Article Per Year (5 Year)
p-Index From 2020 - 2025
1.857
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi JOIV : International Journal on Informatics Visualization Jurnal Mantik Penusa JURIKOM (Jurnal Riset Komputer) Jurnal ICT : Information Communication & Technology Madani : Indonesian Journal of Civil Society Journal of Systems Engineering and Information Technology SmartComp
Rumini Rumini
Universitas AMIKOM Yogyakarta
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
KLASIFIKASI PEMINJAMAN BUKU MENGGUNAKAN NEURAL NETWORK BACKPROPAGATION Norhikmah Norhikmah; Rumini Rumini
Sistemasi: Jurnal Sistem Informasi Vol 9, No 1 (2020): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1142.68 KB) | DOI: 10.32520/stmsi.v9i1.562

Abstract

Peminjaman buku merupakan salah satu wujud pelayanan yang diberikan oleh perpustakaan. Peminjaman sangat erat kaitannya dengan persediaan. Pada perpustakaan A dalam menentukan persediaan buku, pegawai perpustakaan kesulitan untuk menentukan jenis-jenis buku apa saja yang sangat dibutuhkan mahasiswa. Dimana penentuan jumlah dan jenis buku belum menggunakan  sistem perhitungan yang pasti, hanya berdasarkan perkiraan jumlah mahasiswa dan matakuliah setiap program studi. Maka dari itu dibutuhkan klasifikasi peminjaman jenis buku berdasarkan transaksi peminjaman buku mahasiswa, data yang digunakan dalam penelitian ini yang sebanyak 269.116 dari tahun 2014 sampai 2019 bulan ke 6. Data jenis buku yang diolah sebanyak 184 jenis buku dari 1700 jenis buku, tahapan pertama yang dilakukan melakukan teknik forecasting untuk meramalkan target persediaan setiap jenis buku pada tahun selanjutya, tahapan kedua data transaksi peminjaman buku diproses untuk mengetahui klasifikasi jenis buku dengan menggunakan neural network backpropagation. Didapatkan hasil tingkat error atau MSE sebesar 0,021, menggunakan layer hidden 9 dan fungsi aktivasi tansiq dengan epoch 2000, dengan rekomendasi jumlah jenis buku yang disarankan untuk restock sebanyak 86 jenis buku dengan jumlah prediksi disetiap jenis buku. Tahapan ketiga  melakukan pengujian  validasi data untuk mengetahui tingkat error klasifikasi dan prediksi, terakhir dilakukan uji regresi menunjukan hasil hubungan yang siqnifikan sebesar 0,006 dengan data variabel yang dujikan yaitu  data prediksi, klasifikasi dan target.. Hasil dari penelitian ini adalah dapat memberikan data rekomendasi jenis buku beserta jumlah prediksi di setiap jenis buku yang dibutuhkan ditahun yang akan datang dengan menggunakan metode neural network backpropagation  dengan tingkat akurasi sebesar 95,5%.
PERBANDINGAN METODE ARIMA DAN EXPONENTIAL SMOOTHING HOLT-WINTERS UNTUK PERAMALAN DATA KUNJUNGAN Rumini Rumini; Norhikmah Norhikmah
Sistemasi: Jurnal Sistem Informasi Vol 9, No 3 (2020): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1551.557 KB) | DOI: 10.32520/stmsi.v9i3.975

