Interact of Things has received much attention over the past de cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather ing and related p...Interact of Things has received much attention over the past de cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather ing and related problems arc becoming more complex and uncer tain. Researchers have therefore turned to AI as an efficient way of dealing with the problems created by big data.展开更多
From the viewpoints of both fuzzy system and fuzzy reasoning, a new fuzzy reasoning method which contains the α- triple I restriction method as its particular case is proposed. The previous α-triple I restriction pr...From the viewpoints of both fuzzy system and fuzzy reasoning, a new fuzzy reasoning method which contains the α- triple I restriction method as its particular case is proposed. The previous α-triple I restriction principles are improved, and then the optimal restriction solutions of this new method are achieved, especially for seven familiar implications. As its special case, the corresponding results of α-triple I restriction method are obtained and improved. Lastly, it is found by examples that this new method is more reasonable than the α-triple I restriction method.展开更多
Understanding people's emotions through natural language is a challenging task for intelligent systems based on Internet of Things(Io T). The major difficulty is caused by the lack of basic knowledge in emotion ex...Understanding people's emotions through natural language is a challenging task for intelligent systems based on Internet of Things(Io T). The major difficulty is caused by the lack of basic knowledge in emotion expressions with respect to a variety of real world contexts. In this paper, we propose a Bayesian inference method to explore the latent semantic dimensions as contextual information in natural language and to learn the knowledge of emotion expressions based on these semantic dimensions. Our method synchronously infers the latent semantic dimensions as topics in words and predicts the emotion labels in both word-level and document-level texts. The Bayesian inference results enable us to visualize the connection between words and emotions with respect to different semantic dimensions. And by further incorporating a corpus-level hierarchy in the document emotion distribution assumption, we could balance the document emotion recognition results and achieve even better word and document emotion predictions. Our experiment of the wordlevel and the document-level emotion predictions, based on a well-developed Chinese emotion corpus Ren-CECps, renders both higher accuracy and better robustness in the word-level and the document-level emotion predictions compared to the state-of-theart emotion prediction algorithms.展开更多
In recent years, high-resolution video has developed rapidly and widescreen smart devices have become popular. We present an Android application called WeWatch that enables high-resolution video to be shared across tw...In recent years, high-resolution video has developed rapidly and widescreen smart devices have become popular. We present an Android application called WeWatch that enables high-resolution video to be shared across two mobile devices when they are close to each other. This concept has its inspiration in machine-to-machine connections in the Internet of Things （loT）. We ensure that the two parts of the video are the same size over both screens and are synchronous. Further, a user can play, pause, or stop the video by moving one device a certain distance from the other. We decide on appropriate distances through experimentation. We implemented WeWatch on Android operating system and then optimize Watch so battery consumption is reduced. The user experience provided by WeWatch was evaluated by students through a questionnaire, and the reviews indicated that WeWatch does improve the viewing experience.展开更多
The Internet of Things （IoT） has received much attention over the past decade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gathering （a...The Internet of Things （IoT） has received much attention over the past decade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gathering （and related problems） are becoming more complex and uncertain. Researchers have therefore turned to artificial intelligence （AI） to efficiently deal with the problems ereated by big data.展开更多
Recently,the authors often see words such as youth slang,neologism and Internet slang on social networking sites(SNSs)that are not registered on dictionaries.Since the documents posted to SNSs include a lot of fresh i...Recently,the authors often see words such as youth slang,neologism and Internet slang on social networking sites(SNSs)that are not registered on dictionaries.Since the documents posted to SNSs include a lot of fresh information,they are thought to be useful for collecting information.It is important to analyse these words(hereinafter referred to as‘slang’)and capture their features for the improvement of the accuracy of automatic information collection.This study aims to analyse what features can be observed in slang by focusing on the topic.They construct topic models from document groups including target slang on Twitter by latent Dirichlet allocation.With the models,they chronologically the analyse change of topics during a certain period of time to find out the difference in the features between slang and general words.Then,they propose a slang classification method based on the change of features.展开更多
Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language models.Training ...Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language models.Training data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English resources.This significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain samples.To alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model generation.Furthermore,we employ a multiteacher distillation framework to enhance detection performance with unsupervised data.That is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to AugCOLD.The soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive detector.We conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.展开更多
Insect pest control is considered as a significant factor in the yield of commercial crops.Thus,to avoid economic losses,we need a valid method for insect pest recognition.In this paper,we proposed a feature fusion re...Insect pest control is considered as a significant factor in the yield of commercial crops.Thus,to avoid economic losses,we need a valid method for insect pest recognition.In this paper,we proposed a feature fusion residual block to perform the insect pest recognition task.Based on the original residual block,we fused the feature from a previous layer between two 11 convolution layers in a residual signal branch to improve the capacity of the block.Furthermore,we explored the contribution of each residual group to the model performance.We found that adding the residual blocks of earlier residual groups promotes the model performance significantly,which improves the capacity of generalization of the model.By stacking the feature fusion residual block,we constructed the Deep Feature Fusion Residual Network(DFF-ResNet).To prove the validity and adaptivity of our approach,we constructed it with two common residual networks(Pre-ResNet and Wide Residual Network(WRN))and validated these models on the Canadian Institute For Advanced Research(CIFAR)and Street View House Number(SVHN)benchmark datasets.The experimental results indicate that our models have a lower test error than those of baseline models.Then,we applied our models to recognize insect pests and obtained validity on the IP102 benchmark dataset.The experimental results show that our models outperform the original ResNet and other state-of-the-art methods.展开更多
