Articles
Identifikasi dalam Penentuan Prioritas Usulan Kenaikan Jabatan Fungsional Pegawai Menggunakan Metode TOPSIS
Zulvitri, Z;
Defit, Sarjon;
Sumijan, S
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37034/jsisfotek.v3i3.147
Padang State Polytechnic (PNP) is one of the state universities located in the city of Padang, which has 39 Learning Laboratory Institution Functional Officials, who were later told by PLP. PLP is a Civil Servant (PNS) who is given the task, responsibility, authority and right to carry out activities in the field of learning laboratory management. The problem that occurs is that the PLP does not know the exact time of application for promotion and functional positions of each. Some of the difficulties occur in managing the sub-division of personnel in finding archives. This article is always increasing and accumulating each period of acceptance. So this research aims to process this staffing data to make it easier and to accelerate the promotion process. The method used is the Decision Support System (DSS) in identifying priorities for proposals for functional promotion. The DSS method used is Technique For Order Preference By Similarity to Ideal Solution (TOPSIS). The results of this study have the reliability in considering the shortest distance to the positive ideal solution and also the longest distance to the negative ideal solution. The alternatives and criteria used in this study consisted of 5 alternatives and 3 criteria. The value of ideal positive and negative solutions has a maximum value of K1 which is 0.66, K2 is 0.022, K3 is 0.05 and a minimum value of K1 is 0.1, K2 is 0.017, K3 is 0.022. The highest score in ranking is 2 people with a score of 1 and the lowest is 1 person with a score of 0.0008. So this research is very helpful in identifying promotion priorities appropriately.
Prediksi Hasil Belajar Siswa Secara Daring pada Masa Pandemi COVID-19 Menggunakan Metode C4.5
Fitriani, Yetti;
Defit, Sarjon;
Nurcahyo, Gunadi Widi
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37034/jsisfotek.v3i3.149
Student learning in schools has changed since the Covid-19 pandemic. Student learning in normal conditions is carried out face-to-face and turns into online or online learning. The research was conducted to predict student learning outcomes during the COVID-19 pandemic so that the results of this study can be used as a reference in policymaking in schools. The C4.5 method was used in the study to classify the data for class XII of the Multimedia Department at SMKN 2 Padang Panjang and the classification results could predict student learning outcomes during the pandemic. Processed student value data were taken from 1 (one) subject as the research data sample. Analysis of the value of student learning outcomes using the C4.5 Method to obtain new knowledge from student learning outcomes data carried out during the COVID-19 pandemic. The data analyzed consisted of attributes of attendance, assignments, daily tests, and test scores which influenced the decision criteria for student learning outcomes in online learning. The learning outcome decision criteria consist of "Satisfactory" and "Not Satisfactory" which refer to the Minimum Completion Criteria. Tests conducted on the training data of learning outcomes show that the value of the Daily Test is the most influential attribute in decision making. Implementation of the results using the RapidMiner Studio 9.2.0 software and produces an accuracy of 83.33% of the test data testing with the rules of data analysis training results. The results of the C4.5 classification testing method in this study can be used to predict student learning outcomes. The test results with an accuracy of 83.33% can be recommended to help schools in making policies.
Akurasi Klasifikasi Pengguna terhadap Hotspot WiFi dengan Menggunakan Metode K-Nearest Neighbour
Syaljumairi, Raemon;
Defit, Sarjon;
Sumijan, S;
Elda, Yusma
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37034/jsisfotek.v3i3.152
The Current wireless technology is used to find out where the user is in the room. Utilization of WiFi strength signal from the Access Point (AP) can provide information on the user position in a room. Alternative determination of the user's position in the room using WiFi Receive Signal Strength (RSS). This research was conducted by comparing the distance between users to 2 or more APs using the euclidean distance technique. The Euclidean distance technique is used as a distance calculator where there are two points in a 3-dimensional plane or space by measuring the length of the segment connecting two points. This technique is best for representing the distance between the users and the AP. The collection of RSS data uses the Fingerprinting technique. The RSS data was collected from 20 APs detected using the wifi analyzer application, from the results of the scanning, 709 RSS data were obtained. The RSS value is used as training data. K-Nearest Neighbor (K-NN) uses the Neighborhood Classification as the predictive value of the new test data so that K-NN can classify the closest distance from the new test data to the value of the existing training data. Based on the test results obtained an accuracy rate of 95% with K is 3. Based on the results of research that has been done that using the K-NN method obtained excellent results, with the highest accuracy rate of 95% with a minimum error value of 5%.
