Claim Missing Document
Check
Articles

Found 24 Documents
Search

A PERANCANGAN SISTEM KENDALI KENDARAAN BERMOTOR JARAK JAUH MENGGUNAKAN NodeMCU ESP8266 Choresy Michael G. Butar-butar; Yusran Timur Samuel
TeIKa Vol 9 No 1 (2019): TeIKa: April 2019
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v9i01.793

Abstract

Turning on a vehicle from a distance is an obstacle for the owners. This happens if he travels far and no one can turn on the vehicle. For this reason, the authors conduct a study to utilize IoT technology (internet of things) that can turn off and turn on a vehicle remotely. By using ESP8266 NodeMCU which is connected with 2 relays and 2 sensor that is a SW420 vibration sensor and a tilt sensor the SW460D can produce a hardware configuration to control the vehicles from a distance. As an interface controller, one application has been programmed using the Android-based Blynk application. This design has been tested on a motorcycle for a month, from March 1 to April 1. the result shows that it works, and it is always succeeded to control the motorcycle from a far if the system gets a wifi signal with an internet connection. Keywords: IoT, NodeMCU, SW420 vibration sensor, SW460D tilt sensor
Perancangan Sistem Informasi Absensi Dan Nilai Siswa Beserta Absensi Dan Laporan Kegiatan Guru Di Sekolah Advent Pancaran Kasih Berbasis Web Boston Pahala Siahaan; Yusran Timur Samuel
TeIKa Vol 7 No 2 (2017): Teika : Oktober 2017
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v7i2.826

Abstract

Generally attendance system and teacher activity report in school is done by manual that is teacher fillthe attendance by writing in paper of their attendance data after that teacher also doing attendancefor student by calling student name one by one done by teacher teaching. Therefore, it needs a changewith the computerization process to fix any deficiencies and fraud in the process of absenteeism andvalue on the students. Sekolah Pancaran Kasih is very eager to have a useful school website to provideinformation - information, teacher and student attendance along with better student scores. Systemdevelopment method used in this research is SDLC consisting of (1) Information, (2) design, (3)implementation, (4) maintenance. From this research which have been done, the writer conclude that(1) This system can be used by teacher and admin (2) teacher easily input student attendance dataand give value to its student (3) All attendance data and student value and teacher attendance dataand the activity report will be saved to the system that has been created. With the design of attendanceinformation system and students' values along with absences and reports of teacher activities it can beconcluded, the system can provide convenience to users and administrators involved in processing andstoring data so as to provide information in accordance with the needs of the user.
Perancangan Aplikasi Untuk Memprediksi Seseorang Menderita Penyakit Hipertensi Menggunakan Data Mining Yusran Timur Samuel; Frengky Simbolon
TeIKa Vol 7 No 2 (2017): Teika : Oktober 2017
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v7i2.834

Abstract

Hypertension is one of the diseases of blood vessel disorders. In Indonesia, people with hypertension disease increased by 3.6% every year. The occurrence of hypertension increases due to the lack of care of the public for health, as well as the lack of time to consult a specialist or an expert. The purpose of this study (1) the data obtained can be used to predict a person suffering from hypertension. (2) Applications are made easy to use and have high accuracy prediction. The method used in this research is data mining with Naïve Bayes Classification method which is a classification method using probability and statistic. In collecting data required for Data Mining, researcher giving questionnaires to patients who visited hospital X for 3 weeks with questionnaire attributes that contains age, sex, weight, height, smokers, type of cigarette, the number of cigarettes, the consumption of alcoholic beverages, physical, sleep hours, meat consumption, vegetable consumption, salt level, history of father's hypertension, history of maternal hypertension. Conclusion (1) by using Data Mining, the patient can immediately find out whether the patient is suffering from hypertension based on the lifestyle he/she has. (2) Applications that have been developed can be used and has a fairly high accuracy of 88% and has a sensitivity of 77%, and 96% of specificity. (3) The use of Naïve Bayes to predict a person suffering from hypertension can be used because it has a high accuracy of 88%.
Penggunaan Metode NAÏVE BAYES Dalam Mengukur Tingkat Kepuasan Pengguna Terhadap Online System Universitas Advent Indonesia Yusran Timur Samuel; Kemala DEwi
TeIKa Vol 9 No 2 (2019): TeIKa: Oktober 2019
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v9i02.2162

