Pub Date : 2015-10-31DOI: 10.1109/IJCNN.2011.6033463
J. Bahi, Nathalie Côté, C. Guyeux
As protein folding is a NP-complete problem, artificial intelligence tools like neural networks and genetic algorithms are used to attempt to predict the 3D shape of an amino acids sequence. Underlying these attempts, it is supposed that this folding process is predictable. However, to the best of our knowledge, this important assumption has been neither proven, nor studied. In this paper the topological dynamic of protein folding is evaluated. It is mathematically established that protein folding in 2D hydrophobic-hydrophilic (HP) square lattice model is chaotic as defined by Devaney. Consequences for both structure prediction and biology are then outlined.
{"title":"Chaos of protein folding","authors":"J. Bahi, Nathalie Côté, C. Guyeux","doi":"10.1109/IJCNN.2011.6033463","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033463","url":null,"abstract":"As protein folding is a NP-complete problem, artificial intelligence tools like neural networks and genetic algorithms are used to attempt to predict the 3D shape of an amino acids sequence. Underlying these attempts, it is supposed that this folding process is predictable. However, to the best of our knowledge, this important assumption has been neither proven, nor studied. In this paper the topological dynamic of protein folding is evaluated. It is mathematically established that protein folding in 2D hydrophobic-hydrophilic (HP) square lattice model is chaotic as defined by Devaney. Consequences for both structure prediction and biology are then outlined.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134477713","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 : 2011-10-24DOI: 10.1109/IJCNN.2011.6033401
Chin-Teng Lin, Shi-An Chen, L. Ko, Yu-kai Wang
Distraction during driving has been recognized as a significant cause of traffic accidents. The aim of this study is to investigate Electroencephalography (EEG) -based brain dynamics in response to driving distraction. To study human cognition under specific driving tasks in a simulated driving experiment, this study utilized two simulated events including unexpected car deviations and mathematics questions. The raw data were first separated into independent brain sources by Independent Component Analysis. Then, the EEG power spectra were used to evaluate the time-frequency brain dynamics. Results showed that increases of theta band and beta band power were observed in the frontal cortex. Further analysis demonstrated that reaction time and multiple cortical EEG power had high correlation. Thus, this study suggested that the features extracted by EEG signal processing, which were the theta power increases in frontal area, could be used as the distracted indexes for early detection of driver inattention in real driving.
{"title":"EEG-based brain dynamics of driving distraction","authors":"Chin-Teng Lin, Shi-An Chen, L. Ko, Yu-kai Wang","doi":"10.1109/IJCNN.2011.6033401","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033401","url":null,"abstract":"Distraction during driving has been recognized as a significant cause of traffic accidents. The aim of this study is to investigate Electroencephalography (EEG) -based brain dynamics in response to driving distraction. To study human cognition under specific driving tasks in a simulated driving experiment, this study utilized two simulated events including unexpected car deviations and mathematics questions. The raw data were first separated into independent brain sources by Independent Component Analysis. Then, the EEG power spectra were used to evaluate the time-frequency brain dynamics. Results showed that increases of theta band and beta band power were observed in the frontal cortex. Further analysis demonstrated that reaction time and multiple cortical EEG power had high correlation. Thus, this study suggested that the features extracted by EEG signal processing, which were the theta power increases in frontal area, could be used as the distracted indexes for early detection of driver inattention in real driving.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134027103","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033475
Udhay Ravishankar, M. Manic
Current developments in autonomous vehicle systems typically consider solutions to single problems like road detection, road following and object recognition individually. The integration of these individual systems into a single package becomes difficult because they are less compatible. This paper introduces a generic Integrated Neural System for Autonomous Vehicles (INSAV) package solution with processing blocks that are compatible with each other and are also suitable for hardware implementation. The generic INSAV is designed to account for important problems such as road detection, road structure learning, path tracking and obstacle detection. The paper begins the design of the generic INSAV by building its two most important blocks: the Road Structuring and Path Tracking Blocks. The obtained results from implementing the two blocks demonstrate an average of 92% accuracy of segmenting the road from a given image frame and path tracking of straight roads for stable motion and obstacle detection.
{"title":"A hardware suitable Integrated Neural System for Autonomous Vehicles - Road Structuring and Path Tracking","authors":"Udhay Ravishankar, M. Manic","doi":"10.1109/IJCNN.2011.6033475","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033475","url":null,"abstract":"Current developments in autonomous vehicle systems typically consider solutions to single problems like road detection, road following and object recognition individually. The integration of these individual systems into a single package becomes difficult because they are less compatible. This paper introduces a generic Integrated Neural System for Autonomous Vehicles (INSAV) package solution with processing blocks that are compatible with each other and are also suitable for hardware implementation. The generic INSAV is designed to account for important problems such as road detection, road structure learning, path tracking and obstacle detection. The paper begins the design of the generic INSAV by building its two most important blocks: the Road Structuring and Path Tracking Blocks. The obtained results from implementing the two blocks demonstrate an average of 92% accuracy of segmenting the road from a given image frame and path tracking of straight roads for stable motion and obstacle detection.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115371837","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033279
J. Bullinaria
A common problem in speech technology is the alignment of representations of text and phonemes, and the learning of a mapping between them that generalizes well to unseen inputs. The state-of-the-art technology appears to be symbolic rule-based systems, which is surprising given the number of neural network systems for text to phoneme mapping that have been developed over the years. This paper explores why that may be the case, and demonstrates that it is possible for neural networks to simultaneously perform text to phoneme alignment and mapping with performance levels at least comparable to the best existing systems.
