Paper2Wire – A Case Study of User-Centred Development of Machine Learning Tools for UX Designers

i-com ◽  
2021 ◽  
Vol 20 (1) ◽  
pp. 19-32
Author(s):  
Daniel Buschek ◽  
Charlotte Anlauff ◽  
Florian Lachner
Keyword(s):  
Machine Learning ◽  
Development Process ◽  
User Study ◽  
Concept Development ◽  
Lessons Learned ◽  
Design Tool ◽  
Learning Tools ◽  
Interface Elements ◽  
Industry Partner

Abstract This paper reflects on a case study of a user-centred concept development process for a Machine Learning (ML) based design tool, conducted at an industry partner. The resulting concept uses ML to match graphical user interface elements in sketches on paper to their digital counterparts to create consistent wireframes. A user study (N=20) with a working prototype shows that this concept is preferred by designers, compared to the previous manual procedure. Reflecting on our process and findings we discuss lessons learned for developing ML tools that respect practitioners’ needs and practices.

Factors Influencing Adoption of Information Technologies for Public Transportation Project Inspection: A WSDOT Case Study

2019 ◽  
Vol 2673 (2) ◽  
pp. 1-12
Author(s):  
Julian Yamaura ◽  
Stephen T. Muench ◽  
Kim Willoughby
Keyword(s):  
Organizational Change ◽  
Change Management ◽  
Public Transportation ◽  
Information Technologies ◽  
User Study ◽  
New Technology ◽  
Management Program ◽  
Lessons Learned ◽  
Structured Interviews

This paper presents a case study of the organizational change process associated with the Washington State Department of Transportation (WSDOT) year-long research program that implemented a cloud-based mobile project inspection application to 18 project engineering offices (PEO) across the state. Ultimately, four out of the 18 PEOs decided to adopt the new technology. Data from semi-structured interviews and a user study conducted two months after implementation are used to identify organizational change strategies used by WSDOT, and how those relate to ideas from the general literature on change management. The loss of upper management program leaders, inadequate communication and training to prepare personnel for the change, and policy and procedural uncertainties in integrating the change with other systems and operations were found to be factors that may have influenced the outcome of the program. While this paper focuses on one DOT’s efforts, other DOTs may have similar organizational structures and implementation efforts, and the findings and lessons learned could serve as a representative model for how such implementation might best be accomplished in a DOT and how that might differ from traditional change management guidance.

Speech Technologies for Language Therapy

2011 ◽  
pp. 408-433
Author(s):  
Ingrid Kirschning ◽  
Ronald Cole
Keyword(s):  
Markov Models ◽  
Lessons Learned ◽  
Learning Tools ◽  
Speech And Language ◽  
Language Therapy ◽  
Effective Interactions ◽  
Speech And Language Therapy ◽  
Recognition Systems ◽  
Special Education School

This chapter presents the development and use of speech technologies in language therapy for children with hearing disabilities. It describes the challenges that must be addressed to design and construct a system to support effective interactions. The chapter begins with an introduction to speech and language therapy and discusses how speech-based systems can provide useful tools for speech and language therapy and to overcome the lack of sufficient human resources to help all children who require it. Then it describes the construction of adequate speech recognition systems for children, using artificial neural networks and hidden Markov models. Next, a case study is presented with the system we have been developing for speech and language therapy for children in a special education school. The chapter concludes with an analysis of the obtained results and the lessons learned from our experiences that will hopefully inform and encourage other researchers, developers, and educators to develop learning tools for individuals with disabilities.

