- Email: [email protected]
Special issue on advanced intelligent computing theories and applications
Author's Accepted Manuscript
Editorial: Special Issue on Advanced Intelligent Computing Theories and Applications De-Shuang Huang Prof. & Ph.D
www.elsevier.com/locate/neucom
PII: DOI: Reference:
S0925-2312(14)01363-0 http://dx.doi.org/10.1016/j.neucom.2014.10.024 NEUCOM14807
To appear in:
Neurocomputing
Cite this article as: De-Shuang Huang Prof. & Ph.D, Editorial: Special Issue on Advanced Intelligent Computing Theories and Applications, Neurocomputing, http://dx.doi.org/10.1016/j.neucom.2014.10.024 This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting galley proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Editorial Special Issue on Advanced Intelligent Computing Theories and Applications Guest Editor: De-Shuang Huang All the 29 articles appearing in this special issue on Advanced Intelligent Computing Theories and Applications are the extended versions of the papers presented at the 2013 Ninth International Conference on Intelligent Computing (ICIC2013) held on July 28-31, 2013 in Nanning, China. All the papers included here have been thoroughly reviewed and revised with the support of many reviewers under the Elsevier Editorial System (EES). Twenty-eight papers representing less than four percent of all eligible papers accepted at the ICIC2013 are selected for inclusion in this special issue. The selected papers are organized into the following sections. Neural Network Based Theories and Applications This issue starts with using a self-organized fuzzy neural network for rule generation of fuzzy logic systems by J.C. F. Garcia. et.al by proposing an algorithm for creating rules of a fuzzy logic system using a neuro-fuzzy approach. This is followed by an interesting article by A. Hussain et al. about dynamic neural network architecture inspired by the immune algorithm for predicting preterm deliveries in pregnant women by proposing a new dynamic self-organised network immune algorithm that classifies term and preterm records. Next, A. Hussain et.al, present a paper about how to use hybrid neural network for predictive-wavelet image compression system. And the simulation results indicated that the proposed technique can achieve good compressed images at high decomposition levels in comparison to JPEG2000. Then, an interesting paper by Wu et.al is about wavelet transform and texture recognition based on spiking neural network for visual images. After that, Kang et.al present a paper focused on discussing a calibration method for enhancing robot accuracy through integration of an extended Kalman filter algorithm and an artificial neural network. Feature Exaction-based Learning and Classification Feature learning and extracting in classification has become a very popular topic in the pattern recognition field nowadays. Firstly, Chong et.al propose a new pedestrian detection method based on combined Histogram of Oriented Gradient (HOG) and Local Self-Similarity (LSS) Features. Next, Ma et.al present Bayesian Ying-Yang (BYY) harmony learning of log-normal mixtures with automated model selection. This is followed by the paper by K. Seeja et.al about feature selection based on closed frequent item set mining for a case study on SAGE data classification. Jo et.al propose a method for LED text detection and recognition in natural scene images. And the experimental results showed the robustness and effectiveness of the 1
proposed method. In addition, Zhou et.al present a new method for deception detecting from speech signal using relevance vector machine and non-linear dynamics features. After that, Liu et.al present a robust reversible data hiding scheme for h.264 without distortion drift. And the experimental results showed that this new robust reversible data hiding algorithm can get more robustness, effectively avert intra-frame distortion drift and get good visual quality. Jiang et.al propose a novel strategy named Label propagation algorithm in synchronous version (LPA-S) to update the labels of nodes synchronously by the probability of each surrounding label, which is easy to be parallelized. And the experimental results showed the proposed LPA-S does not harm the quality of the partitioning while can be easily parallelized. Then Liu et.al present a new robust data hiding method for H.264/AVC without intra-frame distortion drift. Image Processing and Biomentric Recognition This issue also contains interesting articles on multi-scale local region based level set method for image segmentation in the presence of intensity inhomogeneity by Wang et al.; An integrated approach to region based image retrieval using firefly algorithm and support vector machine by T. Kanimozhi et al.; ApLeaf for an efficient android-based plant leaf identification system by Zhao et al.; Designing an accurate hand biometric based authentication system fusing finger knuckleprint and palmprint by Nigam et.al.; An active contour model based on fused texture features for image segmentation by Wu et.al.; Perceptual image quality assessment by independent feature detector by Chang et.al.; Image reconstruction algorithm from compressed sensing measurements by