Jurnal Sistem Informasi dan Informatika (Simika)

EVALUASI KUALITAS FITUR LAYANAN APLIKASI CUSTOMER INFORMATION SYSTEM (CIS) PDAM SURYA SEMBADA KOTA SURABAYA MENGGUNAKAN METODE E-SERVQUAL

Adelia Desi Agnesita — 2024-12-31

PDAM Surya Sembada Surabaya has developed the Customer Information System (CIS) application since 2013 to facilitate bill payment transactions and complaints about water problems and so on. Despite more than 100,000 downloads, some users complained about the service, including problems recording water meters and failures when registering. Therefore, it is necessary to evaluate the quality of service on the CIS PDAM Surya Sembada Kota Surabaya application using E-Service Quality (E-Servqual) to measure the level of user satisfaction. This method is a measurement dimension to determine service quality which focuses more on electronic services. E-Servqual generally provides how well a company is able to meet customer needs through the use of electronic facilities. This evaluation is needed to find areas of improvement to increase user satisfaction. The aim of this research is to identify factors that influence user satisfaction of CIS PDAM Surya Sembada Surabaya City and provide recommendations for service improvements. This research uses quantitative methods by collecting data through surveys and applying purposive sampling techniques based on primary data obtained through questionnaires given to respondents. -From the analysis it was found that the dimensions of efficiency, system availability, compliance, privacy, responsiveness and compensation did not have a positive and significant impact on user satisfaction. However, the contact dimension has a patch coefficient value of 0.764, a t-statistic value of 9.714 (>1.98) and a p-value of 0.000 (<0.05) indicating that the contact variable has a positive and significant effect on user satisfaction. The ability to contact PDAM service centers via the CIS application has a positive and significant impact, demonstrating the importance of easy and effective access to customer service to increase user satisfaction.

PERBANDINGAN METODE NAÏVE BAYES DAN SVM UNTUK SENTIMEN ANALISIS MASYARAKAT TERHADAP SERANGAN RANSOMWARE PADA DATA KIP-K

Nabil Safiq Ramadan — 2024-12-31

This research examines ransomware attacks on KIP-K data by analyzing the opinions of Social Media X users, using the naïve bayes classifier (NBC) and support vector machine (SVM) methods. The rapid development of technology not only brings great benefits but also increases the risk of digital attacks by certain parties. One example is a ransomware attack that caused a KIP-K data leak. In this study, sentiment analysis was applied to identify public opinions or responses obtained from Social Media X, with the help of python programming and google colab. Of the total 2,648 raw data collected, pre-processing was carried out resulting in 1,738 cleaned data. The study compared two methods, namely Naïve Bayes and Support Vector Machine, to determine what method is more effective in analyzing public sentiment related to ransomware attacks on KIP-K data. The focus of this study is to understand the percentage of Social Media X users' comments and responses related to the KIP-K ransomware taken from media sosial X. The stages of sentiment analysis in this study include crawling, labeling, preprocessing, method classification, and visualization. Before the classification process was carried out, the data was divided into two parts, namely 30% for test data and 70% for training data. Data labeling resulted in 1,313 negative data, 957 positive data and 377 neutral data. The classification results show that the NBC method has an accuracy of 70%, while the SVsM achieves an accuracy of 88%. Based on these results, SVM is proven to be superior in data analysis compared to NBC, especially for big data.

ANALISIS SENTIMEN MASYARAKAT TERHADAP KASUS JUDI ONLINE MENGGUNAKAN DATA DARI MEDIA SOSIAL X PENDEKATAN NAIVE BAYES DAN SVM