Optimalisasi Parameter dengan Cross Validation dan Neural Back-propagation Pada Model Prediksi Pertumbuhan Industri Mikro dan Kecil
Windarto, Agus Perdana;
Defit, Sarjon;
Wanto, Anjar
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 11, No 1 (2021): Volume 11 Nomor 1 Tahun 2021
Publisher : Universitas Diponegoro
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21456/vol11iss1pp34-42
It is important for us to predict what will happen in future and to reduce uncertainty. Various analyzes are therefore necessary in order to optimize or improve the prediction results by several methods. The objective of this research is to analyze predictive results by optimizing the training and testing by means of cross validating parameters on the growth of micro and small-scale production in Indonesia through the exactness of the return-propagative method. The method of reproduction is used. These results are compared with results of backpropagation during training and testing without optimisation of the same architectural model. The dataset is based on the growth in production in micro and small businesses by province from the Central Statistical Agency(BPS). There were 34 records in which data from 2015-2019 for growth of production were collected. The results with optimisation have surpassed without optimisation the back propagation model by looking at RMSE, in which the best RMSE in the 3-2-1 architectural model was obtained and the side type is mixed sampling. The obtained RMSE value is 0.1526, or a difference between the best background architectural model, 3-2-1 and 0.0034. (0.157). The results of this model were 94 percent.
Sistem Pakar dalam Menganalisis Defisiensi Nutrisi Tanaman Hidroponik Menggunakan Metode Certainty Factor
Febrina, Yerri Kurnia;
Defit, Sarjon;
Nurcahyo, Gunadi Widi
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 4 (Accepted)
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37034/jsisfotek.v3i4.170
Saat ini sistem Pakar telah menjadi bidang penelitian bagi ilmuwan komputer juga ilmuwan pertanian untuk aplikasi dalam berbagai pengembangan informasi. Sistem Pakar dapat dirancang untuk mensimulasikan satu atau lebih dari cara seorang ahli pertanian menggunakan pengetahuan dan pengalamannya dalam membuat diagnosis dan meneruskan rekomendasi yang diperlukan terkait defisiensi nutrisi. Defesiensi nutrisi adalah kekurangan bahan makanan untuk kelangsungan hidup pada tanaman. Kandungan hara pada bagian tanaman, terutama didaun, sangat relevan digunakan untuk mengidentifikasi defisiensi nutrisi. Memberikan hasil diagnosis defisiensi nutrisi kepada petani untuk dapat menjadi patokan perbaikan hara tanaman serta pemberian nutrisi yang baik untuk tanaman hidroponik. Data yang digunakan adalah data defisiensi nutrisi dan gejala serta solusi pemberian nutrisi yang diperoleh dari data petani pada Dinas Pertanian Kota Payakumbuh. Metode yang dipakai dalam system pakar ini adalah metode Certainty Factor (CF). Metode ini memberikan diagnosis berupa kepastian atau ketidakpastian kondisi dalam rule yang digunakan untuk menyimpulkan. Hasil dari pengujian terhadap metode ini menunjukan sebanyak 12 defisiensi nutrisi yang terdeteksi dengan 41 gejala yang dialami. Sehingga dapat mengukur tingkat defisiensi nutrisi yang terjadi. Sistem Pakar dalam Menganalisis Defisiensi Nutrisi Tanaman Hidroponik Menggunakan Metode Certainty Factor dapat menunjukkan bahwa prediksi hamper 94% akurat.
TEXT MINING DALAM MEMBANDINGKAN METODE NAÃVE BAYES DENGAN C.45 DALAM MENGIDENTIFIKASI BERITA HOAX PADA MEDIA SOSIAL
Handika, Yola Tri;
Defit, Sarjon;
Nurcahyo, Gunadi Widi
Rang Teknik Journal Vol 5, No 1 (2022): Vol. 5 No. 1 Januari 2022
Publisher : Fakultas Teknik Universitas Muhammadiyah Sumatera Barat
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (243.712 KB)
|
DOI: 10.31869/rtj.v5i1.2855
Hoax news (hocus to trick) has a very big influence in disseminating information, especially in the world of social media. News has an important impact on social and political conditions, and news can move the economy of a country. For this reason, it is necessary to have an analysis to classify hoax news and not hoaxes, and have high accuracy in classifying the news. In this study, two methods were used as a comparison in achieving high accuracy, namely the Naïve Bayes method which is famous for having high accuracy in classification with little data, and the C.45 method which can minimize noise in the data. The data used are 300 articles with 10 topics which contain hoax and non-hoax news. The data is obtained from the internet through social media, such as Twitter, Instagram and Facebook. Testing using the Naïve Bayes method has a higher accuracy than the C.45 method. The amount of data used has a major influence on the test results, if more data enters the training stage, then this study will have higher accuracy. However, the results of this test can be recommended to increase accuracy in the construction of a hoax news detection system.
