Share with us your published research that uses Notch technology to receive 1 year of Extended license and discount towards your next Notch Pioneer purchase.

Peer-Reviewed Articles and Publications Featuring Notch Technology

Aws4 request&x amz signedheaders=host&x amz signature=9fd4bb6def0426866fd39657635319da0ea4227afc5282fbbcb410a8a0264e76

Comparison Among Standard Method, Dedicated Toolbox and Kinematic-Based Approach in Assessing Risk of Developing Upper Limb Musculoskeletal Disorders

ergonomics
Stefano Elio Lenzi, Carlo Emilio Standoli, Giuseppe Andreoni, Paolo Perego, Nicola Francesco Lopomo

OCRA (Occupational Repetitive Action) index is one of the most used method for supporting risk assessment in tasks requiring manual handling of low loads at high frequency. One of the main drawbacks of this method is that the operator analyses the activities by observing videos. This kind of procedure is inherently not objective and operator-dependent. To overcome these limitations, we developed a toolbox to support the analysis with contextual noting and wearable sensors kinematic data. Three expert operators were asked to evaluate seven videos with and without the aid of the developed toolbox. Results underlined a high inter (R2 mean 0.4) and intra-operator variability (posture time percentage and technical actions (TAs) count mean errors respectively 7.44%, 4 TAs) when using the only video-based approaches. On the contrary, research outcomes showed that the introduction of wearable device allow to overcome these issues and to reduce noticeably the evaluation time (−98%).

Read more
Aws4 request&x amz signedheaders=host&x amz signature=3e2d3b7840910eb2d5257f46d792d54673c9566dee93ab38b1ee5c452680c985

A Software Toolbox to Improve Time-Efficiency and Reliability of an Observational Risk Assessment Method

ergonomics
Stefano Elio Lenzi, Carlo Emilio Standoli, Giuseppe Andreoni, Paolo Perego, Nicola Francesco Lopomo

OCRA is a standard risk assessment method addressing manual handling of low loads at high frequency. This method requires the operator to perform a video analysis checking kind and extension of the movements made by workers. The analyst has to take note about number of performed actions and joint angles amplitude. Often this turn out to be a poorly reliable and time-consuming operation because of the inherent 2D nature of the data. The main goal of this work was to design a software toolbox able to support the operator in collecting, organizing and analyzing the information to obtain the Checklist OCRA index in a more reliable and time-effective way. This toolbox presents three different GUIs to: (1) support the operator in counting the number of technical actions; (2) help the operator in determine the percentage of time in which the worker has an incorrect upper limb posture; (3) automatically perform posture analysis considering real 3D angles data acquired through an IMU-based movement analysis system. Preliminary analysis on reliability was performed on three different operators. Obtained findings confirmed our hypothesis; the automatic analysis, in particular, reduced significantly intra- and inter-operator variability thus making the analysis more objective and reliable. Further evaluations will include structured assessment including several operators with different expertise levels and collecting information about user experience (usability, GUI design, etc.) and overall performance compared to standards (operation time and results accuracy).

Read more
Aws4 request&x amz signedheaders=host&x amz signature=d4ddb2fdea039ca243d1f88d3f6a8fce5fcaf3f5ff34d4cce1e5aa3d4cd85f26

SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning

healthcare
Taylor R. Mauldin, Marc E. Canby, Vangelis Metsis, Anne H. H. Ngu, Coralys Cubero Rivera

This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the prediction of falls in real time without incurring latency in communicating with a cloud server, while also preserving data privacy. We experimented with both traditional (Support Vector Machine and Naive Bayes) and non-traditional (Deep Learning) machine learning algorithms for the creation of fall detection models using three different fall datasets (Smartwatch, Notch, Farseeing). Our results show that a Deep Learning model for fall detection generally outperforms more traditional models across the three datasets. This is attributed to the Deep Learning model’s ability to automatically learn subtle features from the raw accelerometer data that are not available to Naive Bayes and Support Vector Machine, which are restricted to learning from a small set of extracted features manually specified. Furthermore, the Deep Learning model exhibits a better ability to generalize to new users when predicting falls, an important quality of any model that is to be successful in the real world. We also present a three-layer open IoT system architecture used in SmartFall, which can be easily adapted for the collection and analysis of other sensor data modalities (e.g., heart rate, skin temperature, walking patterns) that enables remote monitoring of a subject’s wellbeing.

Read more
Aws4 request&x amz signedheaders=host&x amz signature=1a59fa7397a8ccabe3e64d21f3f53224c79f428944b82171f72215b3de5eaa86

The Movement Undercommons: Movement Analysis as Meaning Making in a Time of Global Migrations

interactive art
Grisha Coleman, Brenda McCaffrey

While migration studies are generally approached in geographical/statistical/geo-political terms [time, histories, routes], this project considers migratory movement at the scale of individual human movement. movement as a marker of identity expressed through qualities of posture, rhythm, gesture, tempo, orientation. Each person’s movement is unique, an individual’s movement ‘fingerprint’, and this project seeks to reveal and honor the specific, fluid, complex qualities of a people in motion of body and location, while adding to a critical discourse surrounding issues of contemporary migration. This is a position paper describing the research framework behind a new project which proposes an exploration of movement and mobility amongst internal migratory populations within two pilot areas; South Africa and Greece. This work develops our previous work, creating a repository for a growing collection of highresolution motion-capture ‘portraits’. This repository will not only hold the source documentation of movement sequences, but also serve as an open platform for those recorded. It will become a space for discussion, creative interpretation, translation, annotation, and analysis. The repository opens a public space for artists, researchers, dancers, ethnographers, humanists, and somatic movement educators to respond and add diverse layers of meaning; creative interpretation, social and historical context, and technological and somatic analysis. Thus, we build an expandable platform for exploring the linguistics of movement through a range of responses.

Read more
Aws4 request&x amz signedheaders=host&x amz signature=5f02e2f30e58443fa656185b06942c23705afe1c4694c36188c285e71f06a849

Interfacing Gestural Data from Instrumentalists

interactive art
Martin Jaroszewicz

This paper presents preliminary work on a system for capturing gestures from music instrumentalists. A saxophone player performed an étude from standard repertoire in two different manners: firstly, constraining their physical gestures to pro- duce sound and execute the written music; secondly, to exaggerate the gestures to include expressions of emotions. The author used a “non-invasive” way to capture the performance gesture using wearable IMU devices with sensor fusion. Using open source 3D creation software, the author extracted motion paths from the data generated by the performer. A 3D Kernel Density Estimation (KDE) algorithm was implemented to create a visualization of density of the trajectories of the head, left elbow and left hand. Analyzing the gestural space of a work of music to develop composition strategies when interfacing the machine and the performer in real time electroacoustic music is highlighted.

Read more