Zhanpeng Zhang

In global navigation satellite system-denied underground environments, developing high-precision positioning technologies faces dual measurement challenges: magnetic aliasing effects and structural repetitiveness. Although magnetic fingerprinting provides an effective alternative, its measurement reliability is often compromised by sensor noise and environmental magnetic interference. This paper proposes multi-scale dilated dynamic time warping (MS-DDTW)-Net, an artificial intelligence-enhanced framework designed for robust two-stage positioning. The first stage employs a MS-DDTW algorithm to capture hierarchical temporal patterns, effectively mitigating positioning deviations caused by magnetometer drift. The second stage utilizes a Siamese network based on a CNN-GRU architecture for deep semantic verification, mapping measurement sequences into a discriminative metric space to resolve spatial ambiguity and suppress erroneous matching. Experimental results in real-world underground facilities demonstrate that the proposed method achieves a mean absolute error (MAE) of 3.472 m and a root mean square error of 5.771 m, outperforming traditional dynamic time warping and k-nearest neighbors methods by 44.74% and 65.39% in terms of MAE, respectively. This hybrid framework significantly enhances measurement reliability and positioning robustness, offering a novel technical solution for localization in complex underground environments.

Indoor geomagnetic positioning utilizes the pervasive magnetic field as a natural signal source for navigation. However, the nonuniqueness of magnetic signatures and environmental interference introduces significant measurement ambiguity, hindering high-precision instrumentation in complex environments. Furthermore, the lack of quantitative metrics for assessing the “localizability” of a magnetic map limits the reliability of existing positioning systems. To address these measurement challenges, this article proposes a quality-driven positioning framework that integrates a robust signal matching strategy with a novel fingerprint quality evaluation system. First, a dual-index evaluation system comprising a discrimination index (DI) and a variation index (VI) is established to quantitatively characterize the spatial distinguishability and temporal consistency of the magnetic field data. This system demonstrates a strong coefficient of determination (R ${}^{2}~=0.91$ ) with the mean overall positioning error (MOPE), providing a theoretical basis for predicting measurement uncertainty. Second, to mitigate signal mismatches in repetitive environments, we introduce a modulus-weighted constrained derivative dynamic time warping (CDDTW) method. This method incorporates physical constraints of the magnetic modulus into the matching process to enhance coarse-level signal retrieval. Subsequently, a Multiscale BiGRU-Attention Siamese Network is employed as a fine-grained metric learning model to extract robust features from noisy sensor data. Experimental results indicate that the proposed framework achieves a localization accuracy of better than 3 m. Compared to traditional baseline methods, the proposed approach improves accuracy by over 35% and significantly reduces large error outliers, validating its effectiveness in enhancing the robustness and reliability of geomagnetic measurement systems.

Wi-Fi Channel State Information (CSI)-based indoor localization has garnered significant attention owing to its high resolution, cost-effectiveness, and compatibility with existing Wi-Fi infrastructure. Nonetheless, its practical implementation is hindered by the intricate spatiotemporal properties of CSI signals and the significant disparities among different Access Points (APs). This paper introduces a continuous indoor localization system utilizing ConvNeXt-driven deep feature learning and a heterogeneous dual-stream fusion architecture to tackle these difficulties. A ConvNeXt-based feature extraction backbone is utilized to acquire essential spatiotemporal CSI representations, facilitating the effective modeling of local and global interdependence. Secondly, a multi-AP domain-embedded adaptation technique is proposed to overcome cross-AP system biases via Media Access Control address-based alignment, hence improving the model’s generalization capabilities. A main-auxiliary dual-stream fusion architecture is developed to collaboratively model primary CSI features with auxiliary modalities, including the Foot-Mounted Positioning Module and Inter-Subcarrier Phase Difference, facilitating effective multimodal complementarity. Empirical experiments indicate that the proposed method attains average localization errors of 1.0223 meters and 1.2025 meters in the complex Corner and Corridor scenarios, respectively, markedly surpassing the baseline methods of Vision Transformer and Long Short-Term Memory. The findings demonstrate that the suggested method offers dependable and accurate continuous indoor localization in settings marked by complex multipath circumstances.

The performance of smartphone-based fingerprinting indoor positioning methods heavily depends on the database quality and matching algorithms, typically providing only 2D coordinates. Traditional methods also face challenges like labor-intensive data collection, limited accuracy, and reduced longterm reliability. This paper proposes a Self-Attention-Enhanced Pre-Sequence Warmup Long Short-Term Memory (PSW-LSTM) framework, integrated with WiFi, barometer, and magnetometer sensors, to achieve accurate 3D pedestrian indoor positioning. Specifically, foot-mounted positioning devices are introduced to assist smartphones in collecting sparse fingerprint data, improving database efficiency. The proposed Self-Attention-Enhanced PSW-LSTM framework improves initial matching accuracy, reduces convergence time, and enhances trajectory continuity. Experimental results demonstrate that, in typical indoor environments such as educational and office spaces, the horizontal and vertical positioning accuracy for pedestrians is better than 2 meters and 0.5 meters, significantly improving smartphone-based 3D indoor positioning performance.