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
Penerapan Data Mining Untuk Penjurusan Kelas dengan Menggunakan Algoritma K-Medoids Jhiro Faran; Rima Tamara Aldisa
Building of Informatics, Technology and Science (BITS) Vol 5 No 2 (2023): September 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i2.4313

Abstract

Class assignments are carried out to focus students on the subjects that will be studied during Senior High School (SMA). Class majors are generally carried out in class of all the main values used in the class majoring process. This is a problem with the class majoring process, where mistakes often occur in the class majoring process. Mistakes regarding class majors made by students will have quite a fatal impact on the student, apart from not being able to change classes, it will also have a laziness effect on the student because it does not match the student's abilities. Solving this problem can be done using a technique called data mining. The solution to this problem is done using clustering. The K-Medoids algorithm is the algorithm used to solve the problems in this research. The process of grouping or forming clusters in the K-Medoids algorithm is based on calculating the closest distance to each object, calculating the closest distance is based on determining the centeroid value first. The K-Medoids algorithm can form 2 (two) clusters according to existing class majors. The results obtained show that there are 3 (three) alternatives included in cluster 1 and also 12 (twelve) alternatives included in cluster 2.
Penerapan Algoritma K-Means Clustering untuk Daerah Penyebaran Sampah Kelurahan Yantria Gusta Nugraha; Maimunah Maimunah; Pristi Sukmasetya
Building of Informatics, Technology and Science (BITS) Vol 5 No 2 (2023): September 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i2.4158

Abstract

Waste in Indonesia, especially in Magelang City, has become a serious problem due to rapid population growth. Waste management issues, including landfills and collection, need effective handling. Data mining methods, such as K-Means clustering, can help identify areas with the highest levels of waste generation. This approach provides insights for the development of a more focused and efficient waste management strategy, a significant contribution to the improvement of Magelang City. By identifying the areas with the highest waste generation, waste management measures can be directed more efficiently and effectively. This includes increasing the transparency, capacity, and role of waste banks, as well as other efforts to reduce the negative impact of waste on the environment and human health. After clustering, the waste in Magelang City was grouped into 3 clusters according to the supplier area and the volume of waste. Then after the evaluation stage with the silhouette score displays a value of 0.79 which is a good value because it is close to the value of 1.0. With this method, it is expected that the city government in handling waste in Magelang city can be done optimally, efficiently, and on target
Decision Support System for Determining the Best Internship Students Using the Combined Compromise Solution Method Pasaribu, A. Ferico Octaviansyah; Aldino, Ahmad Ari; Surahman, Ade; Setiawansyah, Setiawansyah
Building of Informatics, Technology and Science (BITS) Vol 5 No 3 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i3.4231

Abstract

Interns are individuals who are undergoing a period of practical learning in an organization or company as part of their educational curriculum. During the internship, students have the opportunity to apply the knowledge they learn in class to real-world situations, as well as gain valuable work experience. The selection of the best intern can involve several problems or challenges. One of them is the difficulty in evaluating students' practical skills based solely on their academic performance. The Decision Support System (DSS) to determine the best internship students using the Combined Compromise Solution Method provides a holistic approach in the selection process. This method combines elements of the Compromise Solution Method that consider compromise solutions between alternatives. With this comprehensive approach, DSS can assist institutions or companies in selecting internship students that best suit their needs and expectations, as well as ensure the success of internships that are beneficial to both parties. The results of the ranking of the best internship student alternatives showed that rank 1st with a value of 5.7847 was obtained by Jonathan, rank 2nd with a value of 5.2625 was obtained by Handoko R, and rank 3rd with a value of 4.6117 was obtained by M. Ali Fikri. The results of this ranking help companies determine the best internship students by applying the combine compromise solution method
Algorithmic Advancements in Heuristic Search for Enhanced Sudoku Puzzle Solving Across Difficulty Levels Pratama, Moch Deny; Abdillah, Rifqi; Herumurti, Darlis; Hidayati, Shintami Chusnul
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.4622

