In the existing emergency rescue process for sudden incidents, the lack of effective emergency rescue information communication mechanisms and sharing strategies between mining enterprises and rescue teams often leads to information asymmetry, inefficient information transmission, and low rescue efficiency. To address these issues, this article constructs a payoff matrix for emergency rescue information sharing between mining enterprises and rescue teams based on five premises: bounded rationality, benefit maximization, active participation, cost minimization/loss reduction, and maximization of additional benefits. First, combining Shapley value allocation theory, we analyze the evolutionary trends of the emergency rescue information sharing system. Second, based on the expected returns of both parties choosing to share or not share information, combined with the replicator dynamic equations, we derive the evolutionary stable strategies (ESS) for both parties. We utilize the Jacobian matrix to analyze the stability paths of the system’s equilibrium points. Third, stability tests are conducted on four types of indicators proposed in the evolutionary game model: basic benefits, costs, losses, and additional benefits. In the scenario where both mining enterprises and rescue teams share information, a comprehensive evaluation function is proposed, incorporating the shortest convergence time, the shortest path, and the most stable spectral radius of the Jacobian matrix (the “Triple-Indicator” method) to identify the benchmark preferred initial point for the initial probability of information sharing. Finally, in accordance with the “Mine Rescue Regulations” regarding mandatory comprehensive information sharing, MATLAB simulation is used to verify the rationality and practicality of the optimal strategy. This study provides a typical reference model and strategy for rescue information sharing during emergencies, offering theoretical and practical grounds for revising emergency response communication regulations and constructing safety management information platforms.

Indoor trajectory mapping is essential for applications such as health status monitoring, context-aware computing, and tracking systems. These applications often require accurate location information in environments where the Global Navigation Satellite System (GNSS) is unavailable or unreliable. Infrastructure-free approaches, such as inertial sensor-based Pedestrian Dead Reckoning (PDR), have gained popularity due to their ease of deployment and low cost. However, a key limitation of PDR is not only its susceptibility to cumulative drift over time but also its lack of absolute position references, which prevents reliable alignment of the trajectory with real-world coordinates. To address this challenge, we propose an activity-driven audio-IMU fusion solution that uses Factor Graph Optimization (FGO) to accurately reconstruct indoor walking trajectories on a room-scale floor plan. Specifically, we use two fixed microphone arrays to estimate absolute coordinates from activity-driven audio events. These events act as sparse, high-confidence anchors to map PDR trajectories. We validate our system through experiments in a 6 m × 6 m room. The proposed fusion solution achieves a mean positioning error of 0.31 m, with 68% and 95% of errors below 0.38 m and 0.53 m, respectively. The results demonstrate the potential of sparse, activity-driven audio anchoring to improve infrastructure-free indoor trajectory mapping.

We propose a method for linear-time diversity maintenance in particle filtering. It clusters particles based on ancestry tree topology: closely related particles in sufficiently large subtrees are grouped together. The main idea is that the tree structure implicitly encodes similarity without the need for spatial or other domain-specific metrics. This approach, when combined with intra-cluster fitness sharing and the protection of particles not included in a cluster, effectively prevents premature convergence in multimodal environments while maintaining estimate compactness. We validate our approach in a multimodal robotics simulation and a real-world multimodal indoor environment. We compare the performance to several diversity maintenance algorithms from the literature, including Deterministic Resampling and Particle Gaussian Mixtures. Our algorithm achieves high success rates with little to no negative effect on compactness, showing particular robustness to different domains and challenging initial conditions.

