Pub Date : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012196
Zhenbing Liu, Xinlong Li, Weiwei Li, Rushi Lan, Xiaonan Luo
Along with the development of deep learning, convolutional neural networks (CNN) have become more and more widely used in the field of image compression, and have made image compression technology significantly improved on performance and cost. In order to make the image better preserve the details and texture of the original image while compressing, we propose a novel method to optimize image compression. We first focus on slight deformation image which is changed by original image, which means that we preserve the features of image detail information when the bits are not increased, and then the deformed image is transmitted to our network framework to achieve image compression and the reconstruction process. In our system, first, a multi-scale convolutional neural network is used to learn the best compact representation from the input image to achieve the purpose of extracting multiscale structural information of natural images. The result of compact representation is then encoded and decoded by a conventional image codec. Finally, a reconstructed convolutional neural network is used for reconstructing the decoded image with high quality and accurate quality at the decoding end. Experimental results demonstrate that our network is superior to most existing methods and can improve image quality with more visual detail.
{"title":"An Image Compression Framework Based on Multi-scale Convolutional Neural Network for Deformation Images","authors":"Zhenbing Liu, Xinlong Li, Weiwei Li, Rushi Lan, Xiaonan Luo","doi":"10.1109/ICICIP47338.2019.9012196","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012196","url":null,"abstract":"Along with the development of deep learning, convolutional neural networks (CNN) have become more and more widely used in the field of image compression, and have made image compression technology significantly improved on performance and cost. In order to make the image better preserve the details and texture of the original image while compressing, we propose a novel method to optimize image compression. We first focus on slight deformation image which is changed by original image, which means that we preserve the features of image detail information when the bits are not increased, and then the deformed image is transmitted to our network framework to achieve image compression and the reconstruction process. In our system, first, a multi-scale convolutional neural network is used to learn the best compact representation from the input image to achieve the purpose of extracting multiscale structural information of natural images. The result of compact representation is then encoded and decoded by a conventional image codec. Finally, a reconstructed convolutional neural network is used for reconstructing the decoded image with high quality and accurate quality at the decoding end. Experimental results demonstrate that our network is superior to most existing methods and can improve image quality with more visual detail.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127587320","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012183
Yueqin Li, Zhi-hui Zhan, Hu Jin, Jun Zhang
Although evolutionary algorithms (EAs) have been widely applied in static optimization problems (SOPs), it is still a great challenge for EAs to solve dynamic optimization problems (DOPs). This paper proposes a Cloudde-based differential evolution (CDDE) algorithm based on Message Passing Interface (MPI) technology to solve DOPs. During the evolutionary process, different populations are sent to different slave processes to perform mutation and crossover operations independently using different evolution strategies and then return to the master process to apply migration operation under an adaptive probability. Experimental studies were taken on several DOPs generated by the Generalized Dynamic Benchmark Generator (GDBG) which was used in 2009 IEEE Congress on Evolutionary Computation (CEC2009). The simulation result indicates that the proposed algorithm achieves promising performance in a statistical efficient manner.
