Garuda - Garba Rujukan Digital

Kriptanalisis Algoritma Vigenere Chiper dengan Algoritma Genetika untuk Penentuan Kata Kunci Tsuraya Ats Tsauri; Nurochman Nurochman
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 2 No. 2 (2017): September 2017
Publisher : UIN Sunan Kalijaga Yogyakarta

Cryptanalysis is the art to solve without key ciphers, in contrast to cryptography, namely to maintain the confidentiality of data by encode a plaintext. Vigenere ciphers is one of the kriptanalisis algorithm. Brute force attack and exhaustive attack is a technique of kriptanalisis vigenere ciphers, but less optimal in result. In my research this time proposed a way of solving the secret key (Cryptanalysis), using a genetic algorithm on text Indonesia-speaking ciphers. .The first step in this study performed a chromosome design would be the length of the keyword, the method used is the coincidence index (IOC), the IOC values with text Indonesian is 0,075. To get the value of fitness done the search weights by comparison Word decryption of keywords with Indonesian Language Dictionary. Genetic algorithms will seek all possible keywords, there are genetic algorithms in the process of reproduction includes crossover, mutation and elitisme. There are parameters that are included in the process of a keyword search that is the value of the probability of crossover, mutation probability and population, number of the parameter that you want to optimize to get keywordsThis analysis is performed on the five scenarios with any combination of parameters, number of characters chipertext and two types of different keywords. After 1000 times testing with a combination of parameters generated 467 the data successfully guessing keywords within approximately 60 minutes. With the testing of two different keywords and two different ciphers text amount done by as much as five times the test showed that both have the value of the average test time the fastest standard deviation value. After an analysis of the results of the research, the optimal parameters is obtained with a value Pc 0.09, Pm 0.3 and Pop_size 20.Keywords : Cryptanalysis, Genetic Algorithm, Vigenere Chiper, Index Coincidence.

Aplikasi Metode Simple Additive Weighting (SAW) Dalam Pengembangan Sistem Pencarian Toko Batik Berbasis Android Hafid Iqbalgis; Nurochman Nurochman
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 4 No. 2 (2019): September 2019
Publisher : UIN Sunan Kalijaga Yogyakarta

Informasi merupakan hal yang sangat diperlukan pada saat ini. Salah satu bentuk informasi adalah simbol informasi publik. Peneliti melakukan penilitian untuk mencari toko batik dengan menggunakan metode Simple Additive Weighting dengan menggunakan berbagai kriteria. Penelitian yang akan dilakukan adalah membuat suatu sistem pendukung keputusan untuk memilih toko batik dengan menggunakan metode Simple Additive Weighting. Dalam perhitungannya, kriteria yang dipertimbangkan adalah jarak, harga, produk, kemudahan transportasi, kenyamann, kebersihan dan keamanan toko. Hasil penelitian ini menunjukkan bahwa sistem yang dibangun mampu memberikan rekomendasi toko batik sesuai dengan kriteria yang inginkan.Kata Kunci : Android, Sistem Pendukung Keputusan, Simple Additive Weighting, Extreme Programming.

Perbandingan SVM dan LSTM Untuk Memprediksi Gangguan Kecemasan (Anxiety Disorder) Berdasarkan Cuitan di Platform Aplikasi X (Twitter) Nurochman Nurochman; Luthfia Ashiilah
JURNAL TEKNIK KOMPUTER AMIK BSI Vol 10, No 2 (2024): Periode Juli 2024
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/jtk.v10i2.23112

