Jurnal Riset Informatika

The Expert System for Diagnosing Respiratory Diseases for Cats

Fitria Adyati Mardha — 2024-03-11

Cats are the most common pet in Indonesia with a cat ownership rate of 47% (Rakuten Insight, 2021). Cat owners need to know and recognize the signs and symptoms of the diseases that often occur in cats, especially respiratory problems and diseases. Although vaccines in cats can significantly reduce the incidence of respiratory diseases, they do not eliminate infectious disease pathogens. During the COVID-19 pandemic, it was necessary to adjust health consultations that could reduce the transmission of COVID-19, which is the contactless method. In animal health, there is an online consultation through the WhatsApp platform between veterinarians and cat owners. Cat owners manually type every symptom experienced by the cat. However, there are several shortcomings in the online consultation, including that the symptoms described by the cat owner are unclear, so the diagnosis data is lacking and the consultation fee is quite expensive. Based on the problems that have been mentioned, the purpose of this study is to create an expert system for diagnosing respiratory diseases in cats using the Certainty Factor method. The result of this study is the availability of an expert system that can be used to diagnose respiratory diseases in cats.

Enhancing Financial Technology Operations: A Comprehensive Evaluation Using COBIT 2019 Framework

Sherly Sherly — 2024-03-11

This research aims to enhance information technology (IT) governance in a financial technology company by focusing on peer-to-peer lending services. The main challenges faced by the company involve a lack of system design details, leading to post-implementation imperfections and negative impacts on business process performance, including unnecessary delays and adjustments. The lack of transparency in system evaluation is also a hindrance caused by incomplete recording of test results. Therefore, this research aims to address these challenges by utilizing the COBIT 2019 framework. The study employs a qualitative approach, utilizing data obtained through interviews and literature studies supported by the COBIT Tool Kit. The analysis is conducted on three main objectives: security management, solution identification, and IT change management, to identify disparities between the current status and desired targets. The analysis results highlight the need for improvements in specific aspects, including the lack of system design details, more precise information in the change process, and deficiencies in recording test results. Recommendations for improvement involve the development of more detailed guidelines for system design, enhanced documentation of changes, and improvements in testing instructions and result reporting. Additionally, recommendations focus on enhancing capabilities through proactive evaluation, refining security plans, developing more adaptive solution acquisition strategies, and improving testing practices. Thus, this research underscores the importance of strategic improvements within the IT and Information Systems governance framework to shape a more effective and transparent operational environment in Financial Technology companies.

Phrase Detection's Impact on Sentiment Analysis of Public Opinion and online Media Toward Political Figures

Muhammad Irsa Nurodin — 2024-03-11

Public opinion of political figures and policy significantly impacts general elections. Sentiment analysis, as a method to comprehend opinion and emotion in texts, requires the step of text preprocessing to improve data quality. However, textual data often encounters irrelevant words and ambiguous language. These conditions can impact the accuracy of sentiment analysis. Given the significance of precisely interpreting public opinion toward political figures, these issues may result in biased or inaccurate sentiment analysis outcomes. Irregular punctuation or unclear language can disturb the text's intended context, compromising sentiment analysis quality. Additionally, irrelevant words can obscure the focus of the analysis, causing fundamental changes in the original text's meaning. This research focuses on the impact of a specific preprocessing technique, namely Phrase Detection with N-Gram, on sentiment analysis of political figures. By applying this method, the study aims to detail the effects of using Bigram, Trigram, and Unigram on the quality of sentiment analysis, particularly in the context of political figures on Twitter and online media articles. This research indicates that using Bigram in Phrase Detection provides more significant results than Trigram and Unigram for most political figures at Twitter, with the highest accuracy score of 88,23%. Sentiment analysis of articles in online media also indicates various results depending on the type of N-Gram. The results indicate that using N-gram phrase detection can influence the accuracy of sentiment analysis, and the resulting accuracy values are pretty high.

Application of Social Network Analysis for Comparison and Ranking of Internet Service Providers

Tedy Setiadi — 2024-03-11

In this digital era, the Internet has become a basic necessity in life. This has had a significant impact on the growth of internet service provider (ISP) companies in Indonesia. Comparison and ranking of ISPs is needed to make it easier for users to choose services according to their needs as well as to encourage healthy competition between ISPs in improving their services. The problem is ranking ISPs using conventional methods (surveys) to obtain primary data is expensive and takes a long time. On the other hand, Social Network Analysis (SNA) is a method that has been widely used to understand customer desires by extracting information from social media. This information is in the form of User Generated Content (UGC), namely track records left by customers on social media. This research aims to measure the ISP rankings of Indihome, Biznet and FirstMedia using UGC data. The research method used is to collect consumer tweet data rapidly, carry out preprocessing to eliminate irrelevant data and apply SNA, including network structure analysis in the form of visualization and network property analysis with the Gephi application, as well as network content analysis in the form of sentiment analysis and WordCloud analysis. The number of dominant network properties and sentiment analysis calculates ISP ranking. Apart from that, the results of this SNA are in the form of recommendations for ISPs to improve services to customers.

