Search results for "Task Analysis"

A novel clustering-based algorithm for solving spatially-constrained robotic task sequencing problems

2021

The robotic task sequencing problem (RTSP) appears in various forms across many industrial applications and consists of developing an optimal sequence of motions to visit a set of target points defined in a task space. Developing solutions to problems involving complex spatial constraints remains challenging due to the existence of multiple inverse kinematic solutions and the requirements for collision avoidance. So far existing studies have been limited to relaxed RTSPs involving a small number of target points and relatively uncluttered environments. When extending existing methods to problems involving greater spatial constraints and large sets of target points, they either require subst…

Comprehensive Experimental Analysis of Handcrafted Descriptors for Face Recognition

2018

Over the past few decades, LBP descriptor, which shown its high robustness in extracting discriminative features from an image, has been successfully applied in diverse challenging computer vision applications including face recognition. The efficiency and usability of the LBP operator and its success in various real world applications has inspired the development of much new powerful LBP variants. Indeed, after the appearance of the LBP operator, several renowned extensions and modifications of LBP have been proposed in the literature to the point that it can be difficult to recognize their respective LBP-related strategies, strengths and weaknesses according to a given application, and th…

ASR performance prediction on unseen broadcast programs using convolutional neural networks

2018

In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably …

The Use of Multimodal Resources by Technical Managers and Their Peers in Meetings Using English as the Business Lingua Franca

2020

Background: Engineers increasingly work and advance their careers in international business settings. As technical managers, they need management and technical skills when working with different stakeholders with whom they may not share a common first language. Studies have revealed that informal oral communication skills are of prime importance for global engineers who face challenges in building shared meaning and formulating clear messages in meetings with non-native speakers of English. This article proposes that studying the use of multimodal resources (spoken language, gaze, gestures, and objects) in meetings can unpack how work tasks are accomplished in business through different com…

Video-assisted surgery: suggestions for failure prevention in laparoscopic cholecystectomy

2014

Background: Surgery differs from other medical specialties in its execution. It is often complex and includes considerable individual variations. Observing problems in operating theatres (OT) allows for the identification of system failures which should be defined for learning purposes to increase patient safety and enhance general safety culture within hospital organizations. This study evaluates a common video-assisted surgical procedure, laparoscopic cholecystectomy (LC) through failure analysis. The profile of the LC procedure and failure sources is presented. Methods: Data consisted video-observations and interviews concerning twelve LC operations performed at a day surgery unit. All o…

CrowdVAS-Net: A Deep-CNN Based Framework to Detect Abnormal Crowd-Motion Behavior in Videos for Predicting Crowd Disaster

2019

With the increased occurrences of crowd disasters like human stampedes, crowd management and their safety during mass gathering events like concerts, congregation or political rally, etc., are vital tasks for the security personnel. In this paper, we propose a framework named as CrowdVAS-Net for crowd-motion analysis that considers velocity, acceleration and saliency features in the video frames of a moving crowd. CrowdVAS-Net relies on a deep convolutional neural network (DCNN) for extracting motion and appearance feature representations from the video frames that help us in classifying the crowd-motion behavior as abnormal or normal from a short video clip. These feature representations a…

Learning via Summarizing Infographics Assignment in Software Engineering Management e-Course?

2020

This Research-to-Practice, Work in Progress Paper focuses on how learners experience creation of infographics as a summarizing assignment in an advanced level e-course on software engineering management (SEM). We have previously investigated how learners perceive infographics as a repeated reflection assignment during a requirements engineering e-course. To complement this research project, we studied how learners experience the use of infographics as a method for summarizing a whole software engineering management course in e-education setting. The SEM course participants (N=36) found that infographics as a summarizing assignment required complex learning that was altogether deemed highly …

Neural Processing of Congruent and Incongruent Audiovisual Speech in School-Age Children and Adults

2017

Asymmetries of Knowledge and Epistemic Change in Social Gaming Interaction

2014

While a growing number of studies investigate the role of knowledge and interactional management of knowledge asymmetries in conversation analysis, the epistemic organization of multilingual and second language interactions is still largely unexplored. This article addresses this issue by investigating how knowledge asymmetries and changing positions with regard to knowledge impact social interaction in multilingual gaming activities. Drawing on a collection of video recordings of social gaming sessions collected over a two year period and involving the same two participants, we examine how the participants orient to knowledge and deal with knowledge asymmetries while solving game-related p…

An Analytical Scheme to Characterise the Mathematical Discourse of Biology Tasks

2021

The chapter describes an analytical scheme designed for investigating the mathematical discourse of biology tasks. The scheme was developed in the context of analysing tasks that are part of a fisheries management graduate-level course at a Norwegian university. Grounded in the commognitive perspective, the scheme focuses on the following aspects of the tasks: the mathematical content, its relation to biology discourse and students’ expected engagement with both discourses. To illustrate the potential of analysis, I present and justify the choice of the categories included in the scheme, exemplify its use on one specific task and discuss some of the limitations of this approach to task anal…