Anxiety disorder adalah gangguan kecemasan yang menyerang kesehatan mental seseorang sehingga bisa mengganggu aktivitas. Pengaruh media sosial menjadi salah satu adanya pemicu gangguan kecemasan, dimana media sosial dijadikan objek untuk meluapkan perasaan yang dialami pengguna, contohnya Twitter atau aplikasi X. Penelitian ini dilakukan untuk memprediksi adanya anxiety disorder pada pengguna Twitter dilihat berdasarkan cuitan yang ada dengan menggunakan dua model, yaitu Support Vector Machine (SVM) dan Long Short-Term Memory (LSTM) sehingga bisa dibandingkan mana yang lebih baik diantara dua metode tersebut. Data yang digunakan merupakan data hasil dari crawling yang kemudian dilakukan beberapa pemrosesan sehingga bisa diolah sesuai dengan medel yang ada. Hasil dari penelitian ini menunjukkan bahwa untuk memprediksi anxiety disorder menggunakan Long Short-Term Memory (LSTM) lebih unggul daripada Support Vector Machine (SVM) dari 3 matriks perhitungan yang ada, yaitu precision, recall, dan f1-score dengan nilai 75%. Sedangkan, untuk metode Support Vector Machine (SVM) hanya unggul dalam perhitungan nilai akurasi, yaitu 81%.

Performance Evaluation of Long Short-Term Memory for Chili Price Prediction Fikri, Fata Nabil; Nurochman, Nurochman
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 10 No. 1 (2025): January 2025
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.2025.10.1.33-47

Grocery prices often experience fluctuations in several regions of Indonesia, such as East Java Province. One of the commodities affected is chili, including both red chilies and bird’s eye chilies. Predictive steps that utilise machine learning, such as Long Short-Term Memory (LSTM), can be taken to estimate the next price of chili, with the expectation that the authorities can implement the appropriate strategy. LSTM is a network that was developed from RNN networks in previous times by offering a longer cell memory, allowing for the storage of more information. This research focuses on determining whether the LSTM network can be applied to the task of chili price prediction and identifying the suitable architecture and hyperparameter configuration for this case. For this reason, the experimental method is employed by testing several predetermined variables to determine the optimal architecture and hyperparameter configuration. The results of this research demonstrate that the LSTM network can be effectively applied in this case, and the obtained architecture and optimal hyperparameter configuration are consistent for both types of chilies, namely red chilies and bird’s eye chilies. For red chili, the best RMSE value that can be produced is 1751.890 and 1888.741 for bird’s eye chili.

Price Forecasting of Chili Variant Commodities Using Radial Basis Function Neural Network Ramadhan, Ade Umar; Siregar, Maria Ulfah; Nafisah, Syifaun; Anshari, Muhammad; Ndungi, Rebeccah; Mulyawan, Rizki; Nurochman, Nurochman; Gunawan, Eko Hadi
IJID (International Journal on Informatics for Development) Vol. 12 No. 1 (2023): IJID June
Publisher : Faculty of Science and Technology, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2023.5129

This study addresses the challenge of price instability in chili markets, which can lead to economic losses and inflation. To mitigate this issue, we propose a machine learning model using Radial Basis Function Neural Networks (RBFNN) to predict prices of various chili variants. Our quantitative approach involves a comprehensive data preparation process, including preprocessing and normalization of time series data collected from 2018 to 2022. The RBFNN model is constructed with K-Means clustering for optimal hidden layer configurations and evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results demonstrate promising accuracy, with MAPE error rates below 20% and relatively low RMSE values for large red chili (10.37%, 4484) and curly red chili (14.77%, 5590). Our findings indicate the potential for creating a reliable forecast model for predicting chili prices over 7 days, enabling better supply and demand management. The study's results also suggest that increased training data enhances forecasting accuracy. This research contributes to the development of effective price forecasting models, providing valuable insights for policymakers and stakeholders in the chili industry.

A Better Performance of GAN Fake Face Image Detection Using Error Level Analysis-CNN Siregar, Maria Ulfah; Nurochman, Nurochman; Setianingrum, Anif Hanifa; Larasati, Dwi; Santoso, William; Stefany, Meisia Dhea
JOIV : International Journal on Informatics Visualization Vol 9, No 2 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.2.2698

