cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Syahrizal
Contact Email
syahrizal83.budidarma@gmail.com
Phone
+6282370070808
Journal Mail Official
pdsi.bids@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Informatics and Data Science
Published by Asosiasi Peneliti Data Science Indonesia
ISSN : -     EISSN : 25808389     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering Engineering
The Bulletin of Informatics and Data Science journal discusses studies in the fields of Informatics, DSS, AI, and ES, as a forum for expressing research results both conceptually and technically related to Data Science
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 8 Documents
 1 
Search results for , issue "Vol 2, No 2 (2023): November 2023" : 8 Documents clear
Combination of Grey Relational Analysis (GRA) and Simplified Pivot Pairwise Relative Criteria Importance Assessment (PIPRECIA-S) in Determining the Best Staff Setiawansyah, Setiawansyah; Sintaro, Sanriomi; Saputra, Very Hendra; Aldino, Ahmad Ari
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.67

Abstract

Problems in selecting the best staff often involve complex challenges such as difficulty finding candidates with good performance. The problems faced in the selection of the best are only based on the assessment of discipline and productivity of performance carried out by the staff, so the assessment process does not use aspects of criteria that are considered important in selecting the best staff.  This study aims to determine the best staff based on predetermined criteria and in determining the selection of the best staff using the Gray Relational Analysis (GRA) decision model while in determining the weight of criteria using the Simplified Pivot Pairwise Relative Criteria Importance Assessment (PIPRECIA-S) model so that the weight of the resulting criteria is not based on assumptions from decision makers. The results of the best staff assessment ranking using the Gray Relational Analysis method and the Simplified Pivot Pairwise Relative Criteria Importance Assessment weighting method obtained the results, namely for Rank 1 obtained by Denis Irawan with a final Gray Relational Analysis value of 0.243014. The results of data processing in the TRITAM Model test for the best staff selection application were adjusted to the conclusion of the overall results of the TRITAM Model criteria for technology acceptance, the results were good at 82.56%.
Lightweight Deep Learning for Object Detection on Mobile Device Lika, Sudiharyanto; Pernando, Yonky; Kurniawan, Ade
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.82

Abstract

Computer vision is a research in the development of technology to obtain information from images and replicate or imitate human visual processes, so that computers can know the objects around them. Deep learning is now the key word as a new era in machine learning that trains computers in finding patterns from large amounts of data. The Convolution Neural Networks (CNN) algorithm has proven impressive in terms of performance for detecting objects, image classification and semantic segmentation. Object detection is a technique used to identify the type of object in an image and also the exact location of the object in the image. Face detection is one of the most challenging problems of pattern recognition. Effective training needs to be done to be able to detect faces effectively. The accuracy in face detection using machine learning does not give good results. This research focuses on the level of accuracy of detecting faces using deep learning methods. This study compares the level of accuracy of deep learning and machine learning in detecting faces effective and efficient. This study uses the Convolution Neural Networks (CNN) model in the deep learning method to detect faces in real time on Android. According to the test results, the accuracy obtained in this study reached 97.97% in several normal facial conditions and face masks.
Decision Support System for Determining New Branch Location Applying the MAUT Method with ROC Weighting Mesran, Mesran; Kusuma, Ade Ayunda; Lubis, Ridha Maya Faza
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.76

Abstract

The new branch location is close to people's activities with the availability of adequate facilities, making it convenient for consumers to access the services/products they need. The determination of the feasibility of a new branch location by several product or service producers still uses an inaccurate system, which can lead to problems in determining a strategic and targeted new branch location. However, there are some challenges in selecting a new branch location, so the utilization of technology is considered efficient, easy, and flexible, widely used by entrepreneurs, especially in determining new branch locations. This is done by using the assistance of a decision support system, which is expected to help determine an efficient and strategic new branch location. The aid comes in the form of a Decision Support System using the MAUT method with ROC weighting. After calculating each criterion and alternative, the best ranking is obtained for alternative A6 with a value of 0.6847. This way, business groups will not have difficulty in determining a new branch location through alternatives and criteria. The use of the MAUT method with ROC weighting is expected to assist in obtaining the best and valid alternatives up to the ranking stage
Implementation of a Combination of Rank Reciprocal and Additive Ratio Assessment Approaches for 3D Printer Selection Fatmayati, Fryda; Soares, Teotino Gomes; Tonggiroh, Mursalim; Alexander, Allan Desi
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.83

Abstract

With the wide selection of 3D printers available on the market, the challenge arises for consumers and businesses to choose the device that best suits their specific needs. To determine the choice, the decision-maker must know one by one the specifications of the 3D printer to be purchased, which results in making difficult decisions and requiring a long time. This research aims to implement a combination of the Rank Reciprocal and additive ratio assessment (ARAS) approaches to make it easier to determine decisions for selecting a 3D printer. The Reciprocal Rank approach provides weight values by utilizing the reciprocal or inverse principle. Meanwhile, the ARAS approach is used to obtain the best alternative by evaluating alternative rankings based on their utility function. From the case studies that have been carried out, the highest to lowest utility values are Anycubic 4Max Pro (A2) getting a score of 0.8289, Creality Ender-3 Pro (A1) getting a score of 0.6174, Anet 3D Printer ET4 Pro (A3) getting a score of 0.5510, and Mingda Magician X2 (A4) getting a score of 0.5116. The output produced by the system in the case study carried out produces the same value as the manual calculation, meaning that the ARAS method calculation in the system is declared valid. Based on usability testing, it got a score of 90%, which shows the system is suitable for use
The Decision Support System Uses the Preference Selection Index Method in Determining Healthy Cooperatives Sulistiani, Heni; Maryana, Sufiatul; Palupiningsih, Pritasari; Mehta, Abhishek
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.72