Analisis Optimasi Fungsi Pelatihan Machine Learning Neural Network dalam Peramalan Kemiskinan
Sitanggang, Sahat Sonang;
Defit, Sarjon;
Ramadhan, Mukhlis
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 7, No 3 (2021): Volume 7 No 3
Publisher : Program Studi Informatika
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.26418/jp.v7i3.50092
Banyak metode fungsi pelatihan dalam Machine Learning Neural Network yang digunakan dalam menyelesaikan masalah komputasi yang berkaitan dengan prediksi. Fungsi pelatihan yang digunakan pada Machine Learning metoda algoritma backpropagation dapat menghasilkan prediksi yang berbeda, yang dipengaruhi oleh parameter dan data yang digunakan. Tujuan dari penelitian dilakukan untuk menganalisa performance dan keakuratan algoritma backpropagation standard serta mengoptimalkan fungsi pelatihan dengan algoritma Bayesian Regulation, dan One Step Secant. Dalam proses analisis, penelitian ini menggunakan Dataset jumlah kemiskinan di Indonesia dalam jangka waktu 12 tahun (tahun 2009 - 2020) yang terdiri dari 34 provinsi. Data diperoleh dari website Badan Pusat Statistik (BPS) Indonesia https://www.bps.go.id/. Berdasarkan pelatihan, pengujian, dan analisa yang dilakukan diperoleh hasil dari penelitian, bahwa model jaringan 5-9-1 menggunakan fungsi pelatihan Bayesian Regulation mampu melakukan optimasi yang lebih baik dengan percepatan waktu pelatihan, MSE Pengujian, Performance lebih rendah dibandingkan denga 2 metode yang lain, dengan demikian disimpulkan bahwa model jaringan 5-9-1 menggunakan algoritma Bayesian Regulation dapat digunakan untuk prediksi kemiskinan di Indonesia.
Determination of Student Subjects in Higher Education Using Hybrid Data Mining Method with the K-Means Algorithm and FP Growth
Larissa Navia Rani;
Sarjon Defit;
L. J. Muhammad
International Journal of Artificial Intelligence Research Vol 5, No 1 (2021): June 2021
Publisher : STMIK Dharma Wacana
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (379.161 KB)
|
DOI: 10.29099/ijair.v5i1.223
The large number of courses offered in an educational institution raises new problems related to the selection of specialization courses. Students experience difficulties and confusion in determining the course to be taken when compiling the study plan card. The purpose of this study was to cluster student value data. Then the values that have been grouped are seen in the pattern (pattern) of the appearance of the data based on the values they got previously so that students can later use the results of the patterning as a guideline for taking what skill courses in the next semester. The method used in this research is the K-Means and FP-Growth methods. The results of this rule can provide input to students or academic supervisors when compiling student study plan cards. Lecturers and students can analyze the right specialization subject by following the pattern given. This study produces a pattern that shows that the specialization course with the theme of business information systems is more followed by students than the other 2 themes
Prediction of Scholarship Recipients Using Hybrid Data Mining Method with Combination of K-Means and C4.5 Algorithms
Mardison Mardison;
Sarjon Defit;
Shaza Alturky
International Journal of Artificial Intelligence Research Vol 5, No 2 (2021): December 2021
Publisher : STMIK Dharma Wacana
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (408.759 KB)
|
DOI: 10.29099/ijair.v5i2.224
Obtaining a scholarship is the desire of every student or student who studies, especially those who come from poor families. The scholarship can lighten the burden on parents who pay for these students and can streamline the lecture process. However, students do not know exactly what they have to do to get the scholarship. Aside from that, students naturally want to know what causes and conditions have the greatest impact on achievement. The objective of this research is how to predict which number of students among them are predicted to get a scholarship at the opening of the scholarship acceptance using the K-Means and C4.5 methods. Apart from that, the aim of this research is to discover how the K-Means algorithm conducts data clustering (clustering) of student data to determine if they will succeed or not, as well as how the C4.5 algorithm makes predictions against students who have been clustered together. The Rapid Miner program version 9.7.002 was used to process the data in this report. The results of this study were that out of 100 students, 32 students were not scholarship recipients and 68 students were scholarship recipients. Another result of this research is that out of 100 students it is predicted that 9 (9%) will receive scholarships and 91 (91%) will not receive scholarships.
Hybrid Data Mining with the Combination of K-Means Algorithm and C4.5 to Predict Student Achievement
Agung Ramadhanu;
Sarjon Defit;
Shahab Wahhab Kareem
International Journal of Artificial Intelligence Research Vol 5, No 2 (2021): December 2021
Publisher : STMIK Dharma Wacana
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (480.052 KB)
|
DOI: 10.29099/ijair.v6i1.225
Getting academic achievement is the dream of every student who studies at higher education, especially undergraduate level. Undergraduate students aspire to the highest achievement (champion) at the last achievement of their studies. However, students cannot predict whether these students with the habits that have been done and the current conditions will make them excel or not. Apart from that, of course, students also want to know what factors and conditions influence the achievement the most. The objective to be achieved in this research is how to predict which number of students among them are predicted to excel (champion) at the end of the semester with a combination of the K-Means and C4.5 methods. Besides, the purpose of this study reveals how the K-Means algorithm performs data clustering of student data who will excel or not and how the C4.5 algorithm predicts students who have been grouped. Data processing in this study uses the Rapid Miner software version 9.7.002. The result of this research is that it is easier to group data in numerical form than data in polynomial form. Other results in this study were that out of 100 students, 27 students (27%) were predicted to excel (champions) and 73 (73%) did not achieve (not champions).