The need to quantify aleatory and epistemic uncertainties has been widely recognized in the engineering applications. Aleatory uncertainty arises from inherent randomness, whereas epistemic uncertainty is due to the lack of knowledge. Traditionally uncertainty has been quantified by probability measures and the two uncertainty components are not readily differentiated. Intervals naturally capture the systematic error during data acquisition. We develop a new feature extraction and back propagation neural network in the context of generalized interval theory, where all parameters are in the form of a generalized interval. Calculation of generalized interval based on the Kaucher arithmetic is greatly simplified in this application. To demonstrate the new framework, this paper provides a case study of recognizing the cutting states in the manufacturing process. The stable, transition, and chatter state states are recognized by the generalized back propagation neural network (GBPNN) model. The results show that the proposed method has a good recognition performance.
{"title":"An Uncertainty Quantification Method Based on Generalized Interval","authors":"Youmin Hu, Fengyun Xie, Bo Wu, Yan Wang","doi":"10.1109/MICAI.2013.25","DOIUrl":"https://doi.org/10.1109/MICAI.2013.25","url":null,"abstract":"The need to quantify aleatory and epistemic uncertainties has been widely recognized in the engineering applications. Aleatory uncertainty arises from inherent randomness, whereas epistemic uncertainty is due to the lack of knowledge. Traditionally uncertainty has been quantified by probability measures and the two uncertainty components are not readily differentiated. Intervals naturally capture the systematic error during data acquisition. We develop a new feature extraction and back propagation neural network in the context of generalized interval theory, where all parameters are in the form of a generalized interval. Calculation of generalized interval based on the Kaucher arithmetic is greatly simplified in this application. To demonstrate the new framework, this paper provides a case study of recognizing the cutting states in the manufacturing process. The stable, transition, and chatter state states are recognized by the generalized back propagation neural network (GBPNN) model. The results show that the proposed method has a good recognition performance.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116586866","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}
Byron Enrique Portilla Rosero, Jaime Alberto Guzmán Luna, G. Alor-Hernández
Service composition can be considered as a Linked Data model due to the way that each one of the services that make up the composition is structured. For doing this, a service composer is required in order to evaluate the input and output data of various web-distributed services for linking them. These links can be analyzed from a quality perspective in which a service may fail when it does not fulfill the requirements that satisfy the linking conditions. Therefore, these conditions are analyzed from two points of view: 1) service availability and, 2) the handling of composer's beliefs. The latter refers to the fact that a service must not consider only two types of data to perform links, it should consider also the value of the instances, taking into account a same context. This work presents a new approach for the consumption of Linked Data in a service composition environment which uses as reference those links which have less probability of failing, selecting those services that can reduce the risk of a composition failure.
{"title":"Towards Service Composition for Consuming Linked Data: A Failure Perspective","authors":"Byron Enrique Portilla Rosero, Jaime Alberto Guzmán Luna, G. Alor-Hernández","doi":"10.1109/MICAI.2013.23","DOIUrl":"https://doi.org/10.1109/MICAI.2013.23","url":null,"abstract":"Service composition can be considered as a Linked Data model due to the way that each one of the services that make up the composition is structured. For doing this, a service composer is required in order to evaluate the input and output data of various web-distributed services for linking them. These links can be analyzed from a quality perspective in which a service may fail when it does not fulfill the requirements that satisfy the linking conditions. Therefore, these conditions are analyzed from two points of view: 1) service availability and, 2) the handling of composer's beliefs. The latter refers to the fact that a service must not consider only two types of data to perform links, it should consider also the value of the instances, taking into account a same context. This work presents a new approach for the consumption of Linked Data in a service composition environment which uses as reference those links which have less probability of failing, selecting those services that can reduce the risk of a composition failure.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"1115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122931213","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}
This paper uses a semantic technique by adopting a Rhetorical Structure Theory (RST) for summarization purpose, to discover the most significant paragraphs based on functional and semantic criteria. However, the quality of RST summarization suffers when dealing with large documents. This paper proposes a new hybrid summarization model for Arabic text, which mingles two sub-models: The first sub-model produces a primary summary by using Rhetorical Structure Theory for identifying a range of the most significant parts of the text (the nucleus). Then the second sub-model ranks the significant parts in the primary rhetorical-summary based on the cosine similarity feature. To evaluate the proposed model, a prototype was developed on a range of articles, which have been classified into three groups different in size. The final output summary was evaluated in relation to its manual counterpart. In terms of enhancement of the rhetorical-summary precision, the experiment shows that proposed model HSM average precision is 71.6%, superior over the primary rhetorical-summary precision 56.3%.