M Febrian As Shidiq — 2025-01-03

Research conducted by analyzing public sentiment related to online gambling cases using datasets from x social media using the naïve bayes method approach and support vector machine (SVM). The analysis phase starts with data gathering or crawling, followed by data labeling, data preprocessing, and ultimately method categorization. The dataset comprises 2,866 tweets, with 1,436 classified as positive (50.12%) and 1,429 as negative (49.88%). The data before to the classification process is partitioned into training data and testing data, including 70% training data and 30% testing data. The analysis with the SVM approach yielded a classification accuracy of 83%, whereas the naïve Bayes method achieved just 79%. Upon completion of the method classification process, the subsequent phase involves visualization and assessment. During the visualization step, bar plots, word clouds, and word frequencies derived from sentiment analysis calculations are shown, alongside a visualization of words from the dataset. The investigation indicates that the SVM approach outperforms Naive Bayes in sentiment classification. The benefit of SVM resides in its capability to manage data with elevated limits and accuracy, enhancing its efficiency in discerning positive and negative thoughts. The findings of this study demonstrate that SVM is better appropriate for data exhibiting complicated distributions, whereas the Naive Bayes approach yields suboptimal results. Thus, SVM can be proposed as a more appropriate and reliable approach for similar sentiment analysis in the future.

PENGARUH KOMPOSISI SPLIT DATA PADA AKURASI KLASIFIKASI PENDERITA DIABETES MENGGUNAKAN ALGORITMA MACHINE LEARNING

Febby Refindha Aftha Harianto — 2025-01-07

The increasing number of people with diabetes is an international health problem. To prevent diabetic complications, early diagnosis and accurate classification are essential. This study looks at how the composition of split data affects the classification performance of diabetics with machine learning algorithms such as Random Forest, Naive Bayes, and Support Vector Machine (SVM). The research data is taken from Bojonegoro Regency Hospital, which consists of 128 samples that have 10 main features. To ensure the data is ready for use, the research method goes through a preprocessing stage. Next, the data was divided into training and testing data with a ratio of 90:10, 80:20, 70:30, 60:40, and 50:50 respectively. Using confusion matrix, the algorithm is assessed for accuracy, precision, recall, and F1 score. In this study we focus on the accuracy values obtained and the results show that the proportion of data sharing affects the performance of the algorithm. Random Forest achieved 100% accuracy in some scenarios. This algorithm also proved to be the most effective in the classification of diabetics. In conclusion, algorithm selection and data split composition are very important for model performance optimization. These results are important for the development of more accurate and efficient Machine Learning-based diagnosis systems. Further research can consider larger datasets and additional algorithms for better results.

PENGEMBANGAN ALUMNI RELATION MANAGEMENT FTI UKDW BERBASIS WEBSITE SEBAGAI MEDIA MEMPERERAT RELASI DENGAN ALUMNI

Ivan Pradipta Gunawan — 2025-01-13

Universities face the challenge of a lack of alumni engagement, with many losing contact after graduation. This results in difficulties in leveraging alumni potential. Insufficient communication leads alumni to feel that their relationship with the university is limited to their time as students. The low response rate to Tracer Studies, which track alumni careers and gather feedback, highlights this issue. Data from various universities indicate low response rates, primarily due to weak relationships and alumni's lack of awareness about the importance of Tracer Studies. Therefore, the development of an Alumni Relation Management system is necessary. The development of a web-based Alumni Relation system used the prototyping method. Evaluation was conducted using Heuristic Evaluation with experts, followed by system implementation through email campaigns to enhance alumni-university engagement. These steps aim to address alumni engagement issues and improve Tracer Study response rates. System testing was performed using black box testing and usability testing. The results indicated that the system functions well in both functional and non-functional aspects. Based on these findings, the system is ready for use and is expected to enhance alumni engagement and the effectiveness of Tracer Studies.

ESTIMASI LAJU PERTUMBUHAN PENDUDUK DI KABUPATEN JEPARA DENGAN PENDEKATAN REGRESI LINIER BERGANDA

Hetta Rachma — 2025-01-16

One of the main factors in planning the development of a region is the change in population. A rapid population growth rate can have adverse effects, such as poverty, unemployment, and a decrease in the quality of human resources. The purpose of this study is to predict the population growth rate in Jepara Regency by applying the multiple linear regression method, which can be used as a basis for the government in planning strategies to improve the economy, infrastructure, and other sectors, so that in the end it can have an impact on improving the welfare and quality of life of the community. The data used was obtained from BPS Jepara Regency for the period 2019-2023. Multiple linear regression analysis was applied as the method, with the number of males (X1) and females (X2) as independent variables, and the total population (Y) as the dependent variable. Based on the analysis, the predicted population in 2024 is 1,264,598 people, the same number as in 2023, indicating a stagnant growth condition. The results of this study provide important implications for government policy planning, especially in infrastructure development strategies, economic improvement, and human resource processing. The multiple linear regression method is effective in providing an accurate estimation picture, and can be the basis for future decision-making.