Abstract

Achieving user satisfaction in using an information system is one of the factors to determine the system as expected. The UNAI Online System has been operating since 2008 and granting students a convenient access to their academic data. In order to enhance users' satisfaction on using the UNAI Online System, it needs to be done according to the right measurements towards an information system. The methods that were used in this study is data mining along with the Naïve Bayes classifications method and data that were obtained from questionnaires. The attributes used are content quality, relevance, privacy, easily operated, speed, visual appeal, online completeness, and customer services. The test results showed that the first test for users' satisfaction using the Naïve Bayes method scored up to 81.3%. The second test with 80% data training and 20% data testing obtained 80% accuracy value. As for cross-validation test, the score reached 78.7%. Lastly, the test with 66% training data and 33% test data get the accuracy value up to 68.6%.
ANALISIS SENTIMEN TOKOH PUBLIK MENGGUNAKAN METODE NAÏVE BAYESIAN CLASSIFICATION PADA APLIKASI TWITTER Yusran Timur Samuel; Kevin Jeremy Manurip
TeIKa Vol 7 No 1 (2017): TeIKa : April 2017
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v7i1.2218

Abstract

Social media has provided a variety of information, especially content that is subjective or reflects the opinions of people who write. Today more and more people express their opinions or opinions on community leaders such as regional leaders, officials, influential people, and so on. Social media has provided a variety of information, especially content that is subjective or reflects the opinions of people who write. Today more and more people express their opinions or opinions on community leaders such as regional leaders, officials, influential people, and so on. Sentiment analysis on the Twitter social media application there are weaknesses in the words contained in the sentence uploaded by the application user. In this case the object of the research was carried out to Ridwan Kamil with Sentiment Analysis from the people. Based on the research conducted, it was concluded that 59 training data had an accuracy of 81.3559%, and the results obtained from testing data were: 1. There were 3 data that were truly classified as having neutral sentiments, 2. There were 7 data classified really have positive sentiment, 3. And there are 2 data that really have negative sentiment.
Analisis Harga Saham PT Astra Internasional Tbk Menggunakan Data Dari Bursa Efek Indonesia dalam Jangka Waktu Pendek Menggunakan Metode Naïve Bayes dan Decision Tree-J48 Heima Sitorus; Yusran Tarihoran
TeIKa Vol 8 No 1 (2018): TeIKa : April 2018
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v8i1.2239

Abstract

Stock price prediction is a very necessary action as a first step to taking the decision to determine when to transact a sale and purchase of existing shares in Indonesia stock exchange. Stock price prediction is done using two methods are compared, i.e.; Naїve Bayes method and the method of Decision Tree-J48. The amount of data used is as much as 1,195 and data used as the data for testing is as much as 20% or 239 the data. As a result of the level of accuracy of the Naïve Bayes Method using data testing is 92.0502%. With the presentation for the value of precision or accuracy of information expected by the author with the answers given by the system of 0920 and the value for the recall or the success rate of taking action against information found by the system of 0.961. While the results of a prediction using Decision Tree J-48 results for accuracy using data testing is 98.7448%. %. With the presentation for the value of precision or accuracy of information expected by the author with the answers given by the system. of 0.989 and value for the recall or the success rate of taking action against information found by the system of 0.997.
Analisis Sentimen Pemilihan Gubernur Jawa Barat Tahun 2018 Dengan Aplikasi Twitter Menggunakan Metode Naïve Bayesian Classification Yusran Tarihoran; Kevin Jeremy Manurip
TeIKa Vol 8 No 1 (2018): TeIKa : April 2018
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v8i1.2243