{"title":"Cloudde-based Distributed Differential Evolution for Solving Dynamic Optimization Problems","authors":"Yueqin Li, Zhi-hui Zhan, Hu Jin, Jun Zhang","doi":"10.1109/ICICIP47338.2019.9012183","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012183","url":null,"abstract":"Although evolutionary algorithms (EAs) have been widely applied in static optimization problems (SOPs), it is still a great challenge for EAs to solve dynamic optimization problems (DOPs). This paper proposes a Cloudde-based differential evolution (CDDE) algorithm based on Message Passing Interface (MPI) technology to solve DOPs. During the evolutionary process, different populations are sent to different slave processes to perform mutation and crossover operations independently using different evolution strategies and then return to the master process to apply migration operation under an adaptive probability. Experimental studies were taken on several DOPs generated by the Generalized Dynamic Benchmark Generator (GDBG) which was used in 2009 IEEE Congress on Evolutionary Computation (CEC2009). The simulation result indicates that the proposed algorithm achieves promising performance in a statistical efficient manner.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116564574","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012172
Ningning Zhou, Yang Liu, Long Hong
Super-pixel can improve the computational efficiency of image segmentation algorithm, which is a description of image with more visual significance. The research on super-pixel extraction algorithm has always been a hot spot of current research. SLIC is a common super-pixel extraction algorithm. This method can generate compact and nearly uniform super-pixels. It has a high comprehensive evaluation in the aspects of computing speed, object contour preservation and super-pixel shape. As a result it has been widely used. However, when extracting SLIC (Simple Linear Iterative Clustering) super-pixel blocks, the determination of weight m needs to be specified manually, and the same weight value for different images leads to the problem of unsatisfactory segmentation effect. In order to solve this problem, this paper introduces the medium mathematics used to deal with the fuzzy phenomenon into the super-pixel extraction, and proposes a super-pixel extraction algorithm based on MMTD (Measuring of Medium Truth Scale) and applies it to image segmentation. Firstly, the similarity between Lab distance and coordinate distance is obtained based on MMTD. Then, the weight m of SLIC super-pixel extraction algorithm is adaptively determined by iteration method. Finally, the isolated points are corrected by connected components. The experimental results show that this algorithm has better super-pixel extraction effect than the SLIC algorithm, which can effectively improve the quality of image segmentation in the later stage.
超像素可以提高图像分割算法的计算效率，是一种更具有视觉意义的图像描述。超像素提取算法的研究一直是当前研究的热点。SLIC是一种常用的超像素提取算法。该方法可以生成紧凑且几乎均匀的超像素。它在计算速度、目标轮廓保持和超像素形状等方面具有较高的综合评价。因此，它已被广泛使用。然而，在提取SLIC (Simple Linear Iterative Clustering，简单线性迭代聚类)超像素块时，需要手动指定权值m的确定，不同图像的权值相同会导致分割效果不理想的问题。为了解决这一问题，本文将处理模糊现象的介质数学引入到超像素提取中，提出了一种基于MMTD (measurement of medium Truth Scale)的超像素提取算法，并将其应用到图像分割中。首先，基于MMTD得到实验室距离与坐标距离的相似度;然后，采用迭代法自适应确定SLIC超像素提取算法的权值m;最后，通过连通分量对孤立点进行校正。实验结果表明，该算法比SLIC算法具有更好的超像素提取效果，可以有效提高后期图像分割的质量。
{"title":"An Improved SLIC Super-pixel Extraction Algorithm Based on MMTD","authors":"Ningning Zhou, Yang Liu, Long Hong","doi":"10.1109/ICICIP47338.2019.9012172","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012172","url":null,"abstract":"Super-pixel can improve the computational efficiency of image segmentation algorithm, which is a description of image with more visual significance. The research on super-pixel extraction algorithm has always been a hot spot of current research. SLIC is a common super-pixel extraction algorithm. This method can generate compact and nearly uniform super-pixels. It has a high comprehensive evaluation in the aspects of computing speed, object contour preservation and super-pixel shape. As a result it has been widely used. However, when extracting SLIC (Simple Linear Iterative Clustering) super-pixel blocks, the determination of weight m needs to be specified manually, and the same weight value for different images leads to the problem of unsatisfactory segmentation effect. In order to solve this problem, this paper introduces the medium mathematics used to deal with the fuzzy phenomenon into the super-pixel extraction, and proposes a super-pixel extraction algorithm based on MMTD (Measuring of Medium Truth Scale) and applies it to image segmentation. Firstly, the similarity between Lab distance and coordinate distance is obtained based on MMTD. Then, the weight m of SLIC super-pixel extraction algorithm is adaptively determined by iteration method. Finally, the isolated points are corrected by connected components. The experimental results show that this algorithm has better super-pixel extraction effect than the SLIC algorithm, which can effectively improve the quality of image segmentation in the later stage.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131269738","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012213
Jing Huang, Shuguo Yang, Wenwu Wang
Content-based image retrieval is an active area of research where image content is used to guide the search of relevant images from a dataset. Given a query image, the images in the dataset are ranked in terms of their scores of similarity to this image based on their visual appearance. Many existing algorithms are based on either single feature or the fusion of multi-features with a one-step search method, which may lead to undesirable results due to the mismatch between low-level features and high-level semantics. To address this issue, we propose a two-stage sequential search algorithm where the color feature, represented by a color histogram in the HSV space, is used to form an image set containing images of similar color distributions to that of the query image, then a second stage of search is performed via the matching of feature points, in terms of discrete wavelet transform (DWT), and the scale invariant feature transform (SIFT) feature, extracted from a low-frequency subgraph. Experiments are performed on the ZuBuD dataset and UKBench dataset. Compared to some state-of-the-art algorithms, the proposed algorithm gives higher precision score.