{"title":"Improve the Automatic Summarization of Arabic Text Depending on Rhetorical Structure Theory","authors":"A. Ibrahim, T. Elghazaly","doi":"10.1109/MICAI.2013.35","DOIUrl":"https://doi.org/10.1109/MICAI.2013.35","url":null,"abstract":"This paper uses a semantic technique by adopting a Rhetorical Structure Theory (RST) for summarization purpose, to discover the most significant paragraphs based on functional and semantic criteria. However, the quality of RST summarization suffers when dealing with large documents. This paper proposes a new hybrid summarization model for Arabic text, which mingles two sub-models: The first sub-model produces a primary summary by using Rhetorical Structure Theory for identifying a range of the most significant parts of the text (the nucleus). Then the second sub-model ranks the significant parts in the primary rhetorical-summary based on the cosine similarity feature. To evaluate the proposed model, a prototype was developed on a range of articles, which have been classified into three groups different in size. The final output summary was evaluated in relation to its manual counterpart. In terms of enhancement of the rhetorical-summary precision, the experiment shows that proposed model HSM average precision is 71.6%, superior over the primary rhetorical-summary precision 56.3%.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133145445","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}
Statistical methods to correlate multiple variables has long been applied in many fields of research. This paper applies such techniques to Unified Parkinson's Disease Rating Scale (UPDRS) data to examine relationships between speech and movement variables. This data analysis uses select speech and motor variables to explore Parkinson's Disease (PD) symptom correlations. The analysis is a prerequisite study of speech and movement symptoms prior to collecting data from everyday living in PD patients using HCI systems for movement and AI methods for analyzing speech and language. This data analysis is a first level examination of the current gold standards for measuring speech and movement in PD patients.
{"title":"Examining Everyday Speech and Motor Symptoms of Parkinson's Disease for Diagnosis and Progression Tracking","authors":"N. Howard, J. Bergmann, Rebecca Howard","doi":"10.1109/MICAI.2013.47","DOIUrl":"https://doi.org/10.1109/MICAI.2013.47","url":null,"abstract":"Statistical methods to correlate multiple variables has long been applied in many fields of research. This paper applies such techniques to Unified Parkinson's Disease Rating Scale (UPDRS) data to examine relationships between speech and movement variables. This data analysis uses select speech and motor variables to explore Parkinson's Disease (PD) symptom correlations. The analysis is a prerequisite study of speech and movement symptoms prior to collecting data from everyday living in PD patients using HCI systems for movement and AI methods for analyzing speech and language. This data analysis is a first level examination of the current gold standards for measuring speech and movement in PD patients.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116063085","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}
A compactified horizontal visibility graph for the language network and identification of the words that define the informational structure of a text is proposed. It was found that the networks constructed in such a way are scale free, and have a property that among the nodes with largest degrees there are words that determine not only communicative text structure, but also its informational structure.
{"title":"The Use of Horizontal Visibility Graphs to Identify the Words that Define the Informational Structure of a Text","authors":"D. Lande, A. Snarskii, E. Yagunova","doi":"10.1109/MICAI.2013.33","DOIUrl":"https://doi.org/10.1109/MICAI.2013.33","url":null,"abstract":"A compactified horizontal visibility graph for the language network and identification of the words that define the informational structure of a text is proposed. It was found that the networks constructed in such a way are scale free, and have a property that among the nodes with largest degrees there are words that determine not only communicative text structure, but also its informational structure.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125022113","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}
This paper deals with a computer-aided system for design of ship power plants safe for their operators. The specificity of ship power plants allows to assert that all plant spaces can be more or less dangerous for operators carrying out any operational or maintenance tasks. For this reason, these plants should be well-designed to minimize the possible hazards for their operators. The proposed system of the hazard zone identification in the ship power plants is based on both their preliminary design and the expert subjective assessments enable to assess the potential risk for operators. It has been prepared a special questionnaire to collect this kind of subjective information. The acquired results have been used to build the risk assessment system with the fuzzy knowledge base.
