GPUs(Graphics processing units) have been increasingly adopted for large-scale graph processing by exploiting the inherent parallelism. There have been many efforts in designing specialized graph analytics and general...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
GPUs(Graphics processing units) have been increasingly adopted for large-scale graph processing by exploiting the inherent parallelism. There have been many efforts in designing specialized graph analytics and generalized frameworks. The two classes of graph processing systems share some common design choices, and often make specific trade-offs. However, there is no characterization study that provides an in-depth understanding of both approaches. In this paper, we analyze two GPU-based graph processing systems(Enterprise and Gunrock) from the perspective of breadth-first graph traversal. We conduct both high-level performance comparison and low-level characteristic evaluation such as workload balancing, synchronization, and memory subsystem. We investigate the differences based on10 real-world and synthetic graphs. Our results reveal some uncommon findings that would be beneficial to the research and development of large-scale graph processing on GPUs.
Network-on-chip(NoC) mapping algorithms significantly affect NoC system performance in terms of communication cost and energy consumption. For a specific application represented by a task graph, this paper proposes ...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
Network-on-chip(NoC) mapping algorithms significantly affect NoC system performance in terms of communication cost and energy consumption. For a specific application represented by a task graph, this paper proposes an energyaware mapping algorithm that searches for the mapping solution with best communication locality and therefore lowest energy consumption. During the search procedure, we employ a simulation-free, communication locality-based energy model to evaluate the quality of each candidate mapping. By iteratively updating the best candidate mapping using a greedy search heuristic, the search procedure converges to an mapping decision with optimal energy efficiency in the search space. Compared with the round-robin mapping strategy, the proposed method is capable of exploring energy-efficient mapping decision for various applications as well as network sizes.
Hashing learning has attracted increasing attention these years with the rapid increase of data. Some highdimensional data have caused the ’dimension disaster’ which make traditional methods ineffective. In this pap...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
Hashing learning has attracted increasing attention these years with the rapid increase of data. Some highdimensional data have caused the ’dimension disaster’ which make traditional methods ineffective. In this paper, we propose a method to find the nearest neighbor quickly from the highdimensional data, named pseudo-inverse locality preserving iterative hashing(PLIH).We use pseudo-inverse to replace the inverse matrix in order to solve the problem of matrix *** construct adjacency graphs and minimize the distance of the neighbors in the subspace to make the projected matrix maintain the neighborhood relations of high dimension, which solves the problem that the locality sensitive hashing cannot preserve the high-dimensional neighborhood relations effectively. Because different bit with different weight has more discriminating power than the same weight, Loss of the projection matrix in the quantization process is minimized by weighted iterative quantization. Experiments on public datasets Cnn096daltech and Gist12 daltech demonstrated that accuracy and recall of the PLIPH are both better than the traditional hashing algorithms.
Up to now, the relation classification systems focus on using various features generated by parsing modules. However, feature extraction is a time consuming work. Selecting wrong features also lead to classification e...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
Up to now, the relation classification systems focus on using various features generated by parsing modules. However, feature extraction is a time consuming work. Selecting wrong features also lead to classification errors. In this paper, we study the Convolutional Neural Network method for entity relation classification. It uses the embedding vector and the original position information relative to entities of words instead of the features extracted by traditional methods. The N-gram features are extracted by filters in the convolutional layer and the whole sentence features are extracted by the pooling layer. Then the softmax classifier in the fully connected layer is applied for relation classification. Experimental results show that the method of random initialization of the position vector is unreasonable, and the method using the vector and the original position information of words performs better. In addition, filters with multiple window sizes can capture the sentence features and the original location information can replace the complex window sizes.
In this paper, we propose a video enhancement method using temporal-spatial total variation Retinex and luminance adaption. To utilize the temporal information between video frames, we construct a illumination data fi...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
In this paper, we propose a video enhancement method using temporal-spatial total variation Retinex and luminance adaption. To utilize the temporal information between video frames, we construct a illumination data fidelity term and propose an temporal-spatial total variation model for Retinex. In order to further enhance the contrast of video frames, we use the adaptive Gamma correction with weighting distribution as a post processing step. Thus, the proposed method is able to enhance ation. Experimental results demonstrate the efficiency of the proposed method.