KOMPARASI ALGORITMA DECISION TREE DAN SUPPORT VECTOR MACHINE (SVM) DALAM KLASIFIKASI SERANGAN JANTUNG

Elok Fathiyatul Laili — 2025-01-16

The heart is one of the most important organs in the human body. According to the WHO, heart attacks are the most common cause of sudden death worldwide, with more than 17.8 million people dying from heart attacks. A heart attack occurs when blood flow to the coronary arteries stops, depriving the heart muscle of oxygen, and causing a heart attack. Detecting a heart attack is very difficult due to the various symptoms. The purpose of this research is to compare the performance of the accuracy values of two algorithms, namely Decision Tree and Support Vector Machine (SVM) in classifying heart attacks. The results of this study show that the Decision Tree algorithm achieves the highest accuracy results compared to the SVM algorithm. The accuracy of the Decision Tree algorithm using a 60:40 ratio data splitting is 98.11% with a negative precision of 98.01% and positive of 98.17% and a negative recall of 97.04% and positive of 98.77%. Meanwhile, the SVM algorithm using data splitting with the same ratio produces an accuracy value of 92.80% with a negative precision of 90.24% and a positive of 94.43% and a negative recall of 91.13% and a positive of 93.85%.

DEVELOPMENT OF ACADEMIC ADMINISTRATION AND STUDENT SERVICES SYSTEM AT THE FACULTY OF ENGINEERING AND MARITIME TECHNOLOGY, RAJA ALI HAJI MARITIME UNIVERSITY

Berta Erwin SLAM — 2025-01-17

The Administrative Information System is a system developed to enhance the efficiency of administrative management, involving student graduation reporting and visit letter processing. The development of the information system utilizes the Waterfall method through stages of planning, requirements analysis, design, development, and testing. The development process begins with identifying administrative issues, followed by collecting user requirements data through interviews and observations. The results of this stage are then translated into a system design that includes system architecture, interface design, and database structure. This system is expected to provide benefits, particularly in accelerating administrative processes, facilitating archiving, improving data accuracy, and delivering information more quickly and in a structured manner. The designed system not only supports the operational activities of the faculty in managing administration but is also expected to serve as a reference for the development of similar systems in other educational institutions.

IMPLEMENTASI METODE SMOTE DAN RANDOM OVER-SAMPLING PADA ALGORITMA MACHINE LEARNING UNTUK PREDIKSI CUSTOMER CHURN DI SEKTOR PERBANKAN

Fannisa Salsabila Pratiwi — 2025-01-18

The ability to anticipate unsubscribed customers is a challenge in the competitive banking industry, where it is more efficient to retain customers than to attract new ones. The purpose of this study is to improve the effectiveness of churn prediction by overcoming data imbalances using SMOTE (Synthetic Minority Oversampling Technique) and Random Over-sampling. The data set used consists of 10. 000 bank customer data, with 12 important attributes, including churn indicators as targets. The machine learning algorithms used are Random Forest and Neive Bayes, evaluated based on accuracy, precision, recall, and F1 scores. The results of the experiment showed that the highest accuracy of 87.13% could be achieved with the Random Forest algorithm without using the oversampling method, but its effectiveness in detecting churn customers was slightly limited. The use of SMOTE and Random Over-sampling methods has improved the model's performance in identifying churn patterns, although it has led to a decrease in accuracy to 86.20% for Random Over-sampling and 81.47% for SMOTE. Nevertheless, the Neive Bayes algorithm showed the best accuracy rate of 79.20% without oversampling, although it was still slightly lacking in optimal churn handling. The study underscores the importance of using oversampling methods to improve prediction balance in minority classes, which is often overlooked in conventional models. It is hoped that the results of this research can be used as a guide in improving strategies to maintain customer trust that are more up-to-date and efficient.