{"title":"A Method for Content-Based Image Retrieval with a Two-Stage Feature Matching","authors":"Jing Huang, Shuguo Yang, Wenwu Wang","doi":"10.1109/ICICIP47338.2019.9012213","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012213","url":null,"abstract":"Content-based image retrieval is an active area of research where image content is used to guide the search of relevant images from a dataset. Given a query image, the images in the dataset are ranked in terms of their scores of similarity to this image based on their visual appearance. Many existing algorithms are based on either single feature or the fusion of multi-features with a one-step search method, which may lead to undesirable results due to the mismatch between low-level features and high-level semantics. To address this issue, we propose a two-stage sequential search algorithm where the color feature, represented by a color histogram in the HSV space, is used to form an image set containing images of similar color distributions to that of the query image, then a second stage of search is performed via the matching of feature points, in terms of discrete wavelet transform (DWT), and the scale invariant feature transform (SIFT) feature, extracted from a low-frequency subgraph. Experiments are performed on the ZuBuD dataset and UKBench dataset. Compared to some state-of-the-art algorithms, the proposed algorithm gives higher precision score.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132748878","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012159
Jiasen Wang, Jun Wang, Wei Zhang
In this paper, neural networks based on linearly translated features (LTFs) are presented. LTFs including uniform, non-uniform, and multiple translation vectors are embedded into feedforward neural networks. Learning algorithms are presented for the neural networks. Learning capabilities of the neural networks are analyzed. Experimental results on approximation’ identification, and evaluation problems are reported to substantiate the efficacy of the neural networks and learning algorithms.
{"title":"Design and Analysis of Neural Networks Based on Linearly Translated Features","authors":"Jiasen Wang, Jun Wang, Wei Zhang","doi":"10.1109/ICICIP47338.2019.9012159","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012159","url":null,"abstract":"In this paper, neural networks based on linearly translated features (LTFs) are presented. LTFs including uniform, non-uniform, and multiple translation vectors are embedded into feedforward neural networks. Learning algorithms are presented for the neural networks. Learning capabilities of the neural networks are analyzed. Experimental results on approximation’ identification, and evaluation problems are reported to substantiate the efficacy of the neural networks and learning algorithms.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130769364","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012197
J. Rochac, L. Liang, N. Zhang, T. Oladunni
In recent years, using oceans of data and virtually infinite cloud-based computation power, deep learning models leverage the current state-of-the-art classification to reach expert level performance. Researchers continue to explore applications of deep machine learning models ranging from face-, text- and voice-recognition to signal and information processing. With the continuously increasing data collection capabilities, datasets are becoming larger and more dimensional. However, manually labeled data points cannot keep up. It is this disparity between the high number of features and the low number of labeled samples what motivates a new approach to integrate feature reduction and sample augmentation to deep learning classifiers. This paper explores the performance of such approach on three deep learning classifiers: MLP, CNN, and LSTM. First, we establish a baseline using the original dataset. Second, we preprocess the dataset using principal component analysis (PCA). Third, we preprocess the dataset with PCA followed by our Gaussian data augmentation (GDA) technique. To estimate performance, we add k-fold cross-validation to our experiments and compile our results in a numerical and graphical using the confusion matrix and a classification report that includes accuracy, recall, f-score and support. Our experiments suggest superior classification accuracy of all three classifiers in the presence of our PCA+GDA approach.