{"title":"Text to phoneme alignment and mapping for speech technology: A neural networks approach","authors":"J. Bullinaria","doi":"10.1109/IJCNN.2011.6033279","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033279","url":null,"abstract":"A common problem in speech technology is the alignment of representations of text and phonemes, and the learning of a mapping between them that generalizes well to unseen inputs. The state-of-the-art technology appears to be symbolic rule-based systems, which is surprising given the number of neural network systems for text to phoneme mapping that have been developed over the years. This paper explores why that may be the case, and demonstrates that it is possible for neural networks to simultaneously perform text to phoneme alignment and mapping with performance levels at least comparable to the best existing systems.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"517 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123104433","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033551
R. Jafari, M. Hagan
This paper describes a modification to the method of Reduction Of Dissipativity Domain with Linear Boundaries (RODD-LB1) which was introduced by Barabanov and Prokharov [7]. The RODD method is a computational technique for the global stability analysis of nonlinear dynamic systems. In this paper we introduce an extension to the original RODD method that is designed to speed up convergence. The efficiency of the extended algorithm is demonstrated through numerical examples.
{"title":"Global stability analysis using the method of Reduction Of Dissipativity Domain","authors":"R. Jafari, M. Hagan","doi":"10.1109/IJCNN.2011.6033551","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033551","url":null,"abstract":"This paper describes a modification to the method of Reduction Of Dissipativity Domain with Linear Boundaries (RODD-LB1) which was introduced by Barabanov and Prokharov [7]. The RODD method is a computational technique for the global stability analysis of nonlinear dynamic systems. In this paper we introduce an extension to the original RODD method that is designed to speed up convergence. The efficiency of the extended algorithm is demonstrated through numerical examples.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"500 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123059437","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033563
J. Hernández, M. U. Suarez-Duran, R. García-Hernández, E. Shelomov, E. N. Sánchez
In this paper a recurrent neural network is used as associative memory for pattern recognition. The goal of associative memory is to retrieve a stored pattern when enough information is presented in the network input. The network is training with twelve bipolar patterns to determine the corresponding weights. The weights are calculated by means of support vector machines training algorithms as the optimal hyperplane and soft margin hyperplane. Once the neural network is trained its performance is evaluated to retrieval stored patterns which correspond to characters encoded as bipolar vectors.
{"title":"Designing associative memories implemented via recurrent neural networks for pattern recognition","authors":"J. Hernández, M. U. Suarez-Duran, R. García-Hernández, E. Shelomov, E. N. Sánchez","doi":"10.1109/IJCNN.2011.6033563","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033563","url":null,"abstract":"In this paper a recurrent neural network is used as associative memory for pattern recognition. The goal of associative memory is to retrieve a stored pattern when enough information is presented in the network input. The network is training with twelve bipolar patterns to determine the corresponding weights. The weights are calculated by means of support vector machines training algorithms as the optimal hyperplane and soft margin hyperplane. Once the neural network is trained its performance is evaluated to retrieval stored patterns which correspond to characters encoded as bipolar vectors.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114650616","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033301
Ronaldo Aquino, O. N. Neto, M. Lira, Manoel A. Carvalho
This paper deals with an application of Artificial Neural Network (ANN) and a Hybrid Intelligent System (HIS) to solve a large scale real world optimization problem, which is an operation planning of generation system in the mid-term operation. This problem is related to economic power dispatch that minimizes the overall production cost while satisfying the load demand. These kinds of problem are large scale optimization problems in which the complexity increases with the planning horizon and the accuracy of the system to be modeled. This work considers the two-phase optimization neural network, which solves dynamically linear and quadratic programming problems with guaranteed optimal convergence and HIS, which combines ANN and Heuristics Rules (HRs) to boost the convergence speed. This network also provides the corresponding Lagrange multiplier associated with each constraint (marginal price). The results pointed out that the applications of the HIS have turned the implementation of ANN models in software more attractive.
{"title":"Solving a real large scale mid-term scheduling for power plants via hybrid intelligent neural networks systems","authors":"Ronaldo Aquino, O. N. Neto, M. Lira, Manoel A. Carvalho","doi":"10.1109/IJCNN.2011.6033301","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033301","url":null,"abstract":"This paper deals with an application of Artificial Neural Network (ANN) and a Hybrid Intelligent System (HIS) to solve a large scale real world optimization problem, which is an operation planning of generation system in the mid-term operation. This problem is related to economic power dispatch that minimizes the overall production cost while satisfying the load demand. These kinds of problem are large scale optimization problems in which the complexity increases with the planning horizon and the accuracy of the system to be modeled. This work considers the two-phase optimization neural network, which solves dynamically linear and quadratic programming problems with guaranteed optimal convergence and HIS, which combines ANN and Heuristics Rules (HRs) to boost the convergence speed. This network also provides the corresponding Lagrange multiplier associated with each constraint (marginal price). The results pointed out that the applications of the HIS have turned the implementation of ANN models in software more attractive.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"26-27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116776100","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033337
D. Viejo, J. G. Rodríguez, M. Cazorla, D. G. Méndez, Magnus Johnsson
Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.