{"title":"Modeling of Decision-Making Process Relating to Design of Ship Power Plants Safe for Operators","authors":"W. Tarelko, T. Kowalewski","doi":"10.1109/MICAI.2013.8","DOIUrl":"https://doi.org/10.1109/MICAI.2013.8","url":null,"abstract":"This paper deals with a computer-aided system for design of ship power plants safe for their operators. The specificity of ship power plants allows to assert that all plant spaces can be more or less dangerous for operators carrying out any operational or maintenance tasks. For this reason, these plants should be well-designed to minimize the possible hazards for their operators. The proposed system of the hazard zone identification in the ship power plants is based on both their preliminary design and the expert subjective assessments enable to assess the potential risk for operators. It has been prepared a special questionnaire to collect this kind of subjective information. The acquired results have been used to build the risk assessment system with the fuzzy knowledge base.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122626604","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}
D. Cabrera-Gaona, L. Torres-Treviño, A. Rodríguez-Liñán
A maximum sensibility neural network is implemented in an embedded system to make an online machine learning system, which is used to control the temperature of a small chamber. This is made by manually controlling the temperature to different set-points with a potentiometer, and using these values as an online training data for the neural network. Then the neural network is able to automatically adjust the temperature to any given set point with a good performance.
{"title":"Control by Learning in a Temperature System Using a Maximum Sensibility Neural Network","authors":"D. Cabrera-Gaona, L. Torres-Treviño, A. Rodríguez-Liñán","doi":"10.1109/MICAI.2013.19","DOIUrl":"https://doi.org/10.1109/MICAI.2013.19","url":null,"abstract":"A maximum sensibility neural network is implemented in an embedded system to make an online machine learning system, which is used to control the temperature of a small chamber. This is made by manually controlling the temperature to different set-points with a potentiometer, and using these values as an online training data for the neural network. Then the neural network is able to automatically adjust the temperature to any given set point with a good performance.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130591535","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}
C. A. D. L. Ortega, Jorge A. Ramirez-Marquez, M. Mora-González, J. Romo, Cesar A. Lopez-Luevano
This paper describes a new implementation of a mixture of techniques not used before for fingerprint recognition. The implementation consists of three stages: the location of the core, which is done through Radon transformation, the extraction of features (out of which a square fingerprint is produced with the core, and the center of the mass is obtained from it), in stage three, the resulting image is used to train the neural network in order to obtain better LVQ classification. The improvement of effectiveness is tested using two databases of fingerprints. Correct recognition rates have exceeded 90 percent, which demonstrate its great stability with fingerprints that display a well-defined core.
{"title":"Fingerprint Verification Using the Center of Mass and Learning Vector Quantization","authors":"C. A. D. L. Ortega, Jorge A. Ramirez-Marquez, M. Mora-González, J. Romo, Cesar A. Lopez-Luevano","doi":"10.1109/MICAI.2013.21","DOIUrl":"https://doi.org/10.1109/MICAI.2013.21","url":null,"abstract":"This paper describes a new implementation of a mixture of techniques not used before for fingerprint recognition. The implementation consists of three stages: the location of the core, which is done through Radon transformation, the extraction of features (out of which a square fingerprint is produced with the core, and the center of the mass is obtained from it), in stage three, the resulting image is used to train the neural network in order to obtain better LVQ classification. The improvement of effectiveness is tested using two databases of fingerprints. Correct recognition rates have exceeded 90 percent, which demonstrate its great stability with fingerprints that display a well-defined core.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127842231","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}
Because of their fuzzy and non-stationary nature, financial time series forecasting is still a challenge. In this paper, we propose and implement a hybrid model by combining the Maximum Entropy (ME), Support Vector Regression (SVR) and Trend model based on Artificial neural networks (ANNs) for forecasting financial time series. The approach contains three steps: feature and time alignment in data preprocessing, adopting ME, SVR and Trend model for different features as the input for ANNs, and obtaining the final predicted value using Back Propagation algorithm. The feature selection flexibility of ME and global optimality of SVR make the input model better because of its different features, which helps to have a better forecasting accuracy of ANN sin proposed model. Experimental results clearly show that the accuracy of prediction for Chinese closed-end fund net value can achieve 98.3% using the hybrid model, which is more accurate than some institutions or known financial websites in China, and we provide the prediction of real time fund net value for free in our Hai tianyuan knowledge service platformhttp://www.haitianyuan.com.