dictionary learning by Shen et.al.; An efficient technique for automatic segmentation of fingerprint ROI from digital slap image by Tiwari et.al.; Compressed sensing image reconstruction using intra prediction by Song et.al.; A novel face recognition method by using random weight networks and quasi-singular value decomposition by Cao et.al. Further, Li et.al proposed learning kernel subspace for face recognition by applying radial basis function neural network (RBFNN) to learn the feature extraction process of kernel subspace methods. And the experimental results showed that the proposed method can reach approximately the recognition accuracy of the original KPCA or the two-phase KLDA. Optimization and Classification This special issue also contains five papers on Optimization and Classification. The research presented by Zhang et.al. describe two modified artificial bee colony algorithms inspired by grenade explosion method. Lin et al. present adaptive comprehensive learning bacterial foraging optimization and its application on vehicle routing problem with time windows. A cellular learning automata based algorithm for detecting community structure in complex networks is presented by Li et al. Zhou et al. describe a discrete invasive weed optimization algorithm for solving traveling salesman problem. And Liu et.al propose a hybrid learning particle swarm optimizer with genetic disturbance. It should be stressed that recommendations for this special issue were made by the
2
ICIC2013's International Program Committee, and the final selections were made on the basis of quality, novelty, and theoretical or practical importance. Each paper was subject to two or three rounds of review with a minimum of three reviewers, reflecting the high standards for the selected papers in this issue. We hope that you will find this special issue informative and beneficial to your own work. As guest editor, we would like to take this opportunity to thank all the authors for their contributions to this special issue, and the reviewers for their expert review comments. We would also like to thank the Editor-in-Chief of Neurocomputing, Tom Heskes, for his advice and support during the preparation of this special issue. Finally, what it must be stressed is that this special issue was financially supported by the grants of the Natural Science Foundation of China, No.61133010 & 61472280.
Guest Editor, De-Shuang Huang, Prof. & Ph.D Machine Learning and Systems Biology Laboratory, School of Electronics and Information Engineering, Tongji University, 4800 Caoan Road, Shanghai 201804, China URL: http://www.intelengine.cn/English/people/hds.htm Email: [email protected]
3
Editorial: Special Issue on Advanced Intelligent Computing Theories and Applications De-Shuang Huang Prof. & Ph.D
www.elsevier.com/locate/neucom
PII: DOI: Reference:
S0925-2312(14)01363-0 http://dx.doi.org/10.1016/j.neucom.2014.10.024 NEUCOM14807
To appear in:
Neurocomputing
Cite this article as: De-Shuang Huang Prof. & Ph.D, Editorial: Special Issue on Advanced Intelligent Computing Theories and Applications, Neurocomputing, http://dx.doi.org/10.1016/j.neucom.2014.10.024 This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting galley proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Editorial Special Issue on Advanced Intelligent Computing Theories and Applications Guest Editor: De-Shuang Huang All the 29 articles appearing in this special issue on Advanced Intelligent Computing Theories and Applications are the extended versions of the papers presented at the 2013 Ninth International Conference on Intelligent Computing (ICIC2013) held on July 28-31, 2013 in Nanning, China. All the papers included here have been thoroughly reviewed and revised with the support of many reviewers under the Elsevier Editorial System (EES). Twenty-eight papers representing less than four percent of all eligible papers accepted at the ICIC2013 are selected for inclusion in this special issue. The selected papers are organized into the following sections. Neural Network Based Theories and Applications This issue starts with using a self-organized fuzzy neural network for rule generation of fuzzy logic systems by J.C. F. Garcia. et.al by proposing an algorithm for creating rules of a fuzzy logic system using a neuro-fuzzy approach. This is followed by an interesting article by A. Hussain et al. about dynamic neural network architecture inspired by the immune algorithm for predicting preterm deliveries in pregnant women by proposing a new dynamic self-organised network immune algorithm that classifies term and preterm records. Next, A. Hussain et.al, present a paper about how to use hybrid neural network for predictive-wavelet image compression system. And the simulation results indicated that the proposed technique can achieve good compressed images at high decomposition levels in comparison to JPEG2000. Then, an interesting paper by Wu et.al is about wavelet transform and texture recognition based on spiking neural network for visual images. After that, Kang et.al present a paper focused on discussing a calibration method for enhancing robot accuracy through integration of an extended Kalman filter algorithm and an