p-Index From 2020 - 2025
5.214
P-Index
Claim Missing Document
Check
Articles

Found 38 Documents
Search

Sistem Pakar Diagnosa Error Sistem Pada “PT. Danaco Global Solusi – OXY System” Menggunakan Metode Certainty Factor Berbasis Web Ginantra, Ni Luh Wiwik Sri Rahayu; Sandi, Victor Ari
SINTECH (Science and Information Technology) Journal Vol 1 No 1 (2018): SINTECH Journal Edisi April 2018
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1330.137 KB) | DOI: 10.31598/sintechjournal.v1i1.227

Abstract

In building a system can’t be separated from an error where for a company that works in Building a software this will be very dangerous if not quickly Handled, certainly beside with quickly also need to be handled accurately. Expert systems can be a solution where the expert system is capable of recording a person's ability to think or reason. Thought or reasoning of an expert will be used to diagnose from some of the symptoms that exist to conclude error with expert's specified weight while the belief to symptoms that are not certain will be determined by the user and determined using Certainty Factor method that can calculate the value of uncertainty so that error fixed can be concluded. The results of the implementation is 2 diagnosis with the highest level of confidence and the step to handling. Other results is the system accuracy by performing a comparison between the results of the diagnosis system to the actual event so that the accuracy is 91.667%
Analysis of ANN Backpropagation Ability to Predict Expenditure Group Inflation Mhd Ali Hanafiah; Ni Luh Wiwik Sri Rahayu Ginantra; Achmad Daengs GS
IJISTECH (International Journal of Information System and Technology) Vol 4, No 2 (2021): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v4i2.103

Abstract

The Covid-19 pandemic that has hit the world, especially Indonesia, has greatly disturbed the stability of the inflation rate. Inflation that continues to increase will disrupt the economy in this country. Therefore this study aims to analyze the ability of ANN backpropagation which will be applied to predict the development of the inflation in Indonesia during the Covid-19 pandemic so that later it can be useful information for the government and society. The research data used is inflation data according to expenditure groups obtained from CBS (Central Statistics Agency) in January-May 2020. Prediction is done using the backpropagation neural network algorithm. This paper uses four network architectures, namely: 3-5-1, 3-10-1, 3-25-1 and 3-50-1. Based on the training and testing of the four models, the 3-10-1 model is the best architectural model that is suitable for predicting the development of the inflation in Indonesia with an accuracy of 75%. Also, this model performs an iteration of 25303 and an MSE test of 0.0362820326. Based on the prediction results in June-August 2020 and real data obtained from the Central Statistics Agency, ANN using the backpropagation method is highly recommended to be used to predict the development of Indonesian Inflation according to the Expenditure Group.
Deteksi Batik Parang Menggunakan Fitur Co-Occurence Matrix Dan Geometric Moment Invariant Dengan Klasifikasi KNN Ni Luh Wiwik Sri Rahayu Ginantra
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 7, No. 1 April 2016
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (528.312 KB) | DOI: 10.24843/LKJITI.2016.v07.i01.p05

Abstract

Batik motifs are the base or the blueprint of batik patterns which serve as the core of the batik image design, and therefore the meaning of a sign, symbol or logo in a batik work can be revealed through its motifs. Visual identification requires visual skills and knowledge in classifying patterns formed in a batik image. Lack of media providing information on batik motifs makes the public unable to have sufficient information about batik motifs. Looking at this phenomenon, this study is conducted in order to perform visual identification using a computer that can assist and facilitate in identifying the types of batik. The methods used for batik image recognition are the Co-occurrence Matrix method to provide extraction of batik texture features, and the Geometric Moment Invariant method, while K Nearest Neighbor is used to classify batik images. The results on the accuracy values obtained reveal that the of 80%, compared to the accuracy value result using the Co-occurrence Matrix method that is 70%.
Sistem Pakar Diagnosa Error Sistem Pada “PT. Danaco Global Solusi – OXY System” Menggunakan Metode Certainty Factor Berbasis Web Ni Luh Wiwik Sri Rahayu Ginantra; Victor Ari Sandi
SINTECH (Science and Information Technology) Journal Vol. 1 No. 1 (2018): SINTECH Journal Edition April 2018
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v1i1.227

