Omnidirectional image quality assessment (OIQA) is a hot research topic in image processing. Besides, IQA is also very important in the field of instrumentation and measurement. In this article, we propose a new no-reference OIQA model by analyzing the relationship between image features and perceived quality. A gradient weighted local phrase quantization map is built to complement the gradient map to model the structure degradation of omnidirectional images caused by various distortions. Considering the large amount of information contained in the omnidirectional image, we extract the luminance features, global entropy instead of local entropy, and color features, which are ignored in most previous works to estimate the naturalness quality of the omnidirectional image. Finally, support vector regression is utilized to train and test our model based on the image features and human subjective quality assessment scores. The experiments on two databases show that our model outperforms the state-of-the-art IQA models and correlates well with subjective scores in the two databases.

Time series classification is a basic task in the field of streaming data event analysis and data mining. The existing time series classification methods have the problems of low classification accuracy and low efficiency. To solve these problems, this paper proposes a T-CNN time series classification method based on a Gram matrix. Specifically, we perform wavelet threshold denoising on time series to filter normal curve noise, and propose a lossless transformation method based on the Gram matrix, which converts the time series to the time domain image and retains all the information of events. Then, we propose an improved CNN time series classification method, which introduces the Toeplitz convolution kernel matrix into convolution layer calculation. Finally, we introduce a Triplet network to calculate the similarity between similar events and different classes of events, and optimize the squared loss function of CNN. The proposed T-CNN model can accelerate the convergence rate of gradient descent and improve classification accuracy. Experimental results show that, compared with the existing methods, our T-CNN time series classification method has great advantages in efficiency and accuracy.

Algorithms for skyline querying based on wireless sensor networks (WSNs) have been widely used in the field of environmental monitoring. Because of the multi-dimensional nature of the problem of monitoring spatial position, traditional skyline query strategies cause enormous computational costs and energy consumption. To ensure the efficient use of sensor energy, a geometry-based distributed spatial query strategy (GDSSky) is proposed in this paper. Firstly, the paper presents a geometry-based region partition strategy. It uses the skyline area reduction method based on the convex hull vertices, to quickly query the spatial skyline data related to a specific query area, and proposes a regional partition strategy based on the triangulation method, to implement distributed queries in each sub-region and reduce the comparison times between nodes. Secondly, a sub-region clustering strategy is designed to group the data inside into clusters for parallel queries that can save time. Finally, the paper presents a distributed query strategy based on the data node tree to traverse all adjacent sensors’ monitoring locations. It conducts spatial skyline queries for spatial skyline data that have been obtained and not found respectively, so as to realize the parallel queries. A large number of simulation results shows that GDSSky can quickly return the places which are nearer to query locations and have larger pollution capacity, and significantly reduce the WSN energy consumption.