Recently, Distributed Energy Resources (DERs) have been utilized with increasing frequency in Industrial Internet of Things (IIoT) to deal with energy and environmental challenges. IIoT with wireless communication technology, which is easy to be intercepted, often facing various attack. For the safety of the network, more complex algorithms need to be run on IIoT, but the action need more energy. In addition, in some application scenarios, the location where the packets were generated indicates that an event occurred. An attacker can find the sensor node through a backtracking attack, which is equivalent to reaching the place where the event occurred. In order to hide the location information of the event, it is necessary to protect source location privacy (SLP), which will also increase the energy consumption of IIoT. If only the traditional battery is used to power the nodes in IIoT, the lifetime of the system will be limited. When IIoT is deployed outdoors, it is often difficult to replace the battery. The existence of lakes make IIoT have coverage holes during deployment. In order to implement SLP and make the system work for a long time in the environment with deployment holes, we use DERs. Herein, we propose an SLP protection scheme based on phantom nodes, rings, and fake paths (PRFs) for IIoT. To increase the safety time of the network, the PRFs dynamically selects the phantom nodes. To adapt to a complex deployment environment, the ring can be flexibly deployed according to the terrain. The PRFs uses fake paths to confuse attackers. We integrate DERs technology into PRFs, such as using solar power modules, looking forward to extending the lifetime of the system.The experimental results proved that the PRFs could efficiently reduce backtracking attacks while maintaining a balance between security and network energy consumption of IIoT.

A seizure is a neurological disorder caused by abnormal neuronal discharges in the brain, which severely reduces the quality of life of patients and often endangers their lives. Automatic seizure detection is an important research area in the treatment of seizure and is a prerequisite for seizure intervention. Deep learning has been widely used for automatic detection of seizures, and many related research works decomposed the electroencephalogram (EEG) raw signal with a time window to obtain EEG signal slices, then performed feature extraction on the slices, and represented the obtained features as input data for neural networks. There are various methods for EEG signal decomposition, feature extraction, and representation, and most of the studies have been based on fixed hardware resources for the design of the scheme, which reduces the adaptability of the scheme in different application scenarios and makes it difficult to optimize the algorithms in the scheme. To address the above issues, this paper proposes a deep learning-based model for seizure detection, mainly characterized by the two-dimensional representation of EEG features and the scalability of neural networks. The model modularizes the main steps of seizure detection and improves the adaptability of the model to different hardware resource constraints, in order to increase the convenience of the algorithm optimization or the replacement of each module. The proposed model consists of five parts, and the model was tested using two epilepsy datasets separately. The experimental results showed that the proposed model has strong generality and good classification accuracy for seizure detection.

No abstract