Pub Date : 2022-02-01DOI: 10.4108/eai.1-2-2022.173294
R. Shalini, R. Manoharan
. Abstract Blockchain technology is a revolution started as a new economy with an alternative currency namely Bitcoin. Besides the economical aspect, the technological capabilities of Blockchain such as distributed computing, record keeping, irrecoverability of transactions, reliability and etc., are harnessed by variety of real-world applications. Blockchain is a rising pool of records known as blocks linked using security procedure. It is typically managed by a group of nodes in a distributed network technology which integrates technologies such as distributed ledger, security and consensus algorithm to ensure reliability and immutability. In Blockchain, the access privileges are determined by a set of nodes called miners, which run the consensus algorithm to access and submit transactions in to the block after authentication. However, in the existing Blockchain, there is no mechanism to ensure the trust and robustness of the miners and eliminate the malicious miners which runs the consensus algorithm. Therefore, this paper proposes a trust model with an objective of eliminating untrusted nodes from the mining process to enhance the reliability and security of the Blockchain. Further, the proposed trust model is suitably analysed for transaction rate, efficiency and scalability with Hyper Ledger framework to ensure the robustness.
{"title":"Trust Model for Effective Consensus in Blockchain","authors":"R. Shalini, R. Manoharan","doi":"10.4108/eai.1-2-2022.173294","DOIUrl":"https://doi.org/10.4108/eai.1-2-2022.173294","url":null,"abstract":". Abstract Blockchain technology is a revolution started as a new economy with an alternative currency namely Bitcoin. Besides the economical aspect, the technological capabilities of Blockchain such as distributed computing, record keeping, irrecoverability of transactions, reliability and etc., are harnessed by variety of real-world applications. Blockchain is a rising pool of records known as blocks linked using security procedure. It is typically managed by a group of nodes in a distributed network technology which integrates technologies such as distributed ledger, security and consensus algorithm to ensure reliability and immutability. In Blockchain, the access privileges are determined by a set of nodes called miners, which run the consensus algorithm to access and submit transactions in to the block after authentication. However, in the existing Blockchain, there is no mechanism to ensure the trust and robustness of the miners and eliminate the malicious miners which runs the consensus algorithm. Therefore, this paper proposes a trust model with an objective of eliminating untrusted nodes from the mining process to enhance the reliability and security of the Blockchain. Further, the proposed trust model is suitably analysed for transaction rate, efficiency and scalability with Hyper Ledger framework to ensure the robustness.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85876806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-01DOI: 10.4108/eai.1-2-2022.173292
P. Deepan, L. R. Sudha, K. Kalaivani, J. Ganesh
Remote Sensing Image (RSI) analysis has seen a massive increase in popularity over the last few decades, due to the advancement of deep learning models. A wide variety of deep learning models have emerged for the task of scene classification in remote sensing image analysis. The majority of these models have shown significant success. However, we found that there is significant variability, in order to improve the system efficiency in characterizing complex patterns in remote sensing imagery. We achieved this goal by expanding the architecture of VGG-16 Net and fine-tuning hyperparameters such as batch size, dropout probabilities, and activation functions to create the optimized Remote Sensing Image Scene Classification (RSISC-16 Net) deep learning model for scene classification. Using the Talos optimization tool, the results are carried out. This will increase efficiency and reduce the risk of over-fitting. Our proposed RSISC-16 Net model outperforms the VGG-16 Net model, according to experimental results.
