ระบบคัดกรองผู้ที่เสี่ยงต่อภาวะซึมเศร้าผ่านสมาร์ทโฟนโดยใช้เทคนิคเหมืองข้อมูล SCREENING SYSTEM FOR DEPRESSION ON SMARTPHONE USING DATA MINING TECHNIQUES
Keywords:
Smartphone, Depression, Screening System, Data Mining, Neural NetworksAbstract
Depression is a psychiatric illness that affects daily life. Current social conditions found that the number of patients is increasing. Therefore, this research aims to create a model for screening patients with data mining techniques to obtain the most effective model to analyze the factors that affect the risk of depression and develop screening system for depression on Smartphone. The data used in the experiment were collected from random sampling of 505 data sets. Data mining techniques applied in modeling are 3 techniques, Decision tree, Neural Networks and Naive Bayes. Measure the performance of the model with Accuracy, Precision, Recall, F-measure and Root Mean Square Error (RMSE). The results showed that the model of neural network is the best performance with the Accuracy 97.43%, Precision 97.50%, Recall 97.40%, F-measure 97.40% and RMSE 0.1091. The analysis of the most effect factors by reducing the import of factors. The results showed that the sleepless factor, uneatable and don’t self-esteem are factors that influence depression risk. Then, this model was developed in the form of an application on Smartphone. Development tools use Android Studio and Java languages. The results of the system quality assessment from two groups of sample from 3 experts and 30 general users, it was found that the experts had an average satisfaction of 4.25 and the standard deviation was 0.44. The average user satisfaction was 4.20 and the standard deviation was 0.58. Shows that this system is effective, and it can be applied to real work.
Downloads
References
[2] Nantapak Chanphan. (2013, January-June). Recovery from depressive disorders in depressed patients. Thai Red Cross Nursing Journal. 6(1): 19-33.
[3] Saichon Sonsomboonthong. (2015). Data Mining. 1st edition. Bangkok: Chamchuri Product.
[4] Ekasit Patcharawongsakda. (2014). Data analysis with basic data mining techniques. 2nd edition.Bangkok: Data Cube.
[5] Jariya Chiranukul. (2016, January-February). Depression and anxiety in elderly patients with chronic diseases at the Faculty of Medicine Hospital Mahasarakrm university. Journal of Science and Technology Mahasarakrm university. 35(1): 94-101.
[6] MookKhirapa DaMayanand; and Somporn Rungruangkolkit. (2016, January-March). Prevalence and prediction factors depressed in Indonesian secondary school students. Journal of Nursingand Health. 39(1): 132-145.
[7] Mallikarjun H M; and H N Suresh. (2014). Depression Level Prediction using Egg Signal Processing. In 2014 International Conference on Contemporary Computing and Informatics (IC3I). pp. 928-933. Mysore, India.
[8] Raid Khalil; and Adel AI-Jumaily. (2017). Machine Learning Based Prediction of Depression among Type 2 Diabetic Patients. In 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE2017). Nanjing, China.
[9] PhetNarin KaewLa; and Chirasak Numpradit. (2011). Forecasting system for heart disease patients using artificial neural networks. In The 7th National Conference on Computer and Information Technology (NCCIT2011). pp. 168-173. Bangkok: King Mongkut's University of Technology North Bangkok.
[10] Konwipa Phunupha, Ravi Chawiwong, Wongkon SriUrai. (2012). System for analyzing the risk of obesity and suggesting food for patients. In The 8th National Conference on Computer and Information Technology (NCCIT2012). pp. 56-62. Bangkok: King Mongkut's University of Technology North Bangkok.
[11] Natthakon Muangkaew, Kanchana Viriyaphan, Sakda Vallipakorn, Phimpha Chamolsuk. (2013). Severity and opportunity forecasting systems for children injured or accidents using artificial neural networks. In The 9th National Conference on Computer and Information Technology (NCCIT2013). pp. 27-32. Bangkok: King Mongkut's University of Technology North Bangkok.
[12] Nopparat Potejiraporn, Chirasak Numpradit ,Sakchai Tangwanwit. (2015). Support system medical practice to analyze aneurysm disease using data mining techniques case studies of the treatment of aneurysms through the catheter. In The 11th National Conference on Computer and Information Technology (NCCIT2015). pp. 346-351. Bangkok: King Mongkut's University of Technology North Bangkok.
[13] Department of Mental Health. (2016, March). Public Relations Department of Mental Health. Retrieved March 22, 2016, from http://www.prdmh.com
[14] Banchob Onkun, Chari Thong, Watinee Sukmak. (2014, November-December). Modeling for forecasting foot ulcers of diabetic patients using data mining techniques. Journal of Science and Technology Mahasarakrm university. 33(6): 703-710.
Downloads
Published
How to Cite
Issue
Section
License
Srinakharinwirot University Journal of Sciences and Technology is licensed Under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC-BY-NC-ND 4.0) License, Unless Otherwise Stated. Please Read Journal Policies Page for More Information on Open Access, Copyright and Permissions.