Abstract

Elections on West Java Governor 2018 are busy discussed in the real world and cyberspace, especially in social media Twitter. Everyone is free to argue about the candidate of West Java Governor 2018 that raises many opinions, not only positive or neutral opinion, but also negative opinion. Nowadays, social media especially Twitter is one of the place to promote or to campaign effectively and efficiently to increase supporters interest. In this case researchers will conduct research on one of the public figures who run for governor elections West Java. The research method used in this research is the Naïve Bayesian Classifer Classification algorithm. The data used is an Indonesian tweet with the keyword Ridwan Kamil (#RidwanKamil) as much as 1031 data tweet every day starting from January 15, 2018 to April 15, 2018. Results from the classification using the Naïve Bayesian Classifier algorithm obtained 690 number of tweets or 67% all data tweets that support Mr. Ridwan Kamil or are positive especially on the work program that will be done and this provides a probability statistics of 73.13% accuracy level Correctly Classified Instances.
PREDIKSI INDEKS PRESTASI MAHASISWA YANG BERKULIAH SAMBIL BEKERJA DI UNIVERSITAS ADVENT INDONESIA DENGAN MENGGUNAKAN METODE DECISION TREE C4.5 DAN SMOTE Yusran Timur Samuel; Chrystle Beatrix Allbright Nahuway
TeIKa Vol 10 No 1 (2020): TeIKa: April 2020
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v10i01.2281

Abstract

Higher education is one way to get job easier, this thing happens because through education the individual is able to increase the level of human resources in this era. However, the high cost of education is very expensive so individuals who wants to study must also work at the same time, so this research aims to predict the student GPA who is studying while working at the same time at Adventist University of Indonesia. From the results of this research there are 8 attributes that have an effect on predicting student GPA at Adventist University of Indonesia, namely the Department of Work, Working Hours, Course, Gender, Residence, Age and Number of Credits. The method that has been used in this research is Decision Tree C4.5 implemented on the WEKA program with the J48 algorithm. This research also uses the SMOTE (Synthetic Minority Oversampling Technique) algorithm to balancing the amount of data in the minor class. The top root of this research is Gender which affects the student GPA at University of Indonesia. The SMOTE algorithm in this research is useful to help raising the result of this research by 7-8% can be seen from the results of the accuracy of the cross validation 10 folds test is 63.6672%, the average result of precision and recall are 0.621 and 0.637. While the accuracy of the split test 70:30 is 62.7955%, then result of precision and recall are 0.621 and 0.628. When compared with the use of the Decision Tree C4.5 algorithm only, the accuracy of the cross validation 10 fold test is 55.5044%, with the average result of precision and recall is -.545 and 0.555. While the accuracy of the split test 70:30 is 55.2995% with the results of precision and recall is 0.554 and 0.553. The analysis results using confusion matrix and ROC curve with results from 0.688 to 0.756, which are in the range of 0.70 - 0.80 which is included in the level of fair classification diagnosis. It can be concluded that there is a strong effect while working on the student GPA. With the order of attributes from the top most are Gender, Total Credit, Department, Age, Department of Work, Working Hours and Residence.
SISTEM PAKAR PENENTUAN TANAMAN PALAWIJA YANG COCOK TUMBUH PADA SUATU DAERA MENGGUNAKAN ALGORITMA FORWARD CHAINING Yusran Timur Samuel; Yank Nekmese K.; Raymond Maulany
TeIKa Vol 8 No 2 (2018): TeIKa : Oktober 2018
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v8i2.2326

Abstract

Farmers often have Difficulties regarding what crops are suitable for planting in their agricultural areas. For this reason, an expert system application is needed that can help farmers determine what crops can be planted on their agricultural land. This study uses a forward chaininig algorithm expert system method with height attributes, temperature, soil ph, rainfall, Intensity of irradiation, and humidity The expected output is information on what crops are suitable for planting on their agricultural land based on the attributes that are input. In this study researchers used the System Development Life Cycle (SDLC) method in designing expert system applications. The knowledge base used in this study is the result of interviews with experts coup/ed with theories obtained from various literature. Testing the performance and performance of applications using the blackbox method with the conclusion that the system can perform its functions properly and as expected
Analisa Pengaruh Penggunaan Gadget Terhadap Nilai Akhir Siswa SMA Secara Umum Menggunakan Metode Data Mining (Decision Tree) Raja Simarmata; Yusran Timur Samuel
TeIKa Vol 11 No 1 (2021): TeIKa: April 2021
Publisher : Fakultas Teknologi Informasi - Universitas Advent Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36342/teika.v11i1.2475

Abstract

The rapid development of technology is currently used by all ages. The use of gadgets among teenagers today is really busy and will certainly affect their learning attitudes and their final grades. Data mining is a method of processing large amounts of data to find information from that data. ID3 is a data mining algorithm that uses the entropy method. The result of this study is that gadgets do not affect the final grades of high school students in general.