scholarly journals Combination of Morphology, Wavelet and Convex Hull Features in Classification of Patchouli Varieties with Imbalance Data using Artificial Neural Network

2021 ◽  
Vol 19 (6) ◽  
pp. 633-643
Author(s):  
Wayan Firdaus Mahmudy ◽  
Candra Dewi ◽  
Rio Arifando ◽  
Beryl Labique Ahmadie ◽  
Muh Arif Rahman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Convex Hull ◽  
Morphological Features ◽  
Variety Identification ◽  
Identification System ◽  
Imbalance Data ◽  
Average Accuracy ◽  
Physical Form ◽  
Artificial Neural

Patchouli plants are main raw materials for essential oils in Indonesia. Patchouli leaves have a very varied physical form based on the area planted, making it difficult to recognize the variety. This condition makes it difficult for farmers to recognize these varieties and they need experts’ advice. As there are few experts in this field, a technology for identifying the types of patchouli varieties is required. In this study, the identification model is constructed using a combination of leaf morphological features, texture features extracted with Wavelet and shape features extracted with convex hull. The results of feature extraction are used as input data for training of classification algorithms. The effectiveness of the input features is tested using three classification methods in class artificial neural network algorithms: (1) feedforward neural networks with backpropagation algorithm for training, (2) learning vector quantization (LVQ), (3) extreme learning machine (ELM). Synthetic minority over-sampling technique (SMOTE) is applied to solve the problem of class imbalance in the patchouli variety dataset. The results of the patchouli variety identification system by combining these three features indicate the level of recognition with an average accuracy of 72.61%, accuracy with the combination of these three features is higher when compared to using only morphological features (58.68%) or using only Wavelet features (59.03 %) or both (67.25%). In this study also showed that the use of SMOTE in imbalance data increases the accuracy with the highest average accuracy of 88.56%.

scholarly journals SPEAKER IDENTIFICATION MENGGUNAKAN TRANSFORMASI WAVELET DISKRIT DAN JARINGAN SARAF TIRUAN BACK-PROPAGATION

2008 ◽  
Vol 2 (1) ◽  
pp. 1
Author(s):  
Anny Tandyo ◽  
Martono Martono ◽  
Adi Widyatmoko
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Speaker Recognition ◽  
Speaker Identification ◽  
Back Propagation ◽  
Identification Accuracy ◽  
Identification System ◽  
Accuracy Rate ◽  
Discrete Transformation ◽  
Artificial Neural

Article discussed a speaker identification system. Which was a part of speaker recognition. The system identified asubject based on the voice from a group of pattern had been saved before. This system used a wavelet discrete transformationas a feature extraction method and an artificial neural network of back-propagation as a classification method. The voiceinput was processed by the wavelet discrete transformation in order to obtain signal coefficient of low frequency as adecomposition result which kept voice characteristic of everyone. The coefficient then was classified artificial neural networkof back-propagation. A system trial was conducted by collecting voice samples directly by using 225 microphones in nonsoundproof rooms; contained of 15 subjects (persons) and each of them had 15 voice samples. The 10 samples were used as atraining voice and 5 others as a testing voice. Identification accuracy rate reached 84 percent. The testing was also done onthe subjects who pronounced same words. It can be concluded that, the similar selection of words by different subjects has noinfluence on the accuracy rate produced by system.Keywords: speaker identification, wavelet discrete transformation, artificial neural network, back-propagation.

COMPARATIVE STUDY OF CONTINUOUS HIDDEN MARKOV MODELS (CHMM) AND ARTIFICIAL NEURAL NETWORK (ANN) ON SPEAKER IDENTIFICATION SYSTEM

2001 ◽  
Vol 09 (06) ◽  
pp. 673-683 ◽  
Author(s):  
SAWIT KASURIYA ◽  
CHAI WUTIWIWATCHAI ◽  
VARIN ACHARIYAKULPORN ◽  
CHULARAT TANPRASERT
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Comparative Study ◽  
Speaker Identification ◽  
Hidden Markov ◽  
Identification System ◽  
Office Environment ◽  
Identification Rate ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

This paper reports a comparative study between a continuous hidden Markov model (CHMM) and an artificial neural network (ANN) on a text dependent, closed set speaker identification (SID) system with Thai language recording in office and telephone environment. Thai isolated digit "0–9" and their concatenation are used as speaking text. Mel frequency cepstral coefficients (MFCC) are selected as the studied features. Two well-known recognition engines, CHMM and ANN, are conducted and compared. The ANN system (multilayer perceptron network with backpropagation learning algorithm) is applied with a special design of input feeding methods in avoiding the distortion from the normalization process. The general Gaussian density distribution HMM is developed for CHMM system. After optimizing some system's parameters by performing some preliminary experiments, CHMM gives the best identification rate at 90.4%, which is slightly better than 90.1% of ANN on digit "5" in office environment. For telephone environment, ANN gives the best identification rate at 88.84% on digit "0" which is higher than 81.1% of CHMM on digit "3". When using 3-concatenated digit, the identification rate of ANN and CHMM achieves 97.3% and 95.7% respectively for office environment, and 92.1% and 96.3% respectively for telephone environment.