Abstract

Computer technology, particularly artificial intelligence, has found diverse applications in the rapidly evolving era of the industrial revolution, notably in gaming, delving into artificial intelligence and explicitly applying game-solving techniques to Sudoku puzzles. Sudoku, a popular game requiring logical precision, serves as an ideal platform for exploring algorithms such as depth-first search, breadth-first search, and heuristic search. This research identifies memory-intensive demands in breadth-first search and the potential issue of infinite traversal in depth-first search. To address these challenges, the study proposes implementing the heuristic search algorithm, which prioritizes promising paths based on estimations of proximity to the goal state made by a heuristic function. The primary objective is to enhance Sudoku puzzle-solving by comparing the performance of the heuristic search algorithm with traditional breadth-first and depth-first search methods, with a particular focus on improving efficiency and reducing memory usage, including time and steps. The results indicate that the heuristic search algorithm outperforms traditional methods, demonstrating faster completion times and reduced memory requirements, thereby contributing to the advancement of Sudoku-solving algorithms. The study evaluates their performance across different difficulty levels, utilizing data from sudoku.com and extremesudoku.info. Notably, the heuristic search algorithm emerges as a superior method, outperforming other algorithms in terms of completion steps and time efficiency. The implementation and analysis involved three types of Sudoku puzzle-solving methods, revealing that the heuristic search algorithm significantly outperforms other algorithms, optimizing its performance in solving Sudoku puzzles. The average time required to complete Sudoku puzzles from data sourced from Sudoku.com was 0.02, 0.05, and 0.61 seconds for each level, respectively. In contrast, according to extremesudoku.info, it took 0.31 seconds for the highest difficulty level. Furthermore, the average total steps needed on sudoku.com ranged from 43 to 1201 steps for each level, spanning from easy to hard. On extremesudoku.info, 509 steps were required for the highest difficulty level. These results affirm the reliability of heuristic search, consistently demonstrating encouraging outcomes and outperforming other algorithms across diverse conditions. This strategic selection facilitates a comprehensive analysis of Sudoku problem-solving algorithms, allowing for the exploration of algorithmic performance and providing a comprehensive range of Sudoku puzzles, thereby ensuring the study's robustness and validity
Prediksi Keterlambatan Pembayaran SPP Siswa dengan Pendekatan Metode Naive Bayes dan K-Nearest Neighbors Alfiansyah, Deden Moh; Soetanto, Hari
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.4643

Abstract

Education in Indonesia faces cost challenges which have an impact on the provision of education, especially Education Development Contributions (SPP) in private schools. This research aims to improve the administrative efficiency of student tuition payments at Wirasaba Karawang Vocational School through a classification approach. 725 payment data for one semester in 2023 are used to predict payment delays. About 22% of students experience delays. By understanding delay patterns, this research proposes solutions to improve administrative efficiency with appropriate preventive measures. The hope is that the results of this research can provide benefits to Vocational School Wirasaba Karawang and contribute to the development of a more efficient education administration system, thereby improving education services in Indonesia as a whole. This research describes the problem of late SPP payments, applies a classification method to predict these delays, aims to increase the efficiency of payment administration, and has the potential to provide preventive solutions that can reduce late payments. The contribution of this research is the development of a more efficient education administration system through an information technology approach, with interim results in the form of analysis of late payment patterns based on 2023 data from Wirasaba Karawang Vocational School
Decision Support System for Tourist Attraction Recommendations Using Reciprocal Rank and Multi-Objective Optimization on the basis of Ratio Analysis Ariany, Fenty; Suryono, Ryan Randy; Setiawansyah, Setiawansyah
Building of Informatics, Technology and Science (BITS) Vol 5 No 3 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i3.4663

Abstract

A tourist attraction is a destination or place visited by tourists to enjoy a variety of attractions, natural beauty, culture, history, or recreation. Attractions can be beaches, mountains, lakes, national parks, historical buildings, museums, amusement parks, and much more. One common problem is confusion in choosing the right attraction, where the information available is incomplete or inaccurate, causing tourists difficulty in making the right decision. Therefore, there needs to be a holistic and integrated approach in choosing tourist attractions, taking into account these aspects so that the tourist experience becomes more meaningful and meaningful for all parties involved. The research objective of the Attraction Recommendation Decision Support System Using Reciprocal Rank and MOORA is to develop a system that can provide optimal attraction recommendations to users based on their preferences against diverse criteria, such as distance, cost, travel time, and cleanliness level. By using the Reciprocal Rank approach to take into account the user's subjective preferences towards each criterion. Meanwhile, by applying MOORA, this study aims to optimize the relative performance of alternative attractions based on the relationship between criteria. Thus, this research is to provide useful tools for users to make better and more informed decisions. The ranking results provide recommendations for alternative krui beach with a final value of 0.3752 to rank 1, alternative tanjung setia beach with a final value of 0.3558 to rank 2, alternative klara beach with a final value of 0.3512 to rank 3
Sentiment Classification of S.E.A Aquarium Singapore Reviews through CRISP-DM using DT and SVM with SMOTE Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 3 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.4703

Abstract

In recent years, sentiment analysis has emerged as a critical area of research due to its wide-ranging applications in understanding public opinion, customer feedback, and social media sentiment. However, one of the significant challenges faced in sentiment analysis is the handling of imbalanced datasets, where the distribution of sentiment classes is uneven, leading to biased model performance. This study employs the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology to investigate sentiment analysis algorithms, mainly focusing on the Support Vector Machine (SVM) algorithm and the integration of the Synthetic Minority Over-sampling Technique (SMOTE). Through systematic experimentation and evaluation, the research demonstrates the superior performance of the SVM-SMOTE model in handling imbalanced datasets, achieving an accuracy of 98.46%, an AUC of 1.000, precision of 100.00%, recall of 96.91%, and an impressive F-measure of 98.42%. Additionally, the evaluation unveils specific toxicity scores across various categories, with Toxicity scoring at 0.11036 and 0.93915, Severe Toxicity at 0.00905 and 0.45895, Identity Attack at 0.02415 and 0.66373, Insult at 0.05149 and 0.85793, Profanity at 0.06392 and 0.93426, and Threat at 0.01562 and 0.51957. These numerical indicators provide quantitative insights into potential harm within analyzed content, emphasizing the efficacy of the SVM-SMOTE model in real-world applications and contributing to the advancement of sentiment analysis within the CRISP-DM framework.
Implementation of MOORA in Decision Support System Optimization for Hotel Accommodation Services Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 3 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i3.4730

