Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains. Existing domain adversarial adaptation methods based on single domain discriminator only align the source and target data distributions without exploiting the complex multimode structures. In this paper, we present a multi-adversarial domain adaptation (MADA) approach, which captures multimode structures to enable fine-grained alignment of different data distributions based on multiple domain discriminators. The adaptation can be achieved by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Empirical evidence demonstrates that the proposed model outperforms state of the art methods on standard domain adaptation datasets.

In energy-constrained wireless sensor networks, energy efficiency is critical for prolonging the network lifetime. A family of ant colony algorithms called DAACA for data aggregation are proposed in this paper. DAACA consists of three phases: initialization, packets transmissions and operations on pheromones. In the transmission phase, each node estimates the remaining energy and the amount of pheromones of neighbor nodes to compute the probabilities for dynamically selecting the next hop. After certain rounds of transmissions, the pheromones adjustments are performed, which take the advantages of both global and local merits for evaporating or depositing pheromones. Four different pheromones adjustment strategies which constitute DAACA family are designed to prolong the network lifetime. Experimental results indicate that, compared with other data aggregation algorithms, DAACA shows higher superiority on average degree of nodes, energy efficiency, prolonging the network lifetime, computation complexity and success ratio of one hop transmission. At last, the features of DAACA are analyzed.

No abstract

No abstract