{"title":"Single image super-resolution via learned representative features and sparse manifold embedding","authors":"Liao Zhang, Shuyuan Yang, Jiren Zhang, L. Jiao","doi":"10.1109/IJCNN.2014.6889739","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889739","url":null,"abstract":"Advances in machine learning technology have made efficient Super-Resolution Image Reconstruction (SRIR) possible. In this paper, we advance a hierarchical support vector machine (HSVM) to learn representative features of both training and test Low-Resolution (LR) image patches. Then a sparse manifold assumption is cast on training patch features to find local HR neighbors for each test LR input. The reconstructed High-Resolution (HR) patches can then be derived via Neighbors Embedding (NE) technology with the help of the HR neighbors from training HR patches, and compensated for the LR images. Some experiments are taken on realizing a 3X amplification of natural images, the recovered results prove its efficiency and superiority to its counterparts visually and qualitatively.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115514191","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}
{"title":"A multiplicative update algorithm for nonnegative convex polyhedral cone learning","authors":"Qizhao Cai, Kan Xie, Zhaoshui He","doi":"10.1109/IJCNN.2014.6889623","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889623","url":null,"abstract":"The nonnegative convex polyhedral cone (NCPC) learning is discussed in this paper. By exploiting the multiplicative update nonnegative quadratic programming, a multiplicative update algorithm is developed for NCPC learning. The proposed algorithm is promising for nonnegative matrix factorization (NMF) and we verify this by numerical experiments.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122558482","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}
{"title":"Dynamic boosting in deep learning using reconstruction error","authors":"Wenhao Huang, Ni Zhang, Weisong Hu, Haikun Hong, Guojie Song, Kunqing Xie","doi":"10.1109/IJCNN.2014.6889534","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889534","url":null,"abstract":"Deep learning has attracted a lot of attention in research and industry in recent years. Behind the success of deep learning, there is much space for improvement. It is difficult to identify if a testing sample can be represented by the deep network effectively before we examining the final result. In this paper, we proposed a dynamic boosting strategy according to reconstruction error in deep networks. We use reconstruction error to determine whether the result is reliable or not. From the perspective of prediction interval, we demonstrated that with the increase of reconstruction error, the prediction interval would become bigger. Therefore, the classification result is not reliable when the reconstruction error exceeds the predetermined threshold. Since we can record the reconstruction error as well as the classification error for all training samples in training set. We can learn an extra boosting model besides the deep network in training set to improve the performance of the model. An important factor in learning the boosting model is to determine an appropriate threshold for selecting training samples. In testing, we first examine whether the reconstruction error of a testing sample exceeds the threshold to determine if we should use the boosting model. If the boosting model is used, the final result is the average of the output of the deep network and the boosting model. We conducted experiments on two widely used classification datasets and an air quality dataset. From the experiments, we see that our boosting strategy is effective in improving the performance of classification. We tested several boosting models in this paper. They can all reduce the test error to some extent under appropriate parameter settings.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131687293","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}
{"title":"Visual saliency via loss coding","authors":"Hao Zhu, Biao Han","doi":"10.1109/IJCNN.2014.6889595","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889595","url":null,"abstract":"A novel and effective bottom-up saliency model inspired by the recent findings of the early vision system is proposed. The lossy coding length, which resembles the neural cost in the hierarchical structure of human vision system, is exploit to measure saliency. We show that the proposed efficient coding network can be considered as the coding process in the early vision system. The sparse coding process in simple cells of the primary visual cortex and a dimensionality reduction process via the principal component analysis are integrated in the proposed network. The saliency value at each image pixel is computed based on the residual of the coding process. The proposed biological-inspired saliency model is evaluated on two different eye-tracking datasets against several state-of-the-art algorithms. Experimental results demonstrate the effectiveness, efficiency as well as robustness of the proposed model, and bear out the hypothesis of lossy coding for visual saliency.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131759955","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}
{"title":"Application of neural networks to evaluate experimental data of galvanic zincing","authors":"P. Michal, J. Pitel’, A. Vagaská, I. Bukovský","doi":"10.1109/IJCNN.2014.6889799","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889799","url":null,"abstract":"In order to improve corrosion resistance of alloy S355 EN 1025, the relationship between the thickness of zinc coating created during the process of acidic galvanic zincing and factors that influence this process were investigated. Influence of individual factors on thickness of zinc coating for sample area with surface current density of 3 A·dm-2 was determined by planned experiment which uses central composite plan. The obtained experimental data were evaluated based on neural network theory using cubic neural unit with Levenberg-Marquardt iterative adaptive algorithm. The influence of number of training data on the reliability of the obtained computational model has been studied. Furthermore, relationship between the amount of training data and reliability of prediction for the thickness of created zinc layer was observed. The relationship between input factors and thickness of layer coating with 88.37% reliability was reached.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115400936","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}