Abstract

ABSTRACTA visit to the creative economy park is a place designed using strategic objectives in collaborating technology capabilities, transferring information and knowledge, planting innovative high-tech companies and entrepreneurs, bringing up new technology industries in the creative economy business to drive economic development. Universitas AMIKOM Yogyakarta has been declared a creative economy park and is known as the Amikom Creative Economy Park (ACEP). ACEP includes several multimedia environments for targeting businesses, for example software development, film, television, games, radio, animation, advertising, investment advisory, and project design. The development of the number of visitors from year to year, predictions need to be made to support the planning and preparation process in receiving visits. The data used in this study are visitor data from January 2019 to December 2019. Analysis of visit prediction data using data mining is the Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing methods. The research resulted from prediction of the number of visit data for 2020 is more accurate using the Holt-Winters exponential smoothing method with a MAPE value of 47,197 when compared to the ARIMA method with a MAPE value of 48,949 so that the MAPE value generated by the ARIMA method is smaller than the Holt-Winters exponential smoothing method. The results of this study are to provide input in the form of predictions of the number of ACEP visitors in the coming year.Keywords: ARIMA, data mining, exponential smoothing, prediction, visitABSTRAKKunjungan di taman ekonomi kreatif adalah meruapakan tempat yang dirancang dengan menggunakan tujuan strategis dalam mengkolaborasikan kemampuan teknologi, transfer informasi dan pengetahuan, penanaman perusahaan teknologi tinggi yang inovatif dan wirausaha, memunculkan industri teknologi baru dalam bisnis ekonomi kreatif untuk mendorong perkembangan ekonomi. Universitas Amikom Yogyakarta telah dinyatakan sebagai taman ekonomi kreatif dan dikenal sebagai Taman Ekonomi Kreatif Amikom (ACEP). ACEP mencakup beberapa lingkungan multimedia untuk membidik bisnis, misalnya pengembangan perangkat lunak, film, televisi, game, radio, animasi, iklan, penasehat investasi, dan desain proyek. Perkembangan jumlah pengunjung dari tahun ke tahun, perlu dilakukan peramalan untuk mendukung proses perencanaan dan persiapan dalam menerima kunjungan. Data yang digunakan dalam penelitian adalah data pengunjung pada Januari 2019 sampai Desember 2019. Analisis data peramalan kunjungan menggunakan data mining yaitu dengan metode Autoregressive Integrated Moving Average (ARIMA) dan Exponential Smoothing. Penelitian yang dihasilkan dari peramalan jumlah data kunjungan untuk tahun 2020 lebih akurat menggunakan metode exponential smoothing Holt-Winters dengan nilai MAPE 47,197 jika dibandingkan metode ARIMA dengan nilai MAPE 48,949 sehingga nilai MAPE yang dihasilkan metode ARIMA lebih kecil dari metode exponential smoothing Holt-Winters. Hasil dari penelitian ini adalah memberikan masukan berupa peramalan jumlah pengunjung ACEP ditahun yang akan datang.Kata Kunci: ARIMA, data mining, exponential smoothing, peramalan, kunjungan
PREDIKSI KEGAGALAN SISWA DALAM DATA MINING DENGAN MENGGUNAKAN METODE NAÏVE BAYES Rumini Rumini; Norhikmah Norhikmah
Jurnal Mantik Penusa Vol. 3 No. 1.1 (19): Manajemen dan Ilmu Komputer
Publisher : Lembaga Penelitian dan Pengabdian (LPPM) STMIK Pelita Nusantara Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (158.985 KB)

Abstract

In an effort to improve the quality of a nation, there is no other way except through improving the quality of education. The success and failure of students' classes in the study determined many factors that influence it. The results of this study are using the naïve bayes data mining method which is used to predict student failures in their studies as well as influential factors including failure, traveltime, internet, romantic, freetime, go-out, health, and absence. Naïve Bayes algorithm is an algorithm that can be used to predict using probability theory with a high degree of accuracy. Naïve Bayes algorithm testing uses WEKA tool which produces an accuracy of 77.22 from 395 datasets. This algorithm is used to predict student class failures
Implementasi Algoritma Greedy Pada Game Pacman Pamela Hapsari Putri; Muhammad Ridlo Arifandi; Edy Hardianto Rifeni; Fakhrur Wiradhika; Rumini Rumini; Anggit Dwi Hartanto
JURIKOM (Jurnal Riset Komputer) Vol 5, No 6 (2018): Desember 2018
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (208.124 KB) | DOI: 10.30865/jurikom.v5i6.1001

Abstract

Pacman is an arcade game developed by Namco and released in Japan on May 22, 1980. Pac-Man, which is still popular today, has also been released on other platforms such as Game Boy and SNES. The designer of this game is Toru Iwatani, who is a Namco employee. The concept of the game in the Pacman game is very simple: Players must control the Pacman character to eat all the small dots and other special objects that are in the maze without being caught by 4 ghosts. The greedy algorithm is used to find the current shortest path from the position of the ghost character to the position of the Pacman character.
IMPLEMENTASI ALGORITMA BREADTH FIRST SEARCH PADA PACMAN UNTUK MENGATUR PERGERAKAN KARAKTERImplementasi Algoritma Breadth First Search Pada Pacman Untuk Mengatur Pergerakan Karakter Ulza Alkindi; Nur Akhmad; Yogo Kartiko; Triono Putro; Rumini Rumini
JURIKOM (Jurnal Riset Komputer) Vol 5, No 6 (2018): Desember 2018
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v5i6.1004

