Search

Recently, the Internet of Things (IoT) has been widely employed in industrial field for data collection and control application based on edge computing. The data security during storage and communication is one of the most concern in industrial system for safety. While the single security strategy and low data throughput of present data security system in embedded platform is hard to meet the increasing requirements, especially in high performance edge computing platform, such as FPGA based embedded platform. Therefore, in this paper, a fast hybrid data encryption is designed and implementation in an FPGA to enhance the data security and throughput, by combining Advanced Encryption Standard (AES) encryption and Message Digest (MD5) encryption with a customized high parallel computation. Experimental results with the National Laboratory for Information Science and Technology dataset in a heterogeneous FPGA show that the proposed mixed encryption implementation can realized the data encryption with a high throughput for the security in edge computing application.

Automatic meter reading (AMR) is faster and more efficient than manual meter reading by meter readers. Due to low cost and non-intrusiveness, image-based automatic meter reading attracts attention of researchers. However, existing image-based meter reading is only for specific type of electric meter, which is lack of adaptability. To deal with this problem, a method of meter reading based on deep learning that is applicable to different types of meters is proposed in this work. With the digital area recognition and meter type identification by deep learning and image enhancement, the effect of different appearances of digital screen different shooting angles and environmental interference can be eliminated, thus improving the adaptability of the method. Experimental results show that digital of different types of electric meters can be recognized efficiently by the proposed method.

In real-time onboard hyperspectral-image(HSI) anomalous targets detection, processing speed and accuracy are equivalently desirable which is hard to satisfy at the same time. To improve detection accuracy, deep learning based HSI anomaly detectors (ADs) are widely studied. However, their large scale network results in a massive computational burden. In this paper, to improve the detection throughput without sacrificing the accuracy, a pruning−quantization−anomaly−detector (P-Q-AD) is proposed by building an underlying constraint formulation to make a trade-off between accuracy and throughput. To solve this formulation, multi-objective optimization with nondominated sorting genetic algorithm II (NSGA-II) is employed to shrink the network. As a result, the redundant neurons are removed. A mixed precision network is implemented with a delicate customized fixed-point data expression to further improve the efficiency. In the experiments, the proposed P-Q-AD is implemented on two real HSI data sets and compared with three types of detectors. The results show that the performance of the proposed approach is no worse than those comparison detectors in terms of the receiver operating characteristic curve (ROC) and area under curve (AUC) value. For the onboard mission, the proposed P-Q-AD reaches over 4.5 × speedup with less than 0.5 % AUC loss compared with the floating-based detector. The pruning and the quantization approach in this paper can be referenced for designing the anomalous targets detectors for high efficiency.