Cognitive load (CL) refers to the mental effort required to process information. Monitoring increased CL is important as it can indicate the onset of cognitive decline and neurodegeneration, allowing for early intervention and management. Traditional techniques using bio-physiological and audio-visual sensors are privacy-invasive and computationally complex. The synchronization, data alignment, and accessibility problems with these techniques can lead to increased noise and errors, reducing the accuracy of CL estimates. This paper presents a first-of-its-kind Radio Frequency (RF) based sensing system that effectively monitors and classifies cognitive load states by detecting cerebral blood flow variations through backscattered RF signal strength. The RF sensors are designed and miniaturized using microwave computational software and fabricated sensors are integrated with glasses to estimate in-vivo CL variations with on-edge processing and classification. The system is validated through user-oriented audio-only (AO) and audio-visual (AV) trials. Participants are tested on their ability to comprehend target speech with different levels of background noise, assessing the impact on CL. The statistical features from the RF reflection data are processed using machine learning (ML) and deep learning (DL) algorithms implemented on a Raspberry Pi. The participants’ CL is classified into high, medium and low categories separately for AO and AV trials. The Multilayer Perceptron (MLP) achieves an overall accuracy of 85% for AO trials and 66.2% for AV trials, with average training and testing times of 6 seconds and 0.001 seconds, respectively. The promising results suggest that the system is an effective, portable, and low-cost alternative for on-edge CL estimation.

Pedestrian trajectory reconstruction is essential for applications such as human behaviour analysis and smart transportation systems. Existing methods often struggle with data gaps and inaccuracies due to the limitations of location-acquisition technologies like GPS and WiFi. While some algorithms have been developed to estimate trajectories using IMU data, they only provide relative information and lack absolute location context, necessitating additional efforts and technologies to compensate for this limitation. This paper proposes an enhanced pedestrian trajectory reconstruction method that leverages GPS and IMU data to provide accurate location information across outdoor and indoor areas. The method integrates a bi-directional Extended Kalman Filter (EKF) to fuse GPS and IMU data, iterating forward and backward trajectories. An automatic refinement approach is applied to merge the forward and backward trajectories against multiple residuals, resulting in the final pedestrian trajectory. Evaluations demonstrate the method’s effectiveness using all available GPS data and under challenging conditions with only 5% GPS data. When using all GPS data, the method achieves a median pointwise distance of 4.76 meters and a $\mathbf{6 8 \%}$ CDF error of 7.10 meters. With 5% GPS data, the median pointwise distance is 10.95 meters, with a 68% CDF error of 13.82 meters. These results highlight the method’s robustness and potential for practical applications where GPS data may be sparse or unreliable.

While Wi-Fi positioning is still more common indoors, using magnetic field features has become widely known and utilized as an alternative or supporting source of information. Magnetometer bias presents significant challenge in magnetic field navigation and SLAM. Traditionally, magnetometers have been calibrated using standard sphere or ellipsoid fitting methods and by requiring manual user procedures, such as rotating a smartphone in a figure-eight shape. This is not always feasible, particularly when the magnetometer is attached to heavy or fast-moving platforms, or when user behavior cannot be reliably controlled. Recent research has proposed using map data for calibration during positioning. This paper takes a step further and verifies that a pre-collected map is not needed; instead, calibration can be done as part of a SLAM process. The presented solution uses a factorized particle filter that factors out calibration in addition to the magnetic field map. The method is validated using smartphone data from a shopping mall and mobile robotics data from an office environment. Results support the claim that magnetometer calibration can be achieved during SLAM with comparable accuracy to manual calibration. Furthermore, the method seems to slightly improve manual calibration when used on top of it, suggesting potential for integrating various calibration approaches.

WiFi fingerprinting has been extensively studied for years to provide location estimation in indoor scenarios. Researchers have used various machine learning algorithms to match the online fingerprint to the pre-collected offline fingerprints, which have location labels, for location estimation. However, neither conventional machine learning algorithms nor modern deep neural networks explore the geometric relations between WiFi access points and the location where the fingerprint was taken. Therefore, they cannot capture the non-Euclidean nature of the WiFi fingerprint. Furthermore, prior research has indicated that fusing multiple modalities can improve positioning performance compared to using only WiFi. Therefore, this study proposes a novel Multimodal Graph Fingerprinting method for indoor positioning systems. The proposed method constructs a multimodal graph at the location of the user’s smart terminal by fusing radio frequency signals, electromagnetic field (EMF) strength, and inertial sensor measurements. A hierarchical deep graph neural network is developed to learn the relations between the multimodal graphs and their locations by capturing the features of the identities (such as MAC addresses, WiFi Received Signal Strength (RSS), and EMF data) and the topology information. Experiments on a real dataset built on a university campus demonstrate that the proposed model can achieve a median positioning error of 2.1m by fusing different modalities.

