Existing planning and scheduling solutions for container terminal logistics systems (CTLS) are not sufficient today due to the highly complexity and uncertain environments. This paper reviews the advantages and shortc...
详细信息
Existing planning and scheduling solutions for container terminal logistics systems (CTLS) are not sufficient today due to the highly complexity and uncertain environments. This paper reviews the advantages and shortcomings of the existing solutions and proposes a container terminal conceptual parallel computing model for scheduling and execution based on multi-processor systems. It is built on the computational architecture and fundamental principles of distributed, cooperative, parallel, heterogeneous, and reconfigurable computation in essence. The proposed approach is demonstrated and validated by investigating the stress testing, tailor-made processor affinity, load migration and load balancing of a typical container terminal logistics service case with comprehensive computational experiments.
Link prediction in network attempts to predict the exist-yet-unknown links or future links in accordance with the node properties and the network typology. It has been used in many domains such as social network, biol...
详细信息
ISBN:
(纸本)9781479986989
Link prediction in network attempts to predict the exist-yet-unknown links or future links in accordance with the node properties and the network typology. It has been used in many domains such as social network, biology experiment, and criminal investigations. Classical methods are based on graph topology structure and path features but few consider clustering information. Actually, clustering information plays an important role in link prediction, it connects the sparse nodes and other communities to form intensive communities. Besides the application of clustering, the MapReduce-based method is used to improve the efficiency. The validity of algorithm is verified by real-world datasets. The experimental results show that the proposed algorithm has a higher prediction accuracy and lower time complexity, and is more scalable than traditional methods executed by a single machine.
In the research area of community detection which aims at detecting some highly cohesive vertex subsets in social network, there mainly exist some problems, such as the algorithms with comparatively excellent quality ...
详细信息
ISBN:
(纸本)9781479986989
In the research area of community detection which aims at detecting some highly cohesive vertex subsets in social network, there mainly exist some problems, such as the algorithms with comparatively excellent quality of the final partitioning usually have high time complexity and some other fast algorithms often result in low quality of partitioning or other disadvantages. Nowadays, the increasing demands for community detection in large-scale social networks necessitate the use of distributed and scalable methods to detect communities in an effective and efficient manner. label propagation algorithm (LPA), whose time complexity is O (m) on a network with m edges, is a near linear time algorithm to detect community effectively. Besides, owing to having good scalability, the parallel version of LPA (DLPA) is suitable for community detection in large-scale social networks. However, DLPA synchronously updates the vertices labels, which usually brings about label oscillations and results in low quality of partitioning. In this paper, we analyze the drawbacks of DLPA and propose a novel method C-DLPA, which combines DLPA with the notion of maximal cliques and at the same time utilizes a new updating mechanism that updating each node' label by probability of its adjacent nodes, to make final partitioning become more accurate and to avoid oscillations effectively. The experimental results show that C-DLPA has better performance is not only low time cost by as much to avoid oscillations but its community detection accuracy compared with DLPA.
It plays an important role to recognize human actions from realistic videos in multimedia event detection and understanding. To this aim, a novel human tracking approach is proposed in this paper. Firstly, salient key...
详细信息
ISBN:
(纸本)9781479986989
It plays an important role to recognize human actions from realistic videos in multimedia event detection and understanding. To this aim, a novel human tracking approach is proposed in this paper. Firstly, salient key points trajectories are generated to track human actions at multiple spatial scales. Then, camera motion elimination is utilized to further improve the robustness of motion trajectories. To depict human motions accurately and efficiently, the Histogram of Oriented Gradient (HOG), Histogram of Optical Flow (HOF) and Motion Boundary Histogram (MBH) are employed with the Fisher vector model being utilized to aggregate these three features. Extensive experimental results on four challenging human action video datasets demonstrate that the proposed approach is able to achieve better recognition performances in a more computationally efficient manner as compared with a number of state-of-the-art approaches.
