scholarly journals Transformation of Nonmultiple Cluster Music Cyclic Shift Topology to Music Performance Style

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Jing Li
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Recurrent Neural Network ◽  
Feature Vector ◽  
Music Performance ◽  
Experimental Simulation ◽  
Performance Style ◽  
Feature Extraction Method ◽  
Intensity Changes ◽  
Music File

Music is an abstract art form that uses sound as its means of expression. It has deeply affected our lives. This paper proposes a method for extracting segment features from nonmultiple cluster music files. We divide each piece of music into multiple segments and extract the features of each segment. The specific process includes nonmultiple cluster music file note extraction, main melody extraction, segment division, and segment feature extraction. The segment feature is extracted from a segment of a piece of music, contains the main melody and accompaniment information of the segment, and can reflect the sequence relationship of the notes. This paper proposes a performance style conversion network based on recurrent neural network and convolutional neural network. The bidirectional recurrent neural network based on Gated Recurrent Unit (GRU) is used to extract different styles of note feature vector sequences, and the extracted note feature vector sequence is used to predict the intensity of a specific style, and the intensity changes of different styles of nonmultiple cluster music are better learned. Through the comparison, the multiclassification strategy of “one-to-the-rest” is selected, and the fuzzy recurrent neural network is applied to the shortcomings of the unrecognizable area. Finally, according to the feature extraction method and the principle of the classifier algorithm studied in this paper, a music style classification system is implemented in the MATLAB environment. Experimental simulation shows that this system can effectively classify music performance styles.

scholarly journals Unsupervised Text Feature Extraction for Academic Chatbot using Constrained FP-Growth

2021 ◽  
Vol 14 ◽  
pp. 1-11
Author(s):  
Suraya Alias
Keyword(s):  
Feature Extraction ◽  
Customer Service ◽  
User Satisfaction ◽  
Feature Vector ◽  
Size Reduction ◽  
Growth Technique ◽  
Feature Extraction Method ◽  
Text Feature ◽  
Text Features ◽  
N Gram

In the edge where conversation merely involves online chatting and texting one another, an automated conversational agent is needed to support certain repetitive tasks such as providing FAQs, customer service and product recommendations. One of the key challenges is to identify and discover user’s intention in a social conversation where the focus of our work in the academic domain. Our unsupervised text feature extraction method for Intent Pattern Discovery is developed by applying text features constraints to the FP-Growth technique. The academic corpus was developed using a chat messages dataset where the conversation between students and academicians regarding undergraduate and postgraduate queries were extracted as text features for our model. We experimented with our new Constrained Frequent Intent Pattern (cFIP) model in contrast with the N-gram model in terms of feature-vector size reduction, descriptive intent discovery, and analysis of cFIP Rules. Our findings show significant and descriptive intent patterns was discovered with confidence rules value of 0.9 for cFIP of 3-sequence. We report an average feature-vector size reduction of 76% compared to the Bigram model using both undergraduate and postgraduate conversation datasets. The usability testing results depicted overall user satisfaction average mean score is 4.30 out of 5 in using the Academic chatbot which supported our intent discovery cFIP approach.

Automatic Segmentation and Classification of COVID-19 CT Image Using Deep Learning and Multi-Scale Recurrent Neural Network Based Classifier

2021 ◽  
Vol 11 (10) ◽  
pp. 2618-2625
Author(s):  
R. T. Subhalakshmi ◽  
S. Appavu Alias Balamurugan ◽  
S. Sasikala
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Superior Performance ◽  
Multi Scale ◽  
Proposed Model ◽  
Class Labels

In recent times, the COVID-19 epidemic turn out to be increased in an extreme manner, by the accessibility of an inadequate amount of rapid testing kits. Consequently, it is essential to develop the automated techniques for Covid-19 detection to recognize the existence of disease from the radiological images. The most ordinary symptoms of COVID-19 are sore throat, fever, and dry cough. Symptoms are able to progress to a rigorous type of pneumonia with serious impediment. As medical imaging is not recommended currently in Canada for crucial COVID-19 diagnosis, systems of computer-aided diagnosis might aid in early COVID-19 abnormalities detection and help out to observe the disease progression, reduce mortality rates potentially. In this approach, a deep learning based design for feature extraction and classification is employed for automatic COVID-19 diagnosis from computed tomography (CT) images. The proposed model operates on three main processes based pre-processing, feature extraction, and classification. The proposed design incorporates the fusion of deep features using GoogLe Net models. Finally, Multi-scale Recurrent Neural network (RNN) based classifier is applied for identifying and classifying the test CT images into distinct class labels. The experimental validation of the proposed model takes place using open-source COVID-CT dataset, which comprises a total of 760 CT images. The experimental outcome defined the superior performance with the maximum sensitivity, specificity, and accuracy.

Research of Face Recognition Methods Based on Binding Feature Extraction

2014 ◽  
Vol 568-570 ◽  
pp. 668-671
Author(s):  
Yi Long ◽  
Fu Rong Liu ◽  
Guo Qing Qiu
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Extraction Method ◽  
Local Binary Pattern ◽  
Feature Vector ◽  
Recognition Rate ◽  
Principal Component ◽  
Face Image ◽  
Feature Extraction Method ◽  
Histogram Feature

To address the problem that the dimension of the feature vector extracted by Local Binary Pattern (LBP) for face recognition is too high and Principal Component Analysis (PCA) extract features are not the best classification features, an efficient feature extraction method using LBP, PCA and Maximum scatter difference (MSD) has been introduced in this paper. The original face image is firstly divided into sub-images, then the LBP operator is applied to extract the histogram feature. and the feature dimensions are further reduced by using PCA. Finally,MSD is performed on the reduced PCA-based feature.The experimental results on ORL and Yale database demonstrate that the proposed method can classify more effectively and can get higher recognition rate than the traditional recognition methods.

scholarly journals AHWR-Net: offline handwritten amharic word recognition using convolutional recurrent neural network

2021 ◽  
Vol 3 (8) ◽  
Author(s):  
Fetulhak Abdurahman ◽  
Eyob Sisay ◽  
Kinde Anlay Fante
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Feature Extraction ◽  
Word Recognition ◽  
Recurrent Neural Network ◽  
Text Recognition ◽  
Input Word ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
Word Images

AbstractAmharic ("Image missing") is the official language of the Federal Government of Ethiopia, with more than 27 million speakers. It uses an Ethiopic script, which has 238 core and 27 labialized characters. It is a low-resourced language, and a few attempts have been made so far for its handwritten text recognition. However, Amharic handwritten text recognition is challenging due to the very high similarity between characters. This paper presents a convolutional recurrent neural networks based offline handwritten Amharic word recognition system. The proposed framework comprises convolutional neural networks (CNNs) for feature extraction from input word images, recurrent neural network (RNNs) for sequence encoding, and connectionist temporal classification as a loss function. We designed a custom CNN model and compared its performance with three different state-of-the-art CNN models, including DenseNet-121, ResNet-50 and VGG-19 after modifying their architectures to fit our problem domain, for robust feature extraction from handwritten Amharic word images. We have conducted detailed experiments with different CNN and RNN architectures, input word image sizes, and applied data augmentation techniques to enhance performance of the proposed models. We have prepared a handwritten Amharic word dataset, HARD-I, which is available publicly for researchers. From the experiments on various recognition models using our dataset, a WER of 5.24 % and CER of 1.15 % were achieved using our best-performing recognition model. The proposed models achieve a competitive performance compared to existing models for offline handwritten Amharic word recognition.

Sign in / Sign up

Export Citation Format

Share Document