Abstract

In building a system can’t be separated from an error where for a company that works in Building a software this will be very dangerous if not quickly Handled, certainly beside with quickly also need to be handled accurately. Expert systems can be a solution where the expert system is capable of recording a person's ability to think or reason. Thought or reasoning of an expert will be used to diagnose from some of the symptoms that exist to conclude error with expert's specified weight while the belief to symptoms that are not certain will be determined by the user and determined using Certainty Factor method that can calculate the value of uncertainty so that error fixed can be concluded. The results of the implementation is 2 diagnosis with the highest level of confidence and the step to handling. Other results is the system accuracy by performing a comparison between the results of the diagnosis system to the actual event so that the accuracy is 91.667%
Pelatihan Aplikasi Mendeley untuk Referensi dalam Menulis Karya Ilmiah Bagi Guru SMK Dwijendra Denpasar Ni Wayan Wardani; Ni Luh Wiwik Sri Rahayu Ginantra
JURPIKAT (Jurnal Pengabdian Kepada Masyarakat) Vol 1 No 1 (2020)
Publisher : Politeknik Piksi Ganesha Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37339/jurpikat.v1i1.279

Abstract

Guru saat ini dituntut untuk menjadi guru yang professional. Disamping menjalankan tugas pokoknya, seorang guru dituntut untuk memiliki ketrampilan menulis karya ilmiah sebagai salah satu syarat kenaikan pangkat. Akan tetapi pada kenyataannya masih banyak guru yang memiliki ketrampilan yang minim dalam menulis karya ilmiah. Salah satu ketrampilan yang masih jarang mereka miliki adalah ketrampilan dalam membuat daftar pustaka dan sitasi. Kegiatan pengabdian ini bertujuan untuk memberikan pelatihan penggunaan software Mendeley untuk referensi dalam menulis karya ilmiah di SMK Dwijendra Denpasar. Metoda yang digunakan pada kegiatan pengabdian ini adalah ceramah, diskusi, tanya jawab, pendampingan selama pelatihan dan praktek langsung menggunakan software Mendeley. Hasil dari kegiatan pengabdian ini menunjukkan bahwa peserta memiliki pemahaman materi dan kemampuan untuk membuat referensi dengan baik dengan bantuan software Mendeley
Pelatihan Penggunaan Sosial Media Pada Usaha Pande Besi di Desa Kedisan–Gianyar Ni Kadek Nita Noviani Pande; Christina Purnama Yanti; Komang Redy Winatha; Ni Luh Wiwik Sri Rahayu Ginantra
JPM: Jurnal Pengabdian Masyarakat Vol. 1 No. 2 (2020): Nopember 2020
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Balinese handicrafts are also a worldwide attraction. For example, handicrafts from wood carvings, paintings, endek fabrics, keris, gamelan, copper, gold, silver, and many more. Keris and gambelan in Bali are generally made by the Pande people or you can say Soroh Pande and the manufacturing process is done in a Prapen. Prapen is always identified with cheer pande, apart from being a place for people to do their swadharma, namely memande. Prapen itself is very important for the Pande people not only as their identity as a Pande but also as a livelihood for Pande residents to work which has been passed down by their ancestors from generation to generation. In Kedisan Kaja Village, Tegalalang District, Gianyar Regency, there is a Small and Medium Enterprise (UKM) group that is engaged in memande. The business that has been going on for years only uses a pre-order system (making when there is an order). Based on the results of the interview, the main problems experienced by the partners, namely (1) their knowledge of product marketing is still very limited, and (2) they do not have a storage place for memande completeness. The purpose of this PKM is to increase the understanding and skills of partners in the form of product marketing techniques. The method used in achieving this goal is the use of technology by holding training on the use of Instagram and Facebook social media to improve marketing so that craftsmen can market their handicrafts on social media independently and be able to increase sales
IMPLEMENTASI METODA NAÏVE BAYES DAN VECTOR SPACE MODEL DALAM DETEKSI KESAMAAN ARTIKEL JURNAL BERBAHASA INDONESIA Ni Luh Wiwik Sri Rahayu Ginantra; Ni Wayan Wardani
Jurnal Infomedia:Teknik Informatika, Multimedia & Jaringan Vol 4, No 2 (2019): Jurnal Infomedia
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (752.293 KB) | DOI: 10.30811/jim.v4i2.1530

