Sensors

Multi-modal Exercises Dataset is a multi- sensor, multi-modal dataset, implemented to benchmark Human Activity Recognition(HAR) and Multi-modal Fusion algorithms. Collection of this dataset was inspired by the need for recognising and evaluating quality of exercise performance to support patients with Musculoskeletal Disorders(MSD).The MEx Dataset contains data from 25 people recorded with four sensors, 2 accelerometers, a pressure mat and a depth camera.

Herein we present a multi-threshold-based constant micro-increment control strategy to detect and suppress the slip for the prosthetic hand, and to minimize the loading force increment after the stabilization. The proposed strategy primarily encompasses slipping process model, multi-threshold detection method, constant micro-increment controller and a preset filter. First and foremost, a slipping process model is proposed that involves the nonlinear and noise characteristics of the system.

This dataset is in support of my 3 research papers - 'Comparative SoC Analysis using Non-Linear Kalman Estimation in 8RC ECM of 72Ah LIB - Part I', ' Comparative SoC Analysis using Non-Linear Kalman Estimation in 8RC ECM of 72Ah LIB - Part II' , and 'Comparative SoC Analysis using Non-Linear Kalman Estimation in 8RC ECM of 72Ah LIB - Part III'. 

Indoor positioning systems based on radio frequency systems such as UWB inherently present multipath related phenomena. This causes ranging systems such as UWB}to lose accuracy by detecting secondary propagation paths between two devices. If a positioning algorithm uses ranging measurements without considering these phenomena, it will make important errors in estimating the position. This work analyzes the performance obtained in a localization system when combining location algorithms with machine learning techniques for a previous classification and mitigation of the propagation effects.