{"title":"Scene Classification of Remotely Sensed Images using Optimized RSISC-16 Net Deep Convolutional Neural Network Model","authors":"P. Deepan, L. R. Sudha, K. Kalaivani, J. Ganesh","doi":"10.4108/eai.1-2-2022.173292","DOIUrl":"https://doi.org/10.4108/eai.1-2-2022.173292","url":null,"abstract":"Remote Sensing Image (RSI) analysis has seen a massive increase in popularity over the last few decades, due to the advancement of deep learning models. A wide variety of deep learning models have emerged for the task of scene classification in remote sensing image analysis. The majority of these models have shown significant success. However, we found that there is significant variability, in order to improve the system efficiency in characterizing complex patterns in remote sensing imagery. We achieved this goal by expanding the architecture of VGG-16 Net and fine-tuning hyperparameters such as batch size, dropout probabilities, and activation functions to create the optimized Remote Sensing Image Scene Classification (RSISC-16 Net) deep learning model for scene classification. Using the Talos optimization tool, the results are carried out. This will increase efficiency and reduce the risk of over-fitting. Our proposed RSISC-16 Net model outperforms the VGG-16 Net model, according to experimental results.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84233653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-01DOI: 10.4108/eai.1-2-2022.173293
M. Akhtar, Tao Feng
Incorporating digital technologies into security systems is a positive development. It's time for the digital system to be appropriately protected from potential threats and attacks. An intrusion detection system can identify both external and internal anomalies in the network. There are a variety of threats out there, both active and passive. If these dangers aren't addressed, attacks and data theft could occur from the point of origin all the way to the point of destination. Machine learning is still in its infancy, despite its wide range of applications. It is possible to predict the future by using machine learning. A cyber-attack detection system is depicted in this study using machine learning models. Machine learning algorithms were trained to predict cyber-attack scores using data from prior cyber-attacks on an open source website. In order to detect an attack at its earliest possible stage, this research also examined multiple linear machine learning algorithm-based categorization models. Classifiers' accuracy is also compared in the presentation, as is the presentation itself. Balance procedures were followed. Radio Frequency and GBC have the best accuracy, at 87.93%, followed by ABC at 86.11%, BT at 81.03%, ET at 70.31%, and DT at 70.31 percent (84.48 percent ).
{"title":"Comparison of Classification Model for the Detection of Cyber-attack using Ensemble Learning Models","authors":"M. Akhtar, Tao Feng","doi":"10.4108/eai.1-2-2022.173293","DOIUrl":"https://doi.org/10.4108/eai.1-2-2022.173293","url":null,"abstract":"Incorporating digital technologies into security systems is a positive development. It's time for the digital system to be appropriately protected from potential threats and attacks. An intrusion detection system can identify both external and internal anomalies in the network. There are a variety of threats out there, both active and passive. If these dangers aren't addressed, attacks and data theft could occur from the point of origin all the way to the point of destination. Machine learning is still in its infancy, despite its wide range of applications. It is possible to predict the future by using machine learning. A cyber-attack detection system is depicted in this study using machine learning models. Machine learning algorithms were trained to predict cyber-attack scores using data from prior cyber-attacks on an open source website. In order to detect an attack at its earliest possible stage, this research also examined multiple linear machine learning algorithm-based categorization models. Classifiers' accuracy is also compared in the presentation, as is the presentation itself. Balance procedures were followed. Radio Frequency and GBC have the best accuracy, at 87.93%, followed by ABC at 86.11%, BT at 81.03%, ET at 70.31%, and DT at 70.31 percent (84.48 percent ).","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85590809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-27DOI: 10.4108/eai.27-1-2022.173163
Faiz Ullah, K. Kumar, M. Khuhro, A. Laghari, A. Wagan, Umair Saeed
INTRODUCTION: In image processing noise removal is a hot research field. Lots of studies have been carried out and many algorithms and filters have been planned to improve the image information. There are various noise removal procedures to identify and remove the corrupted pixels. But several image de-noising algorithms apply the filter to the overall image to filter non-corrupted pixels also. To overcome these weaknesses, we proposed an efficient denoising algorithm by cascading Adaptive Median Filter (AMF) with Modified Decision Based Median Filter (MDBMF). OBJECTIVES: To acquire an efficient denoising algorithm for impulse noise reduction by combining AMF and MDBMF methods which are effective, efficient for denoising various kinds of images. To retain the edges, prevent signal deterioration, and ensure non-corrupted image pixels are remaining intact, regardless of various degrees of noise in the image. To avoid the condition where noisy pixels are replaced by other noisy pixels to maintain the quality of images from its degraded noise version such as blur which often takes place during transmission, acquisition, storage, etc. METHODS, RESULTS AND CONCLUSION: The performance corroboration of the proposed efficient denoising algorithmis accomplished employing nine standard grayscale images. The size of all standard images kept 256x256 pixels in this research. The proposed image denoising system has experimented on those images affected with 10% to 90% salt & pepper noise density. Additionally, the performance of the existing state-of-art denoising techniques like AMF, MF, WMF, UMF, and DBMF are contrasted with the proposed hybrid approach. The results showed that de-noised images obtained for 10% to 90% densities levels by proposed hybrid approach are quite better than the quality of denoised images achieved from WMF, UTMF, AMF, and DBMF methods. The proposed algorithm effectively eradicates salt and pepper noise for lower to higher image noise densities
