Bidirectional Nested Long short-term memory based SVM Classifier
碩士 === 國立虎尾科技大學 === 電子工程系碩士班 === 107 === This paper first proposes a bidirectional nested LSTM model. The bidirectional LSTM neural network is a combination of two independent LSTM neural networks. Sometimes it is predicted that it needs to be determined by past or previous data, and it needs to be...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/eadn5r |
id |
ndltd-TW-107NYPI0428005 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107NYPI04280052019-10-06T03:35:29Z http://ndltd.ncl.edu.tw/handle/eadn5r Bidirectional Nested Long short-term memory based SVM Classifier 基於雙向巢狀長短期記憶之支持向量機分類器 DAI, JUN-WEI 戴君瑋 碩士 國立虎尾科技大學 電子工程系碩士班 107 This paper first proposes a bidirectional nested LSTM model. The bidirectional LSTM neural network is a combination of two independent LSTM neural networks. Sometimes it is predicted that it needs to be determined by past or previous data, and it needs to be determined jointly by future or subsequent information. The structure, the model training is more accurate via the input sequence forward and reverse inputs. This model also uses a nested structure, replacing the memory cells in the LSTM with another complete LSTM, giving the model a better long-term dependence. Second, because LSTM performs well in long-term time series predictions and SVM has strong generalization and robustness, past research has introduced SVM in LSTM for classification to complete prediction results. However, when the SVM is unbalanced, the hyperplane will shift or tilt to a few classes. This offset will reduce the performance of the model in a few categories. Therefore, we try to use the Bidirectional Nested LSTM RF model combined with SMOTE oversampling, OSS undersampling and random forest algorithm to improve the SVM classifier's performance degradation for a few classes when data is unbalanced. As SMOTE oversampling and OSS undersampling provide a balancing mechanism for data categories, classification performance is improved. In the random forest model, the features judged by each decision tree are different from the sample samples, so that the correlation between each decision tree is reduced and independent of each other. This feature also makes it easier for random forests to avoid the degradation of a few classes when applied to unbalanced data. In this paper, weather data is used as an example. The weather data used in the training is taken from Kaggle's New York City - Hourly Weather Data, and the root mean square error (RMSE) is used to evaluate the performance of the prediction results. The results of this study show that the bidirectional nested LSTM model has higher prediction accuracy than other LSTM models with the same number of parameters. In addition, the Bidirectional Nested LSTM SVM combined with SVM is still superior to Bidirectional Nested LSTM RF. CHEN, PO-HUNG 陳柏宏 2019 學位論文 ; thesis 53 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立虎尾科技大學 === 電子工程系碩士班 === 107 === This paper first proposes a bidirectional nested LSTM model. The bidirectional LSTM neural network is a combination of two independent LSTM neural networks. Sometimes it is predicted that it needs to be determined by past or previous data, and it needs to be determined jointly by future or subsequent information. The structure, the model training is more accurate via the input sequence forward and reverse inputs. This model also uses a nested structure, replacing the memory cells in the LSTM with another complete LSTM, giving the model a better long-term dependence. Second, because LSTM performs well in long-term time series predictions and SVM has strong generalization and robustness, past research has introduced SVM in LSTM for classification to complete prediction results. However, when the SVM is unbalanced, the hyperplane will shift or tilt to a few classes. This offset will reduce the performance of the model in a few categories. Therefore, we try to use the Bidirectional Nested LSTM RF model combined with SMOTE oversampling, OSS undersampling and random forest algorithm to improve the SVM classifier's performance degradation for a few classes when data is unbalanced. As SMOTE oversampling and OSS undersampling provide a balancing mechanism for data categories, classification performance is improved. In the random forest model, the features judged by each decision tree are different from the sample samples, so that the correlation between each decision tree is reduced and independent of each other. This feature also makes it easier for random forests to avoid the degradation of a few classes when applied to unbalanced data. In this paper, weather data is used as an example. The weather data used in the training is taken from Kaggle's New York City - Hourly Weather Data, and the root mean square error (RMSE) is used to evaluate the performance of the prediction results. The results of this study show that the bidirectional nested LSTM model has higher prediction accuracy than other LSTM models with the same number of parameters. In addition, the Bidirectional Nested LSTM SVM combined with SVM is still superior to Bidirectional Nested LSTM RF.
|
author2 |
CHEN, PO-HUNG |
author_facet |
CHEN, PO-HUNG DAI, JUN-WEI 戴君瑋 |
author |
DAI, JUN-WEI 戴君瑋 |
spellingShingle |
DAI, JUN-WEI 戴君瑋 Bidirectional Nested Long short-term memory based SVM Classifier |
author_sort |
DAI, JUN-WEI |
title |
Bidirectional Nested Long short-term memory based SVM Classifier |
title_short |
Bidirectional Nested Long short-term memory based SVM Classifier |
title_full |
Bidirectional Nested Long short-term memory based SVM Classifier |
title_fullStr |
Bidirectional Nested Long short-term memory based SVM Classifier |
title_full_unstemmed |
Bidirectional Nested Long short-term memory based SVM Classifier |
title_sort |
bidirectional nested long short-term memory based svm classifier |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/eadn5r |
work_keys_str_mv |
AT daijunwei bidirectionalnestedlongshorttermmemorybasedsvmclassifier AT dàijūnwěi bidirectionalnestedlongshorttermmemorybasedsvmclassifier AT daijunwei jīyúshuāngxiàngcháozhuàngzhǎngduǎnqījìyìzhīzhīchíxiàngliàngjīfēnlèiqì AT dàijūnwěi jīyúshuāngxiàngcháozhuàngzhǎngduǎnqījìyìzhīzhīchíxiàngliàngjīfēnlèiqì |
_version_ |
1719262605952942080 |