scholarly journals Sistem Identifikasi Tingkat Kematangan Buah Nanas Secara Non-Destruktif Berbasis Computer Vision

2021 ◽  
Vol 2 (1) ◽  
pp. 1-10
Author(s):  
Nevalen Aginda Prasetyo ◽  
◽  
Arif Surtono ◽  
Junaidi Junaidi ◽  
Gurum Ahmad Pauzi
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Artificial Neural Network ◽  
Pearson Correlation ◽  
Statistical Parameter ◽  
Identification System ◽  
Maturity Level ◽  
Validation Data ◽  
Artificial Neural ◽  
Level Identification

A computer vision-based non-destructive pineapple maturity level identification system has been realized. This research was conducted to create a system capable of identifying six indexes of pineapple maturity level. An artificial neural network is used as a classifier for the level of maturity pineapples. Artificial neural network input is a statistical parameter consisting of mean, standard deviation, variance, kurtosis, and skewness of RGB and HSV color models pineapple images. Statistical parameters of the color model with a Pearson correlation value greater than 0.5 were used to characterize pineapple images. A total of 360 pineapple images were used in the training process with a percentage of 75% of training data and 25% of validation data. An image segmentation process is applied to separate the pineapple image from the image background. The result of this research is a pineapple maturity level identification system consisting of software and hardware which is able to identify six indexes of pineapple maturity level with average accuracy value of 98,4%.

Inner Knuckle Print Identification Using Artificial Neural Network

2020 ◽  
pp. 115-118
Author(s):  
Hema Rajini N ◽  
Chandra Prabha K
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Support Vector ◽  
Identification System ◽  
System A ◽  
Artificial Neural Network Classifier ◽  
Artificial Neural ◽  
Efficient Matching ◽  
The Given

A inner knuckle print identification system has been designed and developed. This work presents a new approach to authenticate people according to their finger textures. This proposed method consists of three stages. They are preprocessing, feature extraction and matching. In the first stage, noise is suppressed using an image filtering. In the second stage, features are extracted by local line binary pattern. Artificial neural network and support vector machine are used to provide an efficient matching algorithm for inner knuckle print authentication. After matching, the algorithm returns the best match for the given fingerprint parameters. The use of inner knuckle print in biometric identification has been the most widely used authentication system. A classification with an accuracy of 89% and 97% has been obtained by support vector machine and artificial neural network classifier.

scholarly journals Jaringan Syaraf Tiruan Perambatan Balik Untuk Pengenalan Wajah

2016 ◽  
Vol 6 (1) ◽  
pp. 30
Author(s):  
Nahdi Sabuari ◽  
Rizal Isnanto ◽  
Kusworo Adi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Face Recognition ◽  
Face Detection ◽  
Image Data ◽  
Training Algorithm ◽  
Accuracy Rate ◽  
Average Accuracy ◽  
The Face ◽  
Artificial Neural

This research discusses about face detection and face recognition in an image. Face detection has only two classifications, i.e face and not face. Face recognition is compatible with some classifications of a number individuals who want to be recognized. Face detection and face recognition in thi study using Haar-Like Feature method and Artificial Neural Network Backpropagation. A method Haar-Like Feature used for detection and extraction in an image, because the clasification on this method showed success at used to detect image of the face. Artificial Neural Network Backpropagation is a training algorithm that is used to do training simulated on facial image data training stored in a database. This study uses Ms. Excel 2007 as database with 10 individual sample image, every image in each individuals having three distance with every range has four defferent light intensities, so that the data training stored in the database reached 120 data training. The results shows that the face detection and face recognition which is developed can recognize a face image with an average accuracy rate reaches 80,8% for each distance.

Development of Quran Reciter Identification System Using MFCC and Neural Network

2016 ◽  
Vol 1 (1) ◽  
pp. 168 ◽  
Author(s):  
Tayseer Mohammed Hasan Asda ◽  
Teddy Surya Gunawan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Identification System ◽  
Successful Match ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Mel Frequency Cepstral Coefficient

Currently, the Quran is recited by so many reciters with different ways and voices.  Some people like to listen to this reciter and others like to listen to other reciters. Sometimes we hear a very nice recitation of al-Quran and want to know who the reciter is. Therefore, this paper is about  the development of Quran reciter recognition and identification system based on Mel Frequency Cepstral Coefficient (MFCC) feature extraction and artificial neural network (ANN). From every speech, characteristics from the utterances will be extracted through neural network model. In this paper a database of five Quran reciters is created and used in training and testing. The feature vector will be fed into Neural Network back propagation learning algorithm for training and identification processes of different speakers. Consequently,  91.2%  of the successful match between targets and input occurred with certain number of hidden layers  which shows how efficient are Mel Frequency Cepstral Coefficient (MFCC) feature extraction  and artificial neural network (ANN) in identifying the reciter voice perfectly.

Sign in / Sign up

Export Citation Format

Share Document