Many QoS-aware service selection approaches assume that the QoS attributes are crisp values and the actual user requirements are not taken into consideration, when the service-oriented applications are constructed. As...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
Many QoS-aware service selection approaches assume that the QoS attributes are crisp values and the actual user requirements are not taken into consideration, when the service-oriented applications are constructed. As a result, users searching result may not be correct and good, because there are uncertainties in the data and the optimal solutions but not satisfying some requirements may not be acceptable to some users. In this paper, we propose to use Fuzzy Set Theory(FST) and fuzzy genetic algorithm(FGA) for QoS-based service selection. FST is applied to specify the triangular fuzzy-valued description of the QoS properties. A FGA is proposed to solve the QoS-aware service composition problem, which considers the actual QoS requirements from users in the selection *** comparisons with two algorithms on different scales of composite service indicate that FGA is highly competitive regards to searching capability.
A 3D face shape derived from 2D images may be useful in many applications,such as face recognition,face synthesis and human computer *** do this,we develop a fast 3D Active Appearance Model(3D-AAM) method using depth ...
详细信息
ISBN:
(纸本)9781424467860
A 3D face shape derived from 2D images may be useful in many applications,such as face recognition,face synthesis and human computer *** do this,we develop a fast 3D Active Appearance Model(3D-AAM) method using depth *** training images include specific 3D face poses which are extremely different from one *** landmark's depth information of landmarks is estimated from the training image sequence by using the approximated Jacobian *** is added at the test phase to deal with the 3D pose variations of the input *** experimental results show that the proposed method can efficiently fit the face shape,including the variations of facial expressions and 3D pose variations,better than the typical AAM,and can estimate accurate 3D face shape from images.
Due to the recent significant improvements in game entertainment, CAD, CAE and some other 3D fields, the number of 3D models is increasing rapidly. As a result, there is an increasing need for procedures supporting th...
详细信息
With the growing trends of cloud computing, the security issues in this area are growing at the same speed as its development. Some malicious intruders and other malware activities tend to find the inner vulnerabiliti...
详细信息
ISBN:
(纸本)9781467390880
With the growing trends of cloud computing, the security issues in this area are growing at the same speed as its development. Some malicious intruders and other malware activities tend to find the inner vulnerabilities and spare no effort to control the administration or conduct the pure break-down service with curiosity or on purpose. Traditional defense systems such as firewall, intrusion detection and malware code system are still utilized in nowadays network scenes, but they may not support enough in cloud computing environment with old-fashioned architectures. Here we focus on intrusion detection system (IDS) to defend against intruders and other attacks. In this paper, we proposed a collaborative intrusion detection service and our goal is to make use of the state-of-the-art computing framework in cloud environment and to provide a rounded IDS service for both cloud providers and cloud tenants, while the collaborative architecture will help to respond to the attacks promptly. We set up our system prototype and discuss the empirical results on the preference. The experimental results demonstrate that our system does enhance the security when some network-based attacks happen and ensure that both cloud service providers and tenants are protected with satisfaction.
High-resolution(HR) image reconstruction from single low-resolution(LR) image is one of the important vision applications. Despite numerous algorithms have been successfully proposed in recent years, efficient and rob...
详细信息
ISBN:
(纸本)9781538619797;9781538619780
High-resolution(HR) image reconstruction from single low-resolution(LR) image is one of the important vision applications. Despite numerous algorithms have been successfully proposed in recent years, efficient and robust single-image superresolution(SR) reconstruction is still challenging by several factors, such as inherent ambiguous mapping between the HRLR images, necessary huge exemplar images, and computational load. In this paper, we proposed a new learning-based method of single-image SR. Inspired by simple mapping functions method, a mapping matrix table of HR-LR feature patches is calculated in the training phase. Each atom of dictionary learned from LR feature patches is corresponding to a mapping matrix in the mapping matrix table. Combining this mapping table with sparse coding, high quality and HR images are reconstructed in reconstruction phase. The effectiveness and efficiency of this method is validated with experiments on the training datasets. Compared with state-of-art methods, jagged and blurred artifacts are depressed effectively and high reconstruction quality is acquired with less exemplar images.
暂无评论