Abstract

Artificial intelligence is an important factor in games between humans against computers (NPC = Non-Character Player). One method of artificial intelligence that can be used is the Breadth First Search (BFS) algorithm and fuzzy logic. This study chose the classic Pac-Man game, in the game the Pac-Man BFS algorithm was applied to the process of finding and pursuing Pac-Man. For fuzzy logic, the Sugeno method is used when making decisions, namely ghost behavior in the game. The methodology used is the prototype methodology. In the testing process, the BFS algorithm is used in the black box testing technique, while the Sugeno fuzzy logic method is used to compare computation testing during decision making. With the testing process, it can be drawn that the appropriate BFS algorithm to find the shortest path while pursuing Pac-Man and Sugeno Fuzzy Logic method can be used for ghost behavior decision making with search speed 10 times faster than DFS algorithm.
Study Program Selection Using the Fp-Growth and J48 Algorithm Nor Hikmah; Rumini .
Jurnal ICT : Information Communication & Technology Vol 21, No 1 (2022): JICT-IKMI, Juli 2022
Publisher : STMIK IKMI Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36054/jict-ikmi.v21i1.423

Abstract

The study program is an absolute thing and must be chosen by prospective new students when registering to become a student, the lack of knowledge of the courses offered by the campus becomes a difficulty in determining study programs that match their interests. The first research method of analyzing data uses the association rule to get the relationship of study programs with other study programs, and subsequently classifies the study program using decision tree j48, and is followed by examiners using confusion matrux. The results of this study are to use the association rule Fp-Growth method obtained 10 best rules, namely for the first rule D3 Informatics with International Relations. Of the 10 rules obtained as a reference or basis for determining classes on the j48 algorithm, from the results of the 10 rules, analyzed according to the rules applied in Amikom, then obtained into 11 classes where the rules are based on the origin of natural science or social studies schools. By using the j48 algorithm, 99.8% accuracy is obtained with the highest hierarchy in the decision tree, namely the D3 Informatics study program and for the origin school, namely IPS high school
Evaluasi System Usability Scale Pada Sistem Presensi Pengunjung Resource Center Rumini Rumini; Norhikmah Norhikmah
JURIKOM (Jurnal Riset Komputer) Vol 9, No 4 (2022): Agustus 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v9i4.4721

Abstract

Resource center (RC) or can be called also in this case is a library. The library is a place to study or to access information. The RC system of Amikom Yogyakarta University has attendance services for visitors from the user side, namely internal students and external visitors and stores visitor data to find out how many people visit the library, both internal and external visitors. Usability problems that usually appear in system features for users, indicate the need for usability testing. Usability testing uses the SUS (System Usability Scale) method in order to find problems with the visitor attendance system by referring to usability principles, which can involve users. This research was conducted in 3 main stages, namely compiling a questionnaire in accordance with the provisions of the SUS method, processing the results of the respondents' answers from those distributed to visitors by the SUS method rules to obtaining test results in the form of SUS scores. Based on the results of the evaluation carried out, the average SUS score from the study was 55.56, which means it has a D rating (less) which indicates that the presence system visitor feature cannot be accepted by users from the usability aspect, it is still minimal in use, because it only stores visitor data, the recommendations given from the results of this evaluation in order to increase usability for visitor features are such as visitor entry hours, exit hours, input facilities in the form of input related to collections of books, journals, magazines, e-books, facilities inside, room atmosphere, and others, because things like this affect the optimal library services for visitors.
The Effect of Layer Batch Normalization and Droupout of CNN model Performance on Facial Expression Classification - Norhikmah; Afdhal Lutfhi; - Rumini
JOIV : International Journal on Informatics Visualization Vol 6, No 2-2 (2022): A New Frontier in Informatics
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.2-2.921