Abstract

Salah satu cara untuk menjaga kualitas karya ilmiah di Indonesia adalah dengan memeriksa artikel sebelum dipublikasikan. Pengecekan sebelum publikasi dilakukan agar tingkat kesamaan tidak tinggi karena makalah yang diterbitkan dapat dikutip untuk menyebabkan tingkat kesamaan yang tinggi. Masalah selanjutnya adalah pentingnya pengelompokkan makalah topik, dimana makalah yang akan diperiksa harus memiliki kategori yang sama dengan makalah yang dibandingkan. Dalam penelitian ini, untuk mengklasifikasikan topik jurnal menggunakan algoritma Naive Bayes dan untuk mengukur kesamaan makalah menggunakan metoda Vector Space Model. Algoritma Naive Bayes tidak dapat mengklasifikasikan ke dalam satu topik jurnal dengan tepat tetapi mengklasifikasikan menjadi beberapa topik jurnal sehingga mempengaruhi kinerja metoda Vector Space Model. Hasil perhitungan deteksi kesamaan teks oleh Vector Space Model dapat mencapai 90% ke atas untuk data uji tertentu. Hasil perhitungan deteksi kesamaan teks dengan metoda Vector Space Model juga sangat dipengaruhi oleh data pelatihan. Semakin lengkap dan kompleks data pelatihan, maka semakin valid hasil pengujian kinerja Vector Space Model
Penerapan Apriori Hybrid Pada Transaksi Penjualan Barang I Made Dwi Putra Asana; Ni Luh Wiwik Sri Rahayu Ginantra; Wayan Gede Suka Parwita; Ni Kadek Bumi Krismentari; Ni Putu Suci Meinarni
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 4 (2021): Oktober 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i4.3350

Abstract

Ayu Nadi Swalayan is a retail company that produces a lot of every day sales transaction data, and it is stored for years without knowing the benefits and the placement of the goods is still random. From these problems, an effort is needed to process the data so the data is useful in the future. One of the process is using data mining techniques with apriori hybrid algorithm to find association rules for an items combination. Data product sale in a certain period is used to find the association rules. The results of this study are the development of applications that are used to determine consumer spending habits. So that the company can develop a strategy to promote the product sale and close placement for items that are often purchased together. The application testing found the effect of minimum support, minimum confidence on the number of rules, and lift ratio testing. The smaller the minimum support and minimum confidence, the more rules are generated and vice versa. The lift ratio value is directly proportional to the minimum confidence value and inversely proportional to the minimum support value. The higher the minimum confidence value, the higher the lift ratio value and vice versa. The more items in the transaction cause the minimum support threshold to be lowered in order to generate rules for the data analysis process with the hybrid apriori algorithm
IMPLEMENTASI ALGORITMA GENETIKA BERBASIS WEB PADA SISTEM PENJADWALAN MENGAJAR DI SMK DWIJENDRA DENPASAR Ni Luh Wiwik Sri Rahayu Ginantra; Ida Bagus Gede Anandita
Jurnal Teknologi Informasi dan Komputer Vol 5, No 1 (2019): Jurnal Teknologi Informasi dan Komputer
Publisher : LPPM Universitas Dhyana Pura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (721.327 KB)