PENGELOMPOKAN TRANSAKSI KARTU DEBIT PERBANKAN MENGGUNAKAN ALGORITMA K-MEANS

Iwan Irawan — 2025-01-19

One of bank customers' most widely used non-cash payment methods is making payments to merchants using debit cards. The data generated from these transactions can be utilized effectively by banks. This study analyzes customer spending habits through debit card transactions, employing a data mining technique called K-means clustering. By identifying patterns in customer transactions, the research aims to assist business units in developing targeted product strategies. The analysis determined that four clusters were optimal, resulting in a tightly grouped dataset with an average distance of 5.764 from the respective cluster centers. Grouping nominal transactions based on the date and time of the transaction can provide valuable insights for bank management when considering customer fund allocation.

PERANCANGAN ENTERPRISE ARCHITECTURE MENGGUNAKAN FRAMEWORK TOGAF ADM PADA DINAS KOPERASI DAN UKM KOTA PEKANBARU

Susilawati Susilawati — 2025-01-19

The advancement of information technology and information systems has a significant impact on various organizations, both in the private and government sectors. This study aims to design an enterprise architecture using the TOGAF ADM framework in the training process in the SME sector at the Cooperatives and SMEs Service. This process was chosen because it is still done manually, resulting in obstacles such as slow data management, lack of transparency, and minimal integration between work units. The study used a qualitative approach with a case study method. Data were obtained through observation, interviews, and document analysis, which were then analyzed using the TOGAF ADM stages, including the Preliminary, Architecture Vision, and Business Architecture phases. The results of the study show that the proposed architectural design can overcome the constraints of the manual training process by presenting an integrated digital solution. This solution can accelerate the training management process, increase transparency, and strengthen coordination between work units.

APLIKASI MONITORING PEMBELAJARAN IQRO’ PADA SANTRI TK QUR’AN ASSYUKURIAH BERBASIS WEB DAN ANDROID

Tifani Intan Solihati — 2025-01-20

This study explores the design and development of applications to monitor student learning at TKQ Assyukuriyah. This research was conducted to increase the efficiency and effectiveness of the teaching and learning process, which was previously carried out conventionally and faced several obstacles, including loss or damage to books, and the ineffectiveness of providing learning progress reports from schools to parents. The formulation of the research problem is how the application provides access to questions for students and makes it easy to record reports on the results of evaluations of learning progress using the iqro' and juz amma methods with safe data storage and how parents obtain information on learning progress. This research aims to provide easy access to questions for students, teachers record the results of evaluations of learning progress in reading using the iqro and juz'amma methods with secure data storage and make it easier for parents to obtain information on learning progress. Using the waterfall method for software development. The results of this research show that this application has succeeded in simplifying the process of recording monitoring of students' learning progress by storing data safely, reducing the time and energy of teachers in preparing questions, and making it easier to provide information on learning progress to parents.

Keywords: Monitoring, Kindergarten-Qur'an, Learning, School, Waterfall.word

PENINGKATAN AKSESIBILITAS DATA DENGAN MENERAPKAN GEO-REPLICATION DATABASE

Indra Warman — 2025-01-21

Database replication is a critical technology that needs to be implemented to improve database performance for applications that require fast data access and high reliability with many users. Very large data query process requests by applications impact decreasing database server performance because many applications use only one database resource. One solution to this is replication, placing the database server and several replications in different locations, which allows database performance to be maximized. This requires a study of research related to replication strategies, especially the implementation of multi-location database geo-replication mechanisms, which aim to ensure the availability of services and replication processes run well and that consistency between database servers can be achieved. The increasing number of replicated databases with different geographic locations will make data access load requests from applications can be directed to several replication servers and reduce the delay time to user responses (low latency). This research implemented a geo-replication database for three database servers on the Ubuntu 22.04.4 LTS Virtual Private Server located in Singapore, West Jakarta, and South Jakarta, using the MariaDB database version 10.6.18. To measure the replication results related to time, consistency, and accessibility, a database replication query processing time test was carried out using queries with data from 250 to 150,000 records. The test results from the consistency side can be seen from the same number of data records on the master and slave replication databases, and from the accessibility side, data query requests can be served from three database server locations.