artificial neural network. Feature Exaction-based Learning and Classification Feature learning and extracting in classification has become a very popular topic in the pattern recognition field nowadays. Firstly, Chong et.al propose a new pedestrian detection method based on combined Histogram of Oriented Gradient (HOG) and Local Self-Similarity (LSS) Features. Next, Ma et.al present Bayesian Ying-Yang (BYY) harmony learning of log-normal mixtures with automated model selection. This is followed by the paper by K. Seeja et.al about feature selection based on closed frequent item set mining for a case study on SAGE data classification. Jo et.al propose a method for LED text detection and recognition in natural scene images. And the experimental results showed the robustness and effectiveness of the 1
proposed method. In addition, Zhou et.al present a new method for deception detecting from speech signal using relevance vector machine and non-linear dynamics features. After that, Liu et.al present a robust reversible data hiding scheme for h.264 without distortion drift. And the experimental results showed that this new robust reversible data hiding algorithm can get more robustness, effectively avert intra-frame distortion drift and get good visual quality. Jiang et.al propose a novel strategy named Label propagation algorithm in synchronous version (LPA-S) to update the labels of nodes synchronously by the probability of each surrounding label, which is easy to be parallelized. And the experimental results showed the proposed LPA-S does not harm the quality of the partitioning while can be easily parallelized. Then Liu et.al present a new robust data hiding method for H.264/AVC without intra-frame distortion drift. Image Processing and Biomentric Recognition This issue also contains interesting articles on multi-scale local region based level set method for image segmentation in the presence of intensity inhomogeneity by Wang et al.; An integrated approach to region based image retrieval using firefly algorithm and support vector machine by T. Kanimozhi et al.; ApLeaf for an efficient android-based plant leaf identification system by Zhao et al.; Designing an accurate hand biometric based authentication system fusing finger knuckleprint and palmprint by Nigam et.al.; An active contour model based on fused texture features for image segmentation by Wu et.al.; Perceptual image quality assessment by independent feature detector by Chang et.al.; Image reconstruction algorithm from compressed sensing measurements by dictionary learning by Shen et.al.; An efficient technique for automatic segmentation of fingerprint ROI from digital slap image by Tiwari et.al.; Compressed sensing image reconstruction using intra prediction by Song et.al.; A novel face recognition method by using random weight networks and quasi-singular value decomposition by Cao et.al. Further, Li et.al proposed learning kernel subspace for face recognition by applying radial basis function neural network (RBFNN) to learn the feature extraction process of kernel subspace methods. And the experimental results showed that the proposed method can reach approximately the recognition accuracy of the original KPCA or the two-phase KLDA. Optimization and Classification This special issue also contains five papers on Optimization and Classification. The research presented by Zhang et.al. describe two modified artificial bee colony algorithms inspired by grenade explosion method. Lin et al. present adaptive comprehensive learning bacterial foraging optimization and its application on vehicle routing problem with time windows. A cellular learning automata based algorithm for detecting community structure in complex networks is presented by Li et al. Zhou et al. describe a discrete invasive weed optimization algorithm for solving traveling salesman problem. And Liu et.al propose a hybrid learning particle swarm optimizer with genetic disturbance. It should be stressed that recommendations for this special issue were made by the
2
ICIC2013's International Program Committee, and the final selections were made on the basis of quality, novelty, and theoretical or practical importance. Each paper was subject to two or three rounds of review with a minimum of three reviewers, reflecting the high standards for the selected papers in this issue. We hope that you will find this special issue informative and beneficial to your own work. As guest editor, we would like to take this opportunity to thank all the authors for their contributions to this special issue, and the reviewers for their expert review comments. We would also like to thank the Editor-in-Chief of Neurocomputing, Tom Heskes, for his advice and support during the preparation of this special issue. Finally, what it must be stressed is that this special issue was financially supported by the grants of the Natural Science Foundation of China, No.61133010 & 61472280.
Guest Editor, De-Shuang Huang, Prof. & Ph.D Machine Learning and Systems Biology Laboratory, School of Electronics and Information Engineering, Tongji University, 4800 Caoan Road, Shanghai 201804, China URL: http://www.intelengine.cn/English/people/hds.htm Email: [email protected]
3