE scholarship recipients manually, which results in the decision-making process not being able to be carried out quickly, accurately and efficiently. As one way to improve data accuracy, a method or computational model is needed in the form of a machine learning algorithm using the Naive Bayes method. With this Naive Bayes method, it is very appropriate to use to produce Knowledge. This study shows how the Karya Salemba Empat Foundation can utilize data to increase its value. From the results of the test carried out using 4,492 rows of data and 6 data variables and the pattern accuracy of 92% with an error margin of 8%, it shows that the naïve bayes method is almost perfect in processing its data. The results of this study are expected to provide in-depth insight into how the application of data science can help the Karya Salemba Empat Foundation increase its appeal and strategy
Perbandingan Kinerja Klasifikasi Penyakit Ginjal Menggunakan Algoritma Support Vector Machine (SVM) dan Decision Tree (DT) Madani, Puja Milenia Sriwildan; Rohana, Tatang; Baihaqi, Kiki Ahmad; Fauzi, Ahmad
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5206

Abstract

Chronic Kidney Disease is one of the deadliest diseases. In the early stages, the disease may go undetected, so patients tend to take it lightly, however, the disease can progress little by little and become serious without being detected. This can lead to complications of other diseases and can cause permanent damage to the kidney organs. Therefore, this study aims to classify individuals who are at risk of having Chronic Kidney Disease which can help medical personnel in an effort to reduce the number of people with the disease. This study uses Chronic Kidney Disease data obtained from the UCI Repository web. The data has 25 attributes with 400 rows. This research compares the Support Vector Machine and Decision Tree algorithms and uses the Confusion Matrix evaluation method. The results showed that the Support Vector Machine algorithm has superior accuracy, precision, recall, and f1-score results compared to the Decision Tree algorithm. The accuracy of the Support Vector Machine algorithm is 97.5, precision is 0.98, recall is 0.96, and f1-score is 0.97. While the Decision Tree algorithm obtained accuracy of 92.5, precision of 0.92, recall of 0.90, and f1-score of 0.91. with these results, this research can be continued into an application that can classify individuals at risk of Chronic Kidney Disease
Side Dish Store Recommendation System Utilizes A Collaborative Filtering Methodology Suryani, Suryani; W Soetikno, Y Johny; Octavianus, Michael; Faizal, Faizal; Hasriani, Hasriani; Nurdiansah, Nurdiansah; Bahtiar, Akbar
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5229

Abstract

Side Dish Stores serve as traditional venues for buying and selling a diverse array of products, including fish, foodstuffs, beverages, kitchen spices, clothing, souvenirs, and more. In their pursuit of maximizing profits, traders use competitive strategies, such as online marketing, to expand their sales channels and promote products digitally. This research aims to generate recommendations for selling fish, and traditional supermarkets through a collaborative filtering method. The criteria used to generate recommendations for shops or fish sellers among 25 alternatives include product type, availability, service quality, shop cleanliness, product quality, and sales volume. The research results indicate that the highest predicted value is 0.70, where user 16 exhibits the highest similarity with user 14. Consequently, TSF 1= 4.17, TSF 5= 3.5, TSF 9= 3.33, TSF 13= 3.83, and TSF 15= 4.5. When ranked, TSF 15 will be the first recommendation for user 16, followed by TSF 1, TSF 13, TSF 5, and TSF 9. This recommendation system facilitates consumers in determining the appropriate shop or fish seller to visit when shopping at the Side Dish Store. Traders can easily market products to enhance sales. Moreover, the system streamlines buying and selling transactions for traders and consumers without the necessity of direct visits to the Side Dish Store
Pembentukan Pola Peminjaman Buku Pada Perpustakaan Dengan Menerapkan Metode CART dan Normalisasi Z-Score Ahyuna, A; Lasena, Marlin; Aminuddin, Rosihan; Ardimansyah, Ardimansyah; Azhar, Zulfi
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5238

Abstract

The library is a service place that is useful as a place to borrow all kinds of books to read or as reference material in the form of images, text or other forms. In simplifying book borrowing strategies, the library utilizes realistic borrowing data as an object for strategy discovery by exploring knowledge that can provide information to simplify the book borrowing system. Data Mining can be interpreted as data mining, where in the data mining process a data mining process is carried out which aims to find important, valuable and useful information in a very large collection of databases. If the data held is very large, it is necessary to carry out a preliminary process as a stage to help simplify the process carried out in data mining, or this process is known as data normalization. One method that can be used in the process of normalizing data is the Z-Score Normalization method. The Z-Score Normalization method is a process in the preprocessing stage by decomposing numerical attribute data which can change the values ​​in the data into a certain range. The Z-Score Normalization method itself can also be combined with other methods such as the CART method. The CART method is a method used to carry out the classification process in data mining. The classification process carried out using the CART method is based on the formation of a decision tree with the binary values ​​obtained. The CART method itself is a method used to assist in processing all types of data such as continuous, ordinal, nominal and other data. The results obtained from the Cart Method research can be applied to obtain book borrowing patterns or book association relationships in libraries in the form of rules which can provide important information about book borrowing patterns in the library
Analisis Sentimen Ulasan Pengguna E-commerce di Google Play Store Menggunakan Metode IndoBERT Pradhisa, Kireyna Cindy; Fajriyah, Rohmatul
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5247

