Stars in a star map can be regarded as a point pattern, and we can utilize the matching of point pattern to recognize the star pattern. First, the nth Radius-Weighted-Mean Points (RWMPs) are proposed which are invaria...
详细信息
We shed light on the key ingredients of reservoir computing and analyze the contribution of the network dynamics to the spatial encoding of inputs. Therefore, we introduce attractor-based reservoir networks for proces...
详细信息
ISBN:
(纸本)9783642158216
We shed light on the key ingredients of reservoir computing and analyze the contribution of the network dynamics to the spatial encoding of inputs. Therefore, we introduce attractor-based reservoir networks for processing of static patterns and compare their performance and encoding capabilities with a related feedforward approach. We show that the network dynamics improve the nonlinear encoding of inputs in the reservoir state which can increase the task-specific performance.
In this paper, we propose a novel approach to automatically learn a compact and yet discriminative representation for humane action recognition. Considering the static visual information and motion information, each f...
详细信息
ISBN:
(纸本)9781450304603
In this paper, we propose a novel approach to automatically learn a compact and yet discriminative representation for humane action recognition. Considering the static visual information and motion information, each frame is represented in two feature subsets (views) and Gaussian Mixture Model (GMM) is adopted to model the distributions of those features. In order to complement the strengths of the different features (views), a Co-EM based multiview learning framework is introduced to estimate the parameters of GMM instead of conventional single view based EM. Then Gaussian components are considered as video words to describe videos with different time resolutions. Compared with the traditional method to recognize action, there are several advantages with the proposed method using Co-EM strategy. First, complex actions are efficiently modeled by GMM, and the number of its component is automatically determined with the Minimum Description Length (MDL). Second, because the imperfectness of single view can be compensated by the other view in the Co-EM, the resulting bag of video words are superior to that formed by any single view. To the best of our knowledge, we are the first to try the Co-EM based multi-view learning method for action recognition and obtain significantly better results. We extensively verify our proposed approach on two publicly available challenging datasets: the KTH dataset and Weizmann dataset. The experimental results show the validity of our proposed method. Copyright 2010 ACM.
In this paper we introduce a new model called iso-picture splicing system, to generate iso-pictures. We compare the family of languages generated by the proposed system with existing family of languages such as local ...
详细信息
An extension of an evolving spiking neural network (eSNN) is proposed that enables the method to process spatio-temporal information. In this extension, an additional layer is added to the network architecture that tr...
详细信息
ISBN:
(纸本)9783642175367
An extension of an evolving spiking neural network (eSNN) is proposed that enables the method to process spatio-temporal information. In this extension, an additional layer is added to the network architecture that transforms a spatio-temporal input pattern into a single intermediate high-dimensional network state which in turn is mapped into a desired class label using a fast one-pass learning algorithm. The intermediate state is represented by a novel probabilistic reservoir computing approach in which a stochastic neural model introduces a non-deterministic component into a liquid state machine. A proof of concept is presented demonstrating an improved separation capability of the reservoir and consequently its suitability for an eSNN extension.
Water leakage is now a serious widespread problem in water distribution network (WDN), no matter what pipe material it used, leakage will occur inevitably with time. Therefore, the problem of water leakage has become ...
详细信息
ISBN:
(纸本)9780415548519
Water leakage is now a serious widespread problem in water distribution network (WDN), no matter what pipe material it used, leakage will occur inevitably with time. Therefore, the problem of water leakage has become the focus of China's water supply industry. When leakage occurs, the values of the pressure at monitoring points will fluctuate which are relation with leakage degree or location. And it is just like the fingerprints by which software can identify a person. Therefore, in this paper, PNN (PNN) is provided for recognizing fluctuations caused by leakage so as to find the leakage locations approximately by the method of Bayesian classifier selector. The model is applied in water supply networks of a city located in Northeast of China, using its actual monitoring data to check the established leakage locating model. Then we analyzed the existing problems of model and proposed possible measures for leakage control of water industry.
A tool for discovery of gait anomalies of elderly from motion sensor data is proposed. The gait of the user is captured with the motion capture system, which consists of tags attached to the body and sensors situated ...
详细信息
ISBN:
(纸本)9780769542638
A tool for discovery of gait anomalies of elderly from motion sensor data is proposed. The gait of the user is captured with the motion capture system, which consists of tags attached to the body and sensors situated in the apartment. Position of the tags is acquired by the sensors and the resulting time series of position coordinates are analyzed with dynamic time warping and machine learning algorithms in order to identify the specific gait anomaly. We designed medically oriented features for training a machine learning classifier that classifies the user's gait into: i) normal, ii) with hemiplegia, iii) with Parkinson's disease, iv) with pain in the back and v) with pain in the leg. Experimental results show that the proposed tool is usable for discovery of gait anomalies.
This publication discusses intelligent systems for cognitive data categorisation with a particular emphasis on image analysis systems used to analyse medical images. This type of systems used to interpret, analyse and...
详细信息
ISBN:
(纸本)9783642134661
This publication discusses intelligent systems for cognitive data categorisation with a particular emphasis on image analysis systems used to analyse medical images. This type of systems used to interpret, analyse and reason work following the operating principles of cognitive information system. Cognitive systems interpret complex data by extracting semantic levels from it, which they use to determine the meaning of the data analysed, to cognitively understand it, as well as to reason and forecast changes in the area of the phenomena researched. Thus the course of human processes of leaning about the described phenomenon becomes the foundation for developing automatic cognitive systems which are called cognitive data analysis systems.
In this paper, we present a palmprint recognition method which combines local binary pattern (LBP) and cellular automata. The LBP descriptor is proposed as a unifying texture model that describes the formation of a te...
详细信息
The proceedings contain 1,072 papers. The topics discussed include: vehicle surface affection on antenna polarization;RBF intelligent model of microwave rectangular PDGS-LPF;printed 6-element dipole array antenna for ...
ISBN:
(纸本)9781424437092
The proceedings contain 1,072 papers. The topics discussed include: vehicle surface affection on antenna polarization;RBF intelligent model of microwave rectangular PDGS-LPF;printed 6-element dipole array antenna for omnidirection applied in WiMAX;an effective target tracking algorithm in infrared images video;residual-feedback particle filter for maneuvering target tracking;nonlinear analog circuit diagnosis based on Volterra series and neural network;simulation on the fast frequency estimation algorithm of FH signal;a new MMSE estimator based on signal correlation property;performance analysis and simulation of both QPSK and OQPSK;a review of adaptive beamforming techniques for wideband smart antennas;a practical and efficient algorithm for distributed interference alignment based on cognitive radio;the use of remote sensing technology in environmental protection;and research on patternrecognition based on the universal electronic tongue system.
暂无评论