Emotion recognition has been used widely in various applications such as mental health monitoring and emotional management.Usually,emotion recognition is regarded as a text classification task.Emotion recognition is a...Emotion recognition has been used widely in various applications such as mental health monitoring and emotional management.Usually,emotion recognition is regarded as a text classification task.Emotion recognition is a more complex problem,and the relations of emotions expressed in a text are nonnegligible.In this paper,a hierarchical model with label embedding is proposed for contextual emotion recognition.Especially,a hierarchical model is utilized to learn the emotional representation of a given sentence based on its contextual information.To give emotion correlation-based recognition,a label embedding matrix is trained by joint learning,which contributes to the final prediction.Comparison experiments are conducted on Chinese emotional corpus RenCECps,and the experimental results indicate that our approach has a satisfying performance in textual emotion recognition task.展开更多
The dialogue system has always been one of the important topics in the domain of artificial intelligence.So far,most of the mature dialogue systems are task-oriented based,while non-task-oriented dialogue systems stil...The dialogue system has always been one of the important topics in the domain of artificial intelligence.So far,most of the mature dialogue systems are task-oriented based,while non-task-oriented dialogue systems still have a lot of room for improvement.We propose a data-driven non-task-oriented dialogue generator“CERG”based on neural networks.This model has the emotion recognition capability and can generate corresponding responses.The data set we adopt comes from the NTCIR-14 STC-3 CECG subtask,which contains more than 1.7 million Chinese Weibo post-response pairs and 6 emotion categories.We try to concatenate the post and the response with the emotion,then mask the response part of the input text character by character to emulate the encoder-decoder framework.We use the improved transformer blocks as the core to build the model and add regularization methods to alleviate the problems of overcorrection and exposure bias.We introduce the retrieval method to the inference process to improve the semantic relevance of generated responses.The results of the manual evaluation show that our proposed model can make different responses to different emotions to improve the human-computer interaction experience.This model can be applied to lots of domains,such as automatic reply robots of social application.展开更多
文摘Interact of Things has received much attention over the past de cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather ing and related problems arc becoming more complex and uncer tain. Researchers have therefore turned to AI as an efficient way of dealing with the problems created by big data.
基金supported by the National Natural Science Foundation of China (61105076 61070124)+2 种基金the National High Technology Research and Development Program of China (863 Program) (2012AA011103)the Open Project of State Key Laboratory of Virtual Reality Technology and Systems of China (BUAA-VR-10KF-5)the Fundamental Research Funds for the Central Universities (2011HGZY0004)
文摘From the viewpoints of both fuzzy system and fuzzy reasoning, a new fuzzy reasoning method which contains the α- triple I restriction method as its particular case is proposed. The previous α-triple I restriction principles are improved, and then the optimal restriction solutions of this new method are achieved, especially for seven familiar implications. As its special case, the corresponding results of α-triple I restriction method are obtained and improved. Lastly, it is found by examples that this new method is more reasonable than the α-triple I restriction method.
基金supported in part by the National Natural Science Foundation of China(NSFC)Key Program(61573094)Fundamental Research Funds for the Central Universities(N140402001)
文摘Understanding people's emotions through natural language is a challenging task for intelligent systems based on Internet of Things(Io T). The major difficulty is caused by the lack of basic knowledge in emotion expressions with respect to a variety of real world contexts. In this paper, we propose a Bayesian inference method to explore the latent semantic dimensions as contextual information in natural language and to learn the knowledge of emotion expressions based on these semantic dimensions. Our method synchronously infers the latent semantic dimensions as topics in words and predicts the emotion labels in both word-level and document-level texts. The Bayesian inference results enable us to visualize the connection between words and emotions with respect to different semantic dimensions. And by further incorporating a corpus-level hierarchy in the document emotion distribution assumption, we could balance the document emotion recognition results and achieve even better word and document emotion predictions. Our experiment of the wordlevel and the document-level emotion predictions, based on a well-developed Chinese emotion corpus Ren-CECps, renders both higher accuracy and better robustness in the word-level and the document-level emotion predictions compared to the state-of-theart emotion prediction algorithms.
基金supported by the National Natural Science Funds of China under Grant No.61300034the National High-Tech Research&Development Program of China("863"Program)under Grant No.2012AA011103+1 种基金the Key Science and Technology Program of Anhui Province under Grant No.1206c0805039,a start-up fund for Huangshan Mountain Scholars(Outstanding Young Talents Program of Hefei University of Technology)under Grant No.405-037070
文摘In recent years, high-resolution video has developed rapidly and widescreen smart devices have become popular. We present an Android application called WeWatch that enables high-resolution video to be shared across two mobile devices when they are close to each other. This concept has its inspiration in machine-to-machine connections in the Internet of Things （loT）. We ensure that the two parts of the video are the same size over both screens and are synchronous. Further, a user can play, pause, or stop the video by moving one device a certain distance from the other. We decide on appropriate distances through experimentation. We implemented WeWatch on Android operating system and then optimize Watch so battery consumption is reduced. The user experience provided by WeWatch was evaluated by students through a questionnaire, and the reviews indicated that WeWatch does improve the viewing experience.
