Inertial Measurement Units (IMUs) embedded in commercial mobile devices are a good choice for continuous monitoring healthcare domain due to their attractive form factor and low power consumption. We present improved accurate sensing algorithms using single IMU sense basic events like step count, stride length, fall, immobility etc. Our have been shown perform better than the state of art algorithms, implemented such way that is not bound any specific position or orientation with respect...

This paper discusses `InLoc', an accurate and a robust positioning tracking system using commercial mobile devices, with integrated feature of route finding for the user from source to desired destination. The exploits easily available building floor maps in raster form, easy conversion vector model, eliminating need specially designed maps, thereby making scalable large indoor more implementation friendly. also enables map be used both Particle Filter based IMU tracking, routing....

Efficient evacuation of large buildings which seat more than twenty thousand people is a major challenge for building management authorities. Although many enterprise have access control to count those entering various areas, such controls need be switched off at times emergency avoid getting trapped particular location. Hence, counting during remains largely manual and error prone. Also, last known location based on from business systems can erroneous due issues like tail gating. Accurate...

In this paper, viability of low-cost off-the-shelf Piezoelectric ceramic disc elements is explored for an insole-based gait monitoring system, `PI-Sole' (Piezo In-Sole). can sense dynamic changes in pressure a closed-loop environment with good sensitivity and wide measurement range. method to enable these continuously plantar while walking proposed, making them very cost-efficient alternative the widely used Force Sensing Resistors (FSR) plates human gait. However, piezoelectric show...

In this paper we propose an IoT based framework for driving style assessment using the driver owned smartphone as sensing platform. The GPS and inertial sensors, embedded in phone are used to continually sample measurements of position, speed acceleration moving vehicle. required computation is segregated between a remote server. We present fusion algorithm which offers accurate estimation velocity, thereby position. To obviate need human intervention, adaptive process multi-sensor...

Cardiopulmonary disease prognosis can achieve therapeutic edge if the disorders be detected and attended to at an early stage. This work proposes 'Cardiopulmonary Care Platform (C2P)' which in its current initial phase, targets subjects stage of Functional Capacity II as per NYHA staging system by detecting physiological fatigue, signs dispnea palpitation, using a smartwatch after subject has undergone spell physically intensive activity. A novel computationally efficient solution is devised...

In this work, an end-to-end indoor routing and guiding solution, 'InLocW' (InLoc - Wearable) is discussed. The initial location fix of the user obtained using infrastructure BLE beacons. Primary focus on continuous calculation instantaneous walking direction (a primary arrow displayed smartwatch) based user's current estimated by a particle filter which runs in back end. A solution devised to synchronize these directions walking, thereby solving problem inherent latency between actual PDR...

In the wake of recent COVID-19 pandemic, contact tracing has turned out to be an indispensable technique help administrative authorities contain localized infections efficiently. absence a definitive and official vaccine for infection, practicing social distancing proved effective norm prevent risk infection. this paper, we present 'ProxiTrak', smartphone based solution enterprise scenario capable not only chain possible infection transmission among set population, but also guiding users...

In this work, we present a solution for an accurate and real-time monitoring of breathing rate (BR) from photoplethysmogram (PPG) signal on both smartphone smartwatch. Respiration induces multiple modulations in PPG which are difficult to extract low-quality collected using consumer devices. We effective method validating the data is evaluated compared open dataset. The also implemented as smartwatch app provide on-device BR, subjects. For demonstration, shall show pattern smartwatch, can be...

In the paradigm of remote patient monitoring, clinical significance, robustness and repeatability measurements are key aspects. Such using sensors or wearables, implantable proxemics devices often termed "Digital Biomarkers" as they surrogate markers for patient's health condition. We have invested in creating digital biomarkers platform which connects patients & physicians by enabling monitoring augmenting reports physical examination data with insights derived from continuous these...

Precise tracking of smart wearables in 3-D space is foundational domains ranging from Augmented Reality (AR) and gesture recognition to robotics indoor localization. Usually, a sensor-dependent approximation model, complementary infrastructure like acoustic, vision etc. implemented alongside an onboard IMU (Inertial Measurement Unit) for effective tracking. In this work, we present novel solution, `AiRite' commercial-grade wearables/mobiles using only their IMU. Our method mitigates the...

Inertial Measurement Units (IMUs) embedded in commercial mobile devices are a good choice for continuous monitoring healthcare domain due to their attractive form factor and low power consumption. We present improved accurate sensing algorithms sense basic events like step count, stride length, fall, calorie, with accuracies better than those of existing arts. The can be directed server running event analytics, yielding important cues about subject's health. One the spheres is elderly...

Patients surviving a brain stroke often experience an impaired neuro-motor coordination and cognitive capability. Rehabilitation assisted by therapists can help them regain much of this coordination. In recent past, gamified activities have proved to be effective in regard with enhanced patient engagement. But, they may require special hardware certain usage restrictions regarding patient's positioning etc. for operating effectively. We set out develop suite games using smartwatch sense...

Calculating accurate distance from an accelerometer during motion involves integrating its raw data and it has been well-established that when the is imparted by humans, consumer-grade MEMS accelerometers are rendered unsuitable for this task due to their high error-profiles even short-interval applications. This work presents 'EMeasure', a step towards addressing problem with completely sensor-agnostic elegantly error-mitigating model using temporal parameters modeling cumulated error in...

Tracking arm motion in real-time with wearables like smartwatches has proved to be a challenging task. Ex-isting approaches either require additional sensing modality affecting ubiquity, and/or are not efficient enough for tracking, especially on low-power embedded devices limited computing capabilities. In addition, tracking air-writing trajectories while the user is move, e.g. walking, adds up challenges. 'NNTrak' our attempt address these issues focusing practicality, current work...

In this work, we demonstrate a radically novel approach towards inertial-only tracking of wrist in real-time on smartwatch for air-writing tasks. Deriving motion trajectories from commercial-grade Inertial Measurement Units (IMU) has always been challenging task due to inherent sensor errors and associated trajectory drift. Computationally expensive solutions offered literature cannot be used fully while also maintaining acceptable accuracy. This work presents 'NNTrak', marking our attempt...

Inertial sensors have been used for tracking applications on every scale decades. Commercial IMUs suffer from a spectrum of errors such as axes misalignment, bias etc. leading to drifted output. Approximation models are usually implemented address these issues which highly sensor-dependent with constrained testing and sometimes use complementary infrastructure limits their in the wild. In this demonstration we introduce 'AiRite', an effective solution 3-D smart device using only onboard IMU....

Wearable-based motion sensing solutions are capable of automatically detecting and tracking individual smoking puffs and/or episodes to aid the users in their journey cessation. But they either obtrusive use, perform with a low accuracy, or have questionable ability running fully on low-power device like smartwatch, all affecting widespread adoption. We propose 'CigTrak', novel pipeline for an accurate puff episode detection using 6-DoF sensor smartwatch. A multi-stage method is devised,...

In this poster, we present a new lightweight multithreaded software model for target location detection system. Our localization algorithm is based on trilateration using RSSI ranging.This work can be applied collecting the information of mobile sensor nodes in network. runs and base station. To support our clam performed experimental analysis telosb motes.

The exposure of ultraviolet radiation is increasing day by and the need shielding from this harmful an emerging demand. major problem with mostly used UV absorbers photodegradation that they degrade under exposure. In order to solve above problem, conventional such as titanium dioxide zinc oxide are studied doping a natural product, flavonoid. work, nano-sized particles successfully synthesised using sol-gel process their composites at five TiO2:ZnO ratios (40:60, 33:66, 30:70, 20:80, 10:90)...