Sparse coding has high-performance encoding and ability to express images, sparse encoding basis vector plays a crucial role. The computational complexity of the most existing sparse coding basis vectors of is relativ...
详细信息
Sparse coding has high-performance encoding and ability to express images, sparse encoding basis vector plays a crucial role. The computational complexity of the most existing sparse coding basis vectors of is relatively large. In order to reduce the computational complexity and save the time to train basis vectors. A new Hebbian rules based method for computation of sparse coding basis vectors is proposed in this paper. A two-layer neural network is constructed to implement the task. The main idea of our work is to learn basis vectors by removing the redundancy of all initial vectors using Hebbian rules. The experiments on natural images prove that the proposed method is effective for sparse coding basis learning. It has the smaller computational complexity compared with the previous work.
With increasing defect density, microprocessors, especially the embedded caches, will encounter more faults. Adding spare resources to replace defective components is a widely accepted method for yield enhancement. In...
With increasing defect density, microprocessors, especially the embedded caches, will encounter more faults. Adding spare resources to replace defective components is a widely accepted method for yield enhancement. In this work, a repair method using content addressable memory combined with spare bits, as well as a novel fault injection method is proposed. With the proposed fault injection technique, various numbers and types of faults can be flexibly injected into the silicon. A wireless sensor network system using our self-repairable microprocessor (SRP) is developed to prove the effectiveness of the proposed technique.
Nowadays complex information system's integrated formal models of function verification and performance evaluation lack properties constraint about space aspect. This paper presents an integrated verification mode...
详细信息
Nowadays complex information system's integrated formal models of function verification and performance evaluation lack properties constraint about space aspect. This paper presents an integrated verification model atsFPM by defining a space requirement function over the states of the considered information system. The patterns of paths which are based on regular expressions is proposed in order to specify the functional specifications. The syntax and semantic of the model atsFPM is defined. A conversion product model is obtained by the combination of the system model and the automaton of the pattern of paths which expresses the functional specifications. The verification of the model atsFPM is tackled by the performance verification technique of Markov Reward Model. Experimental results show that the atsFPM model and its verification approach can satisfy the modeling of information system and verification of functional and performance specifications.
This paper proposes a Sample-Consensus method for viewpoint independent sign language recognition under data deficiency (matched features are possibly deficient with regard to some frame pairs). The proposed method is...
详细信息
This paper proposes a Sample-Consensus method for viewpoint independent sign language recognition under data deficiency (matched features are possibly deficient with regard to some frame pairs). The proposed method is based on the epipolar geometry and inspired by RANSAC. The basic idea is that all corresponded frames between two sequences of the same sign can be roughly considered as captured synchronously by a virtual stereo vision system and thus they will satisfy the same fundamental matrix. In addition, the fundamental matrix can be estimated from point correspondences contained by some part of corresponding frames. Experimental results demonstrate the efficiency of the proposed method. Moreover, this Sample-Consensus method can be easily extended to some similar problems, such as viewpoint independent activity analysis and rigid-motion analysis.
The importance of the data uncertainty was studied deeply with the rapid development in data gathering and processing in various fields, inclusive of economy, military, logistic, finance and telecommunication, etc. Un...
详细信息
The importance of the data uncertainty was studied deeply with the rapid development in data gathering and processing in various fields, inclusive of economy, military, logistic, finance and telecommunication, etc. Uncertain data has many different styles, such as relational data, semistructured data, streaming data, and moving objects. According to scenarios and data characteristics, tens of data models have been developed, stemming from the core possible world model that contains a huge number of the possible world instances with the sum of probabilities equal to 1. However, the number of the possible world instances is far greater than the volume of the uncertain database, making it infeasible to combine medial results generated from all of possible world instances for the final query results. Thus, some heuristic techniques, such as ordering, pruning, must be used to reduce the computation cost for the high efficiency. This paper introduces the concepts, characteristics and challenges in uncertain data management, proposes the advance of the research on uncertain data management, including data model, preprocessing, integrating, storage, indexing, and query processing.
In deep sub-micron designs, the delay caused by power supply noise (PSN) can no longer be ignored. A PSN-induced path delay fault (PSNPDF) model is proposed in this paper, and should be tested to enhance chip quality....
Microprocessors have turned to multicore, i.e. multiple processor cores, along with some levels of on-chip caches and interconnection networks, integrated on a singe chip. However, it brings challenges on how to progr...
详细信息
The amount of die area consumed by scan chains and scan control circuit can range from 15%∼30%, and scan chain failures account for almost 50% of chip failures. As the conventional diagnosis process usually runs on t...
详细信息
The community structure is a basic characteristic of complex networks. A strong community structure has high modularity. It has been proven an NP-Complete problem to identify the community structure with the highest m...
详细信息
ISBN:
(纸本)9781605583877
The community structure is a basic characteristic of complex networks. A strong community structure has high modularity. It has been proven an NP-Complete problem to identify the community structure with the highest modularity. Many approximate algorithms have been proposed to alleviate the problem. However, they suffer from inefficiency or low quality. In this paper, we propose a two-step method. The first step of our method analyze the vertex similarity of the network, which is a microscopic view. If a pair of vertices are similar enough, they will be put into the same community. The second step of our method focuses on the increment of modularity of the similarity-based communities generated by the first step. If the number of edges between two communities is greater than the expected number based on random choice, the two communities will be merged. The second step is implemented by the CNM algorithm or its improvement CNM+HE'. The similarity-based community remedies the defect on microscope introduced by CNM or CNM+HE'. Our method runs efficiently and finds meaningful communities effectively. We tested the method on more than twenty datasets. The modularity of community structure found by the method is higher than the state-of-the-art algorithm. Copyright 2008 ACM.
暂无评论