Wi-Fi/MARG Integration for Indoor Pedestrian Localization

Quantification of energy expenditure during daily living activities after stroke by multi-sensor

Objective: To explore the validity of energy expenditure estimates using the SenseWear Armband during a sequence of four daily living activities in patients post-stroke. Method: Patients with stroke who were able to walk during 6 min without human assistance were asked to wear the SenseWear Armband on the non-paretic arm while performing transfers, a manual task, walking, and walking up and down stairs. The energy expenditure estimated using the SenseWear Armband was compared to the energy expenditure calculated from oxygen consumption, measured by a portable indirect calorimeter (Metamax 3B). The mean of energy expenditure was pooled for each task. Accuracy was explored by mean bias (MB) of Bland-Altman analysis and root mean square error (RMSE), agreement by 95% of limits of agreement (95%LoA) and coefficient of correlation (r). Results: Thirty-eight participants (65.7 ± 13.5 years) were included. The SenseWear Armband globally underestimated energy expenditure, MB = 9.77 kcal for the whole sequence. RMSE were large, accounting for 15% to 41% of the measured energy expenditure. Agreement was low with r < 0.70 and 95%LoA from 42% to 93% of the measured energy expenditure. Conclusions: This study reported a global underestimation and a low level of agreement of the energy expenditure estimated by SenseWear Armband in four daily living activities in patients after stroke. Abbreviations: EE: Energy Expenditure; NIHSS: National Institute of Health Stroke Score.

Coverage of ethics within the artificial intelligence and machine learning academic literature: The case of disabled people

Disabled people are often the anticipated users of scientific and technological products and processes advanced and enabled by artificial intelligence (AI) and machine learning (ML). Disabled people are also impacted by societal impacts of AI/ML. Many ethical issues are identified within AI/ML as fields and within individual applications of AI/ML. At the same time, problems have been identified in how ethics discourses engage with disabled people. The aim of our scoping review was to better understand to what extent and how the AI/ML focused academic literature engaged with the ethics of AI/ML in relation to disabled people.Of the n = 1659 abstracts engaging with AI/ML and ethics downloaded from Scopus (which includes all Medline articles) and the 70 databases of EBSCO ALL, we found 54 relevant abstracts using the term "patient" and 11 relevant abstracts mentioning terms linked to "impair*", "disab*" and "deaf". Our study suggests a gap in the literature that should be filled given the many AI/ML related ethical issues identified in the literature and their impact on disabled people.

Indoor Positioning System: A New Approach Based on LSTM and Two Stage Activity Classification

The number of studies on the development of indoor positioning systems has increased recently due to the growing demands of the various location-based services. Inertial sensors available in commercial smartphones play an important role in indoor localization and navigation owing to their highly accurate localization performance. In this study, the inertial sensors of a smartphone, which generate distinct patterns for physical activities and action units (AUs), are employed to localize a target in an indoor environment. These AUs, (such as a left turn, right turn, normal step, short step, or long step), help to accurately estimate the indoor location of a target. By taking advantage of sophisticated deep learning algorithms, we propose a novel approach for indoor navigation based on long short-term memory (LSTM). The LSTM accurately recognizes physical activities and related AUs by automatically extracting the efficient features from the distinct patterns of the input data. Experiment results show that LSTM provides a significant improvement in the indoor positioning performance through the recognition task. The proposed system achieves a better localization performance than the trivial fingerprinting method, with an average error of 0.782 m in an indoor area of 128.6 m2. Additionally, the proposed system exhibited robust performance by excluding the abnormal activity from the pedestrian activities.

Parametric Loop Division for 3D Localization in Wireless Sensor Networks

Localization in Wireless Sensor Networks (WSNs) has been an active topic for more than two decades. A variety of algorithms were proposed to improve the localization accuracy. However, they are either limited to two-dimensional (2D) space, or require specific sensor deployment for proper operations. In this paper, we proposed a three-dimensional (3D) localization scheme for WSNs based on the well-known parametric Loop division (PLD) algorithm. The proposed scheme localizes a sensor node in a region bounded by a network of anchor nodes. By iteratively shrinking that region towards its center point, the proposed scheme provides better localization accuracy as compared to existing schemes. Furthermore, it is cost-effective and independent of environmental irregularity. We provide an analytical framework for the proposed scheme and find its lower bound accuracy. Simulation results shows that the proposed algorithm provides an average localization accuracy of 0.89 m with a standard deviation of 1.2 m.