In the era of mobile internet, Location Based Services (LBS) have developed dramatically. Seamless Indoor and Outdoor Navigation and Localization (SNAL) has attracted a lot of attention. No single positioning technology was capable of meeting the various positioning requirements in different environments. Selecting different positioning techniques for different environments is an alternative method. Detecting the users’ current environment is crucial for this technique. In this paper, we proposed to detect the indoor/outdoor environment automatically without high energy consumption. The basic idea was simple: we applied a machine learning algorithm to classify the neighboring Global System for Mobile (GSM) communication cellular base station’s signal strength in different environments, and identified the users’ current context by signal pattern recognition. We tested the algorithm in four different environments. The results showed that the proposed algorithm was capable of identifying open outdoors, semi-outdoors, light indoors and deep indoors environments with 100% accuracy using the signal strength of four nearby GSM stations. The required hardware and signal are widely available in our daily lives, implying its high compatibility and availability.

Indoor localization using Received Signal Strength Indication (RSSI) fingerprinting has been extensively studied for decades. The positioning accuracy is highly dependent on the density of the signal database. In areas without calibration data, however, this algorithm breaks down. Building and updating a dense signal database is labor intensive, expensive, and even impossible in some areas. Researchers are continually searching for better algorithms to create and update dense databases more efficiently. In this paper, we propose a scalable indoor positioning algorithm that works both in surveyed and unsurveyed areas. We first propose Minimum Inverse Distance (MID) algorithm to build a virtual database with uniformly distributed virtual Reference Points (RP). The area covered by the virtual RPs can be larger than the surveyed area. A Local Gaussian Process (LGP) is then applied to estimate the virtual RPs’ RSSI values based on the crowdsourced training data. Finally, we improve the Bayesian algorithm to estimate the user’s location using the virtual database. All the parameters are optimized by simulations, and the new algorithm is tested on real-case scenarios. The results show that the new algorithm improves the accuracy by 25.5% in the surveyed area, with an average positioning error below 2.2 m for 80% of the cases. Moreover, the proposed algorithm can localize the users in the neighboring unsurveyed area.

In this paper, we consider wireless positioning using Received Signal Strength (RSS) fingerprinting. To obtain good accuracy, this technique requires a database containing a high density of up-to-date fingerprints. However, as acquiring fingerprints through training is labor intensive and the indoor topology is subject to changes, a high density fingerprint database cannot always be obtained. On the other hand, the time to retrieve data from a database with high density can be too high for real-time positioning. To tackle these issues, we introduce the Hierarchical Positioning Algorithm (HPA). In this algorithm, we divide the database into a number of sub-databases with different densities, each containing a sufficiently small number of fingerprints to reduce the data retrieval time. The algorithm starts with a coarse estimate at the highest level, and gradually improves the accuracy in going to the lowest level. This HPA technique requires the construction of sub-databases containing fingerprints that are properly selected to obtain the wanted level of accuracy. This paper considers two algorithms to construct the database: the Minimum Distance Algorithm (MDA) to select the reference points, and the Local Gaussian Process (LGP) algorithm to determine the RSS values at the selected reference points. Simulation results show that the hierarchical algorithm, combined with MDA and LGP to construct the sub-databases, is a fast algorithm that can achieve high accuracy, even with a database having a variable density of fingerprints.

The development of drone technology has played an increasingly important role in modern warfare. However, the limited endurance of drones and objective factors such as observation of attack strategies and autonomous learning pose new challenges to the formulation of drone patrol strategies. To address these issues, a game model between the attacking side composed of multiple suicide drones and the defending side was constructed based on Stackelberg security game theory. The game model was then transformed into a bilevel programming problem, and the genetic algorithm was used to solve the bilevel programming problem and obtain the Stackelberg equilibrium solution of the game. A comparison was made between the equilibrium strategy and other strategies, and experimental results demonstrated that the transformed model could provide higher quality and robust patrol strategies.