Face recognition technique has been widely applied to personal identification systems due to its satisfying performance. However, its security may be a crucial issue, since many studies have shown that face recognition systems may be vulnerable in an adversarial environment, in which an adversary can camouflage as a legitimate user in order to mislead the system. Although face liveness detection methods have been proposed to distinguish real and fake faces, they are either time-consuming, costly, or sensitive to noise and illumination. This paper proposes a face liveness detection method with flash against 2D spoofing attack. Flash not only can enhance the differentiation between legitimate and illegitimate users, but it also reduces the influence of environmental factors. Two images are taken from a subject, one with flash and another without flash. Four texture and 2D structure descriptors with low computational complexity are used to capture information of the two images in our model. Advantages of our method include low installation cost of flash and no user cooperation required. A data set of 50 subjects collected under different scenarios is used in the experiments to evaluate the proposed method. The experimental results indicate that the proposed model performs better than existing liveness detection methods in different environmental scenarios. This paper confirms that the use of flash successfully improves face liveness detection in terms of accuracy, robustness, and running time.

This paper proposes a home resource management system for a smart home with multiple inhabitants. The system uses home ontology to covers the characteristics of available resources in smart homes. The ontology provides information of living space partition, energy consumption, and network bandwidth to detect resource usage conflict. Case-base reasoning is used to predict inhabitant resource requirement of smart homes. The system then uses BDI agent, blackboard systems, and conceding negotiation to find a common consensus plan of home resources for inhabitants. The BDI agent unfolds the inhabitants' information by belief, desire, and intension model. Blackboard system provides a platform for agent communication and resource usage conflict detection. Finally, conceding negotiation uses utility computation and conceder selection to find a common consensus resource allocation plan. The system is simulated in the sample smart home. It can provide an intelligent mechanism for efficient resource allocation.

This paper proposes a hybrid case-based system to help the physician. It includes a hypermedia human-machine interface and a hybrid case-based reasoner. The hypermedia human-machine interface provides a friendly human body image map for the clinician to easily enter a given consultation. It utilizes a medicine-related commonsense knowledge base to help complete the input data during the consultation. The hybrid case-based reasoner is responsible for selecting and adapting relevant cases from the case library into a diagnosis for the consultation. This reasoner does those jobs by hybridizing many techniques. Basically it uses a distributed fuzzy neural network for case retrieval. It employs decision theory, constrained induction trees, and relevance theory for case adaptation involving case combination. The technique is also used for learning new cases into the case library. Hybridizing these techniques together can effectively produce a high quality diagnosis for a given medical consultation.