{"title":"EEG analysis for cognitive failure detection in driving using neuro-evolutionary synergism","authors":"A. Saha, A. Konar, R. Burman, A. Nagar","doi":"10.1109/IJCNN.2014.6889929","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889929","url":null,"abstract":"The paper proposes a solution to reduce accidents in driving by alarming specific cognitive failures to the drivers on occurrence of the failures. Three different types of cognitive failures that might occur due to lapse of i) visual alertness, ii) cognitive planning and iii) motor execution are studied, and suitable classifiers have been employed to classify these failures. Force exerted by the driver during turning or sudden tracking is also measured to detect his level of cognitive load during significant changes in the driving environment. Recurrent neural networks are introduced here as classifiers to decode cognitive tasks performed by the driver from his acquired EEG. For each recurrent neural net, we use a Lyapunov energy surface the minima of which denote the cognitive tasks during one of three cognitive activities mentioned above. Given the features of the measured EEG for a cognitive tasks, the recurrent net converges to one of several optima, describing a specific cognitive failure. Experimental results obtained by employing a driving simulator and an EEG system are encouraging.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126482701","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}
{"title":"View-invariant gait recognition via deterministic learning","authors":"Wei Zeng, Cong Wang","doi":"10.1109/IJCNN.2014.6889507","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889507","url":null,"abstract":"In this paper, we present a new method to eliminate the effect of view angle for efficient gait recognition via deterministic learning theory. The width of the binarized silhouette models the periodic deformation of human gait silhouettes. It captures the spatio-temporal characteristics of each individual, represents the dynamics of gait motion, and can sensitively reflect the variance between gait patterns across various views. The gait recognition approach consists of two phases: a training phase and a recognition phase. In the training phase, the gait dynamics underlying different individuals' gaits from different view angles are locally accurately approximated by radial basis function (RBF) neural networks. The obtained knowledge of approximated gait dynamics is stored in constant RBF networks. In order to address the problem of view change no matter the variation is small or significantly large, the training patters from different views constitute a uniform training dataset containing all kinds of gait dynamics of each individual observed across various views. In the recognition phase, a bank of dynamical estimators is constructed for all the training gait patterns. Prior knowledge of human gait dynamics represented by the constant RBF networks is embedded in the estimators. By comparing the set of estimators with a test gait pattern whose view pattern contained in the prior training dataset, a set of recognition errors are generated. The average L1 norms of the errors are taken as the similarity measure between the dynamics of the training gait patterns and the dynamics of the test gait pattern. Finally, comprehensive experiments are carried out on the CASIA-B and CMU gait databases to demonstrate the effectiveness of the proposed approach.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130078567","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}
{"title":"Improved modeling of pneumatic muscle actuator using recurrent neural network","authors":"A. Hošovský, J. Mižáková, J. Pitel’","doi":"10.1109/IJCNN.2014.6889785","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889785","url":null,"abstract":"Derivation of models of complex nonlinear systems usually incorporates a number of simplifications in modeled phenomena with the level of these simplifications being dictated primarily by its intended purpose. If the overall model accuracy is insufficient, it might be helpful to use the powerful approximation capabilities of universal approximators like neural networks which are capable of approximating certain types of functions to arbitrary degree of accuracy. On the other hand, using black-box modeling techniques can impair the resulting extrapolation qualities of the model as well as eliminate its physical interpretation. Here an improved dynamic modeling of one-DOF pneumatic muscle actuator using recurrent neural network is proposed. The proposed method preserves the physical meaning of the model while improving its accuracy compared to the original analytic model. System and model responses are compared in closed-loop (using conventional PD controller) and all unmodeled dynamics is treated as disturbance which is identified using Elman neural network It is shown that the resulting model is applicable for model-based control system design with greater precision.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121845018","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}
{"title":"The transformer fault diagnosis combing KPCA with PNN","authors":"Chenxi Dai, Zhigang Liu, Yan Cui","doi":"10.1109/IJCNN.2014.6889580","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889580","url":null,"abstract":"The probabilistic neural network (PNN) can detect the complex relationships and be used to develop its basis for the interpretation of dissolved gas-in-oil data that can identify the fault types. An efficient algorithm known as the kernel principle component analysis (KPCA) is applied to increase features in order to get higher detection accuracy. KPCA reflects the nonlinear or high order features that permit to represent and classify the varying states. More features can be obtained by the nonlinear transformation of KPCA, which can realize the biggest between-class margin of the classifiers. In this paper, we apply the method of combining KPCA with PNN in transformer fault diagnosis. The method has more superior performance than traditional PNN alone method. The property of the nonlinear extension of original data of KPCA can obtain the higher diagnosis accuracy, which can achieve better classification and diagnosis.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130299297","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}
{"title":"User-generated-video summarization using Sparse Modelling","authors":"Yulong Liu, Huaping Liu, Yunhui Liu, F. Sun","doi":"10.1109/IJCNN.2014.6889581","DOIUrl":"https://doi.org/10.1109/IJCNN.2014.6889581","url":null,"abstract":"A novel key-frame extraction method is proposed in this paper. Our method focused on user-generated-videos which were captured by smartphones or tablets or other smart devices which can record acceleration values and orientation values during video capturing. Our method use Dissimilarity-based Sparse Modeling Representative Selection(DSMRS) on orientation information to extract key-frames instead of visual features used by traditional key-frame extraction methods. Acceleration value is used in our method to exclude outliers.","PeriodicalId":189529,"journal":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117075099","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}