{"title":"An Efficient Algorithm for Image De-noising by using Adaptive Modified Decision Based Median Filters","authors":"Faiz Ullah, K. Kumar, M. Khuhro, A. Laghari, A. Wagan, Umair Saeed","doi":"10.4108/eai.27-1-2022.173163","DOIUrl":"https://doi.org/10.4108/eai.27-1-2022.173163","url":null,"abstract":"INTRODUCTION: In image processing noise removal is a hot research field. Lots of studies have been carried out and many algorithms and filters have been planned to improve the image information. There are various noise removal procedures to identify and remove the corrupted pixels. But several image de-noising algorithms apply the filter to the overall image to filter non-corrupted pixels also. To overcome these weaknesses, we proposed an efficient denoising algorithm by cascading Adaptive Median Filter (AMF) with Modified Decision Based Median Filter (MDBMF). OBJECTIVES: To acquire an efficient denoising algorithm for impulse noise reduction by combining AMF and MDBMF methods which are effective, efficient for denoising various kinds of images. To retain the edges, prevent signal deterioration, and ensure non-corrupted image pixels are remaining intact, regardless of various degrees of noise in the image. To avoid the condition where noisy pixels are replaced by other noisy pixels to maintain the quality of images from its degraded noise version such as blur which often takes place during transmission, acquisition, storage, etc. METHODS, RESULTS AND CONCLUSION: The performance corroboration of the proposed efficient denoising algorithmis accomplished employing nine standard grayscale images. The size of all standard images kept 256x256 pixels in this research. The proposed image denoising system has experimented on those images affected with 10% to 90% salt & pepper noise density. Additionally, the performance of the existing state-of-art denoising techniques like AMF, MF, WMF, UMF, and DBMF are contrasted with the proposed hybrid approach. The results showed that de-noised images obtained for 10% to 90% densities levels by proposed hybrid approach are quite better than the quality of denoised images achieved from WMF, UTMF, AMF, and DBMF methods. The proposed algorithm effectively eradicates salt and pepper noise for lower to higher image noise densities","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78320041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-27DOI: 10.4108/eai.27-1-2022.173165
Rui Yang, Dahai Li
Attention mechanism is widely used in fine-grained image classification. Most of the existing methods are to construct an attention weight map for simple weighted processing of features, but there are problems of low efficiency and slow convergence. Therefore, this paper proposes a multi-channel attention fusion mechanism based on the deep neural network model which can be trained end-to-end. Firstly, the different regions corresponding to the object are described by the attention diagram. Then the corresponding higher order statistical characteristics are extracted to obtain the corresponding representation. In many standard fine-grained image classification test tasks, the proposed method works best compared with other methods.
{"title":"Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification","authors":"Rui Yang, Dahai Li","doi":"10.4108/eai.27-1-2022.173165","DOIUrl":"https://doi.org/10.4108/eai.27-1-2022.173165","url":null,"abstract":"Attention mechanism is widely used in fine-grained image classification. Most of the existing methods are to construct an attention weight map for simple weighted processing of features, but there are problems of low efficiency and slow convergence. Therefore, this paper proposes a multi-channel attention fusion mechanism based on the deep neural network model which can be trained end-to-end. Firstly, the different regions corresponding to the object are described by the attention diagram. Then the corresponding higher order statistical characteristics are extracted to obtain the corresponding representation. In many standard fine-grained image classification test tasks, the proposed method works best compared with other methods.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73589613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-27DOI: 10.4108/eai.27-1-2022.173162
Aizhen Liu
In this paper, we propose a new music emotion recognition method based on long short-term memory and forward neural network. First, Mel Frequency Cepstral Coefficient (MFCC) and Residual Phase (RP) are weighted to extract music emotion features, which improves the recognition efficiency of music emotion features. Meanwhile, in order to improve the classification accuracy of music emotion and shorten the training time of the new model, Long short-term Memory network (LSTM) and forward neural network (FNN) are combined. Using LSTM as the feature mapping node of FNN, a new deep learning network (LSTM-FNN) is proposed for music emotion recognition and classification training. Finally, we conduct the experiments on the emotion data set. The results show that the proposed algorithm achieves higher recognition accuracy than other state-of-the-art complex networks.