文摘The Internet of Things （IoT） has received much attention over the past decade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gathering （and related problems） are becoming more complex and uncertain. Researchers have therefore turned to artificial intelligence （AI） to efficiently deal with the problems ereated by big data.
文摘Recently,the authors often see words such as youth slang,neologism and Internet slang on social networking sites(SNSs)that are not registered on dictionaries.Since the documents posted to SNSs include a lot of fresh information,they are thought to be useful for collecting information.It is important to analyse these words(hereinafter referred to as‘slang’)and capture their features for the improvement of the accuracy of automatic information collection.This study aims to analyse what features can be observed in slang by focusing on the topic.They construct topic models from document groups including target slang on Twitter by latent Dirichlet allocation.With the models,they chronologically the analyse change of topics during a certain period of time to find out the difference in the features between slang and general words.Then,they propose a slang classification method based on the change of features.
基金supported by the National Science Foundation for Distinguished Young Scholars(with No.62125604)the NSFC projects(Key project with No.61936010 and regular project with No.61876096)+1 种基金supported by the Guoqiang Institute of Tsinghua University,with Grant No.2019GQG1 and 2020GQG0005sponsored by Tsinghua-Toyota Joint Research Fund.
文摘Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language models.Training data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English resources.This significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain samples.To alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model generation.Furthermore,we employ a multiteacher distillation framework to enhance detection performance with unsupervised data.That is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to AugCOLD.The soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive detector.We conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.
基金partially supported by the Research Clusters Program of Tokushima University and JSPS KAKENHI(No.19K20345)
文摘Insect pest control is considered as a significant factor in the yield of commercial crops.Thus,to avoid economic losses,we need a valid method for insect pest recognition.In this paper,we proposed a feature fusion residual block to perform the insect pest recognition task.Based on the original residual block,we fused the feature from a previous layer between two 11 convolution layers in a residual signal branch to improve the capacity of the block.Furthermore,we explored the contribution of each residual group to the model performance.We found that adding the residual blocks of earlier residual groups promotes the model performance significantly,which improves the capacity of generalization of the model.By stacking the feature fusion residual block,we constructed the Deep Feature Fusion Residual Network(DFF-ResNet).To prove the validity and adaptivity of our approach,we constructed it with two common residual networks(Pre-ResNet and Wide Residual Network(WRN))and validated these models on the Canadian Institute For Advanced Research(CIFAR)and Street View House Number(SVHN)benchmark datasets.The experimental results indicate that our models have a lower test error than those of baseline models.Then,we applied our models to recognize insect pests and obtained validity on the IP102 benchmark dataset.The experimental results show that our models outperform the original ResNet and other state-of-the-art methods.
基金supported in part by the Research Clusters program of Tokushima University under grant no.2003002This research has been partially supported by NSFC-Shenzhen Joint Foundation(Key Project)(Grant no.U1613217).
文摘Emotion recognition has been used widely in various applications such as mental health monitoring and emotional management.Usually,emotion recognition is regarded as a text classification task.Emotion recognition is a more complex problem,and the relations of emotions expressed in a text are nonnegligible.In this paper,a hierarchical model with label embedding is proposed for contextual emotion recognition.Especially,a hierarchical model is utilized to learn the emotional representation of a given sentence based on its contextual information.To give emotion correlation-based recognition,a label embedding matrix is trained by joint learning,which contributes to the final prediction.Comparison experiments are conducted on Chinese emotional corpus RenCECps,and the experimental results indicate that our approach has a satisfying performance in textual emotion recognition task.
基金This work was partially supported by the Research Clusters Program of Tokushima University.
文摘The dialogue system has always been one of the important topics in the domain of artificial intelligence.So far,most of the mature dialogue systems are task-oriented based,while non-task-oriented dialogue systems still have a lot of room for improvement.We propose a data-driven non-task-oriented dialogue generator“CERG”based on neural networks.This model has the emotion recognition capability and can generate corresponding responses.The data set we adopt comes from the NTCIR-14 STC-3 CECG subtask,which contains more than 1.7 million Chinese Weibo post-response pairs and 6 emotion categories.We try to concatenate the post and the response with the emotion,then mask the response part of the input text character by character to emulate the encoder-decoder framework.We use the improved transformer blocks as the core to build the model and add regularization methods to alleviate the problems of overcorrection and exposure bias.We introduce the retrieval method to the inference process to improve the semantic relevance of generated responses.The results of the manual evaluation show that our proposed model can make different responses to different emotions to improve the human-computer interaction experience.This model can be applied to lots of domains,such as automatic reply robots of social application.
