On the Challenges and Potential of Using Barometric Sensors to Track Human Activity

Effects of the interplay between topology and function of an integrated urban development on patterns of user movement

With the advent of distributed multi-sensory networks of devices, vast troves of real-time data can be gathered about our interactions with the built environment. These rich data sets can be mined to achieve improved and informed data-driven designs of buildings, neighborhoods, and potentially entire cities. Among those, integrated developments have the peculiarity of combining multiple functions within a compact space and, as such, behave as microcosms of a city that can help address the problem of urban sprawl and density. However, a general lack of data and framework about integrated developments hinders our ability to test design hypotheses about the complex interplay between heterogeneity in both space and function. Here, we apply a data-driven approach to analyze the joint influence of topology and function on user movement within a state-of-the-art integrated development in Singapore. Specifically, we leverage the network representation of the building and use movement data collected from 51 individuals over a month. We show evidence of correlation (40%) between the spatial network features and human movement at the building level. We are also able to quantify the relationship between the functional and spatial components of the integrated development through user movement. Previous studies have shown a 60% or higher correlation between the topology and human movement at the city or country scales. Our moderate correlation, therefore, implies that more factors influencing user movement are at play. The heterogeneity in the spatial function introduced trips with diverse origins and destinations. A further data-driven analysis integrating origins and destinations reveals both qualitative and quantitative means of studying the relationship between the built environment and the processes that take place in them.

Development and clinical validation of a miniaturized finger probe for bedside hemodynamic monitoring

Our aim is to develop a blood pressure (BP) measurement technology that could be integrated into a finger-worn pulse oximeter, eliminating the need for a brachial cuff. We present a miniature cuffless tonometric finger probe system that uses the oscillometric method to measure BP. Our approach uses a motorized press that is used to apply pressure to the fingertip to measure BP. We verified the functionality of the device in a clinical trial (n = 43) resulting in systolic and diastolic pressures ((mean ± SD) mmHg) of (-3.5 ± 8.4) mmHg and (-4.0 ± 4.4) mmHg, respectively. Comparison was made with manual auscultation (n = 26) and automated cuff oscillometry (n = 18). In addition to BP, we demonstrated the ability of the device to assess arterial stiffness (n = 18) and detect atrial fibrillation (n = 6). We were able to introduce a sufficiently small device that could be used for convenient ambulatory measurements with minimal discomfort.

MEMS-Based Tactile Sensors: Materials, Processes and Applications in Robotics

Commonly encountered problems in the manipulation of objects with robotic hands are the contact force control and the setting of approaching motion. Microelectromechanical systems (MEMS) sensors on robots offer several solutions to these problems along with new capabilities. In this review, we analyze tactile, force and/or pressure sensors produced by MEMS technologies including off-the-shelf products such as MEMS barometric sensors. Alone or in conjunction with other sensors, MEMS platforms are considered very promising for robots to detect the contact forces, slippage and the distance to the objects for effective dexterous manipulation. We briefly reviewed several sensing mechanisms and principles, such as capacitive, resistive, piezoresistive and triboelectric, combined with new flexible materials technologies including polymers processing and MEMS-embedded textiles for flexible and snake robots. We demonstrated that without taking up extra space and at the same time remaining lightweight, several MEMS sensors can be integrated into robotic hands to simulate human fingers, gripping, hardness and stiffness sensations. MEMS have high potential of enabling new generation microactuators, microsensors, micro miniature motion-systems (e.g., microrobots) that will be indispensable for health, security, safety and environmental protection.

Improvement of Baro Sensors Matrix for Altitude Estimation

The article presents the use of barometric sensors to precisely determine the altitude of a flying object. The sensors are arranged in a hexahedral spatial arrangement with appropriately spaced air inlets. Thanks to the solution used, the range of measurement uncertainty can be reduced, resulting in a lower probability of error during measurement by improving the accuracy of estimation. The paper also describes the use of pressure sensors in complex Tracking Vertical Velocity and Height systems, integrating different types of sensors to highlight the importance of this single parameter. The solution can find application in computational systems using different types of data in Kalman filters. The impact of pressure measurements in a geometric system with different spatial orientations of sensors is also presented. In order to compensate for local pressure differences, e.g., in the form of side wind gusts, an additional reference sensor was used, making the developed solution relevant for applications such as industrial ones.

Skyfall: Signal Fusion from a Smartphone Falling from the Stratosphere

A smartphone plummeted from a stratospheric height of 36 km, providing a near-real-time record of its rapid descent and ground impact. An app recorded and streamed useful internal multi-sensor data at high sample rates. Signal fusion with external and internal sensor systems permitted a more detailed reconstruction of the Skyfall chronology, including its descent speed, rotation rate, and impact deceleration. Our results reinforce the potential of smartphones as an agile and versatile geophysical data collection system for environmental and disaster monitoring IoT applications. We discuss mobile environmental sensing capabilities and present a flexible data model to record and stream signals of interest. The Skyfall case study can be used as a guide to smartphone signal processing methods that are transportable to other hardware platforms and operating systems.

Human Action Recognition: A Paradigm of Best Deep Learning Features Selection and Serial Based Extended Fusion

Human action recognition (HAR) has gained significant attention recently as it can be adopted for a smart surveillance system in Multimedia. However, HAR is a challenging task because of the variety of human actions in daily life. Various solutions based on computer vision (CV) have been proposed in the literature which did not prove to be successful due to large video sequences which need to be processed in surveillance systems. The problem exacerbates in the presence of multi-view cameras. Recently, the development of deep learning (DL)-based systems has shown significant success for HAR even for multi-view camera systems. In this research work, a DL-based design is proposed for HAR. The proposed design consists of multiple steps including feature mapping, feature fusion and feature selection. For the initial feature mapping step, two pre-trained models are considered, such as DenseNet201 and InceptionV3. Later, the extracted deep features are fused using the Serial based Extended (SbE) approach. Later on, the best features are selected using Kurtosis-controlled Weighted KNN. The selected features are classified using several supervised learning algorithms. To show the efficacy of the proposed design, we used several datasets, such as KTH, IXMAS, WVU, and Hollywood. Experimental results showed that the proposed design achieved accuracies of 99.3%, 97.4%, 99.8%, and 99.9%, respectively, on these datasets. Furthermore, the feature selection step performed better in terms of computational time compared with the state-of-the-art.