A decision support system for physical and behavioral lifestyle recommendations using principal component analysis | |
| Author | Gontia, Shubhangini Narendrakumar |
| Call Number | AIT RSPR no.CS-23-02 |
| Subject(s) | Decision support systems Principal components analysis |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | The recent COVID-19 pandemic also has had a significant impact on the worldwide healthcare system. Pre-pandemic various surveys show unhealthy lifestyles among people. Since the beginning of the pandemic, people are balancing a healthy lifestyle. Through these technological advancements in the healthcare domain, the person’s lifestyle has a significant impact on an individual's health and well-being. The development of a Decision Support System (DSS) for physical and behavioral lifestyle has been proposed in this study. The system utilizes Principal Component Analysis (PCA) to analyze physical and behavioral parameters such as idle duration, walking duration, anxiety score, and BMI, among others. The DSS is designed to provide personalized recommendations and reports on changes in lifestyle based on the user's input. The system includes a user interface that allows the user to input data on physical and behavioral parameters, such as idle duration, walking duration, running duration, hiking duration, yoga duration, step counts, anxiety score, alcohol consumption, and smoking. The data collected is then transformed into z-scores to identify areas where the user needs to improve. PCA is applied to identify the most significant variables that contribute to the overall variance of the data. The principal components are obtained and displayed on a scree plot. The first principal component represents physical parameters, while the second principal component represents behavioral parameters. The components are used to analyze the data and provide personalized recommendations and reports to the user. The system's effectiveness was evaluated using a sample dataset, and the results showed that the system was capable of providing personalized recommendations and reports to the user. However, the system's limitations include the need for accurate data input and the inability to consider external factors such as genetics or environmental factors. Future work includes improving the accuracy of the data input through the use of wearable devices. In conclusion, the proposed DSS has the potential to improve users' physical and behavioral lifestyles by providing personalized recommendations and reports. The system utilizes PCA to analyze the data and provide meaningful insights. The limitations of the system can be addressed through future work, and the system can be further improved to provide more accurate recommendations and reports. |
| Year | 2023 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Chutiporn Anutariya |
| Examination Committee(s) | Vatcharaporn Esichaikul;Huynh, Trung Luong |
| Scholarship Donor(s) | AIT Scholarships |
| Degree | Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2023 |