Bulletin of Data Science

Analisis Perbandingan Metode Certainty Factor Dan Teorema Bayes Untuk Mendiagnosa Penyakit Paru-Paru Anak

Trifave Sitinjak — 2025-02-28

Expert systems are one of the fields of artificial intelligence engineering that is quite in demand because of its application in various fields both in the fields of science and business which have proven to be very helpful in making decisions and are very broad in application. One of the applications of the expert system is in the field of medicine which is used to diagnose a disease. Lung disease is a disease that attacks the respiratory system in humans whose incidence rate is quite wide and can attack various ages. infect the respiratory tract and cause the patient to experience shortness of breath. Lung diseases that are often found in everyday life are pneumonia, tuberculosis, bronchitis, common cough accompanied by fever. Diagnosing diseases with an expert system, it is necessary to apply methods to solve the problem. The method applied is the certainty factor method, the Bayes theorem method. The use of these two methods will be compared to measure the level of expert confidence and the level of probability of symptoms that are likely to suffer from lung disease so that the most appropriate and best method for diagnosis can be known.

Peningkatan Layanan Customer Service Melalui Chatbot Menerapkan Algoritma Text Mining dan TF-IDF

Fajar Surya Atmaja — 2025-02-28

Dr. Hospital Pirngadi is a regional general hospital owned by the government and is a type B hospital located in the Medan City area, North Sumatra. Apart from that, Dr. Pirngadi is also a referral hospital for the Medan and surrounding areas. As a regional general hospital, Pirngadi Regional Hospital also plays a role in providing health services for the people of Medan city and its surroundings, services provided by customer service at Dr. Pirngadi Medan City, such as registration and information on patients who wish to register for either inpatient or outpatient care, information regarding doctor's practice schedules, facility service information, patient guarantor cooperation, bad management, and visitor information. Customer service is not yet optimal for patients and visitors, such as limited information provided, lack of accessibility and clarity of information, lack of coordination between various hospital departments. To overcome this problem, customer service can utilize artificial intelligence technology to improve customer service. This research provides a solution by building a system in the form of a chatbot, this chatbot system will become an information medium for patients and visitors. The chatbot development process uses a text mining algorithm for text processing and TF-IDF to give weight to each document available in the database. The system provides responses based on the highest level of similarity, with text mining and TF-IDF algorithms, chatbots can provide precise and accurate information on questions asked by patients and visitors. The final result of this research is a chatbot that can be used by patients and visitors to find out available information. The existence of a chatbot can make it easier for patients and visitors to get information about the services available at Dr. RSUD. Pirngadi, Medan City.

Implementasi Metode OCRA Dan ROC Rekomendasi E-Commerce Terbaik Dalam Peningkatan UMKM

Robiah Al-Adawiyah — 2025-02-28

This research aims to implement the OCRA (Ordering and Ranking with Criteria) and ROC (Rank Order Centroid) methods in providing the best e-commerce recommendations to improve the performance of MSMEs (Micro, Small and Medium Enterprises). The OCRA method is used to assess various relevant criteria, such as cost, ease of use, and market reach, while ROC is used to determine the final ranking of each e-commerce platform. The research results show that Bukalapak received the highest final preference score of 0.2324, making it the main choice for MSMEs. It is hoped that these findings can help MSMEs choose the most suitable e-commerce platform, so that they can increase their competitiveness and business growth. This research makes a significant contribution to the development of digitalization strategies for MSMEs in Indonesia

Penerapan Metode Operational Competitiveness Rating Analysis (OCRA) dalan Penentuan Kelayakan Penerima Bantuan Langsung Tunai

Mesran Mesran, M.Kom — 2025-02-28

Bantuan Langsung Tunai (BLT) is a financial assistance program provided by the government to people in need. The main purpose of the BLT program is to support the economy of underprivileged families. In the selection process of BLT recipients, there are several criteria that must be considered, such as the condition of the house, the completeness of the files, the number of dependents, income, and the size of the land owned. To ensure that the determination of BLT recipient eligibility is done objectively and accurately, a decision support system is needed. One method that can be used is Operational Competitiveness Rating Analysis (OCRA). Through this method, it is expected that more accurate results can be obtained in determining who is entitled to receive BLT. The results of the research using the OCRA method showed that Jimmi Nababan was the most deserving BLT recipient candidate with the first rank and a score of 1,297. Thus, this decision support system is expected to be an effective solution in determining BLT recipients who really need this assistance.

Multi-Criteria Decision Support System for Best Warehouse Performance Selection Using Combined Compromise Solution Method

Junhai Wang — 2025-02-28

Selecting the best performing warehouse is a strategic step in supporting the efficiency of the supply chain and distribution of goods. This research aims to design a multi-criterion-based decision support system in evaluating and determining the best warehouse using the Combined Compromise Solution (CoCoSo) method. This method was chosen for its ability to combine the strength of weighted average approaches and relative compromises between alternatives, resulting in more balanced and objective decisions. This research involves eight warehouse alternatives that are assessed based on a number of relevant performance criteria. The process starts from problem identification, determination of criteria, data collection, normalization, weighting, to the application of the CoCoSo method. The final results showed that Warehouse C obtained the highest score of 4.8155, followed by Warehouse E and Warehouse A, indicating that the three warehouses had the best performance. These findings are expected to be a reference in strategic decision-making related to warehousing management as well as the basis for the development of a data-based performance evaluation system.