{"title":"A Gaussian Data Augmentation Technique on Highly Dimensional, Limited Labeled Data for Multiclass Classification Using Deep Learning","authors":"J. Rochac, L. Liang, N. Zhang, T. Oladunni","doi":"10.1109/ICICIP47338.2019.9012197","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012197","url":null,"abstract":"In recent years, using oceans of data and virtually infinite cloud-based computation power, deep learning models leverage the current state-of-the-art classification to reach expert level performance. Researchers continue to explore applications of deep machine learning models ranging from face-, text- and voice-recognition to signal and information processing. With the continuously increasing data collection capabilities, datasets are becoming larger and more dimensional. However, manually labeled data points cannot keep up. It is this disparity between the high number of features and the low number of labeled samples what motivates a new approach to integrate feature reduction and sample augmentation to deep learning classifiers. This paper explores the performance of such approach on three deep learning classifiers: MLP, CNN, and LSTM. First, we establish a baseline using the original dataset. Second, we preprocess the dataset using principal component analysis (PCA). Third, we preprocess the dataset with PCA followed by our Gaussian data augmentation (GDA) technique. To estimate performance, we add k-fold cross-validation to our experiments and compile our results in a numerical and graphical using the confusion matrix and a classification report that includes accuracy, recall, f-score and support. Our experiments suggest superior classification accuracy of all three classifiers in the presence of our PCA+GDA approach.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115595815","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}
Due to the complicated behavior of the ocean wave, significant wave height (SWH) prediction is a difficult field in physical oceanography. In this paper, a novel neural network model, based on multiple sine functions decomposition (MSFD), is exploited to achieve the prediction of SWH. Different from traditional models built on physical processes of wave generation and dissipation, the method presented in this paper predicts and analyzes SWH from a mathematical statistical perspective. In particular, the variation rules of the SWH are learned by decomposing the mapping from time to SWH into a plurality of sine functions, and then the new data are predicted by linear combination of these sine functions. Correlation analysis and error between the forecast data and the actual data indicate that the MSFD neural network performs well in predicting SWH data.
{"title":"Significant Wave Height Prediction Based on MSFD Neural Network","authors":"Huan Wang, Dongyang Fu, Shan Liao, Guancheng Wang, Xiuchun Xiao","doi":"10.1109/ICICIP47338.2019.9012194","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012194","url":null,"abstract":"Due to the complicated behavior of the ocean wave, significant wave height (SWH) prediction is a difficult field in physical oceanography. In this paper, a novel neural network model, based on multiple sine functions decomposition (MSFD), is exploited to achieve the prediction of SWH. Different from traditional models built on physical processes of wave generation and dissipation, the method presented in this paper predicts and analyzes SWH from a mathematical statistical perspective. In particular, the variation rules of the SWH are learned by decomposing the mapping from time to SWH into a plurality of sine functions, and then the new data are predicted by linear combination of these sine functions. Correlation analysis and error between the forecast data and the actual data indicate that the MSFD neural network performs well in predicting SWH data.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125428918","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012186
Wenhui Duan, Xiuchun Xiao, Dongyang Fu, Mei Liu, Jiliang Zhang, Shi Yan, Long Jin
In recent years, with the hypergrowth of the computer technology, the applications of the automatic control in the chemical industry have made significant progress. Due to the inefficiency of traditional industrial agitator tank controllers and the lack of saturated constraints, improving the system capability of agitator tank controllers becomes a thorny problem, which puzzles scholars for many years. To solve this problem, a new kind of agitator tank controller with the fast error convergence rate and the saturated constraint is proposed in this paper. Subsequently, the superiority of the proposed controller is demonstrated by theoretical analysis. Further, the emulations are conducted with the simulation results verifying the superiority of the proposed controller. To some extent, this work increases the production efficiency and quality of the chemical equipment.