A Design Tool for Distributed Concept Development

2008 ◽  
Author(s):  
Kate Nordland ◽  
Edward Hensel
Keyword(s):  
Design Space ◽  
Concept Development ◽  
Design Tool ◽  
Design Environment ◽  
Weighted Voting ◽  
Design Intent ◽  
Morphological Chart ◽  
The Brain ◽  
Over Time

This paper provides an overview of a database tool to support collaborative concept development in an asynchronous, distributed design environment. This paper will illustrate how an ideation method, such as as brainstorming, can be applied to a desired set of functions for a new design. The result of the brain-storming session for each articulated function can then be used in conjunction with a collaborative weighted voting tool to develop a rank-ordered morphological chart of the design space. A case study will be presented to illustrate how the information and knowledge generated in a prior working session by a design group can be introduced into a subsequent design session. The case study will illustrate how knowledge can be effectively transferred from one design project to the next, and preserve design intent over time.

Redesign of Car Body by Reverse Engineering Technique using Steinbichler 3D Scanner and Projet 3D Printer

2020 ◽  
pp. 2050007
Author(s):  
Abid Haleem ◽  
Mohd Javaid ◽  
Abhishek Goyal ◽  
Tarbiya Khanam
Keyword(s):  
Reverse Engineering ◽  
Development Process ◽  
Concept Development ◽  
Design Tool ◽  
Physical Parameters ◽  
3D Printer ◽  
3D Scanner ◽  
Development Tool ◽  
Engineering Technique ◽  
Innovative Solutions

Product designing requires concept development tool like TRIZ to obtain innovative solutions. In this paper, we have applied available concept development and design tool to develop a relationship between the problem definitions, identified as per customer needs, and the design of the products physical parameters complying with the required specifications. Product development techniques like Reverse Engineering, Surface Modeling, and Rapid Prototyping technologies are employed to improve the existing design of a specific problem. These technologies are used for customization of product and are helpful for research and development purpose. In this paper, the outer body of an existing car is redesigned, and we have further created a prototype with improved aerodynamics and futuristic aesthetics. In this Additive Manufacturing (AM) process, Steinbichler 3D Scanner, Projet 3D printer and associated Scanning and printing software are used, by which redesign and associated development process of a car become easy in lesser time and cost.

scholarly journals Deep Learning for Recommender Systems: A Netflix Case Study

AI Magazine ◽  
2022 ◽  
Vol 42 (3) ◽  
pp. 7-18
Author(s):  
Harald Steck ◽  
Linas Baltrunas ◽  
Ehtsham Elahi ◽  
Dawen Liang ◽  
Yves Raimond ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Recommender Systems ◽  
Input Data ◽  
Lessons Learned ◽  
Learning Approaches ◽  
Learning Models ◽  
Learning Methods ◽  
Recommendation Algorithms

Deep learning has profoundly impacted many areas of machine learning. However, it took a while for its impact to be felt in the field of recommender systems. In this article, we outline some of the challenges encountered and lessons learned in using deep learning for recommender systems at Netflix. We first provide an overview of the various recommendation tasks on the Netflix service. We found that different model architectures excel at different tasks. Even though many deep-learning models can be understood as extensions of existing (simple) recommendation algorithms, we initially did not observe significant improvements in performance over well-tuned non-deep-learning approaches. Only when we added numerous features of heterogeneous types to the input data, deep-learning models did start to shine in our setting. We also observed that deep-learning methods can exacerbate the problem of offline–online metric (mis-)alignment. After addressing these challenges, deep learning has ultimately resulted in large improvements to our recommendations as measured by both offline and online metrics. On the practical side, integrating deep-learning toolboxes in our system has made it faster and easier to implement and experiment with both deep-learning and non-deep-learning approaches for various recommendation tasks. We conclude this article by summarizing our take-aways that may generalize to other applications beyond Netflix.

scholarly journals Video-based e-learning tools for geriatric nursing education

2021 ◽  
Vol 12 (4) ◽  
pp. 59
Author(s):  
Vera Habes ◽  
Alice Bakker ◽  
Thijs Aarts ◽  
Bianca Buurman
Keyword(s):  
Nursing Education ◽  
Nursing Students ◽  
Development Process ◽  
Lessons Learned ◽  
Geriatric Nursing ◽  
Learning Tools ◽  
E Learning ◽  
High Level ◽  
Student Centeredness ◽  
Clinical Reasoning Skills