K-Neares Neighbors (KNN) and its variant weighted KNN (WKNN) have been explored for years in both academy and industry to provide stable and reliable performance in WiFi-based indoor positioning systems. Such algorithms estimate the location of a given point based on the locality information from the selected nearest WiFi neighbors according to some distance metrics calculated from the combination of WiFi received signal strength (RSS). However, such a process does not consider the relational information among the given point, WiFi neighbors, and the WiFi access points (WAPs). Therefore, this study proposes a novel Deep Neighborhood Learning (DNL). The proposed DNL approach converts the WiFi neighborhood to heterogeneous graphs, and utilizes deep graph learning to extract better representation of the WiFi neighborhood to improve the positioning accuracy. Experiments on 3 real industrial datasets collected from 3 mega shopping malls on 26 floors have shown that the proposed approach can reduce the mean absolute positioning error by 10% to 50% in most of the cases. Specially, the proposed approach sharply reduces the root mean squared positioning error and 95% percentile positioning error, being more robust to the outliers than conventional KNN and WKNN.

WiFi received signal strength (RSS)-based finger-printing has been widely adopted in many indoor positioning systems due to its implementation simplicity and low computational complexity. Recently, some studies have explored the potential temporal features among WiFi data to provide better positioning accuracy using Long Short-Term Memory (LSTM). However, the large volume of invalid RSS signals/values in the radio map degrades the training performance and the positioning accuracy. Some recent research has shown effort to reduce the impact of the problem mentioned above using deep learning. However, these either lack efficiency (repeated training needed or training resource wasted) or cannot provide precision position estimations. This paper proposes a novel Encoded LSTM network model to efficiently extract main features from the WiFi RSS data and provide high positioning accuracy. Experimental results based on an open-source crowdsourced dataset show that the encoded LSTM can reduce the dimension of the WiFi fingerprints from 992 to 64 and achieve a mean positioning error of 7.37m. Compared to the benchmark results based on the same dataset, the encoded LSTM shows the lowest mean error, which outperforms 13 popular positioning algorithms. The proposed encoded LSTM can also provide a 10% improvement in positioning accuracy in comparison to other conventional LSTM models.

WiFi received signal strength (RSS)-based finger-printing has attracted much attention in indoor positioning in the past decade. One WiFi fingerprint comprises multiple RSS values annotated with the location (reference point) where the signals are obtained. The positioning accuracy of WiFi RSS fingerprinting-based indoor positioning systems is highly reliant on the data volume of the observed signals. However, taking such data in a large complex indoor area is usually time-consuming and labor-intensive. In recent years, crowdsourcing approaches have been proposed to collect WiFi data and record the location by utilizing the trajectories of common users to reduce the burden of constructing the database. Nevertheless, crowdsourced data is usually sensitive to crowd density. The data coverage is usually not enough to cover the entire targeted environment to provide good positioning accuracy, particularly at the beginning stage of constructing a database. Besides, it is also expected that some regions do not have enough fingerprints to provide good positioning performance since they do not have as many visitors as others. Therefore, this paper proposes a WiFi fingerprint augmentation method to generate more fingerprints by predicting RSS values on unsurveyed locations through a multivariate Gaussian process regression (MGPR) model. Evaluations are conducted on an open-source crowdsourced WiFi fingerprint dataset collected in an actual multi-floor university building. The experiment results show that the proposed WiFi fingerprint augmentation method can enhance the global data coverage (considering the entire building) to reduce the positioning error by 5% to 20%. Also, the proposed method can sharply reduce the positioning error in some indoor regions by improving local data density (considering a 2D region on a certain floor).