Testing for Recommendation Method in M-Health Sports Venue Recommendation System
Ratih Kartika Dewi1, Yuita Arum Sari2, Agus Wahyu Widodo3, Faishal Pradipta Astungkoro4, Nurul Ilmi Muhlisah Aziz5
1Ratih Kartika Dewi*, Department of Informatics Engineering, Faculty of Computer Science (FILKOM), Brawijaya University, Malang, Indonesia.
2Yuita Arum Sari, Department of Informatics Engineering, Faculty of Computer Science (FILKOM), Brawijaya University, Malang, Indonesia.
3Agus Wahyu Widodo, Department of Informatics Engineering, Faculty of Computer Science (FILKOM), Brawijaya University, Malang, Indonesia.
4Faishal Pradipta Astungkoro, Department of Informatics Engineering, Faculty of Computer Science (FILKOM), Brawijaya University, Malang, Indonesia.
5Nurul Ilmi Muhlisah Aziz, Department of Information System, Faculty of Computer Science (FILKOM), Brawijaya University, Malang, Indonesia.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 27, 2020. | Manuscript published on April 10, 2020. | PP: 2143-2146 | Volume-9 Issue-6, April 2020. | Retrieval Number: E2490039520/2020©BEIESP | DOI: 10.35940/ijitee.E2490.049620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Exercising can make the body produce more endorphins so people with regular exercise are more resistant to stress than those who have little physical activity. We can get a recommendation of the sport venue in search engine, but it can’t accommodate personal preference. The mobile application for sports venue recommendations (M-health) with specific attribute weighting that can accommodate user preference for a specific attribute can be implemented with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) algorithm. TOPSIS was chosen as a recommendation algorithm because it has a relatively low level of algorithm complexity, so it is suitable to apply in mobile devices. To test the recommendations that are processed with TOPSIS, correlation testing is done as an alternative test besides accuracy. In general, the system takes the user’s location coordinates and then recommends a Futsal court based on location, price and the number of courts. First, the user is inquired to enter the weights for each criterion. Then the user gets a recommendation for a Futsal court recommendation according to the user’s current location. If the user wants detailed information about the desired futsal location, the user can click on one of the futsal places and then the detail page will be appear. After seeing the details of the selected futsal place, users can view the map to go to the relevant sports venue from the user’s current location. Testing the recommendation system was based on correlation testing to see the correlation between the recommendations built by the system compared to the user’s preference choices. Correlation testing was carried out to see whether there was a relationship between the results of the TOPSIS recommendation and the user’s preference of sport venue. The correlation between them shows a positive correlation with a value of 0.770769231.
Keywords: Mobile Recommender System, TOPSIS, M-Health, Test of Correlation.
Scope of the Article: Health Monitoring and Life Prediction of Structures