PENGEMBANGAN PROTOTIPE NAVIGASI AUGMENTED REALITY DENGAN FITUR PENGENALAN SUARA MENGGUNAKAN GDLC STUDI KASUS: DI LINGKUNGAN PENDIDIKAN

Khadijah Khadijah — 2025-01-23

The rapid evolution of digital technology is transforming educational practices, enhancing accessibility and interactivity through innovations like augmented reality (AR) and artificial intelligence (AI). This study aims to develop the PDBI Tour application, an AR-based navigation tool integrated with speech recognition, to improve campus accessibility for new students and promote Politeknik Digital Boash Indonesia, a vocational education in Bogor Regency. A Game Development Life Cycle (GDLC) methodology was adopted, comprising initiation, pre-production, production, testing, beta, and release phases. Data were collected through interviews with promotional teams and prospective students, and prototype design was created using Figma, while Unity was used for production with AR Foundation and Whisper API. Functional testing (black box) confirmed reliable navigation features, and usability testing yielded a 65% satisfaction rate from 25 respondents representation of students in PDBI aged 18-20 years who had tried the prototype, highlighting effectiveness in usability, playability, and accessibility. These findings indicate that the PDBI Tour application prototype meets user needs and offers potential as an immersive navigation and promotional tool. This research demonstrates the GDLC approach’s efficacy in enhancing application development through iterative improvements, validating AR navigation as a powerful tool for interactive and accessible campus experiences.

APLIKASI RENTAL MOBIL TRAVEL BERBASIS ONLINE PADA NUSA TRIP TRAVEL

Mochamad Yusuf Romdoni — 2025-01-24

The aim of this research is to build an online travel application at PT. Nusa Trip Travel, which is intended for tourism and travel bureau companies to serve travel customer requests and can provide travel and tourism information. The presence of this application will be very helpful in serving every ticket ordering transaction carried out by customers wherever they are without having to go to a service bureau. This travel application will be built on an online basis where customers can see information on departure schedules, travel departure routes, rates and payments. The payment system implemented with this application requires customers to carry out a transfer process according to the total bill via a bank account. Payment will be declared successful by the admin if the payment matches the cost of the travel booking. The financial reports received will be detailed and clear with the aim of making each report easier so that all work will be easier to complete, especially in serving travel consumers, monitoring travel and other administration. This application was developed using the PHP programming language, the Codeigniter framework, which has been tested in web-based software development. Meanwhile, the system flow design here uses Unified Modeling Language (UML). This research uses a waterfall method approach in developing the system and the results of this research are expected to be able to help companies serve each customer more quickly, effectively and efficiently.

PEMBUATAN SISTEM PEMANTAUAN PH DAN PPM AIR PADA HIDROPONIK BERBASIS IoT

Agus Hermanto — 2025-01-27

The reduction in agricultural land due to being converted into housing and urban areas means that the amount of food production is decreasing. Based on the problems above, the author offers an innovation to overcome the problem of food security through "Smart Farming". This innovation can be implemented by the community using the concept of integrated agriculture with fisheries which is easy to apply on minimal land which has not been utilized properly. However, currently There is currently no system that can monitor the pH and PPM levels of water automatically and easily. This has an impact on the poor quality of hydroponic plant production so that it cannot be sold to consumers and causes losses for this business Internet of Things (IoT) and website, this smart farming innovation was developed as a system for monitoring the condition of pH and PPM levels of water in hydroponic planting media. The development of a website-based pH and PPM monitoring system offers an innovative approach in utilizing technology to overcome the challenges of monitoring water quality effectively. By utilizing the advantages of information technology and the internet, this system can become an important solution in supporting efforts to protect the environment and sustain water resources in the future.

