Claim Missing Document
Check
Articles

Found 3 Documents
Search

Website Rekomendasi Tempat Kuliner dengan Metode Social Trust Path Oloan Sihombing; Supriadi Sihombing; Marta Lena Pasaribu; Robi Kris Dinata Saragih
Jurnal Sains dan Teknologi Vol. 2 No. 1 (2020): Sains dan Teknologi
Publisher : CV. Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34013/saintek.v2i1.52

Abstract

Nowadays, many culinary websites have emerged which provide various information about culinary places in the city ofMedan, such as qraved and zoobo. The rating system used by these websites has weaknesses, because the websites above providerecommendations based on the rating given by other application users that are not recognized by the user, so the trust level of the ratingis very weak. Looking at the shortcomings of the websites above, this application can be made with features, such as the culinarylocation search feature based on the type of halal food and vegetarian food types. Recommended features based on culinary location,as well as distribution of halal and vegetarian foods. In the process of determining the list of recommendations, the Social Trust Pathmethod will be used. The Social Trust Path method is a method of calculating the level of trust of something depending on the level oftrust of the user who gave the statement. The tools used to do analysis and design are use case diagrams. This website is built usingPHP coding and MySQL database. The results of this study are applications for web-based culinary recommendations that can be usedto provide information on culinary places for users.
Rancang Bangun Aplikasi Objek Wisata Kabupaten Tapanuli Tengah Berbasis Android Oloan Sihombing; Niko Saputra Nainggolan; Beti Lumban Gaol; Nelly Kesuma
Jurnal Sains dan Teknologi Vol. 2 No. 1 (2020): Sains dan Teknologi
Publisher : CV. Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34013/saintek.v2i1.54

Abstract

>Central Tapanuli Regency (Tapteng) a district in North Sumatra. Its capital is Pandan. Central Tapanuli is also a districtthat has a myriad of advantages ranging from natural beauty to cultural heritage. The tourism sector has not been supported byaccommodation facilities or transportation facilities. So that many tourists complain that they have difficulty determining theplanning of a tour because the description of the tourist area is not available such as visualization of places, distances between touristareas, and the roads that must be traversed to travel these tourist attractions. Therefore, through the Mapping of Tourist ObjectRoutes for tourism, it is hoped that it can display an overview of tourist routes or maps, lodging, transportation, culinary, and theprice of every need provided in Tapteng Regency so that it is more attractive and can be enjoyed by the wider community andabroad. The presentation of information that is less informative makes many tourists less interested because of the lack of touristobjects. The presentation of information based on android will make it easier for users to get information on each tourist attraction tobe visited in Tapteng Regency.
KLASIFIKASI PENYAKIT STUNTING DENGAN MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE DAN RANDOM FOREST Mahmin Banurea; Dinda Betaria Hutagaol; Oloan Sihombing
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 2 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i2.927

Abstract

This research aims to utilize machine learning technology, especially the Support Vector Machine (SVM) and Random Forest algorithms to classify stunting in children. Stunting is a condition where a toddler's growth and development is hampered due to malnutrition in the first 1,000 days of life. This research uses a dataset of 6,500 data on stunting sufferers with 8 attribute columns such as age, baby's weight, baby's body length, weight, height, etc. The results of this research show that the SVM algorithm provides an accuracy of 65.6% for testing data and 62.7% for training data, while the Random Forest algorithm provides higher accuracy, namely 88.2% for testing data and 98.8% for training data. The hypertuning process of the SVM algorithm succeeded in increasing accuracy up to 81%. This research contributes to efforts to deal with stunting in children through the application of machine learning technology. The results of this research can be used as a reference in developing more precise stunting prediction and prevention models.