{"title":"Using 3D GNG-based reconstruction for 6DoF egomotion","authors":"D. Viejo, J. G. Rodríguez, M. Cazorla, D. G. Méndez, Magnus Johnsson","doi":"10.1109/IJCNN.2011.6033337","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033337","url":null,"abstract":"Several recent works deal with 3D data in mobile robotic problems, e.g. mapping. Data come from any kind of sensor (time of flight cameras and 3D lasers) providing a huge amount of unorganized 3D data. In this paper we detail an efficient method to build complete 3D models from a Growing Neural Gas (GNG). We show that the use of GNG provides better results than other approaches. The GNG obtained is then applied to a sequence. From GNG structure, we propose to calculate planar patches and thus obtaining a fast method to compute the movement performed by a mobile robot by means of a 3D models registration algorithm. Final results of 3D mapping are also shown.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117116276","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033533
Heiko Hoffmann, M. Howard, M. Daily
We present a novel paradigm for pattern matching. Our method provides a means to search a continuous data stream for exact matches with a priori stored data sequences. At heart, we use a neural network with input and output layers and variable connections in between. The input layer has one neuron for each possible character or number in the data stream, and the output layer has one neuron for each stored pattern. The novelty of the network is that the delays of the connections from input to output layer are optimized to match the temporal occurrence of an input character within a stored sequence. Thus, the polychronous activation of input neurons results in activating an output neuron that indicates detection of a stored pattern. For data streams that have a large alphabet, the connectivity in our network is very sparse and the number of computational steps small: in this case, our method outperforms by a factor 2 deterministic finite state machines, which have been the state of the art for pattern matching for more than 30 years.
我们提出了一种新的模式匹配模式。我们的方法提供了一种方法来搜索连续数据流，以寻找与先验存储的数据序列的精确匹配。从本质上讲，我们使用一个具有输入和输出层以及两者之间可变连接的神经网络。输入层对数据流中每个可能的字符或数字有一个神经元，输出层对每个存储模式有一个神经元。该网络的新颖之处在于，从输入层到输出层的连接延迟被优化，以匹配存储序列中输入字符的时间出现。因此，输入神经元的多时激活导致激活输出神经元，该输出神经元指示检测到存储模式。对于具有较大字母的数据流，我们网络中的连接性非常稀疏，计算步骤的数量也很少:在这种情况下，我们的方法比确定性有限状态机(deterministic finite state machines)的性能要好2倍，确定性有限状态机在模式匹配方面已经领先了30多年。
{"title":"Fast pattern matching with time-delay neural networks","authors":"Heiko Hoffmann, M. Howard, M. Daily","doi":"10.1109/IJCNN.2011.6033533","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033533","url":null,"abstract":"We present a novel paradigm for pattern matching. Our method provides a means to search a continuous data stream for exact matches with a priori stored data sequences. At heart, we use a neural network with input and output layers and variable connections in between. The input layer has one neuron for each possible character or number in the data stream, and the output layer has one neuron for each stored pattern. The novelty of the network is that the delays of the connections from input to output layer are optimized to match the temporal occurrence of an input character within a stored sequence. Thus, the polychronous activation of input neurons results in activating an output neuron that indicates detection of a stored pattern. For data streams that have a large alphabet, the connectivity in our network is very sparse and the number of computational steps small: in this case, our method outperforms by a factor 2 deterministic finite state machines, which have been the state of the art for pattern matching for more than 30 years.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127094945","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033524
Armando A. Gonçalves, Igor Alencar, Ing Ren Tsang, George D. C. Cavalcanti
A novel framework for time series prediction that integrates Genetic Algorithm (GA), Partial Axis Search Tree (PAT) and K-Nearest Neighbors (KNN) is proposed. This methodology is based on the information obtained from Technical analysis of a stock. Experiments have shown that GAs can capture the most relevant variables and improve the accuracy of predicting the direction of daily change in a stock price index. A comparison with other models shows the advantage of the proposed framework
{"title":"GA-PAT-KNN: Framework for time series forecasting","authors":"Armando A. Gonçalves, Igor Alencar, Ing Ren Tsang, George D. C. Cavalcanti","doi":"10.1109/IJCNN.2011.6033524","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033524","url":null,"abstract":"A novel framework for time series prediction that integrates Genetic Algorithm (GA), Partial Axis Search Tree (PAT) and K-Nearest Neighbors (KNN) is proposed. This methodology is based on the information obtained from Technical analysis of a stock. Experiments have shown that GAs can capture the most relevant variables and improve the accuracy of predicting the direction of daily change in a stock price index. A comparison with other models shows the advantage of the proposed framework","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"2096 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127467713","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：