{"title":"Music Emotion Recognition Based on Long Short-Term Memory and Forward Neural Network","authors":"Aizhen Liu","doi":"10.4108/eai.27-1-2022.173162","DOIUrl":"https://doi.org/10.4108/eai.27-1-2022.173162","url":null,"abstract":"In this paper, we propose a new music emotion recognition method based on long short-term memory and forward neural network. First, Mel Frequency Cepstral Coefficient (MFCC) and Residual Phase (RP) are weighted to extract music emotion features, which improves the recognition efficiency of music emotion features. Meanwhile, in order to improve the classification accuracy of music emotion and shorten the training time of the new model, Long short-term Memory network (LSTM) and forward neural network (FNN) are combined. Using LSTM as the feature mapping node of FNN, a new deep learning network (LSTM-FNN) is proposed for music emotion recognition and classification training. Finally, we conduct the experiments on the emotion data set. The results show that the proposed algorithm achieves higher recognition accuracy than other state-of-the-art complex networks.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80037890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-27DOI: 10.4108/eai.27-1-2022.173166
Haiying Liu
Text classification is one of the core tasks in the field of natural language processing. Aiming at the advantages and disadvantages of current deep learning-based English text classification methods in long text classification, this paper proposes an English text classification model, which introduces multi-attention mechanism based on gate recurrent unit (GRU) to focus on important parts of English text. Firstly, sentences and documents are encoded according to the hierarchical structure of English documents. Second, it uses the attention mechanism separately at each level. On the basis of the global object vector, the maximum pooling is used to extract the specific object vector of sentence, so that the encoded document vector has more obvious category features and can pay more attention to the most distinctive semantic features of each English text. Finally, documents are classified according to the constructed English document representation. Experimental results on public data sets show that this model has better classification performance for long English texts with hierarchical structure.
{"title":"Multi-attention mechanism based on gate recurrent unit for English text classification","authors":"Haiying Liu","doi":"10.4108/eai.27-1-2022.173166","DOIUrl":"https://doi.org/10.4108/eai.27-1-2022.173166","url":null,"abstract":"Text classification is one of the core tasks in the field of natural language processing. Aiming at the advantages and disadvantages of current deep learning-based English text classification methods in long text classification, this paper proposes an English text classification model, which introduces multi-attention mechanism based on gate recurrent unit (GRU) to focus on important parts of English text. Firstly, sentences and documents are encoded according to the hierarchical structure of English documents. Second, it uses the attention mechanism separately at each level. On the basis of the global object vector, the maximum pooling is used to extract the specific object vector of sentence, so that the encoded document vector has more obvious category features and can pay more attention to the most distinctive semantic features of each English text. Finally, documents are classified according to the constructed English document representation. Experimental results on public data sets show that this model has better classification performance for long English texts with hierarchical structure.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89137635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-27DOI: 10.4108/eai.27-1-2022.173161
Zengyong Xu
By using the traditional methods, the feature information extracted from vehicle target detection is insufficient, which leads to the low accuracy in identifying small target vehicles or blocked targets. Therefore, we propose a region proposal network (RPN) based on context information feature fusion for vehicle detection. RPN obtains feature vectors of fixed length as vehicle target features. Context information fusion network obtains the corresponding context information features on the feature maps of different layers. Finally, the two features are fused. In addition, in order to solve the problem of data imbalance, experiments on PASCAL VOC2007 and PASCAL VOC2012 data sets with difficult sample training show that the proposed method has significantly improved the mean average accuracy (mAP) compared with other methods.
