Search

Compared with the current gesture recognition system based on radio frequency identification technology, the single-tag non-contact gesture recognition system based on convolutional neural network proposed in this paper can maximize user experience. Without the need for the user to carry any equipment, a single tag and single antenna are used to achieve precise gesture recognition. First, the tag phase signal affected by multipath effect is read by adding interference artificially; Second, the tag phase signal that accords with the characteristics of time series is filtered, and the Dynamic Time Wrapping (DTW) algorithm is selected to match with the coarse-grained gesture recognition of prior fingerprint database; Finally, the tag phase signal is used to generate the feature image by Markov Transition Field (MTF), and then IM-AlexNet model is used for in-depth training and experimental evaluation of the image. The training parameters of the improved model are reduced by 7% compared with those of the original model, and the accuracy rate reaches 96.76%. Experimental results show that taking the advantage of multipath effect, fine-grained real-time gesture recognition can be achieved in the case of an experimental deployment that only uses a single tag and a single antenna. The system is easy to operate, simple to deploy, expandable in a large range, and has high robustness. more...

Abnormal traffic and vulnerability attack monitoring play an important role in today’s Internet of Things (IoT) applications. The existing solutions are usually based on machine learning for traffic, and its disadvantage is that a large number of manual operations are needed in the classification process, and the adaptability is poor. Moreover, for unknown attacks, the system cannot make a relative response in time. In this work, we design a monitoring system of IoT based on C5.0 decision tree and time-series analysis. The system transforms time-series into GAF graph, and uses CNN-LSTM combination model to monitor the traffic. The time-series model based on deep learning can also improve the inefficiency and manual intervention caused by data analysis. At the same time, the system introduces LSTM technology, which can solve a series of problems that may be caused during long sequence training. We select KDD Cup 99 data set for simulation experiments and comparison with traditional traffic monitoring methods. The results show that the average error rate of abnormal traffic attack types is 3.22%. The evaluations show that the system can effectively monitor unknown attacks with 96% accuracy. We further use whitelist matching technology to identify IoT device models. After comparison of experiments, it is proved that this method has its superiority in the monitoring of IoT devices. more...

The smart grid is emerging as a future paradigm for power networks. While it has many successful applications, peer-to-peer trading in the local energy market (LEM) is still challenging due to the lack of security and trading mechanisms. In this paper, we design a data-driven, secure, and smart solution $DS^{2}$ to address this problem. We first propose a five-layer design of LEM based on blockchain. We then model peer-to-peer trading in LEM as a cost minimization problem and derive an efficient online solution leveraging matrix factorization and integer linear programming. $DS^{2}$ is implemented and evaluated on a private Ethereum blockchain. We show that $DS^{2}$ achieves a mean absolute percentage error (MAPE) of 12.8% compared with the offline optimal method through extensive simulations on the real-world dataset. more...

The photovoltaic industry is a strategic and sunrise industry with international competitive advantages. Driven by policy guidance and market demand, the new energy industry represented by the photovoltaic industry has been a significant emerging industry in developing the national economy and people’s livelihood. Stable photovoltaic power generation capacity supply is a critical issue in the photovoltaic industry. With the popularization of industrial Internet technology and Internet of things technology, more and more academic and industrial circles begin to introduce new technologies to provide the latest research results and solutions for the photovoltaic industry. Electroluminescence is a standard detection method for photovoltaic production in the application of solar energy production. This method uses human vision to detect whether the solar silicon unit is defective. In this article, due to the three core pain points in traditional electroluminescence detection: low efficiency of offline identification, low accuracy and accuracy of data detection, and no online diagnosis and prediction, we carry out ISEE research based on edge computing unit. ISEE uses the edge device to collect the real-time video image of the solar panel through the camera. Then it uses the powerful neural network processing unit module of the edge computing unit, combined with the convolutional neural network algorithm transplanted to the edge, to detect the defects of solar panels in real time. It completes the research on intelligent detection of photovoltaic power generation production defects based on the Internet of Things. After a large number of experimental design verification, ISEE effectively improves the automation degree and identification accuracy in the production and detection process of solar photovoltaic cells and reduces the cost of operation and maintenance. The accuracy rate reaches 93.75%, which has significant theoretical research significance and practical application value. more...