Advancing the Kinetics Model in OpenSim for Human Motion Estimation Based on IMUs: Performance Analysis with Wheelchair User Motion

Inertial Measurement Units (IMUs) have become increasingly popular human motion estimation due to their portability, self-contained features, and cost-effectiveness compared to marker-based sensing systems which rely on external cameras to observe the position of the markers. Over the years, many studies have proposed various models and...

Magnetic field SLAM: using an inertial human motion suit and reduced rank Gaussian process regression

Indoor localisation is a growing field of interest in recent studies. While GPS (global positioning system) is a standard for outdoor localisation, no such solution exists for indoor applications. The literature provides several methods to obtain the location of indoor systems, often using optical sensors. A small number of recent studies use...

improving power output of limited stroke automatic watch winding using a nonlinear transmission

Limited stroke automatic watch winding poses a challenge due to the proof mass range being smaller than the input displacements. Traditionally the proof mass is connected to the mainspring by a linear reduction transmission however this setup only functions effectively for specific accelerations. This paper proposes to use a nonlinear...

Complex-Valued Neural Networks for Radar-based Human-Motion Classification

Nowadays, radar has been applied to human activity classification in the aging-in-place for health monitoring. The complex-valued neural networks (CVNNs) have been only minimally explored, especially on complex-valued radar signals, and there is an outstanding question on whether CVNNs can contribute to improving classification performance. This...

Design of travel limits for bistable vibration energy harvesting

Energy harvesting from renewable energy sources has become more popular in the last decades than ever before. New energy sources consisting of human input vibrations are hopeful alternatives for powering wearable low power electronics. These sensors currently rely on the lifetime of the battery and come along with high maintenance costs in case...

Vibration Energy Harvesting from Human Motion: by Frequency up-conversion through Impact

Vibration Energy Harvesting has the potential to become a convenient, sustainable and localized power source for the billions of small electronic devices of the future. One of the most challenging areas within this field is the design of miniaturized generators for power harvesting from human motion. In this thesis, a new strategy, design and...

Easy ID: A Wireless Sensor Package to Measure Human Interaction Features

This thesis proposes a low-cost and small size customized data acquisition sensor badge, called Easy ID, which is specially designed for the Vision Lab Group in TU Delft for their on body data capture during social events. Easy ID is designed based on an open source platform, which provides enough space for future upgrade and extension.<br/>The...

A Sensor Data Fusion Algorithm for Human Motion Estimation

In the elderly population, falls are one of the major causes of injuries. Fall detection algorithms for wearable devices in the literature were found to focus on differentiating Activities of Daily Living (ADL) from falls, rather than on early fall detection and prevention before impact. This thesis work was aimed at providing accurate estimates...

Model-based Classification of Human Motion: Using a Particle Filter Approach

Automatic detection of humans is an important part of many security and surveillance applications. Automatic processing diminishes the effect of human errors on the detection and allows extensive analysis after detection. Radar has certain advantages for human detection because of its all-weather and day and night capability, as well the fact it...