Sriwijaya Journal of Informatics and Applications (SJIA)
Not a member yet
49 research outputs found
Sort by
Comparison Of Dempster Shafer AND Certainty Factor Methods In Expert System For Early Diagnosis Of Stroke Disease
Get PDFStroke is one of endangering disease if not treated properly and could lean to death. Most people unwilling to check their health because of high cost, lack of medical service, medical staff of neurologist and their limited working time. Therefore, we need an expert system that can help in early diagnosis of stroke. The Dempster Shafer and Certainty Factor methods are expert systems methods used in many cases to support uncertainty from the expert. The aim of this study is to compare two methods to determine the best method in the expert system for diagnosing stroke, by calculating symptoms so as to produce CF values in the Certainty Factor method and density values in the Dempster Shafer method. The data used in the study to diagnose stroke consisted of data on eighteen disease symptoms and two types of stroke identified. Based on the results of testing on 105 test data, the accuracy value of the expert system for diagnosing stroke using the Dempster Shafer method is 95.2% and the accuracy value of the expert system for diagnosing stroke with the Certainty factor method is 98.1%
Decision Support System for Selection of Outstanding Students Using the AHP and SAW Methods
Get PDFIt is very important for outstanding students to be directed and guided to get coaching related to the development of each student's personal potential so that superior and quality students are created. The process of selecting outstanding students can get wrong decisions because the process of selecting outstanding students is based on subjectivity, this allows many selected outstanding students not to reach the desired standard and do not get the best candidates. Therefore, a decision support system was created that can carry out the calculation process for all selections for the selection of outstanding students. This final project will implement the AHP and SAW methods in forming a system. The stages are carried out by comparing feature weights with the AHP method. Then the next stage is to rank using the SAW method to get selected outstanding students. Of the 72 students who were selected from the school, they were then selected to become 20 outstanding students based on the highest-ranking order. Software testing is done by comparing the results of school calculations with system calculations. Based on the results of the tests carried out, an accuracy value of 80% was obtained
Comparison Of The Results Of The Jaccard Similarity And KNearest Neighbor Algorithms Using The Case Based Reasoning (CBR) Method On An Expert System For Diagnosing Pediatric Diseases
Get PDFHealth ranks highest in supporting the continuity of every human activity, especially children. The availability of a doctor is still relatively lacking, especially in remote areas. This makes people have difficulty in diagnosing certain diseases so that medical treatment becomes too late and can even be fatal for the patient. So it is necessary to create a system that has the ability to be able to diagnose diseases in children like an expert. The method used in this study is Case Based Reasoning (CBR) with the Jaccard Similarity Algorithm and K-Nearest Neighbor. Jaccard Similarity is one way to calculate the similarity of two objects (items) which are binary. Similarity calculations are used to generate values whether or not there is a similarity between new cases and existing cases in the case base. While the K-Nearest Neighbor (KNN) Algorithm belongs to the instance-based learning group. The KNN algorithm allows the program to find old cases that are most similar to the current case. Based on the test results using 50 sample data, the expert system can provide diagnostic results in accordance with expert diagnoses. The accuracy results for the K-Nearest Neighbor Algorithm are 72% while the accuracy results for the Jaccard Similarity Algorithm are 70%
NL2SQL For Chatbot with Semantic Parsing Using Rule-Based Methods
Get PDFStructured Query Language (SQL) is a command language that allows users to access database information. Ordinary people generally donot know how to make queries with SQL to a database. The chatbot is acomputer program developed to interact with its users via text or voice. In this study, chatbots were developed to help and facilitate users intheNatural Language to Structured Query Language (NL2SQL) process tosearch for information in an Academic Information Systemdatabasewith semantic parsing using a rule-based method that accepts input inthe form of interrogative sentences or order. In the Natural Language toStructured Query Language (NL2SQL) process several problems arise, namely input problems with unique parameters for the knowledge base, and slow searching or translation processes, which make Natural Language to Structured Query Language (NL2SQL) inef icient, problems This problem will be solved using a semantic parsingapproach using a rule-based method that is proven to be ef icient insolving issues such as the Natural Language to Structured QueryLanguage (NL2SQL) process. The results showed that the semanticparsing approach using the rule-based method succeeded in obtainingan accuracy rate of 96.72% using 122 test data in the formof questionsentences or command data about the Academic Information Systemof the Department of Informatics Engineering, Sriwijaya University inIndonesian, and an average execution time of 50.68 milliseconds. seconds or 0.05 seconds
Text Generation using Long Short Term Memory to Generate a LinkedIn Post
Get PDFLinkedIn is one of the most popular sites out there to advertise oneself to potential employer. This study aims to create a good enough text generation model that it can generate a text as if it were made by someone who posts on LinkedIn. This study will use a Neural Network layer called Long Short Term Memory (LSTM) as the main algorithm and the train data consists of actual posts made by users in LinkedIn. LSTM is an algorithm that is created to reduce vanishing and exploding gradient problem in Neural Network. From the result, final accuracy and loss varies. Increasing learning rate from its default value of 0.001, to 0.01, or even 0.1 creates worse model. Meanwhile, increasing dimensions of LSTM will sometimes increases training time or decreases it while not really increasing model performance. In the end, models chosen at the end are models with around 97% of accuracy. From this study, it can be concluded that it is possible to use LSTM to create a text generation model. However, the result might not be too satisfying. For future work, it is advised to instead use a newer model, such as the Transformer model
Application of Elimination Et Choix Transduisant La Realita (ELECTRE) in Hotel Selection in Palembang City
