In today's highly mobile, networked, and interconnected internet world, the flow and volume of information is overwhelming and continuously increasing. Therefore, it is believed that the next frontier in technolog...
ISBN:
(纸本)9781450311137
In today's highly mobile, networked, and interconnected internet world, the flow and volume of information is overwhelming and continuously increasing. Therefore, it is believed that the next frontier in technological evolution and development will rely in our ability to develop intelligent systems that can help us process, analyze, and make-sense of information autonomously just as a well-trained and educated human expert. In computational intelligence, neuromorphic computing promises to allow for the development of computing systems able to imitate natural neuro-biological processes that will form the foundation for intelligent system architectures. This is achieved by artificially re-creating the highly parallelized computing architecture of the mammalian brain. As an interdisciplinary technology inspired from biology, artificial neural systems have been successfully utilized in many applications, such as control systems, signal processing, patternrecognition, vision systems, and robotics etc. In addition, the emerging neuromorphic computing field can also exploit the characteristic behavior of novel material systems with advanced processing techniques to achieve very large scale integration with highly parallel neural architectures for the fabrication physical architectures. This talk will focus on the technological challenges that we are seeking to overcome to enable intelligent parallel neuromorphic computing systems.
In this paper,we study how to use the search session information to improve the retrieval *** propose a session-oriented retrieval model based on Markov random *** model introduces the correlations between query terms...
详细信息
In this paper,we study how to use the search session information to improve the retrieval *** propose a session-oriented retrieval model based on Markov random *** model introduces the correlations between query terms as a retrieval factor into the retrieval *** also presents a dynamic update algorithm based on the analysis of users' search *** model implements a complete session-oriented information retrieval framework *** use ClueWeb09 category B dataset and TREC 2010 (2011) Session dataset to quantitatively evaluate the *** results show that our model can improve retrieval performance substantially using the search session information.
It is a very significant task that how to select informative features from the feature space for patternrecognition. Relief is considered one of the most successful algorithms for evaluating the quality of features. ...
详细信息
It is a very significant task that how to select informative features from the feature space for patternrecognition. Relief is considered one of the most successful algorithms for evaluating the quality of features. In this paper, we provide a valid proof for the first time, which demonstrates a blind selection problem in the previous Relief algorithm. Then we propose an adaptive Relief (A-Relief) algorithm to alleviate the deficiencies of Relief by dividing the instance set adaptively. Last, several experiments are reported by A-Relief and other feature selection methods. The experimental results illustrate the efficiency of A-Relief algorithm proposed in this paper.
This paper proposes a structural damage detection method based on wavelet packet decomposition, non-negative matrix factorization(NMF) and a relevance vector machine(RVM). First, vibration data at multiple points are ...
详细信息
This paper proposes a structural damage detection method based on wavelet packet decomposition, non-negative matrix factorization(NMF) and a relevance vector machine(RVM). First, vibration data at multiple points are used to calculate the wavelet packet node energies and construct a non-negative damage feature matrix. Second, to increase the damage detection accuracy, the NMF technique is employed to obtain the reduced dimensional representation of the non-negative damage feature matrix and extract the underlying features. Last, the RVM, a powerful tool for classification and regression, that can obtain the probability estimation for classification, is used to determine the relationship between features extracted with NMF and the corresponding damage patterns by considering the measurement noise. The trained RVMs are then used to perform damage pattern identification and classification of an unknown state structure. Numerical study on the Binzhou Yellow River Highway Bridge is carried out to validate the ability of the proposed method in damage detection. The results show that the RVM can achieve a high accuracy in damage pattern identification accuracy using the features extracted by NMF.
Recurring to well-rounded fuzzy theory and technology can realize exact expression and manage between imprecise information and imprecise relation on water-bursting prediction. Advanced a method combining the fuzzy cl...
详细信息
Recurring to well-rounded fuzzy theory and technology can realize exact expression and manage between imprecise information and imprecise relation on water-bursting prediction. Advanced a method combining the fuzzy cluster analysis and fuzzy patternrecognition to forecast deep seam mining floor water-bursting. Firstly, the simple integration is classified for the water-bursting by adopting clustering analysis method. The fuzzy model is set up for different degree. Afterwards, the danger degree of the undetermined forecasting sample is predicted by applying fuzzy patternrecognition. Through actual validation, the reliability of the prediction is tested and verified.
Multi-task learning (MTL) has drawn a lot of attentions in machine learning. By training multiple tasks simultaneously, information can be better shared across tasks. This leads to significant performance improvement ...
详细信息
In this paper,we propose a novel approach to improve a statistical model-based voice activity detection(VAD) method based on a modified conditional maximum a posteriori(MAP) criterion incorporating the spectral gradie...
详细信息
In this paper,we propose a novel approach to improve a statistical model-based voice activity detection(VAD) method based on a modified conditional maximum a posteriori(MAP) criterion incorporating the spectral gradient *** proposed conditional MAP incorporates not only the voice activity decision in the previous frame as in Ref.[1] but also the spectral gradient of the observed spectra between the current frame and the past frames to efficiently exploit the inter-frame correlation of voice *** a result,the proposed VAD leads to six separate thresholds to be adaptively determined in the likelihood ratio test(LRT) depending on both the previous VAD result and the estimated spectral gradient *** results demonstrate that the proposed approach yields better results compared to those of the previous conditional MAP-based method.
Content-based image retrieval (CBIR) is an application of computer vision techniques to the image retrieval *** is,the problem of searching for digital images in large *** this paper,we apply an image segmentation tec...
详细信息
Content-based image retrieval (CBIR) is an application of computer vision techniques to the image retrieval *** is,the problem of searching for digital images in large *** this paper,we apply an image segmentation technique to an image retrieval system which is designed for the use on mobile *** an image captured by the mobile devices,edge detection and region merging mechanisms are used in this segmentation technique to extract the ROI from a complex background *** proposed method automatically merges the regions that are initially segmented by mean shift segmentation,and then effectively extracts the object contour by the labeled regions as either background or *** no users interaction,the experimental results show the method is more effective than other automatic segmentation methods.
Image spam has become a new obfuscating method to bypass conventional text based spam *** this paper,a new kind of image spam filtering method is proposed based on the characteristics of the spam being sent repeatedly...
详细信息
Image spam has become a new obfuscating method to bypass conventional text based spam *** this paper,a new kind of image spam filtering method is proposed based on the characteristics of the spam being sent repeatedly and their contents being highly resemble to each *** extract sub-block color histogram and ORB as image feature and run a scalable vocabulary tree to detect image *** system is tested on Mark Dredze's dataset and our own Chinese image spam *** results demonstrate that the proposed method can achieve good accuracy while having a less than 0.02% false positive rate.
In this paper,we introduce a new dataset for scene classification based on camera *** classify the most common scenes that have been researched much *** dataset consists of 12 scene *** category contains 500 to 2000 *...
详细信息
In this paper,we introduce a new dataset for scene classification based on camera *** classify the most common scenes that have been researched much *** dataset consists of 12 scene *** category contains 500 to 2000 *** images are high resolution such as 2000x2000 *** images in the dataset are original,namely,each image brings with a camera metadata (EXIF).Various types,metadata cues of photos,strict definitions among scenes are characteristic factors that make this dataset a very challenging testbed for photo *** supply the scene photos together with scene labeling,as well as the EXIF information extraction via methodology,and we apply the dataset into sementic scene classification up to now.
暂无评论