IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Not a member yet
480 research outputs found
Sort by
Analysis User Satisfaction of XYZ Application with End User Computing Satisfaction Method and Delone and Mclean
Full text linkRapidly developing technology has made internet service providers such as XYZ provide an application which promises convenience for its consumers to make transactions to purchase credit, internet quota, and other services. this application is one of the fairly well-known providers and is currently competing with other providers. this provider targets young people because in terms of its products which are quite competitive with a wide reach and prices that are quite cheap for young people. Of course, customers will feel the convenience of transacting using the official service application. The convenience offered can make business processes more efficient and can be used to improve the quality of their services.This study uses the End User Computing Satisfaction model method and the Delone and Mclean model with 9 research variables (content, accuracy, format, ease of use, timeliness, system quality, information quality, and service quality, and security), The purpose of this study is to assess the effectiveness of the application..Out of the nine variables included in the research results, only two Service Quality and Accuracy have a statistically significant impact. The model provided in this study has a Rsquared score of 0.792, indicating a strong level of customer satisfaction
Multivariat Predict Sales Data Using the Recurrent Neural Network (RNN) Method
Full text linkSales is an activity or business selling a product or service. In this study, I took a case study on Kaggle. Sales problems at the company cause inventory to be very high or vice versa, causing a loss of sales because there are no items to sell. Inventory that is too high results in increased costs due to existing resources being inefficient. In the opposite condition, it will cause a product vacancy in the market. Using the Recurrent Neural Network (RNN) Algorithm, this study predicts sales. The data used is sales data in 2020 with the parameter Number of sales per day in the last four months. The results obtained through testing several training scenarios and testing the implementation of the algorithm, in this case, is the highest accuracy value of 96.92% in the network architecture of three input neuron layers, three hidden layer neurons, one output, division of training, and test data 70: 30, learning value rate of 0.9 and a maximum of 9000000 epoch
Developments and Trends in Indonesian Tourism Technology Using Bibliometric Analysis
Full text linkInformation technology has changed society, services, and the tourism sector has attracted many research and publications. Even though previous research aims to show an understanding of tourism technology factors, there is still little to discuss the technology factors of Indonesian tourism. Discussing scientific publications about tourism technology in Indonesia can provide a deeper understanding of the development of information technology in the Indonesian tourism sector by providing solutions. This research aims to analyze developments and trends in tourism technology factors in Indonesia from 2014 to 2023 with bibliometric analysis from R Studio and using 113 Scopus indexed articles. The methodology includes planning, keyword identification, Scopus data searches, bibliometrics, developments and trends in Indonesian tourism technology. The results of this research show an increase in publications from year to year, in annual citations there are fluctuations, the number of articles published varies with the position of Sustainability (Switzerland) being ranked first with 25 published articles, Indonesia is the country that publishes the most articles and the frequency has increasing, Indonesia has also become a top keyword, and in tourism technology trends there are two clusters within the basic themes, namely tourism and West Java, which are the direction for further researc
Modeling OTP Delivery Notification Status through a Causality Bayesian Network
No full textDigital money is the fundamental driving factor behind today's modern economy. Credit/debit cards, e-wallets, and other contactless payment options are widely available nowadays. This also raises the security risk associated with passwords in online transactions. One-time passwords (OTPs) are another option for mitigating this. A one-time password (OTP) serves as an additional password authentication or validation technique for each user authentication session. Failures in transmitting OTP passwords through SMS can arise owing to operator network faults or technological concerns.To minimize the risk value that arises in online transactions, it is necessary to evaluate the causality of the OTP SMS sending transaction status category by determining the main factors for successful OTP SMS sending and identifying the causes of failure when sending OTP SMS using the Bayesian Network method. According to data analysis, online transactions occur more frequently in the morning, with status summaries such as no delay, unknown status, and others. Furthermore, there is causality with at least three variables in the principal status summary, including no delay, uncertain summary, long delay, normal, likely operator issues, abnormal, and more. With a high accuracy rate of around 90% in forecasting the likelihood of recurrence
Rule-Based Natural Language Processing in Volcanic Ash Data Searching System
Full text linkIndonesia is a country with a unique geography. The confluence of three tectonic plates located in the country results in frequent natural disasters, from earthquakes to volcanic activity. BMKG is a monitoring agency tasked with providing information related to these natural disasters. However, one type of natural disaster data, the SIGMET data (Significant Meteorological Information) used to provide information on volcanic ash, has a complicated format that is difficult for ordinary people to understand. Therefore, this research seeks to make finding information related to volcanic ash and volcanic eruptions in Indonesia easier in terms of access and comprehension. In this research, an application design will be carried out that can search SIGMET data by implementing natural language processing with a production rule base. The research results have an accuracy rate of 84% using 25 test sample sentences that combine sentences and words contained in the important words section