Application of Data Mining Using Methods K-Means Clustering for Clustering Baby Goods Rental Patterns (Case Study: Baby Kha House Store)

Roja' Putri Cintani — 2024-03-11

A baby item rental business is a practical option for parents who want to fulfill their baby's needs without buying them. Babykhahouse is one of the stores that offer rental services for various kinds of mother, baby, and child equipment. As the volume of data related to rental transactions increases, it is also increasingly difficult to know and understand the rental patterns found at the Babykhahouse store. This research aims to get a rental pattern that can later be a consideration for the store in determining promos and adding stock items. In handling these problems, data mining methods, especially clustering, are applied to group data and classify it based on certain groups. The clustering method used in this research is K-Means Clustering, which generates clusters to find similar rental patterns. In this study, 2 (two) types of clusters were formed, where, based on the 2 (two) clusters, it will be known which products have high and low rental rates. Based on the research, the results are 100 data in cluster 0, or the unsold cluster, and 64 in cluster 1, or the sold cluster. Products included in cluster 1 or in-demand clusters are products with a high level of sales.

Classification of Patient Satisfaction Level on Health Services Using the C4.5 Algorithm

Sriani — 2024-03-11

Quality health services are related to patient satisfaction. Patient satisfaction can be used as a benchmark for improving the quality of health services. Problems often occur when implementing health techniques, such as service problems at the Restu Clinic. Patients and their families indicated that although the Restu Clinic was established with adequate facilities, it had not yet reached the maximum level of service. These indications include long waiting times for examinations, a lack of thoroughness by medical personnel, and services that are not timely. Service quality cannot be separated from the dimensions that are the core of quality services, which are expected to meet patient needs. Patient satisfaction is considered an important indicator of good quality. This research will only discuss four aspects of service quality, which are reliability, responsiveness, assurance, and empathy, from health workers at the Restu Clinic. The C4.5 algorithm is known to be superior in producing decision trees that efficiently solve discrete and numerical variables and provide satisfactory accuracy. Therefore, the author conducted a study to assess service quality using the C4.5 algorithm. This research aims to determine the factors that influence the quality of health services and to know patient satisfaction with health services at the Restu Clinic. Knowing the intensity of patient satisfaction with services at the Restu Clinic can improve the quality of optimal services and gain patients' trust in government agencies.

Simulation of Small-Scale Solar Power Generation System in The Central Java Region: A Case Study of the Cilacap Area

Vincentius Rayza Lee — 2024-03-11

The limitations of conventional non-renewable energy resources raise concerns about sustainability and energy supply security in the future. One of the worrying factors is the carbon dioxide emissions that can affect living organisms' health. Renewable energy sources, such as solar, wind, and hydropower, emerge as solutions capable of minimizing environmental impacts and reducing dependence on limited resources. Therefore, this research will simulate and design a small-scale renewable energy power generation system, particularly solar energy, in the Cilacap region, Central Java. The main components involved in this research include PV arrays, IGBT diodes, and universal bridges, supported by supporting elements such as displays, scopes, resistors, capacitors, inductors, and bus selectors. The technical data used as input are specific to the area. The simulation results show that the direct power generated by one modelled PV array is 221.7 W per hour. This research contributes to optimising small-scale solar power generation systems in the designated area, considering relevant components and parameters to enhance efficiency and sustainability.

Decision Support System for Outstanding Students’ Selection Using TOPSIS

Irma Suryani — 2024-03-11

In the school environment, determining outstanding students holds significant importance. High academic achievement among students and a low failure rate reflect the overall quality of education. Based on the interviews, it is known that the assessment process for outstanding students at school still needs to be revised, and the current decision-making system needs to consider other factors, resulting in suboptimal selection processes. To address this issue, implementing a Decision Support System (DSS) is necessary to assist the school in selecting the best students. DSS is an interactive system providing access to data and modelling information, designed to support decision-making in both structured and unstructured situations. This DSS will be designed using the Technique for Order of Preferences by Similarity to an Ideal Solution (TOPSIS) as the alternative ranking method. The final results indicate that using the TOPSIS method in this decision support system can improve efficiency and accuracy in selecting outstanding students in the school environment.

Hybrid Neural Network Approach for Tea Leaf Disease Detection Using Pelican and Mayfly Optimization Algorithms

Saja Bilal Hafedh Al-Karawi — 2024-03-11

This study addresses the problem of plant diseases and the difficulty of detecting them, and it presents a unique technique for the automatic detection of tea leaf diseases by combining neural networks and optimization techniques. Our research uses a curated database of tea plant leaf photographs that includes healthy and diseased specimens. The neural network (CNN) is trained and fine-tuned using optimization algorithms. To increase disease identification accuracy, we used a hybrid novel optimization algorithm called (POA-MA) which is Pelican Optimization Algorithm (POA), and Mayfly Optimization Algorithm (MA) for feature selection, followed by classification with Support Vector Machine (SVM). The suggested mechanism performance is evaluated using accuracy, MSE, F-score, recall, and sensitivity measures. The suggested CNN-POAMA hybrid model yielded 94.5%, 0.035, 0.91, 0.93, and 0.92, respectively. This study advances precision agriculture by establishing a strong framework for automated detection, allowing for early intervention, and eventually enhancing tea crop health.