Prevalent domain adaptation approaches are suitable for a close-set scenario where the source domain and the target domain are assumed to share the same data categories. However, this assumption is often violated in real-world conditions where the target domain usually contains samples of categories that are not presented in the source domain. This setting is termed as open set domain adaptation (OSDA). Most existing domain adaptation approaches do not work well in this situation. In this article, we propose an effective method, named joint alignment and category separation (JACS), for OSDA. Specifically, JACS learns a latent shared space, where the marginal and conditional divergence of feature distributions for commonly known classes across domains is alleviated (Joint Alignment), the distribution discrepancy between the known classes and the unknown class is enlarged, and the distance between different known classes is also maximized (Category Separation). These two aspects are unified into an objective to reinforce the optimization of each part simultaneously. The classifier is achieved based on the learned new feature representations by minimizing the structural risk in the reproducing kernel Hilbert space. Extensive experiment results verify that our method outperforms other state-of-the-art approaches on several benchmark datasets.

Mobile crowdsensing is an emerging approach to data collection by exploiting the sensing abilities offered by smart phones and users’ mobility. Data collection can be implemented by exploiting the forwarding opportunities given by the contacts between nodes. However, as cell phones are still resource constrained, most people are socially selfish so that they may not always cooperate with each other in data collection. In this paper, we propose a routing protocol, called Accept aNd Tolerate (ANT), which is tailored for data collection in a social environment with selfish individuals. ANT works by accepting and tolerating social selfishness as an unavoidable human characteristic. It makes relay selection based on nodes’ contacts and their willingness to cooperate. The cooperative willingness of selfish nodes is measured rationally according to the reciprocity relationship between nodes and their resource constraints. Through assessing the worthiness of carrying and forwarding a packet, ANT proposes a buffer management scheme and makes forwarding decisions. Simulations based on real traces show that ANT achieves better performance under resource-constrained circumstances than other comparable approaches.

Network management such as topology discovery and network diagnosis needs to be scanned based on the Internet, and the IPV6 address space is huge and it is difficult to perform global scanning. The existing IPV6 target generation method has a low hit rate, mainly because the spatial division of the address is not accurate enough. We propose an IPV6 address prediction method based on community discovery algorithm, which is called 6Community. 6Community first uses the community discovery algorithm to divide the address space, so that similar addresses can be divided into an address area, and then performs anomaly detection on the divided address space, and re-divides the space. Finally, the obtained address patterns are pre-detected to filter out low-quality address patterns and reduce the size of address scanning space, so as to accelerate the speed of address prediction and increase the hit rate of address prediction. We conducted experiments on three data sets. The results show that compared with the existing methods, the IPV6 address hit rate generated by 6Community is improved, which can reach 13.2% -33.5%. At the same time, the results show that the scanning space obtained by this method is reduced, and the abnormal points in the process of experiment are also reduced.

Traditional data gathering approaches cannot be applied to Mobile Sensor Network (MSN) due to sparse network density and sensor node mobility. In this paper, we propose a utility based data gathering protocol (UDG). The distance utility is used to indicate the closeness between sensor nodes and the sink node, and the activity utility is used to evaluate the ability of sensor nodes acting as relays. UDG combines the distance utility with the activity utility to make routing decisions. It also presents a buffer management scheme based on the utility. Experimental results show that UDG achieves desirable performance with low delivery overhead.