Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Designing Integrated IT Architecture for Health Monitoring Internet of Things: Findings Exploratory Study
No full textIT integration with healthcare, mainly through Internet of Things-based health monitoring systems, is crucial to improving healthcare management in the digital age. However, challenges remain in the design of an integrated IT architecture that can support the sustainability and effectiveness of IoT health monitoring systems, which still need to be addressed. The shortcomings in the literature related to the application of a holistic IT architecture framework to address these challenges indicate a knowledge gap that needs to be filled. Through the application of the TOGAF methodology, this research seeks to design and analyze an integrated IT architecture for IoT-based health monitoring systems in Indonesia, taking a qualitative approach through case studies, in-depth interviews, and document analysis. The main findings show that the application of the TOGAF framework successfully addresses the challenges of interoperability, data security, and system scalability by effectively integrating IoT technologies in the healthcare environment and considering the local social and infrastructural context. The implementation of the IT architecture developed based on the TOGAF methodology demonstrated improved coordination between IoT devices and backend systems, facilitated secure and real-time data flow, and accommodated the scalability and sustainability needs of the system. The findings have significant implications in supporting the development of more efficient and effective health monitoring systems, offering strategic guidance for system developers, policymakers, and IT practitioners within the healthcare sector
Development of Machine Learning Model for Breast Cancer Prediction from Ultrasound Images
No full textIn the past decade, the revolution in information and computing technology has transformed approaches to breast cancer detection and treatment, with Machine Learning technologies offering significant potential in health data analysis. However, the development of accurate and reliable predictive models is faced with the challenges of data heterogeneity and complexity. This research proposes the development and validation of Machine Learning-based classification models using Support Vector Machine and Principal Component Analysis to address these issues, targeting improved accuracy in the early detection of breast cancer. The methodology applied involved the use of a breast cancer dataset from Kaggle, with data analysis conducted through inductive methods to identify relevant patterns. The combination of Support Vector Machine and Principal component Analysis achieved 89% accuracy in medical image classification, proving its efficacy in breast cancer diagnostics and providing a more reliable model for early detection. The implications of these findings are significant, both theoretically and practically, for the fields of Machine Learning and Breast Cancer, expanding the understanding of the applications of advanced data processing techniques. Although this study faces limitations in the variability of the dataset's patient characteristics, the results offer a basis for further development in diagnostic technology while recommending the integration of Deep Learning and Big Data analysis as a direction for future research
Satisfaction Analysis of The Establishment of a Website-Based Rank System Using Customer Satisfaction Index (CSI) And Importance Performance Analysis (IPA) Methods
No full textPromotion is one of the rights and obligations of lecturers for the performance burden that has been carried out by lecturers in order to implement the basic values of the Tri Dharma of Higher Education. The lecturer ranking system is implemented based on the lecturer's performance in teaching, research, and service that has been carried out. The lecturer rank system is implemented through a fairly long process and verification, so that the creation of a good ranking system will provide good added value in higher education services to the performance of lecturers for promotion. In this study, optimization of the lecturer's functional position promotion system will be carried out. The result achieved is a lecturer rating system by calculating the weight of credit scores in order to obtain a recommendation for promotion of lecturers for functional positions in universities and based on the Customer Satisfaction Index from a survey conducted on 50 respondents showing a score of 76.12%. It states that the rating system is at the level of satisfaction
Chatbot Design for Interview Questions Using Neural Network Models on the CarTech Website
No full textAbstract: This research focuses on analyzing interview questions using a neural network model, implemented on the CarTech website. With the main aim of optimizing the interaction between users and the system through the questions asked, this research takes an innovative step by utilizing Google Collab as a development platform. For this research, several paragraphs were carried out, namely problem scoping, data acquisition, data exploration, modeling, evaluation, and deployment. These stages were carried out so that this research could get good results, plus the integration between Google Collab and chatbot which made it possible for this research to get good results. Google Collab makes it easy to use neural network models and integrate with chatbots, enabling efficient and effective testing and deployment of models. The results of this study are quite impressive, with an accuracy of 92%, demonstrating the model's ability to process and understand interview questions with high precision. The aim of this research is not only to explore the potential of neural network models in automatically understanding questions and providing accurate responses, but also to show how this technology can be integrated into web applications to improve the quality of user interactions, making AI-based chatbots a viable solution and effective in improving user experience on the CarTech website. In conclusion, by utilizing AI you will also get good results. As in this research, AI can help analyze interview questions with neural network models
Design E-Learning User Interface On Website-Based Edspert.Id With Kansei Engineering Methods
No full textThe development of information technology has encouraged people to rely on information systems, especially through websites. Websites provide easy access to information and learning with various educational materials. Although e-learning has been implemented in many educational websites, Edspert. id, a company in the education sector, has not implemented it yet. User interface design development is one of the important processes in e-learning website development. A user interface that is easy to use will improve the learning experience of learners. This research proposes a solution to design the user interface of Edspert.id e-learning website by using the Kansei Engineering method. This approach has been done beforefor web-based e-learning based on users' emotions. Principal component analysis (PCA) is used to reduce Kansei Word variables that are relevant to users' emotions. The e-learning website element design was then designed based on the PCA results. The next step is to determine the design elements in the e-learning design. Then, partial Least Square (PLS) was used to analyze the relationship between Kansei Word and element design. The results show that there multiuser interface design has two concepts whose element designs are in accordance with user needs
Innovative Design of ITTS Mart Application with Design Thinking & System Usability Scale Method
No full textIncluding ease of accessing the internet through mobile devices. The emergence of social media applications, such as virtual friend applications, has also played a role in increasing the number of Internet users, primarily through mobile devices. In addition to functioning as a forum for virtual friends, social media also acts as a means of promotion, one of which is to promote online shopping applications, which contribute to an increase in online shopping transactions in Indonesia. One of the strategic choices taken is to use online shopping platforms to market educational institutions' products in the hope that they can make it easier for customers to shop and stimulate significant growth. Design thinking is used in idea formulation and problem-solving. As for creating applications that describe the emotional desires of users, this research uses the Kansei Engineering approach. Data collection was conducted through questionnaires, interviews, and literature studies. Later, it will generate several selected Kansei Words. Furthermore, to determine the best design that suits user needs, application prototypes are tested through Performance Metrics tests to determine the level of Effectiveness, efficiency, and errors, as well as performance and usability evaluations using System Usability Scale (SUS) questionnaires.
