JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Handling Imbalanced Data for Acute Coronary Syndrome Classification Based on Ensemble and K-Means SMOTE Method
Get PDFAcute Coronary Syndrome (ACS) is a disease that has a high mortality rate with a mortality percentage of 40% after 5 years from diagnosis. Despite the high mortality rate, the conventional process of overestimating ACS can be life-threatening. For this reason, several alternatives for prediagnosis have been investigated to reduce the detection of ACS intensively, one of which is by using a machine learning approach. The machine learning-based prediagnosis approach utilizes patient medical record data as input for making detection models. This approach can produce an optimal model when there is quite a lot of data and the labels have a fairly balanced comparison. However, in machine learning-based ACS detection studies, researchers often do not have balanced data between positive and negative labels that have the potential to cause overfitting. That problem occurs because obtaining additional data with specific labels is difficult. To solve the imbalanced problem in ACS detection, we generated synthetic ACS data using the K-Means SMOTE method. The synthesis data is used as training data to build an ensemble-based machine-learning model. In this study, we obtain an increase in the F1 score of more than 10% when compared to machine learning models that do not use the K-Means SMOTE as an oversampling process. In addition to the greater F1 score, the results obtained are relatively more resistant to overfitting because the data variations in the training set are more diverse
The Role of Information Technology in Governance Mechanism for Strategic Business Contribution: A Pilot Study
Get PDFInformation Technology Governance (ITG) aligns IT and business transformation in schools. Private schools need to implement a method to evaluate the process of aligning IT strategy with business strategy and whether IT investment supports business objectives. Â What factors influence the ITG of selected Indonesia High School (HS) aligning IT-Business strategy? Partial Least Squares Structural Equation Modeling (PLS-SEM) is a tool for analyzing the ITG model results in this study. The result is the composition of 9 variables with four independent variables (as structure mechanism variables), four dependent variables (as process and relational mechanism variables), and the ITG variable (as the final variable) shows a significant value of 0.75 at the ITG variable. This considerable value means that the ITG supporting variables of four independent and four dependent variables significantly affect the ITG variable by 75%. This study provides information if the system trust variable is increasing due to the influence of good IT strategy (independent) variables and good business (dependent) variables. The recommendation is that this ITG trust model can be used to evaluate the alignment of IT strategy with business strategy and whether IT investment supports business objectives in H
Test Case Prioritization for Software Product Line: A Systematic Mapping Study
Get PDFCombinatorial explosion remains a common issue in testing. Due to the vast number of product variants, the number of test cases required for comprehensive coverage has significantly increased. One of the techniques to efficiently tackle this problem is prioritizing the test suites using a regression testing method. However, there is a lack of comprehensive reviews focusing on test case prioritization in SPLs. To address this research gap, this paper proposed a systematic mapping study to observe the extent of test case prioritization usage in Software Product Line Testing. The study aims to classify various aspects of SPL-TCP (Software Product Line – Test Case Prioritization), including methods, criteria, measurements, constraints, empirical studies, and domains. Over the last ten years, a thorough investigation uncovered twenty-four primary studies, consisting of 12 journal articles and 12 conference papers, all related to Test Case Prioritization for SPLs. This systematic mapping study presents a comprehensive classification of the different approaches to test case prioritization for Software Product Lines. This classification can be valuable in identifying the most suitable strategies to address specific challenges and serves as a guide for future research works. In conclusion, this mapping study systematically classifies different approaches to test case prioritization in Software Product Lines. The results of this study can serve as a valuable resource for addressing challenges in SPL testing and provide insights for future research
Analyzing the Impact of Project-Based Learning on Student Entrepreneurship Readiness: A Structural Equation Modeling and Statistical Analysis in Higher Education
Get PDFThe study aimed to examine the influence of entrepreneurial passion, entrepreneurial literacy, role model inspiration, and self-efficacy on entrepreneurship readiness among higher education students and the role of the project-based learning model implementation as a moderator variable. The population in the study were students in higher education in Indonesia who had taken entrepreneurship courses. Data from 313 valid respondents were analyzed against the research model using the Partial Least Squares Structural Equation Modelling. The findings revealed that entrepreneurial passion, entrepreneurial literacy, and role model inspiration were found to positively influence self-efficacy as well as entrepreneurship readiness among students in higher education. Unpredictably, the moderator project-based learning models’ implementation was shown to have an insignificant effect on the influence of entrepreneurial passion, entrepreneurial literacy, and role model inspiration toward entrepreneurship readiness among students in higher education. The findings of this study