Garuda - Garba Rujukan Digital

IMPLEMENTASI ALGORITMA MULTINOMIAL NAIVE BAYES CLASSIFIER Anif Hanifa Setianingrum; Dea Herwinda Kalokasari; Imam Marzuki Shofi
JURNAL TEKNIK INFORMATIKA Vol 10, No 2 (2017): Jurnal Teknik Informatika
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

ABSTRAK Informasi diperkirakan lebih dari 80% tersimpan dalam bentuk teks tidak terstruktur. Oleh karena itu, dibutuhkan sistem pengelolaan teks yaitu dengan metode text mining yang diyakini memiliki potensial nilai komersial tinggi. Salah satu implementasi dari text mining yaitu klasifikasi teks. Tidak hanya dokumen, pemanfaatan klasifikasi juga digunakan pada surat. Peneliti mengkaji Multinomial Naive Bayes Classifier untuk mengklasifikasi surat keluar sehingga dapat menentukan nomor surat secara otomatis. Sistem klasifikasi didukung dengan confix-stripping stemmer untuk menemukan kata dasar dan TF-IDF untuk pembobotan kata. Pengujian diukur dengan menggunakan confusion matrix. Dari hasil pengujian menunjukkan bahwa implementasi Multinomial Naive Bayes Classifier pada sistem klasifikasi surat memiliki tingkat accuracy, precision, recall, dan F-measure berturut-turut sebesar 89,58%, 79,17%, 78,72%, dan 77,05%. ABSTRACT The information estimated that more than 80% is stored in the form of unstructured text. Therefore, it takes a text management system, namely text mining method is believed to have high potential commercial. One of text mining implementation is text classification. Not only documents, the use of classification is also used in official letter. Researcher examined Multinomial Naive Bayes Classifier to classify the letter so it can determine the letters classification code automatically. The classification system is supported by confix-stripping stemmer to find root and TF-IDF for term weighting. The test used by confusion matrix of a classified as a measure of its quality. The test results showed that the implementation of Multinomial Naive Bayes Classifier on letter classification system has a level of accuracy, precision, recall, and F-measure respectively for 89.58%, 79.17%, 78.72% and 77.05%.How to Cite : Setianingrum, A. H. Kalokasari, D.H . Shofi. I. M. (2017). IMPLEMENTASI ALGORITMA MULTINOMIAL NAIVE BAYES CLASSIFIER. Jurnal Teknik Informatika, 10(2), 109-118. doi: 10.15408/jti.v10i2.6822Permalink/DOI: http://dx.doi.org/10.15408/jti.v10i2.6822

Implementasi Algoritma Boyer Moore Pada Aplikasi Kamus Istilah Kebidanan Berbasis Web Rizky Ivan Darmawan; Anif Hanifa Setianingrum; Arini Arini
Query: Journal of Information Systems VOLUME: 02, NUMBER: 01, APRIL 2018
Publisher : Program Studi Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1022.74 KB)

The lack of understanding in obstetrics and limit of instructional media has become one of the factors in the making of dictionary application of midwifery. The current dictionary is still a thick book with many terms in it and difficult to use. dictionary midwifery terms have a weakness in the search process, because users should search for words and terms manually by opening pages per page on the dictionary and existing data could not be changed.Keywords: Algorithm, Boyer Moore, Midwifery Dictionary.

Hand-Gesture Detection Using Principal Component Analysis (PCA) and Adaptive Neuro-Fuzzy Inference System (ANFIS) Anif Hanifa Setianingrum; Arifa Fauzia; Dzul Fadli Rahman
JURNAL TEKNIK INFORMATIKA Vol 15, No 1 (2022): JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v15i1.24869

Sign language is a non-verbal language that Deaf persons exclusively count on to connect with their social environment.The problem that occurs in two-way communication using sign language is a misunderstanding when learning new terms that need to be taught to deaf and mute people. To minimize these misunderstandings, a system is needed that can assist in correcting hand gestures so that there is no misinterpretation in teaching new terms. Several optimality properties of PCA have been identified namely: variance of extracted features is maximized; the extracted features are uncorrelated; finds best linear approximation in the mean-square sense and maximizes information contained in the extracted feature. The classification uses the Adaptive Neuro-Fuzzy Inference System (ANFIS) method. From the results of experiments with different image size variables, the largest accuracy was obtained with an image size of 449x449 of 76.20%. While the lowest accuracy of 52.38% is obtained through scenarios with image sizes of 57x57 and 45x45. Therefore, differences in the use of image sizes have an influence on the accuracy of hand signal prediction. The smaller the size given, the smaller the accuracy obtained. This is indicated by the decreasing accuracy value when given a smaller size in the four scenarios that have been studied.