Abstract

Service marketing challenges increase brand awareness related to accommodation services related to services, facilities, room comfort and quality, cleanliness, value for money, and location. Consumers who use Agoda's platform exhibit purchase behavior that makes ratings a benchmark before making a stay decision. This research aims to optimize the decision support system for selecting hotel accommodation services using the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) decision support model. The MOORA method consists of the following stages: first, determining criteria, weights, and alternatives; second, determining the value of criteria, weights, and alternatives; third, the stage of normalization and optimization of attributes; Fourth, the stage of reducing the maximax and minimax values and ranking. Meanwhile, based on the classification of criteria, only the value of money is categorized as min, while other criteria include the max category. In addition, the weight of the criteria is as follows: services (0.15), facilities (0.15), room comfort and quality (0.20), cleanliness (0.20), value for money (0.20), and location (0.10). The results of this study show that The Trans Luxury Hotel ranks first with a total Yi value of 0.200649351. F, Pullman Bandung Grand Central ranked second with a total Yi value of 0.198075614. Meanwhile, Hilton Bandung ranks third with a total Yi value of 0.19758031. This shows that each hotel needs to increase its rating to attract the attention of potential customers in the decision-making process of staying.
Extract Sentiment and Support Vector Machine (SVM) Performance of Hotel Guest Review Classification Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 3 (2023): December 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i3.4737

Abstract

The hotel accommodation business highly depends on consumer preferences regarding products and services. The intensity of hotel guest visits and the level of guest satisfaction with the services provided by hotel management can be seen from various guest reviews on websites used as reservation media. Therefore, this research uses the Cross-Industry Standard Process for Data Mining (CRISP-DM) method to implement the data mining process using the webharvy application and the machine learning process using the Rapidminer application. Meanwhile, the operators used are Synthetic Minority Over-sampling Technique SMOTE in overcoming data imbalances and sentiment extract operators to obtain a total string score before sentiment labels are determined and processed using the Support Vector Machine (SVM) algorithm. The results of this study showed that SVM without using SMOTE operators resulted in an accuracy value of 95.82%, a precision value of 95.80%, a recall value of 100%, and an Area Under Curve (AUC) value of 0.798 (79.8%). Otherwise, SVM performance using SMOTE operators produces an accuracy value of 92.05%, a precision value of 100%, a recall value of 84.08%, and an Area Under Curve (AUC) value of 99.99 (99.9%). Furthermore, based on ten popular words, hotel guests are concerned about breakfast, staff, pool, room, and hotel. Thus, the guests' highlights are the menu served by the hotel, the service provided by employees, room conditions, and hotel brands. Therefore, hotel management needs to improve the quality of products and services to increase satisfaction and intention to stay again.
Reduksi False Positive Pada Klasifikasi Job Placement dengan Hybrid Random Forest dan Auto Encoder Pahlevi, M. Riza; Rasywir, Errissya; Pratama, Yovi; Istoningtyas, Marrylinteri; Fachruddin, Fachruddin; Yaasin, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.4864

Abstract

The False Positive (FP) interpretation shows a negative prediction result and is a type 1 error answer with an incorrect positive prediction result. Based on this, we try to reduce type 1 errors to increase the accuracy value of the classification results. A low FP rate is critical for the use of Computer Aided Detection (CAD) systems. In this research proposal, to reduce FP, we use a Random Forest (RF) evaluation result design which will be reinterpreted by the Auto Encoder (AE) algorithm. The RF algorithm was chosen because it is a type of ensemble learning that can optimize accuracy in parallel. RF was chosen because it performs bagging on all Decision Tree (DT) outputs used. To suppress TP reduction more strongly, we use the Auto Encoder (AE) algorithm to reprocess the class bagging results from RF into input in the AE layer. AE uses reconstruction errors, which in this case is Job Placement classification. From the test results, it was found that combining the use of a random forest using C4.5 as a decision tree with an Autoencoder can increase accuracy in the Job Placement Classification task by a difference of 0.004652 better than without combining it with an autoencoder. Apart from that, in testing using a combination of RF and AE, fewer False Positive (FP) values ​​were produced, namely 11 items in the Cross Validation-5 (CV-5) Test, then 13 items in the Cross Validation-10 (CV-10) test and in testing split training data of 60%, the FP was only 12. This value is less than the false positives produced by testing without Autoencoder, namely 12 items on CV-5, 15 items on CV-10, and 13 on split training data