In order to improve the quality of intelligent test paper generation, an improved Memetic Algorithm (MA) is proposed as the strategy for intelligent test paper generation in this paper, which is based on Particle Swar...
详细信息
This paper proposes a locality correlation discriminant with neighborhood preserving embedding for face recognition, which considers both the locality correlation and manifold structure of the training data. A new loc...
详细信息
Interactive technique for shape manipulation is highly desirable in geometric modeling community. In general, designers are often required to manipulate the shape of large, complex or specific 3D models with no smooth...
详细信息
Video watermark consists of visible and invisible watermark. Visible watermark is mainly used for declaration of copyright ownership and plays a role in advertising while invisible watermark for copyright protection a...
详细信息
Web spam deceives search engines to get high ranking for benefit, and disturbs users to obtain information normally. Detecting web spam is one of the major challenges faced by search engines. Various machine learning ...
详细信息
Multi-label classification refers to learning tasks with each instance being assigned with a set of multiple class labels simultaneously, and many multi-label learning methods focus on supervised settings which assume...
详细信息
Wireless Sensor Networks (WSNs) are subject to node failures because of limited energy and link unreliability which makes the design of routing protocols in such networks a challenging task. The multipath routing sche...
详细信息
ISBN:
(纸本)9781629932170
Wireless Sensor Networks (WSNs) are subject to node failures because of limited energy and link unreliability which makes the design of routing protocols in such networks a challenging task. The multipath routing scheme is an optimal alternative to address this problem which splits the traffic across multiple paths instead of routing all the traffic along a single path. However, using more paths introduces more contentions which degrade energy efficiency. The problem becomes even more difficult in the scenario of multiple source-destination pairs since the flow distribution of each link is uncertain. Our goal is to minimize the energy cost and provide the robust transmission by choosing the optimal paths. We propose a distributed Energy Efficient Routing protocol (D2ER) to achieve this goal. In D2ER, we first study the problem from a theoretical standpoint by mapping it to the multi-commodity network design problem. Then, we employ the transportation method to solve this problem since it is hard to build a global addressing scheme due to the great number of sensor nodes. Simulation results demonstrate that our optimal algorithm can save energy drastically.
Branching morphology is a crucial factor in phenotype of soybeans and the primary tissue to transport nutrients. After the acquirement of an empirical model and distribution interval for soybeans height by nonlinear r...
详细信息
Modeling and simulating group behaviours have been an active research topic in the field of com- puter animation and game. This paper presents some novel approaches for supporting entity modeling and path generation i...
详细信息
Modeling and simulating group behaviours have been an active research topic in the field of com- puter animation and game. This paper presents some novel approaches for supporting entity modeling and path generation in crowd simulation. It analyses related work about crowd simulation first. Then, an entity modeling approach based on CGA (Cellular genetic algorithm) and NURBS (Non uniform relational B splines) technologies is presented. Next, following the analysis to PSO (Particle swarm optimization) and ABC (Artificial bee colony) algo- rithms, a crowd path generative approach based on ABC- PSO is put forward. After that, a simulating example of crowd cohesion and performance comparison are exhibited for showing the efficiency of the algorithms. Finally, the current work is summarized and an outlook for the future work is given.
Label ranking is a complex prediction task, in which the goal is to map instances to a total order over a finite set of predefined labels. To solve this problem, a novel approach named APRiori based Label Ranking (APR...
详细信息
暂无评论