Get PDFThis study develops software for hotel selection using Elimination Et Choix Transduisant La Realita (ELECTRE). In Elimination Et Choix Transduisant La Realita (ELECTRE) multi-criteria decision-making is based on the concept of Outranking by using paired alternative comparisons based on criteria. The test is carried out by determining the normalization of the decision matrix, weighting the normalized matrix, determining concordance and discordance, calculating the concordance matrix, calculating the discordance matrix, determining the dominant concordance and discordance matrix, determining the aggregate dominance matrix, and eliminating less favorable alternatives. After calculating the Elimination Et Choix Transduisant La Realita, the system was tested using the Technology Acceptance Model (TAM). The test results as measured by the Technology Acceptance Model (TAM) method obtained a value of 87.06% for the use of technology (perceived usefulness) and 85.33% for the ease of use of technology (perceived ease of use)
Reconstruction Low- Resolution Image Face Using Restricted Boltzmann Machine
Get PDFLow-resolution (LR) face images are one of the most challenging problems in face recognition (FR) systems. Due to the difficulty of finding the specific features of faces, the accuracy of face recognition is low. To solve this problem, some researchers are using an image reconstruction approach to improve the resolution of their images. In this research, we are trying to use the restricted Boltzmann machine (RBM) to solve the problem. Furthermore, a labelled face in the wild (lfw) database has been used to validate the proposed method. The results of the experiment show that the PSNR and SSIM of the image result are 34.05 dB and 96.8%, respectively
Automatic Data Extraction Utilizing Structural Similarity From A Set of Portable Document Format (PDF) Files
Get PDFInstead of storing data in databases, common computer-aided office workers often choose to keep data related to their work in the form of document or report files that they can conveniently and comfortably access with popular off-the-shelf softwares, such as in Portable Document Format (PDF) format files. Their workplaces may actually use databases but they usually do not possess the privilege nor the proficiency to fully utilize them. Said workplaces likely have front-end systems such as Management Information System (MIS) from where workers get their data containing reports or documents.These documents are meant for immediate or presentational uses but workers often keep these files for the data inside which may come to be useful later on. This way, they can manipulate and combine data from one or more report files to suit their work needs, on the occasions that their MIS were not able to fulfill such needs. To do this, workers need to extract data from the report files. However, the files also contain formatting and other contents such as organization banners, signature placeholders, and so on. Extracting data from these files is not easy and workers are often forced to use repeated copy and paste actions to get the data they want. This is not only tedious but also time-consuming and prone to errors. Automatic data extraction is not new, many existing solutions are available but they typically require human guidance to help the data extraction before it can become truly automatic. They may also require certain expertise which can make workers hesitant to use them in the first place. A particular function of an MIS can produce many report files, each containing distinct data, but still structurally similar. If we target all PDF files that come from such same source, in this paper we demonstrated that by exploiting the similarity it is possible to create a fully automatic data extraction system that requires no human guidance. First, a model is generated by analyzing a small sample of PDFs and then the model is used to extract data from all PDF files in the set. Our experiments show that the system can quickly achieve 100% accuracy rate with very few sample files. Though there are occasions where data inside all the PDFs are not sufficiently distinct from each other resulting in lower than 100% accuracy, this can be easily detected and fixed with slight human intervention. In these cases, total no human intervention may not be possible but the amount needed can be significantly reduced.
Risk Management Evaluation in Hospital Management Information Systems Using Framework COBIT 2019 - Case Study: Ernaldi Bahar South Sumatera Hospital
Get PDFHospital Management Information System (SIMRS) is a system to assist service performance, reporting and data retrieval at hospitals that have been required by the government to be implemented in all hospitals in Indonesia. The existence of SIMRS is certainly an inseparable part of the service process and hospital data management, but it can also cause various IT risks to arise. Therefore, a good risk management is needed to minimize any possible IT risks that have not or have occurred. The performance of an IT risk management can be indicated from its capability levels. This study aims to determine how high the capability levels and the gap value from each process of the IT risk management at Ernaldi Bahar Hospital. The framework used as a reference in the assessment of the risk management process is COBIT 2019 which has 3 stages, namely the mapping process, capability level assessment, and conclusions. This study resulted in the value of capabilities in each process in IT risk management, the gap value, and recommendations for improvement that can be applied to SIMRS Ernaldi Bahar. The results of the measurement of the IT risk management capability of SIMRS Ernaldi Bahar in the EDM03 and DSS03 processes are at level 3, while the APO12 and DSS05 processes are at level 1. The gap values for the EDM03 and DSS03 processes is 1 level, while the gap values for the APO12 and DSS05 processes are 3 levels. Process improvement recommendations refer to COBIT 2019 best practices
Sentiment Analysis Using PSEUDO Nearest Neighbor and TF-IDF TEXT Vectorizer
Get PDFTwitter is one of the social media that is often used by researchers as an object of research to conduct sentiment analysis. Twitter is also a good indicator in influencing research, problems that often arise in research in the field of sentiment analysis are the many factors such as the use of colloquial or informal language and other factors that can affect sentiment results. To improve the results of sentiment classification, it is necessary to carry out a good information extraction process. One of the word weighting methods resulting from the information extraction process is the TF-IDF Vectorizer. This study examines the effect of the TF-IDF Vectorizer weighting results in sentiment analysis using the Pseudo Nearest Neighbor method. The results of the f-measure classification of sentiment using the TF-IDF Vectorizer at parameters k-2 = 89%, k-3 = 89%, k-4 = 71% and k-5 = 75% while without using the TF-IDF Vectorizer on the parameters k-2 = 90%, k-3 = 92%, k-4 = 84% and k-5 = 89%. From the results of the classification of sentiment analysis that does not use the TF-IDF Vectorizer, the f-measure value is slightly better than using it