It is generally accepted that the edge computing paradigm is regarded as capable of satisfying the resource requirements for the emerging mobile applications such as the Internet of Things (IoT) ones. Undoubtedly, the data collected by underlying sensor networks are the foundation of both the IoT systems and IoT applications. However, due to the weakness and vulnerability to attacks of underlying sensor networks, the data collected are usually untrustworthy, which may cause disastrous consequences. In this article, a new model is proposed to collect trustworthy data on the basis of edge computing in the IoT. In this model, the sensor nodes are evaluated from multiple dimensions to obtain accurately quantified trust values. Besides, by mapping the trust value of a node onto a force for the mobile data collector, the best mobility path is generated with high trust. Moreover, a mobile edge data collector is used to visit both the sensors with quantified trust values and collect trustworthy data. The extensive experiment validates that the IoT systems based on trustworthy data collection model gain a significant improvement in their performance, in terms of both system security and energy conservation.

With the increase of the number of IIOT devices in industrial environments, security threats and quality of service (QoS) issues increase drastically. Internal attack is one type of important security threat that makes service environment worse and less reliable. However, there is no unified and fine-grained trust evaluation mechanism to deal with the threats of internal attack and improve QoS of IIoT. To this end, a unified trustworthy environment based on edge computing is established and maintained, which can timely detect malicious service providers and service consumers, filter unreal information and recommend credible service providers. Moreover, a service selection method is designed to choose the corresponding trustworthy and reliable service providers based on the trust evaluation and the recording criterion, which has distinctive advantages in the succinct trust management, convenient searching service and accurate service matching. Experiments validated the feasibility of the proposed trustworthy environment.

This paper presents an improved semi-supervised learning approach for defect prediction involving class imbalanced and limited labeled data problem. This approach employs random under-sampling technique to resample the original training set and updating training set in each round for co-train style algorithm. It makes the defect predictor more practical for real applications, by combating these problems. In comparison with conventional machine learning approaches, our method has significant superior performance. Experimental results also show that with the proposed learning approach, it is possible to design better method to tackle the class imbalanced problem in semi-supervised learning.