Implementation of Data Mining to Determine Public Interest in Automatic Motorcycles
No full textResearch on public interest in automatic motorbikes was carried out with the aim of understanding the factors that influence the decision to purchase an automatic motorbike. Using data mining methods, this research applies the K-Nearest Neighbor (KNN) and Neural Network techniques to identify and analyze people's interest patterns. The data used amounted to 139 samples, of which 127 showed interest in automatic motorbikes, while 12 others showed no interest. The research process begins with data analysis, the next stage is preprocessing, which includes data cleaning, in the model design stage in data mining, two models are built: one using KNN and the other using Neural Network. These two models are designed to classify sample data based on interest in automatic motorbikes. The next stage is model testing. Test results show that both models can classify interests accurately, with most of the sample data being classified correctly. Model evaluation was carried out to measure the effectiveness and accuracy of the two methods. The evaluation results show that both models provide very good performance, with results that almost reach a perfect score. This shows that both methods, KNN and Neural Network, are very effective in classifying and predicting people's interest in automatic motorbikes based on available data. In conclusion, this research not only shows the effectiveness of KNN and Neural Network in data mining for analyzing people's interests, but also provides valuable insights for automatic motorbike manufacturers and sellers about consumer preferences
Decision Support System Using the TOPSIS Method in New Teacher Selection
No full textEvery school needs teachers who have good competence to educate students to become outstanding students. Getting teachers who have good competence is certainly not an easy thing, it must be a very strict selection process. This research aims to help determine teachers who are eligible to be accepted at IT Al Munadi Private Elementary School Medan by using the TOPSIS method. The selection consists of 5 criteria, namely education, microteaching, teaching experience, tahsin and memorization of the Koran. The TOPSIS method is widely used for Multi Attribute Decision Making (MADM) decision making. The TOPSIS method is used as a ranking to see teachers who have competencies that are worthy of acceptance. Based on the results of the TOPSIS calculation where there are 6 alternatives that have been determined, the results obtained are G6 in the first place with a preference value of 2.82, 2nd place with a preference value of 2.48, 3rd place with a preference value of 2.09, 4th place with a preference value of 1.72, 5th place with a preference value of 1.67, while the 6th place is G1 with a preference value of 1.00. It is hoped that the decision support system using TOPSIS can help schools in determining teachers who have good competence so as to produce outstanding students
Analysis of COVID-19 Virus Spread in Jakarta Using Multiple Linear Regression
No full textCOVID-19, first identified in Wuhan, China in December 2019, quickly spread worldwide and was declared a pandemic by WHO in March 2020. Indonesia reported its first case on March 2, 2020, and the pandemic has had a significant impact on the country's economic, social, and health sectors. This study aims to predict the death rate due to COVID-19 in Jakarta using multiple linear regression method. The dataset collected from Andra Farm - Go Green website includes COVID-19 cases recorded in all sub-districts in Jakarta on November 1, 2023. Pre-processing was performed to improve the quality and accuracy of the model. The method used was multiple linear regression. The analysis results show that variables such as total travel and discarded trip have a significant influence in predicting the number of positive cases. The study found that lowering the correlation threshold for selecting independent variables reduced the mean squared error (MSE) and improved model performance, highlighting the importance of variable selection in developing accurate predictive models. These findings provide important insights for the government in making informed decisions regarding post-pandemic healthcare. This research underscores the value of robust data processing and variable selection techniques in enhancing predictive accuracy for public health planning
Enterprise Architecture Implementation Scholastic Learning Zone Literacy Improvement St. Kristoforus 2 High-School
No full textThis research aims to explore the transformation of Enterprise Architecture in the implementation of a Scholastic Learning Zone for the improvement of learners' literacy at Santo Kristoforus 2 High School. The background of this research is based on the importance of literacy as the primary foundation in learning, as well as the need to integrate innovative educational technology. The main objective of the research is to understand how the implementation of Enterprise Architecture can support the implementation of the Scholastic Learning Zone effectively and efficiently. The research method used is a qualitative approach with a case study at Santo Kristoforus 2 High School, involving in-depth interviews with educators, direct observation, and analysis of related documents. The results showed that the implementation of Enterprise Architecture significantly contributed to improving the structure and process of education, thus supporting the improvement of learners' literacy. Key findings include improved accessibility of learning resources, school administration efficiency, and increased learner engagement in the learning process. Additionally, the implementation facilitated the creation of eBooks for learning materials, further enhancing literacy by providing students with readily accessible and interactive content. The conclusion of this study shows that the transformation of Enterprise Architecture in the implementation of the Scholastic Learning Zone not only improves literacy but also strengthens the education system. Further research is recommended to test this model in different educational contexts to extend the validity of the findings