PENERAPAN METODE FORWARD CHAINING PADA SISTEM PAKAR UNTUK MENGATASI REJECT PAINTING SPARE PART OTOMOTIF DI PT ASTRA OTOPARTS TBK

Denny Riandhita Arief Permana — 2025-01-31

PT Astra Otoparts Tbk Divisi Nusametal is a company operating in the automotive industry. This company produces four-wheeled vehicle components, two-wheeled vehicle parts, and other automotive components made from aluminum materials. In the painting process, there is a quality inspection of the products divided into FG (Finish Good) and NG (Not Good) products. The use of technology can be very helpful in quality control, especially in the painting process. In the painting process, rejects often occur on automotive components. Each reject has different symptoms and causes, so the solution to address each reject is also different. Knowledge about solutions to address rejections is only possessed by the engineering team on the second shift, so handling can be delayed by 1 day and the painting process will be halted. The variables used are 13 symptoms and 51 causes. In this study, the use of the Forward Chaining method in the expert system can analyze reject symptoms and reject causes, allowing operators to identify the type of reject and fix the reject results without having to wait for engineering in the second shift. This way, repairs can be done in just 30-60 minutes, and operators can independently resolve 80% of painting reject issues while the painting process continues.

RANCANG BANGUN APLIKASI SIDUMA (SISTEM INFORMASI PENGADUAN MAHASISWA) DI UNIVERSITAS BANTEN JAYA

Yul Hendra — 2025-01-31

In today’s highly competitive educational landscape, universities must focus on enhancing the quality of services they provide to their students. To effectively understand the needs and desires of students, institutions must actively seek their feedback. However, a common challenge faced at Banten Jaya University is that students often hesitate to share their input regarding service processes. This reluctance stems from the absence of a systematic platform for lodging complaints or feedback.To address this issue. necessity of developing a robust system that can efficiently gather and present student complaints and suggestions. The goal is to deliver quick and accurate reporting that can be utilized by the campus management for evaluation and improvement purposes. The research employs the Agile Method for system development, complemented by data collection techniques such as interviews and direct observations.With the introduction of the Student Complaint System, known as SIDUMA, it is anticipated that all student complaints and reports will be systematically captured. The insights derived from these submissions will enable Banten Jaya University to conduct ongoing evaluations, ultimately striving for excellence in service quality.

IMPLEMENTASI METODE DESIGN THINKING DAN SYSTEM USABILITY SCALE PADA USER EXPERIENCE APLIKASI BELAJAR BAHASA INGGRIS TALKTALES MELALUI CERITA RAKYAT

Muhammad Nabhan Rifa’i — 2025-02-09

Indonesia faces significant challenges in improving English proficiency among its population. According to the EF Education First English Proficiency Index 2023, Indonesia ranks 79th out of 113 countries. On the other hand, the current generation begins to forget cultural elements such as folklore or myths that have been passed down from the nation's ancestors. This study aims to design an English learning application for children and teenagers using the design thinking method. The stages of design thinking that are used are empathize, define, ideate, prototyping, and testing. In the prototyping stage, low-fidelity and high-fidelity prototypes were created to visualize the application's design and functionality. Testing was conducted by using task scenarios and the System Usability Scale (SUS). The task scenario testing results revealed that the effectiveness and efficiency rate of 85.71%, indicated that most tasks could be completed successfully by users. The SUS testing results showed an average score of 86.5%, indicated that the application has a high level of usability and well-received by users. Thus, the application's interface is considered easy to use and effective in supporting the English learning process for the target users. This research provides a positive contribution to the development of educational applications using a design thinking approach.

SISTEM PENDETEKSI KESEHATAN MENTAL REMAJA MENGGUNAKAN METODE FORWARD CHAINING DAN NAIVE BAYES

Ida Ayu Gde Suwiprabayanti Putra — 2025-02-10

A very important first step in helping people with mental health disorders get medical care is detection. Mental health problems and drug abuse can be detected with a tool called SDQ (for adolescents aged 10 to 17 years). The twenty-five statements in the SDQ fall into five measurable behavioral categories: (1) emotional symptoms (5 statements), (2) behavioral problems (5 statements), (3) hyperactivity (5 statements), (4) friendship problems (5 statements), and (5) prosocial behavior (5 statements). By using SDQ, this research will create an expert system, a computer-based application, to detect adolescent mental health. Expert systems can be used to solve problems in ways thought by experts. This research will build a web-based expert system that uses the PHP programming language. System and accuracy testing will be carried out using black box testing and accuracy value testing to find out whether the symptoms and diagnosis results are appropriate. The research results in the form of a prototype will be available online so that teenagers can check their mental health freely.