Abstract

One of the implementations of face recognition is facial expression recognition in which a machine can recognize facial expression patterns from the observed data. This study used two models of convolutional neural network, model A and model B. The first model A was without batch normalization and dropout layers, while the second model B used batch normalization and dropout layers. It used an arrangement of 4 layer models with activation of ReLU and Softmax layers as well as 2 fully connected layers for 5 different classes of facial expressions of angry, happy, normal, sad, and shock faces. Research Metodology are 1). Data Analysis, 2). Preprocessing grayscaling, 3). Convolutional Neural Network (CNN), 4). Model validation Testing, Obtained an accuracy of 64.8% for training data and accuracy of 63.3% for validation data. The use of dropout layers and batch normalization could maintain the stability of both training data and validation data so that there was no overfitting. By dividing the batch size on the training data into 50% with 200 iterations, aiming to make the load on each training model lighter, by using the learning rate to be 0.001 which works to improve the weight value, thus making the training model work to be fast without crossing the minimum error limit. Accuracy results in the classification of ekp facial receipts from the distance of the camera to the face object about 30 cm in the room with the use of bright enough lighting by 78%.
Klasifikasi dan Pengaruh Trending Youtube Menggunakan Algoritma Neural Network dan Regresi Linear Norhikmah; Rumini .
Jurnal ICT: Information Communication & Technology Vol. 22 No. 2 (2022): JICT-IKMI, December 2022
Publisher : LPPM STMIK IKMI Cirebon

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

Abstract

The development of social media is very influential which includes Facebook, Instagram, Twitter, YouTube and others. One of them is the social media YouTube which has a very important role for the public and community leaders. Youtube provides very interesting content for those who have channels and those who do not. Trending or not a YouTube channel based on likes, dislikes, comments, and video views. Trending data from YouTube can be processed data. The data processing technique that can be used in the process is classification. Classification is a data processing technique that divides objects into classes. Using the backpropagation neural network algorithm in the classification process, which can determine Youtube trending with a very good and quite good ratio. a dataset of 40,880 obtained the best modeling obtained in neuron 10, layer 4, epoch 2000, with an MSE value of 0.03 and 87% validation, with a duration of 24 seconds, followed by a multiple linear regression test which resulted in the equation Y=0.788 + 4.914X1 + 9.458X2 - 1.977X3 - 4.418X4 + e where the more views and likes, the more trending youtube is, and the more dislikes and comments, the trending status of youtube decreases with a significance value of 0.000 which means it has a very significant relationship or at a strong level.
Application of Data Mining for Visit Prediction at Amikom Creative Economy Park Rumini; Norhikmah
Journal of Systems Engineering and Information Technology (JOSEIT) Vol 1 No 2 (2022): September 2022
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (397.991 KB) | DOI: 10.29207/joseit.v1i2.4941

Abstract

A creative economy park is a place designed with strategic goals for technology skills collaboration, information and knowledge transfer, creation of innovative high-tech enterprises and entrepreneurs, introduction of new technology industries in creative economy enterprises to promote economic development. Yogyakarta Amikom University has been declared a Creative Economy Park and is known as Amikom Creative Economy Park (ACEP). ACEP includes multiple multimedia environments for targeting businesses such as software development, film, television, games, radio, animation, advertising, investment consulting, and project design. Every year, the number of institutions visiting Amikom Yogyakarta University carries the slogan Amikom Creative Economy Park with a fairly busy program of visits. The agenda for accepting this visit was carried out by Amikom's Public Relations Department (DKUI, Directorate of Public Relations and International Affairs). The evolution of visitor numbers from year to year, forecasts must be made to support the planning and preparation process when receiving visits. This research will discuss the trend of visitors having a comparative study in Amikom Creative Economy Park in the future. The data used in this study is visitor data from January 2019 to December 2019. This predictive data analysis uses the Autoregressive Integrated Moving Average (ARIMA) method and Exponential Smoothing as a comparison for the accuracy of the prediction. With the forecast of this visit, the planning and preparation for the Directorate of Public Relations and International Affairs and for the University AMIKOM Yogyakarta is to be done.
Co-Authors - Norhikmah Acihmah Sidauruk Afdhal Lutfhi Ali Mustofa Anggit Dwi Hartanto Devi Wulandari Edy Hardianto Rifeni Fakhrur Wiradhika Galih Purnomo Muhammad Ridlo Arifandi Nor Hikmah Norhikmah Norhikmah Norhikmah Norhikmah Norhikmah Nur Akhmad Pamela Hapsari Putri Sulistyo Pradana Tri Susanto Triono Putro Ulza Alkindi Wiji Nurastuti Yogo Kartiko