{"title":"A Hybrid Model Based on Neural Networks for Financial Time Series","authors":"Dong Huang, Xiaolong Wang, Jia Fang, Shiwen Liu, Ronggang Dou","doi":"10.1109/MICAI.2013.17","DOIUrl":"https://doi.org/10.1109/MICAI.2013.17","url":null,"abstract":"Because of their fuzzy and non-stationary nature, financial time series forecasting is still a challenge. In this paper, we propose and implement a hybrid model by combining the Maximum Entropy (ME), Support Vector Regression (SVR) and Trend model based on Artificial neural networks (ANNs) for forecasting financial time series. The approach contains three steps: feature and time alignment in data preprocessing, adopting ME, SVR and Trend model for different features as the input for ANNs, and obtaining the final predicted value using Back Propagation algorithm. The feature selection flexibility of ME and global optimality of SVR make the input model better because of its different features, which helps to have a better forecasting accuracy of ANN sin proposed model. Experimental results clearly show that the accuracy of prediction for Chinese closed-end fund net value can achieve 98.3% using the hybrid model, which is more accurate than some institutions or known financial websites in China, and we provide the prediction of real time fund net value for free in our Hai tianyuan knowledge service platformhttp://www.haitianyuan.com.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122569920","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}
In this paper, we focus on automatic quality assessment for intelligent essay grading. Our devised system grades essays without depending upon completely overlapping essays in training data. This increases the scope of devised system due to list dependency on highly topic focused labeled data for automatic essay grading. Instead of depending upon direct topic specific matching w.r.t., training data, the devised system judge the quality of essay by exploiting knowledgebase documents and SentiWordNet, etc. To achieve this goal, we concentrate on five different features: (1) relevance of information, (2) presence of sparsely connected words, (3) statistical and semantic role of words, (4) presence of talkative terms and (5) length of essay. We extract all these features by using word graph of text, populated with statistical, semantic and topical relation between words. Next, we use graph theoretical techniques, like: weighted all pair shortest paths, Ego-Networks, entropy based measures for effectiveness of nodes in weighted graph and statistical and probabilistic techniques like: total correlation score and Point wise Mutual Information (PMI) etc. Our experimental result on standard dataset shows that our devised system performs better than state-of-the-Art systems of this area.
{"title":"Automatic Quality Assessment of Documents with Application to Essay Grading","authors":"Niraj Kumar, Lipika Dey","doi":"10.1109/MICAI.2013.34","DOIUrl":"https://doi.org/10.1109/MICAI.2013.34","url":null,"abstract":"In this paper, we focus on automatic quality assessment for intelligent essay grading. Our devised system grades essays without depending upon completely overlapping essays in training data. This increases the scope of devised system due to list dependency on highly topic focused labeled data for automatic essay grading. Instead of depending upon direct topic specific matching w.r.t., training data, the devised system judge the quality of essay by exploiting knowledgebase documents and SentiWordNet, etc. To achieve this goal, we concentrate on five different features: (1) relevance of information, (2) presence of sparsely connected words, (3) statistical and semantic role of words, (4) presence of talkative terms and (5) length of essay. We extract all these features by using word graph of text, populated with statistical, semantic and topical relation between words. Next, we use graph theoretical techniques, like: weighted all pair shortest paths, Ego-Networks, entropy based measures for effectiveness of nodes in weighted graph and statistical and probabilistic techniques like: total correlation score and Point wise Mutual Information (PMI) etc. Our experimental result on standard dataset shows that our devised system performs better than state-of-the-Art systems of this area.","PeriodicalId":340039,"journal":{"name":"2013 12th Mexican International Conference on Artificial Intelligence","volume":"351 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122839110","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：