With the ever-increasing demand for location-based services in the indoor environments, Wi-Fi-based positioning technology has attracted much attention in decades of years because of its ubiquitous deployment and low cost. In view of the fact that Wi-Fi signal not only changes with the distance from the Wi-Fi base station to the receiver, but also changes with time. To improve positioning accuracy and robustness, we consider both the spatial relation and temporal sequential relation simultaneously, and propose a Spatial-Temporal positioning algorithm that combines residual network and LSTM (Long Short-Term Memory) network. In this algorithm, to avoid the degradation problem, we adopt the residual-based network to extract the spatial features of Wi-Fi signal at the same time slice. Furthermore, the LSTM is used to extract temporal features of Wi-Fi signal among successive time slices. Finally, a fully connected layer is used to obtain the final location estimation. Extensive experiments on the IPIN2016 datasets demonstrate that our proposed algorithm can obtain 4.93m, 5.40m, 3.20m and 4.98m average positioning error on the UAH, CAR, UJIUB, and UJITI sub-dataset, respectively. The experimental results show that our proposed algorithm outperforms other state-of-the-art positioning algorithms with better accuracy and robustness.

With the widespread development of location-based services, the demand for accurate indoor positioning is getting more and more urgent. Floor positioning, as a prerequisite for indoor positioning in multi-story buildings, is particularly important. Though lots of work has been done on floor positioning, the existing studies on floor positioning in complex multi-story buildings with large hollow areas through multiple floors still cannot meet the application requirements because of low accuracy and robustness. To obtain accurate and robust floor estimation in complex multi-story buildings, we propose a novel floor positioning method, which combines the Wi-Fi based floor positioning (BWFP), the barometric pressure-based floor positioning (BPFP) with HMM and the XGBoost based user motion detection. Extensive experiments show that using our proposed method can achieve 99.2% accuracy, which outperforms other state-of-the-art floor estimation methods.

Traditional Wi-Fi-based floor identification methods mainly have been tested in small experimental scenarios, and generally, their accuracies drop significantly when applied in real large and multistorey environments. The main challenge emerges when the complexity of Wi-Fi signals on the same floor exceeds the complexity between the floors along the vertical direction, leading to a reduced floor distinguishability. A second challenge regards the complexity of Wi-Fi features in environments with atrium, hollow areas, mezzanines, intermediate floors, and crowded signal channels. In this article, we propose an adaptive Wi-Fi-based floor identification algorithm to achieve accurate floor identification also in these environments. Our algorithm, based on the Wi-Fi received signal strength indicator and spatial similarity, first identifies autonomous blocks parcelling the whole environment. Then, local floor identification is performed through the proposed Wi-Fi models to fully harness the Wi-Fi features. Finally, floors are estimated through the joint optimization of the autonomous blocks and the local floor models. We have conducted extensive experiments in three real large and multistorey buildings greater than 140 000 m $^2$ using 19 different devices. Finally, we show a comparison between our proposal and other state-of-the-art algorithms. Experimental results confirm that our proposal performs better than other methods, and it exhibits an average accuracy of 97.24%.

As one of the main ways to destroy network security, malicious domain name attack often brings economic loss and privacy leakage to enterprises and users. In this paper, a malicious domain name detection model is proposed to optimize SKohonen network based on IWO algorithm. The location information of weed individuals with the smallest fitness value is generated by IWO algorithm as the optimal solution of IWO algorithm. The optimal solution is set as the initial weight vector parameter of SKohonen neural network, and the domain name data set is predicted and classified. Then it is compared with the malicious domain name detection model of SKohonen neural network, and measured by classification histogram, confusion matrix, ROC curve and AUC value. The results show that the malicious domain name detection model based on IWO algorithm to optimize SKohonen network is better for the classification of malicious domain names. In the prevention of malicious domain name attack direction, has high practical value.(Abstract)