Fingerprinting based indoor positioning system (IPS) is gaining more research interest under the umbrella of location-based services. However, existing works have certain limitations in addressing issues such as noisy measurements, high computational complexity, poor generalization ability. In this work, a random vector functional link network based approach is introduced to address these issues. In the proposed system, a subset of informative features from many randomized noisy features are selected to both reduce the computational complexity and boost the generalization ability. Moreover, the feature selector and predictor are jointly learned iteratively in a single framework based on Augmented Lagrangian method. The proposed system is appealing as it can be naturally fit into parallel or distributed computing environment. Extensive realworld indoor localization experiments are conducted on users with smartphone devices and results demonstrate the superiority of the proposed method over the existing approaches.

Due to the unknown spatio-temporal distribution of Battery Electric Vehicles (BEVs) charging load, introducing large quantities of BEVs in the transportation sector has drawn growing concerns about its negative impacts on the power grid system. Based on real-world vehicle driving survey data, this paper presents a deterministic and a probabilistic model to quantitatively investigate the spatio-temporal distribution of BEV charging load for Australia. Whilst the trip-chain-related travel parameters for the deterministic model are directly taken from travel survey data, those for the probabilistic model are generated by the k-Nearest-Neighbour (kNN) algorithm. The probabilistic model is validated and applied to simulate the spatio-temporal distribution of BEV load based on GISgridded data for Australia. We are able to distinguish different temporal BEV charging load distributions for weekdays and weekends, and a heavy spatial concentration in capital cities.

Recent studies have demonstrated the success of using the channel state information (CSI) from the WiFi signal to analyze human activities in a fixed and well-controlled environment. Those systems usually degrade when being deployed in new environments. A straightforward solution to solve this limitation is to collect and annotate data samples from different environments with advanced learning strategies. Although workable as reported, those methods are often privacy sensitive because the training algorithms need to access the data from different environments, which may be owned by different organizations. We present a practical method for the WiFi-based privacy-preserving cross-environment human activity recognition (HAR). It collects and shares information from different environments, while maintaining the privacy of individual person being involved. At the core of our approach is the utilization of the Johnson–Lindenstrauss transform, which is theoretically shown to be differentially private. Based on that, we further design an adversarial learning strategy to generate environment-invariant representations for HAR. We demonstrate the effectiveness of the proposed method with different data modalities from two real-life environments. More specifically, on the raw CSI dataset, it shows 2.18% and 1.24% improvements over challenging baselines for two environments, respectively. Moreover, with the discrete wavelet transform features, it further yields 5.71% and 1.55% improvements, respectively.

Time series analysis is essential to many far-reaching applications of data science and statistics including economic and financial forecasting, surveillance, and automated business processing. Though being greatly successful of Transformer in computer vision and natural language processing, the potential of employing it as the general backbone in analyzing the ubiquitous times series data has not been fully released yet. Prior Transformer variants on time series highly rely on task-dependent designs and pre-assumed “pattern biases”, revealing its insufficiency in representing nuanced seasonal, cyclic, and outlier patterns which are highly prevalent in time series. As a consequence, they can not generalize well to different time series analysis tasks. To tackle the challenges, we propose DifFormer , an effective and efficient Transformer architecture that can serve as a workhorse for a variety of time-series analysis tasks. DifFormer incorporates a novel multi-resolutional differencing mechanism, which is able to progressively and adaptively make nuanced yet meaningful changes prominent, meanwhile, the periodic or cyclic patterns can be dynamically captured with flexible lagging and dynamic ranging operations. Extensive experiments demonstrate DifFormer significantly outperforms state-of-the-art models on three essential time-series analysis tasks, including classification, regression, and forecasting. In addition to its superior performances, DifFormer also excels in efficiency – a linear time/memory complexity with empirically lower time consumption.

Indoor mobile localization in real-life scenarios often suffers from frequent transitions of sensor measurements between line-of-sight (LOS), non-line-of-sight (NLOS), and/or mixed LOS and NLOS conditions (LOS-NLOS). To address this, we propose GIMM-EKF by integrating Gaussian mixture model (GMM), interacting multiple model (IMM), and extended Kalman filter (EKF). In GIMM-EKF, GMM aims at modeling the distribution of a set of mixed LOS-NLOS range estimates. Then, a Kalman-based IMM framework is introduced with the estimated state probabilities from the GMM. Finally, an EKF is employed to estimate the target’s location based on the resulting range estimates. The proposed GIMM-EKF works in a synergistic manner and outperforms several challenging baselines significantly. Experimental results demonstrate the feasibility of GIMM-EKF in mitigating the adverse impacts of severe NLOS errors and accurately estimating the mobile location in the LOS/NLOS/LOS-NLOS transition conditions.