The use of face images has been widely established in various fields, including security, finance, education, social security, and others. Meanwhile, modern scientific and technological advances make it easier for individuals to manipulate images, including those of faces. In one of these advancements, the Generative Adversarial Network method creates a fake image similar to the real one. An error-level analysis algorithm and a convolutional neural network are proposed to detect manipulated images generated by generative adversarial networks. There are two scenarios: a stand-alone convolutional neural network and a combination of error-level analysis and a convolutional neural network. Furthermore, the combined scenario has three sub-scenarios regarding the compression levels of the error-level analysis algorithm: 10%, 50%, and 90%. After training the data obtained from a public source, it becomes evident that using a convolutional neural network combined with compression of error level analysis can improve the model’s overall performance: accuracy, precision, recall, and other parameters. Based on the evaluation results, it was found that the highest quality convolutional neural network training was obtained when using 50% error level analysis compression because it could achieve 94% accuracy, 93.3% precision, 94.9% recall, 94.1% F1 Score, 98.7% ROC-AUC Score, and 98.8% AP Score. This research is expected to be a reference for implementing image detection processes between real and fake images from generative adversarial networks.

Price Forecasting of Chili Variant Commodities Using Radial Basis Function Neural Network Ramadhan, Ade Umar; Siregar, Maria Ulfah; Nafisah, Syifaun; Anshari, Muhammad; Ndungi, Rebeccah; Mulyawan, Rizki; Nurochman, Nurochman; Gunawan, Eko Hadi
IJID (International Journal on Informatics for Development) Vol. 12 No. 1 (2023): IJID June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2023.5129

This study addresses the challenge of price instability in chili markets, which can lead to economic losses and inflation. To mitigate this issue, we propose a machine learning model using Radial Basis Function Neural Networks (RBFNN) to predict prices of various chili variants. Our quantitative approach involves a comprehensive data preparation process, including preprocessing and normalization of time series data collected from 2018 to 2022. The RBFNN model is constructed with K-Means clustering for optimal hidden layer configurations and evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results demonstrate promising accuracy, with MAPE error rates below 20% and relatively low RMSE values for large red chili (10.37%, 4484) and curly red chili (14.77%, 5590). Our findings indicate the potential for creating a reliable forecast model for predicting chili prices over 7 days, enabling better supply and demand management. The study's results also suggest that increased training data enhances forecasting accuracy. This research contributes to the development of effective price forecasting models, providing valuable insights for policymakers and stakeholders in the chili industry.

PENGARUH STRES KERJA DAN KOMPENSASI TERHADAP KINERJA KARYAWAN PRIMAYA HOSPITAL KOTA TANGERANG Nurochman, Nurochman; Sudiarto Sudiarto
JURNAL AKADEMIK EKONOMI DAN MANAJEMEN Vol. 3 No. 1 (2026): JURNAL AKADEMIK EKONOMI DAN MANAJEMEN
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jaem.v3i1.9256

at Primaya Hospital, Tangerang City, both partially and simultaneously. This study uses a quantitative method with a descriptive approach. The technique for determining the sample size used in this study uses the Slovin method. Based on the existing population of 420 people, the number of samples used in this study if calculated using the Slovin method is 80.76 which is rounded up to 81 respondents. Data collection uses a questionnaire with a Likert scale. Data analysis is carried out through validity tests, reliability tests, classical assumption tests, simple and multiple linear regression analysis, and hypothesis testing through t-tests and F-tests. The results of the study indicate that partially, job stress has a positive and significant effect on employee performance with a regression equation of Y = 6.729 + 0.836 X1 and a calculated t-value > t-table (10.398 > 1.990) with a significance of 0.00 < 0.05. Therefore, H0 is rejected and H1 is accepted. Compensation also has a positive and significant effect with the regression equation Y = 6.431 + 0.877 X2 and the calculated t-value > t-table (12.353 > 1.990) with a significance of 0.00 < 0.05. So, H0 is rejected and H2 is accepted. Simultaneously, work stress and compensation have a significant effect on employee performance with the regression equation Y = 2.709 + 0.414 X1 + 0.593 X2 and the calculated F value > F table (105.991 > 3.11) with a significance of 0.00 < 0.05. So, H0 is rejected and H3 is accepted.

Title

Found 18 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 18 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 18 Documents
Search