Background: Future clinical challenges in nursing care of geriatric patients require educational courses that provide a high level of clinical reasoning skills. Serious Soap (www.serioussoap.nl/eng) is a video-based educational tool that combines entertainment with learning and reflection; it can serve as an attractive e-learning tool for nurses, nursing students, and tutors in geriatric care.Objective: This article describes Serious Soap’s development process, the lessons learned, and the most beneficial factors for student-centredness and teacher-centredness.Conclusions: The lessons learned from the development process highlight that it is important to use the experiences from previous gamification projects, co-create with target users, conduct elaborate testing and research before launching the final version, and ensure sustainability. The most valuable features for student-centeredness were the use of humor, authentic critical situations, popular actors, and interactivity. The most favorable aspects for teacher-centeredness were free accessibility of the tool, evidence-based content, and the possibility of using different features of the tool in various manners.

scholarly journals Integrated approach enabling robust and tolerance design in product concept development

2021 ◽  
Vol 7 ◽  
Author(s):  
Stefan Goetz ◽  
Philipp Kirchner ◽  
Benjamin Schleich ◽  
Sandro Wartzack
Keyword(s):  
Product Development ◽  
Development Process ◽  
User Study ◽  
Expert Knowledge ◽  
Integrated Approach ◽  
Concept Development ◽  
Tolerance Design ◽  
Concept Design ◽  
Product Concept ◽  
Tolerance Specification

Abstract Along with the ever-increasing customer demands, early consideration of variation in terms of robust design is important to avoid expensive iterations in the product development. However, existing methods are detached from the development process and can therefore only be applied at a late stage or only with comprehensive expert knowledge. Especially in the concept stage, where the geometry of a product is not yet defined and the optimisation potential is high, effective solution proposals for systematic consideration of variation are lacking. Therefore, this paper describes a new integrated approach facilitating robust and tolerance design in the concept stage. The novelty of the approach using ontologies and graph-based visualisation is the close linkage of product development and tolerance knowledge, which allows automation and helps to avoid time- and cost-intensive iteration loops. As a result, a robust and tolerance-compliant concept design, an initial qualitative tolerance specification and instructions for the further tolerancing process are already available at the end of the concept stage. The applicability and the benefits of the approach are illustrated by representative case studies and a user study allowing a critical comparison between the conventional, mostly subjective procedure and the presented approach.

scholarly journals Building a web-based app for persons with physical disabilities: A collaboration between game developers and rehabilitation researchers (Preprint)

2019 ◽  
Author(s):  
Alexandra Terrill ◽  
Justin J. MacKenzie ◽  
Maija Reblin ◽  
Jackie Tyne Einers ◽  
Jesse Ferraro ◽  
...  
Keyword(s):  
Mental Health ◽  
Software Development ◽  
Development Process ◽  
Physical Disabilities ◽  
End Users ◽  
Lessons Learned ◽  
Software Development Process ◽  
Web Based ◽  
Cord Injury