Abstract

In today's booming digital age, the internet has created global connectivity that links individuals around the world in a global community. Through synergistic collaboration between commerce and information technology, the term e-commerce was born. The analysis of e-commerce product quality is conducted to understand the public's perception of the products offered through the e-commerce platform, which can be accessed through the Google Play Store. The purpose of this research is to find out the sentiment trends of e-commerce users and to know how accurate IndoBERT is in classifying sentiment. By doing so, the founders and managers of both platforms can gain a better understanding of their users' needs and preferences. This information will serve as a foundation for improving service quality and user experience, thereby increasing customer satisfaction and strengthening competitive position in the e-commerce market. In this study, a sentiment analysis of the products of e-commerce platforms Shopee and Bukalapak is conducted, using the NLP-based IndoBERT (Natural Language Processing) model, which classifies the sentiment of user reviews into three categories: negative, neutral, and positive. The review data was taken from Google Play Store with scrapping technique and involved 5000 Shopee and Bukalapak review data with 2500 data each in 2023. The accuracy obtained is 89.84% on Shopee review data and 88.12% on Bukalapak review data. This shows that the model is able to effectively identify sentiment in each user review. Furthermore, another result obtained is that the sentiment of Shopee and Bukalapak e-commerce application users tends to be positive. Therefore, it can be said that the products offered and services carried out by e-commerce platforms Shopee and Bukalapak in 2023 get a good response from the public, which shows that both platforms are trusted and favored by the public.
Implementation of A Decision Support System for Major Selection using AHP and TOPSIS Method Khatimah, Khusnul; Gustalika, Muhamad Azrino
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5256

Abstract

With the rapid development of science and technology, new technology is starting to be used in various fields including education. Education has a very important progress in a nation, because it can optimize individual potential. The educational process in higher education has a big influence on a student's future. However, there are many students who experience difficulties in choosing a college major after graduating from vocational high school (SMK) or senior high school (SMA), because of the complexity in identifying the suitability between interests and study programs. Decision making is a problem that everyone faces, especially in choosing an appropriate college major. There are many factors to consider, and with many options available, the decision-making process can be difficult. To overcome this problem, this research aims to create a decision support system (DSS) using the AHP (Analytical Hierarchy Process) and TOPSIS (Technique For Order By Similarity To Ideal Solution) methods. The AHP method is used to solve complex problems by structuring a hierarchy of criteria and developing weights or priorities. However, when the AHP method is used with many criteria and alternatives, other methods are needed for more effective results. Therefore, a combined method of AHP and TOPSIS was chosen, where AHP focuses on pairwise comparison matrices and consistency analysis, while TOPSIS can measure relative performance and alternative decision making simply and efficiently. The results of research on decision support systems for selecting majors using the AHP and TOPSIS methods show that the application of the combined AHP-TOPSIS method can be used to determine the best alternative in selecting majors by comparing alternatives based on predetermined criteria. In addition, system testing results show that the system functions as expected and meets user needs. With a decision support system for selecting college majors implemented on the website, it can simplify the decision-making process for students and BK teachers in choosing college majors. The results of the calculation of the percentage of system feasibility in blackbox testing show a value of 95.71%, which indicates that this major selection decision support system website can be used.
Steganografi Gambar Menggunakan Metode Least Significant Bit Pada Citra Dengan Operasi XOR Adha, Martin; Yanto, Febi; Handayani, Lestari; Pizaini, Pizaini
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5262

Abstract

One way to secure secret messages from other unauthorized parties is steganography. One of the most widely used methods in steganography is Least Significant Bit. This research uses images as cover images and secret images. The image is resized to a resolution of 512x512 pixels, The cover image uses an RGB channel image and the secret image also uses an RGB channel image. In this research, LSB will be combined with triple XOR so that it can increase the security of this message hiding method. Triple XOR is used to provide extra security to images that have a secret image (Stego Image) inserted. In this research, several tests were also carried out, including testing the Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE), for robustness testing it was also carried out by making modifications to the stego image such as resizing, compressing, and adding and reducing contrast. The results of this research's PSNR testing are very good, namely approximately 49 dB and lower MSE. With the PSNR and MSE results, it can be proven that the LSB method has a good level of imperceptibility. In experiments on image resistance to modification, several experimental results show that secret image extraction in the stego image failed to be extracted, and from several experiments such as adding and reducing contrast, image rotation and lossless compression, the image inserted in the stego image was successfully extracted.
Penerapan Algoritma K-Medoids dan FP-Growth dengan Model RFM untuk Kombinasi Produk Pertiwi, Tata Ayunita; Afdal, M.; Novita, Rice; Mustakim, Mustakim
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.v6i2.5268

Abstract

Competition in the business world has increased, resulting in companies having to optimize sales and retain their customers. Customers are an important company asset that must be well looked after. The aim of customer segmentation is to understand customer purchasing behavior so that companies can implement appropriate marketing strategies. Aurel Mini Mart is a retail business that does not yet consider the recency, frequency and monetary value of customer shopping. So far, promotions have been carried out only based on estimates, without taking into account accurate data and information. This research combines the RFM model with data mining techniques to segment customers. Based on the 5 clusters formed from the clustering process, gold customers are in cluster 1 which has high loyalty with low recency value, high frequency and high monetary value. This shows that customers in this segment often make purchases for quite large amounts of money. Meanwhile, customers in clusters 2, 3, 4, and 5 are dormant customers who rarely make transactions and the amount of money spent is also small. After the customer segmentation process is complete, the next step is to use the FP-Growth Algorithm to associate the products purchased by customers. This aims to obtain a better product combination, so that the sales strategy can be more effective and the company can make a profit.