Based on distributed networks of the Super-Peer Architecture (SPA), this paper proposes Efficient Method for Skyline Recommendation in Distributed Networks (EMSRDN), to handle u skyline recommendation instructions by ...
详细信息
This paper introduces a regularization method called Correlative Filter (CF) for Convolutional Neural Network (CNN), which takes advantage of the relevance between the convolutional kernels belonging to the same convo...
详细信息
ISBN:
(纸本)9781479986989
This paper introduces a regularization method called Correlative Filter (CF) for Convolutional Neural Network (CNN), which takes advantage of the relevance between the convolutional kernels belonging to the same convolutional layer. During the process of training with the proposed CF method, several pairs of filters are designed in a manner of randomness to contain opposite weights in low-level layers. Regarding higher level layers where synthetical features are processed, the relation between correlative filters is explored as translation of various directions. The proposed CF method attempts to optimize the inner structure of convolutional layers and it can work jointly with other regularization techniques, such as stochastic pooling, Dropout, etc. The experimental results on the competitive image classification benchmark dataset CIFAR-10 demonstrates the performance of the proposed CF method, additionally, it is also verified that the proposed CF method is wonderful to be employed to enhance several state-of-the-art regularization models.
Today’s workflow systems are crossing organizational boundaries and usually involve multiple organizations or partners, and the crossorganization workflow has received much public attention from both the academia and...
详细信息
In this paper, we propose a novel subspace learning algorithm, termed as null space based discriminant sparse representation large margin (NDSLM). There are two contributions in the paper. First, we propose a new expe...
详细信息
ISBN:
(纸本)9781479919611
In this paper, we propose a novel subspace learning algorithm, termed as null space based discriminant sparse representation large margin (NDSLM). There are two contributions in the paper. First, we propose a new expectation to obtain the neighborhood information for large margin subspace learning, i.e., the within-neighborhood scatter and between-neighborhood scatter are modeled by the sparse reconstruction weights of the samples from the same class and different classes, respectively. Since the neighborhood information formed by sparse representation can capture non-linearities in the data, the proposed method possesses more discriminative information than the traditional large margin learning methods with the expectation using Euclidean distance, etc. Second, the large margin information integrated into the model of Fisher criterion makes the discriminating power of NDSLM further boosted. NDSLM addresses the small sample size problem by solving an eigenvalue problem in null space. Experiments on ORL, Yale, AR, Extended Yale B and CMU PIE five face databases are performed to evaluate the proposed algorithm and the results demonstrate the effectiveness of NDSLM.
Information recommendation between groups is one of the most important ways for information sharing and transmitting in social networks. However, it needs exponential time cost to achieve the exact optimal recommendat...
详细信息
Virtualizing Hadoop clusters provides many benefits, including rapid deployment, on-demand elasticity and secure multi-tenancy. However, a simple migration of Hadoop to a virtualized environment does not fully exploit...
详细信息
Virtualizing Hadoop clusters provides many benefits, including rapid deployment, on-demand elasticity and secure multi-tenancy. However, a simple migration of Hadoop to a virtualized environment does not fully exploit these benefits. The dual role of a Hadoop worker, acting as both a compute node and a data node, makes it difficult to achieve efficient IO processing, maintain data locality, and exploit resource elasticity in the cloud. We find that decoupling per-node storage from its computation opens up opportunities for IO acceleration, locality improvement, and on-the-fly cluster resizing. To fully exploit these opportunities, we propose StoreApp, a shared storage appliance for virtual Hadoop worker nodes co-located on the same physical host. To completely separate storage from computation and prioritize IO processing, StoreApp pro-actively pushes intermediate data generated by map tasks to the storage node. StoreApp also implements late-binding task creation to take the advantage of prefetched data due to mis-aligned records. Experimental results show that StoreApp achieves up to 61% performance improvement compared to stock Hadoop and resizes the cluster to the (near) optimal degree of parallelism.
暂无评论