BACKGROUND Individuals with disability and their partners, who often provide care, are both at risk for depression and lower quality of life. Mobile health (mHealth) interventions are promising to address barriers for mental health care. Rehabilitation researchers and software development researchers must collaborate effectively with each other, and with clinical and patient stakeholders to ensure successful mHealth development. OBJECTIVE To aid researchers interested in mHealth software development by describing the collaborative process between a team of rehabilitation researchers, software development researchers, and stakeholders. Thus, we provide a framework (conceptual model) for other teams to replicate in order to build a web-based mHealth app for individuals with physical disability. METHODS Rehabilitation researchers, software development researchers, and stakeholders (people with physical disabilities and clinicians) are involved in an iterative software development process. The overall process to develop an mHealth intervention includes initial development meetings and a co-design method called “designbox”, in which the needs and key elements of the app are discussed. Based on the objectives outlined, a prototype is developed and goes through scoping iterations with feedback from stakeholders and end-users. The prototype is then tested by users to identify technical errors and gather feedback on usability and accessibility. RESULTS Illustrating the overall development process, we present a case study based on our experience developing an app (SupportGroove) for couples coping with spinal cord injury. Examples of how we addressed specific challenges are also included. For example, feedback from stakeholders resulted in development of app features for individuals with limited functional ability. Initial designs lacked accessibility design principles made visible by end-users. Solutions included large text, single-click, and minimal scrolling to facilitate menu navigation for individuals using eye-gaze technology. Prototype testing allowed further refinement and demonstrated high usability and engagement with activities in the app. Qualitative feedback indicated high levels of satisfaction, accessibility, and confidence in potential utility. We also present key lessons learned about working in a collaborative interdisciplinary team. CONCLUSIONS mHealth promises to help overcome barriers to mental health intervention access. However, the development of these interventions can be challenging because of the disparate and often siloed expertise required. By describing the mHealth software development process and illustrating it with a successful case study of rehabilitation researchers, software development researchers, and stakeholders collaborating effectively, our goal is to help other teams avoid challenges we faced and benefit from our lessons learned. Ultimately, good interdisciplinary collaboration will benefit individuals with disabilities and their families. CLINICALTRIAL n/a

scholarly journals Industrial Feedback on Implementing Functional Decomposition Design Processes for Reliability and Functional Safety

2018 ◽  
Vol 223 ◽  
pp. 01023
Author(s):  
Matt Pallaver ◽  
Ahed Qaddoura ◽  
Sung-hee Do
Keyword(s):  
System Development ◽  
Implementation Process ◽  
Axiomatic Design ◽  
Lessons Learned ◽  
Design Tool ◽  
Functional Requirements ◽  
Interface Elements ◽  
Systems Of Systems ◽  
Functional Decomposition ◽  
Design Processes

The value of Axiomatic Design functional decomposition as a design analysis point tool has been widely reported. This paper reports on the implementation of functional decomposition design processes as a system design tool on 23 industrial projects over a 5 year period with product development teams ranging from 6 to 35 engineers. The products developed were systems of systems with mechanical, electrical, firmware, software, and operational interface elements. Functional decompositions ranged from about 200 to 1600 Functional Requirements. A number of these projects are now in commercial production. This paper reviews the process definition and implementation process steps that evolved from these experiences. The paper then reports on the implementation lessons learned and the value propositions noted. Conclusions and recommendations are made. The experiences demonstrated that functional requirement decomposition processes aid in achieving on-time, on-cost and on-specification project development targets. The authors propose this paper summarizes the “Endgame” design process impact that axiomatic design can reasonably expect in industry design practices for system development.

scholarly journals CONCEPT DEVELOPMENT PROCESS FOR DOORS OF AUTONOMOUS VEHICLES

2021 ◽  
Vol 1 ◽  
pp. 701-710
Author(s):  
Adrian König ◽  
Patrick Neuhaus ◽  
Koch Alexander ◽  
Schockenhoff Ferdinand ◽  
Hafemann Philipp ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Early Phase ◽  
Development Process ◽  
User Study ◽  
Autonomous Driving ◽  
Concept Development ◽  
Vehicle Concept ◽  
Modular Architecture

AbstractVehicle doors have barely changed in recent decades, and nor has the car. Since autonomous driving will lead to changes in vehicles and how they are used, their doors will also have to be rethought. In the project UNICARagil, researchers from several universities in Germany design and build four prototypes of driverless and autonomous vehicles, which are developed based on a new and modular architecture. As part of this, we developed a concept including a prototype of an automated door system. In this paper, we present our concept development process adapted for door systems of autonomous vehicles. Based on the vehicle concept development process, it should help researchers and engineers to select and design new door concepts in an early phase. At the end, by means of an example, we present the prototype of our door concept as well as a boarding user study we carried out. This study helps evaluate and improve the boarding comfort of future door concepts.

Sign in / Sign up

Export Citation Format

Share Document