provide several important theoretical and practical implications for entrepreneurship readiness among students in higher education. higher education in Indonesia who had taken entrepreneurship courses. Data collected from 313 valid respondents were analyzed against the research model using the Partial Least Squares Structural Equation Modelling. The findings revealed that entrepreneurial passion, entrepreneurial literacy, and role model inspiration were found to positively influence self-efficacy as well as entrepreneurship readiness among students in higher education. Unpredictably, the moderator project-based learning models’ implementation was shown to have an insignificant effect on the influence of entrepreneurial passion, entrepreneurial literacy, and role model inspiration toward entrepreneurship readiness among students in higher education. The findings of this study provide several important theoretical and practical implications for entrepreneurship readiness among students in higher education
Implementation of 5G Telecommunication Network Services in Indonesia based on Techno-economic Analysis
Get PDFThe 2300 MHz spectrum is a medium band that telco operators will not pay much attention to when they deploy 5G. They are more comfortable at 2.6 GHz, 3.5 GHz, 26 GHz, and 28 GHz, in addition to 700 MHz for the breadth of coverage. The performance of cellular telecommunications services based on 5G technology is possible for new operators, although it will be carried out as stand-alone services. This opportunity will be taken by looking at internet subscriber data/data communication from existing operators as active internet users, which is quite large and has a potential of over 250 million users. There has been no previous study regarding the feasibility of deploying this 5G technology-based Broadband Wireless Access (BWA) Network. Based on the experience of implementing previous generations of telecommunication service technology, the government and operators need to be careful in determining the right moment to deploy this 5G technology service, which is predicted to be able to provide broadband services with streaming capabilities of 10 to 100 times the streaming speed of 4G technology. It should be noted that the lack of success of 3G performances in 2006 from 2G, 2.5G, and 2.75 G. Almost all operators who were expected to be very lucky turned out to be not optimal; even now, only 4 operators are playing on 3G. where they have not been able to force users of the 2G generation to switch to 3G, including in big cities where the performance of the 3G network is not yet optimal and evenly distributed. Still, many areas are blank spots from 3G networks and services. From this experience, scientific studies are needed to ensure the feasibility of the upcoming 5G BWA business and identify business opportunities that can be implemented. The feasibility analysis must be viewed from various aspects, namely aspects of technical readiness, market aspects, and financial aspects in terms of the techno-economics of the operators who will provide 5G telecommunications services by calculating several essential parameters as a measure of business feasibility, namely Net Present Value (NPV), Internal Rate of Return (IRR), and Payback Period (PBP)
Illuminance Color Independent in Remote Photoplethysmography for Pulse Rate Variability and Respiration Rate Measurement
Get PDFRemote photoplethysmography (rPPG) is now becoming a new trend method to measure human physiological parameters. Especially due to it noncontact measurement which safe dan suitable to use in this new era condition. Pulse rate variability (PRV) and respiration rate (RR) included as parameters can be measured by using rPPG. PRV and RR are used to measure both physical and psychological wellness of the subject. However, current performance challenges in rPPG algorithm in measuring PRV and RR are illuminance invariant and motion. Especially in different light condition which represent real-life environment, signal-to-noise ratio (SNR) will be affected and directly reduce the measurement accuracy. Therefore in this study, we develop rPPG algorithm and then investigate the performance rPPG in different illuminance scenarios. We perform PRV and RR measurement under each scenario. On this study, for the pulse signal extraction, we were using algorithm is based on the modification of plane orthogonal-to-skin (POS) algorithm. While, for respiration signal extraction is done in CIE Lab color space. Our experimental results show the mean absolute error (MAE) of each measured parameters are 3.25 BPM and 2 BPM for PRV and RR respectively compared with clinical apparatus. The proposed method proved to be more reliable to use in real environments measurement. However, limitation of our proposed algorithm is still running in offline mode, hence for the future we want try to make our algorithm run in real time
Mixed Pixel Classification on Hyperspectral Image Using Imbalanced Learning and Hyperparameter Tuning Methods
Get PDFHyperspectral image technology in land classification is a distinct advantage compared to ordinary RGB and multispectral images. This technology has a wide spectrum of electromagnetic waves, which can be more detailed than other types of imagery. Therefore, with its hyperspectral advantages, the characteristics of an object should have a high probability of being recognized and distinguished. However, because of the large data, it becomes a challenge to lighten the computational burden. Hyperspectral has a huge phenomenon that makes computations heavy compared to other types of images because this image is 3D. The problem faced in hyperspectral image classification is the high computational load, especially if the spatial resolution of the image also has mixed pixel problems. This research uses EO-1 satellite imagery with a spatial resolution of 30 meters and a mixed pixel problem. This study uses a classification method to lighten the computational burden and simultaneously increase the value of classification accuracy. The method used is satellite image pre-processing, including geometric correction and image enhancement using FLAASH while the corrections are geometric correction and atmospheric correction. Then to lighten the computational burden, the steps carried out are using the Slab and PCA method. After obtaining the characteristics, they are entered into a guided learning model using a support vector machine (SVM) for the five-class or multiclass classification. Moreover, the imbalance learning method is proven to produce increased accuracy. The best results were achieved by the ADASYN method with an accuracy of 96.58%, while the computational time became faster with the feature extraction method
