With the continuous development of Chinese economy and the gradual acceleration of urbanization, it has caused tremendous damage to the environment. The bad air environment seriously damages the physical and mental health of people. The change of smog concentration will be affected by many realistic factors and exhibit nonlinear characteristics. The method proposed in this paper is to use the Internet of Things(IoT) technology to monitor the acquired data, process the data and predict the next data using a neural network. The existing prediction models have limitations. They don’t accurately capture the law between the concentration of haze and the factors affecting reality. It is difficult to accurately predict nonlinear smog data. One algorithm proposed in this paper is a two-layer model prediction algorithm based on Long Short Term Memory Neural Network and Gated Recurrent Unit(LSTM&GRU). We set a double-layer Recurrent Neural Network to predict the PM2.5 value. This model is an improvement and enhancement of the existing prediction method Long Short Term Memory(LSTM). The experiment integrates data monitored by the IoT node and information released by the national environmental protection department. First, the data of 96 consecutive hours in four cities were selected as experimental samples. The experimental results are close to the true value. Then, We selected daily smog data from 2014/1/1 to 2018/1/1 as a train and test dataset. It contains smog data for 74 city sites. The first 70% of the data was used for training and the rest for testing. The results of this experiment show that our model can play a better prediction.

Generally, image protection is often accomplished by digital watermark, which is also widely used in the field of data protection and data ownership authentication. However, the existing digital watermark has inherent disadvantages, it needs completely trusted third parties to act as the arbitration parties, which may be difficult to achieve. Second, an image watermark algorithm will inevitably lead to the loss of image data when operating on the image data, while it is usually irreversible. The zero-watermark algorithm can solve the problem of data loss but relies more on the trusted third party than a traditional digital watermark, which makes its prospects limited. With the development of blockchain technology in recent years, its features of de-trusted third parties combine the fairness and process automation of smart contracts to make up for the shortcomings of the zero-watermarking algorithm. This paper studies image storage and authentication frameworks. This framework utilizes the advantages of zero-watermarking algorithm and blockchain, using the Inter-Planetary File System to solve the data expansion problem of blockchain, which well avoids the shortcomings of zero-watermarking algorithm and blockchain. Experiment and inference illustrate that the proposed framework is feasible.

WSANs (Wireless Sensor and Actuator Networks) are derived from traditional wireless sensor networks by introducing mobile actuator elements. Previous studies indicated that mobile actuators can improve network performance in terms of data collection, energy supplementation, etc. However, according to our experimental simulations, the actuator’s mobility also causes the sensor worm to spread faster if an attacker launches worm attacks on an actuator and compromises it successfully. Traditional worm propagation models and defense strategies did not consider the diffusion with a mobile worm carrier. To address this new problem, we first propose a microscopic mathematical model to describe the propagation dynamics of the sensor worm. Then, a two-step local defending strategy (LDS) with a mobile patcher (a mobile element which can distribute patches) is designed to recover the network. In LDS, all recovering operations are only taken in a restricted region to minimize the cost. Extensive experimental results demonstrate that our model estimations are rather accurate and consistent with the actual spreading scenario of the mobile sensor worm. Moreover, on average, the LDS outperforms other algorithms by approximately 50% in terms of the cost.

Human activity recognition has been a hot topic in recent years. With the advances in sensor technology, there has been a growing interest in using smartphones equipped with a set of built-in sensors to solve tasks of activity recognition. However, in most previous studies, smartphones were used with a fixed position—like trouser pockets—during recognition, which limits the user behavior. In the position-independent cases, the recognition accuracy is not very satisfactory. In this paper, we studied human activity recognition with smartphones in different positions and proposed a new position-independent method called PACP (Parameters Adjustment Corresponding to smartphone Position), which can markedly improve the performance of activity recognition. In PACP, features were extracted from the raw accelerometer and gyroscope data to recognize the position of the smartphone first; then the accelerometer data were adjusted corresponding to the position; finally, the activities were recognized with the SVM (Support Vector Machine) model trained by the adjusted data. To avoid the interference of smartphone orientations, the coordinate system of the accelerometer was transformed to get more useful information during this process. Experimental results show that PACP can achieve an accuracy over 91%, which is more effective than previous methods.

In watermarking, the watermark embedding strength is crucial, and the introduction of the strength factor can adjust the trade-off between the quality of the encoded image and the accuracy of the recovered message, thus enabling good imperceptibility and robustness of the encoded image. In traditional watermarking methods, the strength factor is selected in relation to the cover image, and based on different images, different strength factors are manually selected or algorithmically derived to adjust the visual effect of the watermarked image. However, due to the subjectivity and inflexibility of traditional algorithms, they can not achieve the effect of adaptive adjustment of watermarked images. Recently, watermarking methods combined with deep learning have gradually occupied the mainstream of this field. In the testing stage, to balance the overall robustness and imperceptibility, the strength factor is no longer selected based on the cover image as in traditional methods. Instead, it is set to a universal value. Therefore, the watermarking method based on deep learning is still in the primary stage of the trial-and-error method. To solve the subjectivity of the hand-designed embedding strength algorithm of the traditional watermarking methods and the low elasticity of the strength factor of the learning method so as to realize the adaptive embedding of watermarks, we propose an adaptive watermarking method with separate training. The proposed method adds a new component, the Adaptor, compared to other frameworks. The Adaptor can adaptively select strength factors to control the embedding strength of the watermark relying on the cover image and secret message. A two-stage training method is used to maintain the stability of the training and to achieve the best results for each component. With the results obtained from our experiments, our proposed method can find the appropriate strength factor and optimize it, resulting in improved robustness and imperceptibility of the watermark. The proposed method shows better results compared to the current state-of-the-art algorithms.