{"title":"Region proposal network based on context information feature fusion for vehicle detection","authors":"Zengyong Xu","doi":"10.4108/eai.27-1-2022.173161","DOIUrl":"https://doi.org/10.4108/eai.27-1-2022.173161","url":null,"abstract":"By using the traditional methods, the feature information extracted from vehicle target detection is insufficient, which leads to the low accuracy in identifying small target vehicles or blocked targets. Therefore, we propose a region proposal network (RPN) based on context information feature fusion for vehicle detection. RPN obtains feature vectors of fixed length as vehicle target features. Context information fusion network obtains the corresponding context information features on the feature maps of different layers. Finally, the two features are fused. In addition, in order to solve the problem of data imbalance, experiments on PASCAL VOC2007 and PASCAL VOC2012 data sets with difficult sample training show that the proposed method has significantly improved the mean average accuracy (mAP) compared with other methods.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73547189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-27DOI: 10.4108/eai.27-1-2022.173164
Yachao Zhang, Yuxia Yuan
Road scene understanding is one of the important modules in the field of autonomous driving. It can provide more information about roads and play an important role in building high-precision maps and real-time planning. Among them, semantic segmentation can assign category information to each pixel of image, which is the most commonly used method in automatic driving scene understanding. However, most commonly used semantic segmentation algorithms cannot achieve a good balance between speed and precision. In this paper, a road scene segmentation model based on dilated convolutional neural network is constructed. The model consists of a front-end module and a context module. The front-end module is an improved structure of VGG-16 fused dilated convolution, and the context module is a cascade of dilated convolution layers with different expansion coefficients, which is trained by a two-stage training method. The network proposed in this paper can run in real time and ensure the accuracy to meet the requirements of practical applications, and has been verified and analyzed on Cityscapes data set.
{"title":"A novel dilated convolutional neural network model for road scene segmentation","authors":"Yachao Zhang, Yuxia Yuan","doi":"10.4108/eai.27-1-2022.173164","DOIUrl":"https://doi.org/10.4108/eai.27-1-2022.173164","url":null,"abstract":"Road scene understanding is one of the important modules in the field of autonomous driving. It can provide more information about roads and play an important role in building high-precision maps and real-time planning. Among them, semantic segmentation can assign category information to each pixel of image, which is the most commonly used method in automatic driving scene understanding. However, most commonly used semantic segmentation algorithms cannot achieve a good balance between speed and precision. In this paper, a road scene segmentation model based on dilated convolutional neural network is constructed. The model consists of a front-end module and a context module. The front-end module is an improved structure of VGG-16 fused dilated convolution, and the context module is a cascade of dilated convolution layers with different expansion coefficients, which is trained by a two-stage training method. The network proposed in this paper can run in real time and ensure the accuracy to meet the requirements of practical applications, and has been verified and analyzed on Cityscapes data set.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75091157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-13DOI: 10.4108/eai.13-1-2022.172818
X. Guo
In this paper, we propose an automatic scoring method for Chinese-English spoken translation based on attention LSTM. We select semantic keywords, sentence drift and spoken fluency as the main parameters of scoring. In order to improve the accuracy of keyword scoring, this paper uses synonym discrimination method to identify the synonyms in the examinees' answer keywords. At the sentence level, attention LSTM model is used to analyze examinees' translation of sentence general idea. Finally, spoken fluency is scored based on tempo/rate and speech distribution. The final translation quality score is obtained by combining the weighted scores of the three parameters. The experimental results show that the proposed method is in good agreement with the result of manual grading, and achieves the expected design goal compared with other methods.
{"title":"An automatic scoring method for Chinese-English spoken translation based on attention LSTM","authors":"X. Guo","doi":"10.4108/eai.13-1-2022.172818","DOIUrl":"https://doi.org/10.4108/eai.13-1-2022.172818","url":null,"abstract":"In this paper, we propose an automatic scoring method for Chinese-English spoken translation based on attention LSTM. We select semantic keywords, sentence drift and spoken fluency as the main parameters of scoring. In order to improve the accuracy of keyword scoring, this paper uses synonym discrimination method to identify the synonyms in the examinees' answer keywords. At the sentence level, attention LSTM model is used to analyze examinees' translation of sentence general idea. Finally, spoken fluency is scored based on tempo/rate and speech distribution. The final translation quality score is obtained by combining the weighted scores of the three parameters. The experimental results show that the proposed method is in good agreement with the result of manual grading, and achieves the expected design goal compared with other methods.","PeriodicalId":43034,"journal":{"name":"EAI Endorsed Transactions on Scalable Information Systems","volume":null,"pages":null},"PeriodicalIF":1.3,"publicationDate":"2022-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80428142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：