Indoor localization determines target locations by analyzing wireless signal characteristics and is widely used in indoor emergent rescue, mobile healthcare, and intelligent warehousing. Fingerprint-based localization methods mostly adopt received signal strength (RSS), amplitude, or phase. However, in non-line-of-sight (NLOS) scenarios, these classic features are insufficient to accurately distinguish the locations of closely adjacent devices, resulting in limited localization accuracy. Therefore, we propose a heterogeneous spatiotemporal feature fusion (HSFF) and dual-channel convolutional broad learning networks (DC-BLN) for indoor localization. The method first couples phase difference (PD) and power delay profile (PDP) extracted from channel state information (CSI). These fused features are encoded into a three-channel image that preserves both domain and spatial characteristics. A lightweight DC-BLN is then designed to decouple deep spatiotemporal features and perform incremental broad expansion for fast online updates. A large number of tests are carried out in typical laboratory and meeting room, and the experimental results show that the proposed method achieves mean errors of 2.07 m (laboratory) and 1.42 m (meeting room), with corresponding standard deviations of 1.60 m and 0.94 m respectively. These results significantly outperform six existing baseline methods in localization accuracy and robustness.

Node localization technology is increasingly receiving extensive attention from academia and industry due to its strong concealment and high fault tolerance in wireless sensor networks (WSNs). Mobile anchor nodes (MANs) assisted localization is often used in existing WSNs. However, assisted localization based on MANs is still a challenging problem. On one hand, it is difficult to determine the number of anchor nodes (ANs) to support the energy required for the entire movement trajectory. On the other hand, unknown nodes at the boundary region are difficult to obtain sufficient beacon information for localization. A localization algorithm based on the relationship between trapezoidal trajectory and energy consumption of MANs is proposed to solve this challenging problem in the current research. In the proposed algorithm, we design a trapezoidal trajectory based localization algorithm for MANs (TTLMA) to optimize the movement trajectory of ANs. At the same time, determine the number of ANs by analyzing the relationship between the initial energy of ANs and the energy required by the localization algorithm. Select an appropriate algorithm to locate unknown nodes (UNs) according to the number of beacon information received by them. We conducted multiple simulations to evaluate the proposed algorithm’s performance. The experimental results indicate that compared with five existing typical localization algorithms, the proposed algorithms have positive advantages in terms of localization error and coverage, with average localization error reduced by 0.15m-1.16m, average localization coverage improved by 8%-38%. Moreover, the energy consumption of the proposed algorithm is relatively low, requiring only one anchor node to traverse the designed trapezoidal trajectory.

To better solve the contradiction between the localization accuracy, localization coverage, and the location of anchor nodes in wireless sensor networks, a node localization algorithm for wireless sensor networks based on static anchor node location selection strategy is proposed in this paper. Firstly, collect the signal strength between wireless sensor network nodes, judge whether there is a connection between nodes according to the set signal strength threshold, and convert the node distribution diagram into the node connection relationship diagram, that is, the topology diagram. Then, the closeness centrality value of each node is calculated by using the closeness centrality algorithm, and the obtained closeness centrality values are sorted in descending order, the node with the largest closeness centrality value is the first anchor node, the closeness centrality values are traversed at equal intervals, and the optimal equal interval is selected by using the quick sort algorithm, and the selected nodes are used as the other anchor nodes. Finally, other unknown nodes in the network are located according to the location of anchor nodes. Simulation results show that the proposed algorithm is superior to the existing typical algorithms in localization accuracy and localization coverage.