KLASIFIKASI GENDER BERDASARKAN SUARA DENGAN NAIVE BAYES DAN MEL FREQUENCY  CEPSTRAL COEFFICIENT

Abstract For humans, recognizing sounds is an easy thing, by listening carefully and understandingly to what is spoken and humans have intelligence in recognizing sound patterns. Unlike computers, the speech recognition process is a difficult process, this is because the computer requires a standard and logical mechanism to recognize sound patterns. With Mel Frequency Cepstral Coefficient (MFCC) method has an important role in determining the characteristics of a sound. This method is often used for verification of voice, speech recognition, emotion detection of voice. To perform the classification in this study using Naïve Bayes method. The Naive Bayes method is a classification method. In which the classification process in the naïve Bayes method is based on the probability of the data as evidence in probability. The model used in the Naive Bayes method is the independent attribute model. The accuracy rate in this research was 87%. It is based on the amount of data testing 100 samples, the true classified as 87 samples of data while false classified as 13 sample data. Keywords: Voice Recognition; Naïve Bayes; Mel-Frequency Cepstral Coefficient. __________________________ Abstrak Bagi manusia mengenali suara merupakan hal yang mudah, dengan cara mendengarkan dengan seksama dan manusia mempunyai kecerdasan dalam mengenali pola suara. Berbeda dengan komputer, proses pengenalan suara merupakan proses yang sulit, hal ini dikarenakan komputer memerlukan suatu mekanisme yang standar dan logis dalam mengenali pola suara. Dengan metode Mel Frequency Cepstral Coefficient (MFCC) memiliki peran penting dalam menentukan karakteristik dari sebuah suara. Metode ini sering digunakan untuk verifikasi suara, pengenalan suara, deteksi emosi dari suara. Untuk melakukan klasifikasi pada penelitian ini menggunakan metode Naïve Bayes. Metode Naive Bayes merupakan salah satu metode klasifikasi, yang mana proses klasifikasi pada metode naïve bayes berdasarkan dari probabilitas dari data sebagai bukti dalam probalitas. Model yang digunakan pada metode Naive Bayes adalah model atribut independent. Dalam penelitian ini, data suara yang digunakan pada penelitian ini berupa data suara yang direkam mengunkan perekam suara dengan durasi rekaman suara maksimal 30 detik. Tingkat keberhasilan dalam penelitian ini sebesar 87%. Hal ini berdasarkan dari jumlah data pengujian 100 sampel, yang benar diklasifikasi sebanyak 87 sampel data sedangkan yang salah diklasifikasi sebanyak 13 data sampel suara. Kata Kunci: Pengenalan Suara; Naïve Bayes; Mel-Frequency Cepstral Coefficien. __________________________

Download Full-text

KLASIFIKASI GENDER BERDASARKAN SUARA DENGAN NAIVE BAYES DAN MEL FREQUENCY CEPSTRAL COEFFICIENT

VOCATECH: Vocational Education and Technology Journal ◽

10.38038/vocatech.v2i1.45 ◽

2020 ◽

Vol 2 (1) ◽

Author(s):

Safriadi Safriadi ◽

Rahmadani Rahmadani

Keyword(s):

Speech Recognition ◽

Naive Bayes ◽

Naïve Bayes ◽

Emotion Detection ◽

Bayes Method ◽

Sample Data ◽

Attribute Model ◽

Sound Patterns ◽

Mel Frequency Cepstral Coefficient ◽

Naive Bayes Method

Bagi manusia mengenali suara merupakan hal yang mudah, dengan cara mendengarkan dengan seksama dan manusia mempunyai kecerdasan dalam mengenali pola suara. Berbeda dengan komputer, proses pengenalan suara merupakan proses yang sulit, hal ini dikarenakan komputer memerlukan suatu mekanisme yang standar dan logis dalam mengenali pola suara. Dengan metode Mel Frequency Cepstral Coefficient (MFCC) memiliki peran penting dalam menentukan karakteristik dari sebuah suara. Metode ini sering digunakan untuk verifikasi suara, pengenalan suara, deteksi emosi dari suara. Untuk melakukan klasifikasi pada penelitian ini menggunakan metode Naïve Bayes. Metode Naive Bayes merupakan salah satu metode klasifikasi, yang mana proses klasifikasi pada metode naïve bayes berdasarkan dari probabilitas dari data sebagai bukti dalam probalitas. Model yang digunakan pada metode Naive Bayes adalah model atribut independent. Dalam penelitian ini, data suara yang digunakan pada penelitian ini berupa data suara yang direkam mengunkan perekam suara dengan durasi rekaman suara maksimal 30 detik. Tingkat keberhasilan dalam penelitian ini sebesar 87%. Hal ini berdasarkan dari jumlah data pengujian 100 sampel, yang benar diklasifikasi sebanyak 87 sampel data sedangkan yang salah diklasifikasi sebanyak 13 data sampel suara. For humans, recognizing sounds is an easy thing, by listening carefully and understandingly to what is spoken and humans have intelligence in recognizing sound patterns. Unlike computers, the speech recognition process is a difficult process, this is because the computer requires a standard and logical mechanism to recognize sound patterns. With Mel Frequency Cepstral Coefficient (MFCC) method has an important role in determining the characteristics of a sound. This method is often used for verification of voice, speech recognition, emotion detection of voice. To perform the classification in this study using Naïve Bayes method. The Naive Bayes method is a classification method. In which the classification process in the naïve Bayes method is based on the probability of the data as evidence in probability. The model used in the Naive Bayes method is the independent attribute model. The accuracy rate in this research was 87%. It is based on the amount of data testing 100 samples, the true classified as 87 samples of data while false classified as 13 sample data.

