We address the problem of metric learning for multi-view data. Many metric learning algorithms have been proposed, most of them focus just on single view circumstances, and only a few deal with multi-view data. In thi...
详细信息
We address the problem of metric learning for multi-view data. Many metric learning algorithms have been proposed, most of them focus just on single view circumstances, and only a few deal with multi-view data. In this paper, motivated by the co-training framework, we propose an algorithm-independent framework, named co-metric, to learn Mahalanobis metrics in multi-view settings. In its implementation, an off-the-shelf single-view metric learning algorithm is used to learn metrics in individual views of a few labeled examples. Then the most confidently-labeled examples chosen from the unlabeled set are used to guide the metric learning in the next loop. This procedure is repeated until some stop criteria are met. The framework can accommodate most existing metric learning algorithms whether types-of- side-information or example-labels are used. In addition it can naturally deal with semi-supervised circumstances under more than two views. Our comparative experiments demon- strate its competiveness and effectiveness.
Data aggregation in wireless sensor networks is widely used to collect data in an energy efficient manner to eliminate redundant data transmission so that prolong the network lifetime. To meet the data aggregation nee...
详细信息
ISBN:
(纸本)9781479976164
Data aggregation in wireless sensor networks is widely used to collect data in an energy efficient manner to eliminate redundant data transmission so that prolong the network lifetime. To meet the data aggregation needs in wireless sensor networks, this paper proposes a novel multi-path routing algorithm, called EAD, to process in-network data aggregation. For each sensor on the routing paths, EAD evaluates its neighbors based on the residual energy, deviation angle and distance, and selects the k neighbors with the minimal evaluation costs as its forwarding nodes in order to balance energy consumption of the wireless sensor network on the premise of ensuring the reliability and performance. Simulation results show that EAD can effectively prolong network lifetime, reduce latency and ensure the reliability by adjusting the weight of each influencing factor.
Cyber-Physical Systems (CPS) play an important role in the safety-critical systems. It is very significant to verify whether some concerned behaviors exist in a CPS. Hybrid interface automata, extension of a non-hybri...
详细信息
Cyber-Physical Systems (CPS) play an important role in the safety-critical systems. It is very significant to verify whether some concerned behaviors exist in a CPS. Hybrid interface automata, extension of a non-hybrid version, are used to model a CPS. A scenario, described by MARTE sequence diagram, specifies the concerned behaviors. An algorithm is given for bounded checking the behavioral nonexistent consistency, namely, the behaviors specified by a scenario all do not exist in a hybrid interface automaton. The idea of the algorithm is, firstly, encoding the behavioral nonexistent consistency to an unconstrained dynamic programming, secondly, solving the unconstrained dynamic programming by a genetic algorithm. The algorithm can search the results on the real domain, and be applied to nonlinear as well as linear hybrid systems.
It has been shown by Retinex theory that the object's color in the image is determined by its reflectance. Under this frame work, several Retinex-based algorithms have been developed to uncover the real appearance...
详细信息
ISBN:
(纸本)9781467369541
It has been shown by Retinex theory that the object's color in the image is determined by its reflectance. Under this frame work, several Retinex-based algorithms have been developed to uncover the real appearance of objects by estimating their reflectance in image. In this paper we propose an algorithm of optimizing the illumination based on guided image filter theory, where bilateral filter is utilized to estimate the illumination image. The proposed algorithm removes the halo phenomenon precisely and strengthens the partial contrast gradient effectively. Examples are given to demonstrate the effectiveness of the proposed method.
Developing an efficient and highly scalable ray tracer for the Metropolis light transport algorithm is becoming increasingly important as the request for photorealistic images becomes a common trend. Although the Metr...
详细信息
Developing an efficient and highly scalable ray tracer for the Metropolis light transport algorithm is becoming increasingly important as the request for photorealistic images becomes a common trend. Although the Metropolis light transport algorithm has produced some of the most realistic images to date, it usually takes a great amount of time to render an image. The development of an efficient and highly scalable ray tracer for the Metropolis light transport algorithm is hard due in large part to the irregular memory access patterns, the imbalanced workload of light-carrying paths and the complicated mathematical model and complex physical processes. In this paper, we present a highly scalable physically based parallel ray tracer for the Metropolis light transport algorithm. Firstly, we present the idea of snapshot and sub-snapshot, then propose a novel assignment partitioning algorithm for compute nodes and CPU cores since the demand-driven assignment partitioning algorithms don't work. Secondly, we propose a physically based parallel ray racing framework for the Metropolis light transport algorithm, which is based on a master-worker architecture. Finally, we discuss the issue of granularity of the assignment partitioning and some optimization strategies for improving overall performance, then a hybrid scheduling strategy combining a static and dynamic scheduling strategy is described. Experiments show that our physically based ray tracer almost reaches linear speedup by using 26,400 CPU cores on the Tianhe-2 supercomputer. Our ray tracer is more efficient and highly scalable.
Transactions are common in business processes (BPs). Consistency on data, which is defined as satisfaction of a set of data integrity constraints, is one of the basic properties for business process transactions (BPTs...
详细信息
Detecting communities from networks is one of the important and challenging research topics in social network analysis, especially from bipartite network. In unipartite network, communities are usually represented as ...
详细信息
The negative bias temperature instability (NBTI) in CMOS devices is one of most prominent sources of aging mechanisms, which can induce severe threats to the reliability of modern processors at deep submicron semicond...
详细信息
Since smartphones have stored diverse sensitive privacy information, including credit card and so on, a great deal of malware are desired to tamper them. As one of the most prevalent platforms, Android contains sensit...
详细信息
Landmark heuristics are perhaps the most accurate current known admissible heuristics for optimal planning. A disjunctive action landmark can be seen a form of at-least-one constraint on the actions it contains. In ma...
暂无评论