A NEURAL NETWORK MODEL WITH FEATURE SELECTION FOR KOREAN SPEECH ACT CLASSIFICATION

2004 ◽  
Vol 14 (06) ◽  
pp. 407-414 ◽  
Author(s):  
KYUNGSUN KIM ◽  
HARKSOO KIM ◽  
JUNGYUN SEO
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Network Model ◽  
Neural Network Model ◽  
Speech Act ◽  
Feature Selection Method ◽  
Selection Method ◽  
Morphological Features ◽  
Experimental Result ◽  
Real Field

A speech act is a linguistic action intended by a speaker. Speech act classification is an essential part of a dialogue understanding system because the speech act of an utterance is closely tied with the user's intention in the utterance. We propose a neural network model for Korean speech act classification. In addition, we propose a method that extracts morphological features from surface utterances and selects effective ones among the morphological features. Using the feature selection method, the proposed neural network can partially increase precision and decrease training time. In the experiment, the proposed neural network showed better results than other models using comparatively high-level linguistic features. Based on the experimental result, we believe that the proposed neural network model is suitable for real field applications because it is easy to expand the neural network model into other domains. Moreover, we found that neural networks can be useful in speech act classification if we can convert surface sentences into vectors with fixed dimensions by using an effective feature selection method.

Speech Emotion Feature Selection Method Based on Contribution Analysis Algorithm of Neural Network

2008 ◽  
Author(s):  
Xiaojia Wang ◽  
Qirong Mao ◽  
Yongzhao Zhan ◽  
Theodore E. Simos ◽  
George Psihoyios
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Feature Selection Method ◽  
Selection Method ◽  
Analysis Algorithm ◽  
Contribution Analysis

scholarly journals An Enhancement in Cancer Classification Accuracy Using a Two-Step Feature Selection Method Based on Artificial Neural Networks with 15 Neurons

Symmetry ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 271 ◽  
Author(s):  
Md Akizur Rahman ◽  
Ravie Chandren Muniyandi
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Classification Accuracy ◽  
Feature Selection Method ◽  
Selection Method ◽  
Cancer Classification ◽  
Neuron Network ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Risk Of Cancer

An artificial neural network (ANN) is a tool that can be utilized to recognize cancer effectively. Nowadays, the risk of cancer is increasing dramatically all over the world. Detecting cancer is very difficult due to a lack of data. Proper data are essential for detecting cancer accurately. Cancer classification has been carried out by many researchers, but there is still a need to improve classification accuracy. For this purpose, in this research, a two-step feature selection (FS) technique with a 15-neuron neural network (NN), which classifies cancer with high accuracy, is proposed. The FS method is utilized to reduce feature attributes, and the 15-neuron network is utilized to classify the cancer. This research utilized the benchmark Wisconsin Diagnostic Breast Cancer (WDBC) dataset to compare the proposed method with other existing techniques, showing a significant improvement of up to 99.4% in classification accuracy. The results produced in this research are more promising and significant than those in existing papers.

Study on the Levenberg-Marquardt Neural Network Model for Rock Rheology

2011 ◽  
Vol 71-78 ◽  
pp. 4103-4108
Author(s):  
Yu Zhou Jiang ◽  
Rui Hong Wang ◽  
Jie Bing Zhu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Testing Machine ◽  
Experimental Result ◽  
Left Bank ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Rheological Experiments ◽  
Rock Rheology

Rheological experiments were carried out for sandstone and marble specimens from left bank high slope of Jingping First Stage Hydropower Project by using the rock servo-controlling rheology testing machine. Typical triaxial rheological curves under step loading and temperature curves in the process of rheological experiment were gained. BP neural network is improved by Levenberg-Marquardt algorithm. Improved neural network model for rock rheology is established in accordance with the rheology experimental results of rock specimen. The improved neural network model was used to forecast rock rheological experimental curves, and the result shows that the forecasted rock rheology curves are closely accorded with the experimental result. The improved neural network model takes into account the influence of loading history and temperature difference on the rock rheological deformation, and the forecasted result can reflect better the rheology deformation behavior of rock material.

scholarly journals Heart Disease Prediction Based on the Embedded Feature Selection Method and Deep Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Dengqing Zhang ◽  
Yunyi Chen ◽  
Yuxuan Chen ◽  
Shengyi Ye ◽  
Wenyu Cai ◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Heart Disease ◽  
Deep Neural Network ◽  
Feature Selection Method ◽  
Selection Method ◽  
The Body ◽  
Prediction Algorithm ◽  
Disease Prediction ◽  
Risk Of Death

In recent decades, heart disease threatens people’s health seriously because of its prevalence and high risk of death. Therefore, predicting heart disease through some simple physical indicators obtained from the regular physical examination at an early stage has become a valuable subject. Clinically, it is essential to be sensitive to these indicators related to heart disease to make predictions and provide a reliable basis for further diagnosis. However, the large amount of data makes manual analysis and prediction taxing and arduous. Our research aims to predict heart disease both accurately and quickly through various indicators of the body. In this paper, a novel heart disease prediction model is given. We propose a heart disease prediction algorithm that combines the embedded feature selection method and deep neural networks. This embedded feature selection method is based on the LinearSVC algorithm, using the L1 norm as a penalty item to choose a subset of features significantly associated with heart disease. These features are fed into the deep neural network we built. The weight of the network is initialized with the He initializer to prevent gradient varnishing or explosion so that the predictor can have a better performance. Our model is tested on the heart disease dataset obtained from Kaggle. Some indicators including accuracy, recall, precision, and F1-score are calculated to evaluate the predictor, and the results show that our model achieves 98.56%, 99.35%, 97.84%, and 0.983, respectively, and the average AUC score of the model reaches 0.983, confirming that the method we proposed is efficient and reliable for predicting heart disease.

Sign in / Sign up

Export Citation Format

Share Document