Download Full-text

Development of Android-based Rabbit Disease Expert System

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i4.44.26868 ◽

2018 ◽

Vol 7 (4.44) ◽

pp. 82

Author(s):

Dyah Ayu Irawati ◽

Yan Watequlis Syaifudin ◽

Fabiola Ester Tomasila ◽

Awan Setiawan ◽

Erfan Rohadi

Keyword(s):

Naive Bayes ◽

Diagnostic System ◽

Naïve Bayes ◽

Certainty Factor ◽

Bayes Method ◽

Trust Value ◽

User Input ◽

Sample Data ◽

Testing Data ◽

Naive Bayes Method

Many rabbit keepers or breeders are panics when their rabbit has an illness. This paper proposed an expert diagnostic system application for Android-based rabbit disease using the Naïve Bayes method to determine the illness and Certainty Factor for the trust value of the condition by combining the rate of the trust of users and experts due to diagnose the diseases of the rabbit.The testing was using 65 data learning and 160 data learning to test the naïve Bayes method. Furthermore, the certainty factor is using CF user 1 and its variation.The results obtained for 65 data learning is 53%, while 160 data learning is 73%. With the naïve Bayes method, it can be concluded that the more data learning, the better and more accurate the system. The results of conformity with the testing data obtained from the variative CF user value, namely 53% accordingly, 13% inappropriate, 33% near. The effect of compliance with the sample data collected from the CF value of user 1 is 53% appropriate, 7% inappropriate, 40% is near. With the certainty factor method, it can be concluded that differences in user input values affect the overall CF value.

Download Full-text

Forensic Malware Identification Using Naive Bayes Method

2020 International Conference on Information Technology Systems and Innovation (ICITSI) ◽

10.1109/icitsi50517.2020.9264959 ◽

2020 ◽

Author(s):

Beno Ramadhan ◽

Yudha Purwanto ◽

Muhammad Faris Ruriawan

Keyword(s):

Naive Bayes ◽

Naïve Bayes ◽

Bayes Method ◽

Naive Bayes Method

Download Full-text

PENGEMBANGAN SISTEM CERDAS UNTUK PREDIKSI DAFTAR KEMBALI MAHASISWA BARU DENGAN METODE NAIVE BAYES (STUDI KASUS: UNIVERSITAS PENDIDIKAN GANESHA)

SINTECH (Science and Information Technology) Journal ◽

10.31598/sintechjournal.v3i1.523 ◽

2020 ◽

Vol 3 (1) ◽

pp. 22-34

Author(s):

Komang Aditya Pratama ◽

Gede Aditra Pradnyana ◽

I Ketut Resika Arthana

Keyword(s):

Naive Bayes ◽

Intelligent System ◽

Naïve Bayes ◽

The State ◽

State University ◽

Bayes Method ◽

New Students ◽

Computer Based ◽

Entrance Test ◽

Naive Bayes Method

Ganesha University of Education or Undiksha is one of the state universities in Bali, precisely in the city of Singaraja. In the admission of new students, Undiksha applies 3 admissions paths, as follows the State University National Admission Selection (SNMPTN), State University Joint Entrance Test (SBMPTN), and Independent Entrance Test (SMBJM) consisting of 2 parts namely Computer Based Test (CBT) and Interests and Talents. Each year the committees are busy with the re-registration of prospective students. In determining the number of students quota for re-registration, they are still using the manual method in form of an excel file, so they want to use a system to do the process. These problems can be overcome by using “Intelligent System for Re-Registration of New Students Prediction using the Naive Bayes Method (Case Study: Ganesha University of Education)”. The Naive Bayes method is used to determine the re-register probability of the new students so that the number of students who re-register can be determining the new students quota. In developing the system, the researcher use the CRISP-DM methodology as a standard of data mining process as well as a research method. The results of this prediction system research show that the system can predict well with the average predictive system accuracy value of 75.56%.

Download Full-text

OPTIMASI METODE NAIVE BAYES DENGAN FEATURE SELECTION INFORMATION GAIN UNTUK PREDIKSI KETERLAMBATAN PEMBAYARAN SPP SEKOLAH

Jurnal Ilmiah SINUS ◽

10.30646/sinus.v17i1.378 ◽

2019 ◽

Vol 17 (1) ◽

pp. 1

Author(s):

Muqorobin Muqorobin ◽

Kusrini Kusrini ◽

Emha Taufiq Luthfi

Keyword(s):

Feature Selection ◽

Naive Bayes ◽

Information Gain ◽

Confusion Matrix ◽

Education Institution ◽

Naïve Bayes ◽

Bayes Method ◽

Education Development ◽

Main Requirement ◽

Naive Bayes Method

The cost of education is one component of input that is very important in implementing education. Because costs are the main requirement in an effort to achieve educational goals. SMK Al-Islam Surakarta is a private education institution that requires students to pay school fees in the form of Education Development Donations. Educational Development Donation is a routine school fee that is conducted every month. Based on last year's TU report, many students were late in paying Education Development Donations, around 60%. This is a big problem. The purpose of this study is that researchers will build a predictive system using the Naïve Bayes method. Because the method can classify the class right or late, in the payment of school fees. Data processing was taken from the dapodik data of schools in 2017/2018 with the test dataset taking 30 records. To find out the level of accuracy, this research was conducted with the Naive Bayes Method and the Information Gain Method for feature selection. Accuracy testing is done by the Confusion Matrix method. The results showed that the highest accuracy was obtained by combining the Naive Bayes Method with the Information Gain Method obtained by 90% accuracy.

Download Full-text