Abstract

ABSTRACTIntelligence from a computer that can mimic the human work system is commonly referred to as artificial intelligence which can solve problems (problem solving) that are complicated and sometimes humans themselves cannot solve them, as in the process of scheduling subjects. The preparation of scheduling school subjects is prepared by considering several components including; Teachers, time, majors, levels, and subjects themselves. Based on these problems the researchers conducted a study of scheduling school subjects with the method of Genetic Algorithm and took a case study at one of the private vocational high schools in Denpasar, namely SMK Dwijendra Denpasar. Based on the results of the design and discussion that have been conducted, scheduling teaching with Genetic Algorithms with case studies at Dwijendra Vocational School can be done by using subject data and teachers from the Vocational School and producing teaching schedules for teachers at the school so that there is no schedule clash. The results of testing carried out in this study are by testing measurements of population size and size of generations. The test was carried out by using a population size and generation of 150 with a crossover rate (cr) of 50%. The test results show that in a small population and generation produce a variety of fitness values. Good fitness values are generated in populations and generations above 50.Keywords: Genetic Algorithms, Scheduling, Lesson Type.ABSTRAKKecerdasan dari komputer yang dapat meniru system kerja manusia biasa disebut dengan istilah kecerdasan buatan (artificial intelegence) yang dapat memecahkan masalah (problem solving) yang rumit dan kadang manusia sendiri tidak dapat menyelesaikannya, seperti dalam proses penjadwalan mata pelajaran. Penyusunan penjadwalan mata pelajaran sekolah disusun dengan mempertimbangkan beberapa komponen diantaranya ; Guru, waktu, jurusan, jenjang, dan mata pelajaran itu sendiri. Berdasarkan permasalahan tersebut peneliti melakukan penelitian tentang penjadwalan mata pelajaran sekolah dengan metode Algoritma Genetika dan mengambil studi kasus pada salah satu sekolah menengah kejuruan (SMK) swasta di Denpasar yaitu SMK Dwijendra Denpasar. Berdasarkan hasil perancangan dan pembahasan yang telah dilakukan, penjadwalan mengajar dengan algoritma Genetika dengan studi kasus di SMK Dwijendra dapat dilakukan dengan menggunakan data mata pelajaran dan guru dari SMK tersebut dan menghasilkan jadwal mengajar bagi guru di sekolah tersebut sehingga tidak terjadinya bentrokan jadwal. Hasil pengujian yang dilakukan pada penelitian ini yaitu dengan pengujian pengukuran ukuran populasi dan ukuran ukuran generasi. Pada pengujian tersebut dilakukan dengan menggunakan ukurun populasi dan generasi sebanyak 150 dengan crossover rate (cr) 50%. Hasil pengujian menunjukan bahwa pada populasi dan generasi sedikit menghasilkan nilai fitness yang beragam. Nilai fitness yang baik dihasilkan pada populasi dan generasi diatas 50.Kata Kunci : Algoritma Genetika, Penjadwalan, Mata Pelajaran
Analysis of ANN Backpropagation Ability to Predict Expenditure Group Inflation Mhd Ali Hanafiah; Ni Luh Wiwik Sri Rahayu Ginantra; Achmad Daengs GS
IJISTECH (International Journal of Information System and Technology) Vol 4, No 2 (2021): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (599.249 KB) | DOI: 10.30645/ijistech.v4i2.103

Abstract

The Covid-19 pandemic that has hit the world, especially Indonesia, has greatly disturbed the stability of the inflation rate. Inflation that continues to increase will disrupt the economy in this country. Therefore this study aims to analyze the ability of ANN backpropagation which will be applied to predict the development of the inflation in Indonesia during the Covid-19 pandemic so that later it can be useful information for the government and society. The research data used is inflation data according to expenditure groups obtained from CBS (Central Statistics Agency) in January-May 2020. Prediction is done using the backpropagation neural network algorithm. This paper uses four network architectures, namely: 3-5-1, 3-10-1, 3-25-1 and 3-50-1. Based on the training and testing of the four models, the 3-10-1 model is the best architectural model that is suitable for predicting the development of the inflation in Indonesia with an accuracy of 75%. Also, this model performs an iteration of 25303 and an MSE test of 0.0362820326. Based on the prediction results in June-August 2020 and real data obtained from the Central Statistics Agency, ANN using the backpropagation method is highly recommended to be used to predict the development of Indonesian Inflation according to the Expenditure Group.