The Reliability Analysis for Information Security Metrics in Academic Environment
Get PDFToday, academic institution involves digital data to support the educational process. It has advantages, especially related to ease of access and process. However, security problems appear related to digital data. There were several information security incidents in the academic environment. In order to mitigate the problem, metrics identification is required to determine the risk of incidents. There are many risks model and metrics to estimate the risk, such as DREAD, OWASP, CVSS, etc. However, specific metrics are required to obtain appropriate risk values. Therefore, this study aims to define metrics for an academic institution. The proposed metrics are obtained from The Family Educational Rights and Privacy Act (FERPA) regulation. It consists of directory information, educational information, personally identifiable information, and risk of information leakage. In order to achieve the objective, this study involves survey and reliability analysis to result in output. The survey is conducted by involving 90 respondents with various levels of education and jobs. The Cronbach's alpha and Test-retest are methods to determine this study's reliability. According to reliability analysis, the Cronbach's alpha method results in coefficients for the metrics between 0.730 - 0.911, while the Test-retest method results in coefficients between 0.630 - 0.797. These coefficients have a reliable category, so the proposed metrics are adequate for determining risk of information security incidents in academic environments. The reliable metrics will be developed as variables of the risk assessment model for the academic environment in the future study.Â
Chatbot for Diagnosis of Pregnancy Disorders using Artificial Intelligence Markup Language (AIML)
Get PDFArtificial Intelligence has evolved in sophistication and widespread use. This study aims to create a chatbot application in the health sector regarding the early diagnosis of pregnancy disorders. Based on basic health research, only 44 percent of pregnant women know the danger signs of pregnancy. The chatbot application developed is expected to facilitate and increase knowledge for pregnant women about the danger signs of pregnancy, especially early diagnosis of pregnancy disorders. The chatbot application was developed with artificial intelligence technology based on Artificial Intelligence Markup Language with the question-answer concept using the Pandorabots framework. The test is carried out in two stages: functional and pattern matching. The functional testing uses the black-box testing method, and the pattern-matching test on the chatbot uses the sentence similarity and bigram methods based on user input and keywords similarity in the bot's knowledge base. The functional testing results show that the chatbot application runs well, with the eligibility criteria reaching 81.4% and the results of the keyword similarity test (pattern matching) are zero to one, in the sense that the value of one has the same similarity between user input and pattern. Meanwhile, the zero value has no similarities, so the bot will respond to it as free input. So it can be concluded that the bot can respond to user questions when the pattern and input have the same level of similarity
CNN with Batch Normalization Adjustment for Offline Hand-written Signature Genuine Verification
Get PDFSignature genuine verifications of offline hand-written signatures are critical for preventing forgery and fraud. With the growth of protecting personal identity and preventing fraud, the demand for an automatic system for signature verification is high. The signature verification system is then studied by many researchers using various methods, especially deep learning-based methods. Hence, deep learning has a problem. Deep learning requires much training time for the data to obtain the best model accuracy result. Therefore, this paper proposed a CNN Batch Normalization, the CNN architectural adaptation model with a normalization batch number added, to obtain a CNN model optimization with high accuracy and less training time for offline hand-written signature verification. We compare CNN with our proposed model in the experiments. The research method in this study is data collection, pre-processing, and testing using our private signature dataset (collected by capturing signature images using a smartphone), which becomes the difficulties of our study because of the different lighting, media, and pen used to sign. Experiment results show that our model ranks first, with a training accuracy of 88.89%, an accuracy validation of 75.93%, and a testing accuracy of 84.84%—also, the result of 2638.63 s for the training time consumed with CPU usage. The model evaluation results show that our model has a smaller EER value; 2.583, with FAR = 0.333 and FRR = 4.833. Although the results of our proposed model are better than basic CNN, it is still low and overfitted. It has to be enhanced by better pre-processing steps using another augmentation method required to improve dataset quality.Â