A Mamdani FIS to Monitor Programmer Performance on GitHub
Full text linkA collaborative activity used to accomplish shared objectives is teamwork. It is essential to know how unequal contributions can inhibit team members' chances to give their all in achieving these objectives. It will be necessary to manage resources in this joint approach. Monitoring each team member’s performance in one technique to do this. In previous research, performance measurement was designed using Prometer with several parameters, utilizing the crisp set at each stage. This study developed the method by adding variables and utilizing fuzzy logic, which can consider the membership value for each value involved. The membership value considered for each variable is expected to provide a significant assessment of each team working on developing software projects using the GitHub platform. The results will be monitored based on the involvement of each collaborator in project work through the data recorded in the pull requests, issues, commits, additions code, and deletion code variables. The results obtained by utilizing the variables and several rules that have been designed with the Mamdani implication function are then compared with the observations obtained by the Project Manager so that an accuracy value of 86.67% is accepted for the use of inclusive and exclusive rules (operand AND)
Gaussian Blur Filter Effect Analysis on Facial Detection Accuracy Using Viola Jones Method
Full text linkHuman face detection is one of the most studied topics in computer vision. The purpose of facial detection is to find out whether or not a face is present in an image. Blur can be caused by many things, such as motion that occurs when the camera takes a picture or the use of a camera that is not focused when taking a picture. For facial recognition, blur becomes difficult to get information about an object, get a description about it, or identify a face in the image. The more blur a picture, the more difficult it is to identify it. This research applies the Viola-Jones relative method for facial detection with a high degree of accuracy and fast computation. This study analyzed the influence of a gaussian blur filter by calculating how much radius an object has been given a gausian blur filter so that it can no longer be identified as an object, and also looking for the minimum PSNR value that is still acceptable in the object detection process. The minimum PSNR value for the image is 16.6 dB, and the minimum PSR value before the face can no longer be detected is 17.84 dB
Digital Transformation Through E-Master Application in Human Resource Development in Civil Servants
Full text linkThe use of technology has become a crucial aspect in the progress and development of Human Resources (HR). HR management includes various aspects such as planning, organizing, compensation, and maintaining work relationships to achieve individual, organizational, and societal goals. Research in education has a significant impact on youth empowerment, a critical stage in human development. This study aims to describe motivation, personality, and skills in HR Development Management at the East Java Provincial Education Office Branch. Using a qualitative approach, this research understands HR development in depth through the "e-Master" application. The informants consisted of e-master application managers, personnel managers, and e-master application users. Data was collected through semi-structured interviews, primary documentation from direct observation, and non-participant observation. Data analysis was carried out using techniques of reduction, presentation, and drawing conclusions, with the validity of the data strengthened through triangulation of techniques and sources. It is hoped that the research results can improve the quality of human resources at the educational level, bringing a positive impact in empowering the workforce in education for a better future
Effect of Hyperparameter Tuning Using Random Search on Tree-Based Classification Algorithm for Software Defect Prediction
Full text linkThe field of information technology requires software, which has significant issues. Quality and reliability improvement needs damage prediction. Tree-based algorithms like Random Forest, Deep Forest, and Decision Tree offer potential in this domain. However, proper hyperparameter configuration is crucial for optimal outcomes. This study demonstrates the use of Random Search Hyperparameter Setting Technique to predict software defects, improving damage estimation accuracy. Using ReLink datasets, we found effective algorithm parameters for predicting software damage. Decision Tree, Random Forest, and Deep Forest achieved an average AUC of 0.73 with Random Search. Random Search outperformed other tree-based algorithms. The main contribution is the innovative Random Search hyperparameter tuning, particularly for Random Forest. Random Search has distinct advantages over other tree-based algorithm
An Electrocardiogram Signal Preprocessing Strategy in the LSTM Algorithm for Biometric Recognition
No full textElectrocardiogram (ECG) signals are a very important tool for clinical diagnosis and can be used as a new biometric modality. The aim of this research is to determine the results of ECG signal processing using RNN methods such as the Long Short Term Memory (LSTM) algorithm by utilizing several preprocessing techniques. In this study, the ECG signal itself was previously tested by carrying out the LSTM classification process without preprocessing, and the results obtained were 0% accurate, so preprocessing was needed. The preprocessing methods tested with the LSTM classification method are Adjacent Segmentation and R Peak Segmentation to find out which preprocessing techniques greatly influence LSTM classification accuracy. The experimental results were that LSTM classification with R Peak Segmentation preprocessing obtained the highest accuracy on the two data used, namely filtered and raw data, with 80.7% and 78.95%, respectively. Meanwhile, the accuracy obtained from LSTM classification when using Adjacent Segmentation preprocessing is not good. This research compares LSTM accuracy from each preprocessing stage to determine which combination has the best results in the ECG data classification process. This research also offers new insights into the preprocessing stages that can be carried out on ECG data