Abstract

Determining a healthy cooperative is a challenge that requires attention to several key aspects. Effective management, stable finances, active member involvement, and compliance with laws and regulations are key factors to be considered. By paying attention to all these factors and taking appropriate action, the cooperative can achieve optimal health levels and make a significant contribution to its members as well as the surrounding community. This study aims to determine healthy cooperatives using the Preference Selection Index (PSI) method in determining the best healthy cooperatives using the criteria of Capital, Quality of Productive Assets, Management, Efficiency, Liquidity, Independence, and Cooperative Identity so that the results of the best healthy cooperative ranking recommendations will be able to become recommendations for a decision. Based on the results of the calculation of the final value and ranking of the best healthy cooperatives using the PSI method, rank 1 is Koperasi-02 with a final value of 0.10737, rank 2 is Koperasi-01 with a final value of 0.10029, rank 3 is Koperasi-03 with a final value of 0.05223, rank 4 is Koperasi-04 with a final value of 0.0107. The results of testing using blackbox testing that has been carried out obtained the results of the number of answers from respondents have a value of 100% in accordance with testing the functionality of the system using blackbox testing
The Process of Grouping Elementary School Students Receiving PIP Assistance uses the K-Means Algorithm Huang, Jen-Peng; Wang, Pai-Chou; Lubis, Ridha Maya Faza
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.78

Abstract

As part of receiving support from the Smart Indonesia Program (PIP), this study intends to analyze and apply the K-Means algorithm in the process of grouping elementary school students. PIP is a government initiative that attempts to give money to elementary school pupils from disadvantaged or weaker homes. The effective and fair distribution of aid monies depends on the proper grouping of the students. The K-Means approach was selected because it can cluster data, allowing the grouping of pupils based on pertinent traits. Numerous characteristics that can affect kids' financial needs are included in the data utilized in this study, including family income, parental education level, proximity to the school, and other social and economic issues. This study makes use of empirical data from a PIP-affiliated elementary school in an urban setting. The data includes a large number of pertinent features and thousands of pupils. Based on how similar their characteristics are, pupils are divided into numerous clusters using the K-Means technique. The findings of this study will help us better identify the traits of students who are eligible for PIP support. By doing this, the government can allocate funds more wisely and guarantee that aid is given where it is most needed. The PIP program can benefit children in need more by streamlining the process of grouping the students. In addition, this research has broader implications for social aid and education policy. To guarantee effectiveness and equity in resource allocation, the K-Means algorithm can be used in a variety of additional aid initiatives. Data mining-based strategies, like those employed in this study, are becoming more crucial to boost the effectiveness of aid programs like PIP. The findings of this study can help the government and educational institutions improve the efficacy of aid initiatives designed to boost Indonesian children's education
Applying IROC Method in Patent Submission Evaluation in Indonesia: A Comparison with MAGIQ and AHP Ambarsari, Erlin Windia; Rahman, Vierhan; Cholifah, Wahyu Nur
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.75

Abstract

This study applies the Improved Rank Order Centroid (IROC) to the Indonesian patent submission process within a Multi-Criteria Decision Making (MCDM) framework. The study evaluates four primary elements in patent assessment: "Patent Description," "Illustration," "Inventor's Ownership Statement," and "Rights Assignment Declaration." Preliminary findings indicate the importance of "Patent Description," followed by the other elements in descending order of significance. The evaluation also encompasses three applicant alternatives, with the Second Applicant emerging as the most favorable. The study further contrasts IROC outcomes with MAGIQ and AHP methodologies. While rank-based techniques like ROC and IROC generally produce similar weight distributions, the AHP method, which employs pairwise comparisons, often displays variations. The research underscores the potential of IROC in determining criterion weights, its comparison within the MAGIQ framework, and its validation through AHP. These insights aim to deepen our understanding of decision-making processes and analysis. The conclusion from comparing IROC results with MAGIQ and AHP indicates that the applicant rankings remain consistent. Therefore, further research is needed to understand the differences between evaluation methods and their impacts and explore the influence of cultural or regional factors in the patent submission process
Decision Support System for Student Exchange Selection in Support of Independent Campus using the MAUT and ROC Methods Rohayani, Hetty; Arini, Zaza Mutiara; Sussolaikah, Kelik; Syam, Syahrull Hi Fi
Bulletin of Informatics and Data Science Vol 2, No 2 (2023): November 2023
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v2i2.80

Abstract

Independent campus is an off-campus learning activity as an opportunity for students to hone skills in preparation for entering the world of work. One of the programs held is the exchange of students to be able to study on campuses or companies that join the Ministry of Education and Culture, Research and Technology. With the current independent campus program, almost all universities open up opportunities for students to register. However, because there are too many students who register, the campus has difficulty in choosing some students who can be accepted according to the criteria set by the party. For this reason, a Decision Support System is needed that applies the MAUT method along with the use of ROC to produce the best preference value. The calculation of several data samples resulted in the best final utility value in the selection of independent campus student exchanges in Alternative A2 with the best final utility value of 0.9700

Page 1 of 1 | Total Record : 8

 1 

Filter by Year

2023 2023


Reset
Filter By Issues
All Issue Vol 4, No 2 (2025): November 2025 Vol 4, No 1 (2025): May 2025 Vol 3, No 2 (2024): November 2024 Vol 3, No 1 (2024): May 2024 Vol 2, No 2 (2023): November 2023 Vol 2, No 1 (2023): May 2023 Vol 1, No 2 (2022): November 2022 Vol 1, No 1 (2022): May 2022