To build scalable and lightweight wireless sensor networks with energy saving devices, 6LoWPAN-based protocols become emergent technologies that successfully constructed ubiquitous networks and seamlessly connected the traditional Internet with WSNs. However, the existing researches cannot effectively maintain the routing and the network topology for the problems of low cost sensors' malfunctions. In this paper, we improved the HiLow protocol in aspects of interconnection between the Internet and 6LoWPAN and designed a network routing path recovery approach. In addition, we designed and modified the address mapping table in gateway to store and map nodes' EUI-64 address and 16-bit short address. Nodes from the Internet can access the 6LoWPAN nodes by an IPv6 address, which is generated by the EUI-64 address and IPv6 prefix. Due to the benefits of additional data structure and our designs, the simulation results manifested that our protocol improves the routing efficiency and can effectively reduce the cost for network reorganization caused by node failures and mobiles.

Limited communication resources have gradually become a critical factor toward efficiency of decentralized large scale multi-agent coordination when both system scales up and tasks become more complex. In current researches, due to the agent’s limited communication and observational capability, an agent in a decentralized setting can only choose a part of channels to access, but cannot perceive or share global information. Each agent’s cooperative decision is based on the partial observation of the system state, and as such, uncertainty in the communication network is unavoidable. In this situation, it is a major challenge working out cooperative decision-making under uncertainty with only a partial observation of the environment. In this paper, we propose a decentralized approach that allows agents cooperatively search and independently choose channels. The key to our design is to build an up-to-date observation for each agent’s view so that a local decision model is achievable in a large scale team coordination. We simplify the Dec-POMDP model problem, and each agent can jointly work out its communication policy in order to improve its local decision utilities for the choice of communication resources. Finally, we discuss an implicate resource competition game, and show that, there exists an approximate resources access tradeoff balance between agents. Based on this discovery, the tradeoff between real-time decision-making and the efficiency of cooperation using these channels can be well improved.

Distributed reasoning in M2M leverages the expressive power of ontology to enable semantic interoperability between heterogeneous systems of connected devices. Ontology, however, lacks the built-in, principled support to effectively handle the uncertainty inherent in M2M application domains. Thus, efficient reasoning can be achieved by integrating the inferential reasoning power of probabilistic representations with the first-order expressiveness of ontology. But there remains a gap with current probabilistic ontologies since state-of-the-art provides no compatible representation for simultaneous handling of discrete and continuous quantities in ontology. This requirement is paramount, especially in smart homes, where continuous quantities cannot be avoided, and simply mapping continuous information to discrete states through quantization can cause a great deal of information loss. In this paper, we propose a hybrid probabilistic ontology that can simultaneously handle distributions over discrete and continuous quantities in ontology. We call this new framework HyProb-Ontology, and it specifies distributions over properties of classes, which serve as templates for instances of classes to inherit as well as overwrite some aspects. Since there cannot be restriction on the dependency topology of models that HyProb-Ontology can induce across different domains, we can achieve a unified Ground Hybrid Probabilistic Model by conditional Gaussian fuzzification of the distributions of the continuous variables in ontology. From the results of our experiments, this unified model can achieve exact inference with better performance over classical Bayesian networks.

With the development of Machine-to-Machine (M2M) technology, a variety of embedded and mobile devices is integrated to interact via the platform of the Internet of Things, especially in the domain of smart cities. One of the primary challenges is that selecting the appropriate services or service combination for upper layer applications is hard, which is due to the absence of a unified semantical service description pattern, as well as the service selection mechanism. In this paper, we define a semantic service representation model from four key properties: Capability (C), Deployment (D), Resource (R) and IOData (IO). Based on this model, an agent-based middleware is built to support semantic service enablement. In this middleware, we present an efficient semantic service discovery and matching approach for a service combination process, which calculates the semantic similarity between services, and a heuristic algorithm to search the service candidates for a specific service request. Based on this design, we propose a simulation of virtual urban fire fighting, and the experimental results manifest the feasibility and efficiency of our design.

Process management is practical in the state-of-the-art of Internet of things research. However, this has become a bottleneck in recent years since an extreme amount of heterogeneous items have to be recorded and traced with radio frequency identification (RFID) tags. In a typical application of process synthesis management, each item will be involved with multiple processes but when those processes are interconnected, an extremely complex network emerges and has to be managed. Existing works on processing management systems, however, are always case-based and only focus on specific application domains. Thus, the general applied processing management model is rather limited. In this paper, we summarize the characteristics of the RFID application domains, and by abstraction, we propose an innovation of the RFID processing model. In this model, each RFID data were deemed as an operation record and all their processing services are logically interconnected and organized as a procedure graph. In addition, we abstract and summarize the basic RFID data processes into a few types. The advantage of this design is that the basic RFID data processing logic can be preprogrammed and in a real domain, the system can be dynamically programmed by automatically constructing the procedure graph nodes with those basic processes and mapping the interconnection logic according to the topology of the graph. As the last part of this paper, we designed a prototype system for medical instruments infection control to demonstrate our approach.

Accurate and stable traffic sign detection is a key technology to achieve L3 driving automation, and its performance has been significantly improved by the development of deep learning technology in recent years. However, the current traffic sign detection has inadequate difficulty resisting anti-attack ability and even does not have basic defense capability. To solve this critical issue, an adversarial patch attack defense model IYOLO-TS is proposed in this paper. The main innovation is to simulate the conditions of traffic signs being partially damaged, obscured or maliciously modified in real world by training the attack patches, and then add the attacked classes in the last layer of the YOLOv2 which are corresponding to the original detection categories, and finally the attack patch obtained from the training is used to complete the adversarial training of the detection model. The attack patch is obtained by first using RP₂algorithm to attack the detection model and then training on the blank patch. In order to verify the defense effective of the proposed IYOLO-TS model, we constructed a patch dataset LISA-Mask containing 50 different mask generation patches of 33000 sheets, and then training dataset by combining LISA and LISA-Mask datasets. The experiment results show that the mAP of the proposed IYOLO-TS is up to 98.12%. Compared with YOLOv2, it improved the defense ability against patch attacks and has the real-time detection ability. It can be considered that the proposed method has strong practicality and achieves a tradeoff between design complexity and efficiency.