A receive signal strength (RSS) fingerprinting-based indoor wireless localization system (I-WLS) uses a localization machine learning (ML) algorithm to estimate the location of an indoor user using RSS measurements as the position-dependent signal parameter (PDSP). There are two stages in the system’s localization process: the offline phase and the online phase. The offline phase starts with the collection and generation of RSS measurement vectors from radio frequency (RF) signals received at fixed reference locations, followed by the construction of an RSS radio map. In the online phase, the instantaneous location of an indoor user is found by searching the RSS-based radio map for a reference location whose RSS measurement vector corresponds to the user’s instantaneously acquired RSS measurements. The performance of the system depends on a number of factors that are present in both the online and offline stages of the localization process. This survey identifies these factors and examines how they impact the overall performance of the 2-dimensional (2-D) RSS fingerprinting-based I-WLS. The effects of these factors are discussed, as well as previous researchers’ suggestions for minimizing or mitigating them and future research trends in RSS fingerprinting-based I-WLS.

The performance of fingerprint-based indoor wireless localization systems (IWL-Ss) can be enhanced using fingerprint clustering. The localization performance of clustered fingerprint-based IWL-Ss is affected by several factors, including choosing the most optimal initial parameters and the appropriate fingerprint similarity measurement metric. The problem of choosing the best initial parameter is solved by using the affinity propagation clustering (APC) algorithm in this paper, which automatically calculates the number of clusters and cluster centroid vectors. However, the choice of fingerprint similarity measure and the selection of the best cluster centroid when there are multiple potential cluster centroids limit the performance of the APC algorithm. To address this issue, this paper proposes modifying the conventional APC (c-APC) algorithm, which will be referred to as the ''m-APC algorithm.'' The context similarity coefficient (CSC) fingerprint similarity measure replaces the distance-based fingerprint similarity measure used by the c-APC algorithm. Furthermore, the cluster centroids that are generated automatically are replaced by the centroid that is obtained by averaging all fingerprints within a cluster. Using the k-NN localization algorithm and four online fingerprint databases, the performance of the m-APC+CSC algorithm is determined and compared to the c-APC algorithm using cosine, Euclidean, and Shepard distances as fingerprint similarity measures. Based on simulation results, the m-APC algorithm reduced the position root mean square error (RMSE) and mean absolute error (MAE) by about 12% and 8%, respectively, when compared to the c-APC algorithm when both used the CSC as a fingerprint similarity measure. Furthermore, the m-APC+CSC algorithm achieved an 8% and 9%, respectively, position RMSE and MAE reduction over the c-APC algorithm using cosine, Euclidean, and Shepard distances as similarity measurements. The m-APC+CSC algorithm should, however, be used on a reasonably sized fingerprint database with at least four wireless access points (APs) for better localization performance.

Collecting time-series receive signal strength (RSS) observations and averaging them is a common method for dealing with RSS fluctuation. However, outliers in the time-series observations affect the averaging process, making this method less efficient. The Z-score method based on the median absolute deviation (MAD) scale estimator has been used to detect outliers, but it is only efficient with symmetrically distributed observations. Experimental analysis has shown that time-series RSS observations can have a symmetric or asymmetric distribution depending on the nature of the environment in which the measurement was taken. Hence, the use of the Z-score method with the MAD scale estimator will not be efficient. In this paper, the Sn scale estimator is proposed as an alternative to MAD to be used with the Z-score method in detecting outliers in time-series RSS observations. Performance comparison using an online RSS dataset shows that the Z-score with MAD and Sn as scale estimators falsely detected about 50% and 13%, respectively, of the RSS observations as outliers. Furthermore, the average absolute RSS median deviations between raw and outlier-free observations are 3 dB and 0.25 dB, respectively, for the MAD and Sn scale estimators, corresponding to a range error of about 2 m and 0.5 m.

Analysis of leg muscle activation and gait variability during locomotion is an important area of research in physiological and sport sciences. In this paper, we analyzed the coupling between the alterations of leg muscle activation and gait variability in single-task and dual-task walking. Since leg muscle activation in the form of electromyogram (EMG) signals and gait variability in the form of stride interval time series have complex structures, fractal theory and approximate entropy were used to evaluate their correlation at various walking conditions. Sixty subjects walked at their preferred speed for 10 min under the single-task condition and for 90[Formula: see text]s under the cognitive dual-task condition, and we evaluated the variations of the fractal dimension and approximate entropy of EMG signals and stride interval time series. According to the results, dual-task walking caused reductions in the complexity of EMG signals and stride interval time series than single-task walking. This technique can be used to evaluate the correlation between other organs during different locomotion.