{"title":"A Controller of Liquid Material on Fast Saturated Zeroing Dynamics Model in Industrial Agitator Tank","authors":"Wenhui Duan, Xiuchun Xiao, Dongyang Fu, Mei Liu, Jiliang Zhang, Shi Yan, Long Jin","doi":"10.1109/ICICIP47338.2019.9012186","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012186","url":null,"abstract":"In recent years, with the hypergrowth of the computer technology, the applications of the automatic control in the chemical industry have made significant progress. Due to the inefficiency of traditional industrial agitator tank controllers and the lack of saturated constraints, improving the system capability of agitator tank controllers becomes a thorny problem, which puzzles scholars for many years. To solve this problem, a new kind of agitator tank controller with the fast error convergence rate and the saturated constraint is proposed in this paper. Subsequently, the superiority of the proposed controller is demonstrated by theoretical analysis. Further, the emulations are conducted with the simulation results verifying the superiority of the proposed controller. To some extent, this work increases the production efficiency and quality of the chemical equipment.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127065031","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012173
Yuanyuan Xu, Qihe Shan, Tie-shan Li, Min Han
In this paper, an observer-based adaptive fuzzy compensation control scheme of multi-input and multi-output (MIMO) strict-feedback nonlinear systems is developed, where stochastic disturbances, actuator faults and input hysteresis are considered at the same time. The design difficulty of unknown system functions is eliminated via the universal approximators, i.e., fuzzy logic systems, and a reduced-order observer is constructed to estimate the unmeasurable state variables. By applying the backstepping design framework, an adaptive fuzzy controller is constructed that can compensate for the effects of actuator faults/failures and hysteresis nonlinearities when the system operates. It is proved that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB), and the output of a subsystem follows the same trajectory with the corresponding reference signal. Furthermore, a simulation result is demonstrated the validity of the designed scheme.
{"title":"Adaptive Fuzzy Compensation Control of MIMO Stochastic Nonlinear Systems with Input Hysteresis","authors":"Yuanyuan Xu, Qihe Shan, Tie-shan Li, Min Han","doi":"10.1109/ICICIP47338.2019.9012173","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012173","url":null,"abstract":"In this paper, an observer-based adaptive fuzzy compensation control scheme of multi-input and multi-output (MIMO) strict-feedback nonlinear systems is developed, where stochastic disturbances, actuator faults and input hysteresis are considered at the same time. The design difficulty of unknown system functions is eliminated via the universal approximators, i.e., fuzzy logic systems, and a reduced-order observer is constructed to estimate the unmeasurable state variables. By applying the backstepping design framework, an adaptive fuzzy controller is constructed that can compensate for the effects of actuator faults/failures and hysteresis nonlinearities when the system operates. It is proved that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB), and the output of a subsystem follows the same trajectory with the corresponding reference signal. Furthermore, a simulation result is demonstrated the validity of the designed scheme.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114525588","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 : 2019-12-01DOI: 10.1109/ICICIP47338.2019.9012174
Xia He, Long Hong, Guoping Du
Starting from “fuzziness” as a character of pronunciation, this paper proposes the possibility of referencing between different phonetic symbols, and explores the general standards and specific standards of reference. Using the logical quantification tool MMTD, with the qualitative and quantitative analysis, the true value of the reference of the Chinese vowels to the English monophthong is displayed and calculated, and the reference system of the “Chinese Character Reference Frame of English Monophthong” is established. This paper demonstrates the feasibility of the phonetic learning method of “Learning English phonetic with Chinese Character pronunciation”, aiming to provide a path for the development of the phonetic learning concept of learning a foreign phonetic with native language phonetic” and the establishment of other language phonetic pronunciation reference frame.
{"title":"The Establishment of Chinese Character Reference Framework for the English Monophthong","authors":"Xia He, Long Hong, Guoping Du","doi":"10.1109/ICICIP47338.2019.9012174","DOIUrl":"https://doi.org/10.1109/ICICIP47338.2019.9012174","url":null,"abstract":"Starting from “fuzziness” as a character of pronunciation, this paper proposes the possibility of referencing between different phonetic symbols, and explores the general standards and specific standards of reference. Using the logical quantification tool MMTD, with the qualitative and quantitative analysis, the true value of the reference of the Chinese vowels to the English monophthong is displayed and calculated, and the reference system of the “Chinese Character Reference Frame of English Monophthong” is established. This paper demonstrates the feasibility of the phonetic learning method of “Learning English phonetic with Chinese Character pronunciation”, aiming to provide a path for the development of the phonetic learning concept of learning a foreign phonetic with native language phonetic” and the establishment of other language phonetic pronunciation reference frame.","PeriodicalId":431872,"journal":{"name":"2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127677824","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：