Sinyal Elektroensefalografi Untuk Deteksi Emosi Saat Mendengar Stimulus Pembacaan Al-Quran Menggunakan Wavelet Transform Hulliyah, Khodijah; Setianingrum, Anif Hanifa; Santoso, William
Technomedia Journal Vol 8 No 2 Special Issues (2023): Special Issue: Sistem Informasi Manajemen Dalam Menunjang Teknolog
Publisher : Pandawan Incorporation, Alphabet Incubator Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/tmj.v8i2SP.2060

Mendengarkan suara membaca Al-Qur'an (Murottal) diketahui sering digunakan untuk membuat suasana terasa santai. Oleh karena itu, dalam penelitian ini, kami menyelidiki sejauh mana stimulasi suara murottal mempengaruhi penampilan gelombang alfa yang terlihat pada gelombang otak menggunakan detektor sinyal Electoencephalography (EEG). Menggunakan Transformasi Wavelet. Gelombang otak yang terdeteksi oleh sinyal EEG kemudian dianalisis untuk setiap fase gelombang pada frekuensi alfa (8-13 Hz) untuk melihat keadaan rileks. Kami merekam data gelombang EEG dalam 4 kondisi, yaitu kondisi tenang, kondisi tegang, dan keduanya dengan stimulus suara murottal. Setiap kondisi dilakukan masing-masing selama 2 menit. Suara murottal diambil secara acak untuk mendapatkan variasi data. Hasil klasifikasi menggunakan Recurrent Neural Network (RNN) menunjukkan bahwa t raining menggunakan n data ormal dengan tombak s mencapai akurasi 52% ~ 59%, Normal dengan m urottal n ormal menghasilkan nilai akurasi 55% ~ 56%, normal dengan tombak m urottal s mendapatkan nilai akurasi terkecil 35% ~ 46%, s Pike dengan m urrottal n ormal mencapai akurasi 57% ~ 67%, pike S dengan pike M urottal smenghasilkan akurasi 51% ~ 60%, M urottal normal dengan pike M urottal S mencapai nilai akurasi tertinggi 78%. Hal ini menunjukkan bahwa terdapat pengaruh yang signifikan dalam mendengarkan Murottal Al-Quran.

Feature Extraction Using Mel-Frequency Cepstral Coefficients (MfCC) Technique For A Tajweed Guess Based on Android Application Development Khodijah Hulliyah; Lilik Ummi Kultsum; Wahyu Hendarto Wibowo; Anif Hanifa Setianingrum; Arini Arini; Yusuf Durachman
JURNAL TEKNIK INFORMATIKA Vol 18, No 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.44721

The development of information and communication technology today has had a significant impact on various aspects of life, including education. One notable example is the increasing number of applications designed for learning to recite the Quran with proper tartil. The growing trend of tahfidz (Quran memorization) is undoubtedly a positive development from a religious perspective. However, many individuals focus solely on memorization without acquiring the ability to recite the Quran properly and accurately. One discipline that supports proper Quran recitation is the knowledge of tajweed. Numerous applications have been developed in this field, especially on Android platforms. However, applications that utilize artificial intelligence (AI) to recognize tajweed rules and involve users in guessing tajweed readings are still in need of further development. The aim of this research is to develop a tajweed learning application using the concept of Automatic Speech Recognition (ASR). This study employs data collection methods such as literature review, quantitative methods, and testing. The design is represented using Unified Modeling Language (UML), while the application is tested using the Black Box Testing method. For data analysis and testing of the speech recognition model, the Hidden Markov Model (HMM) algorithm is employed, with Mel-Frequency Cepstral Coefficients (MFCC) used for feature extraction. The output of this research is an Android-based tajweed learning application that integrates speech recognition and allows users to guess tajweed rules interactively.

Feature Extraction Using Mel-Frequency Cepstral Coefficients (MfCC) Technique For A Tajweed Guess Based on Android Application Development Hulliyah, Khodijah; Kultsum, Lilik Ummi; Wibowo, Wahyu Hendarto; Setianingrum, Anif Hanifa; Arini, Arini; Durachman, Yusuf
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.44721

The development of information and communication technology today has had a significant impact on various aspects of life, including education. One notable example is the increasing number of applications designed for learning to recite the Quran with proper tartil. The growing trend of tahfidz (Quran memorization) is undoubtedly a positive development from a religious perspective. However, many individuals focus solely on memorization without acquiring the ability to recite the Quran properly and accurately. One discipline that supports proper Quran recitation is the knowledge of tajweed. Numerous applications have been developed in this field, especially on Android platforms. However, applications that utilize artificial intelligence (AI) to recognize tajweed rules and involve users in guessing tajweed readings are still in need of further development. The aim of this research is to develop a tajweed learning application using the concept of Automatic Speech Recognition (ASR). This study employs data collection methods such as literature review, quantitative methods, and testing. The design is represented using Unified Modeling Language (UML), while the application is tested using the Black Box Testing method. For data analysis and testing of the speech recognition model, the Hidden Markov Model (HMM) algorithm is employed, with Mel-Frequency Cepstral Coefficients (MFCC) used for feature extraction. The output of this research is an Android-based tajweed learning application that integrates speech recognition and allows users to guess tajweed rules interactively.

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.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search