scholarly journals Towards Regulatory-Compliant MLOps: Orazivio’s Journey from a Machine Learning Experiment to a Deployed Certified Medical Product

2021 ◽  
Vol 2 (5) ◽  
Author(s):  
Tuomas Granlund ◽  
Vlad Stirbu ◽  
Tommi Mikkonen
Keyword(s):  
Machine Learning ◽  
Joint Replacement ◽  
Medical Product ◽  
Medical Software ◽  
Continuous Delivery ◽  
Development Approach ◽  
Responding To Change ◽  
Agile Software ◽  
Engineering Practices

AbstractAgile software development embraces change and manifests working software over comprehensive documentation and responding to change over following a plan. The ability to continuously release software has enabled a development approach where experimental features are put to use, and, if they stand the test of real use, they remain in production. Examples of such features include machine learning (ML) models, which are usually pre-trained, but can still evolve in production. However, many domains require more plan-driven approach to avoid hazard to environment and humans, and to mitigate risks in the process. In this paper, we start by presenting continuous software engineering practices in a regulated context, and then apply the results to the emerging practice of MLOps, or continuous delivery of ML features. Furthermore, as a practical contribution, we present a case study regarding Oravizio, first CE-certified medical software for assessing the risks of joint replacement surgeries. Towards the end of the paper, we also reflect the Oravizio experiences to MLOps in regulatory context.

Fixed Priced Projects in Agile

2016 ◽  
pp. 222-236
Author(s):  
Anuradha Chaminda Gajanayaka
Keyword(s):  
Software Development ◽  
Agile Software Development ◽  
Development Model ◽  
Software Development Model ◽  
Responding To Change ◽  
The One ◽  
Agile Software ◽  
Development Methods ◽  
Software Development Methods

Agile software development has established as a reliable alternative to waterfall software development model. Unfortunately the use of agile software development has been limited to time based contracts and not for time limited contracts. The main reason for this limitation is the “Agile manifesto” itself. The forth value of the manifesto states that agile believers find more value in “Responding to change over following a plan”. This is the one of the main reasons why agile software development methods are not preferred for a fixed priced contract or time limited contract. The following case study provides an example on how the agile software development can be used for fixed priced software development contracts even when operating in offshore context. The agile software development concepts were used throughout to plan, execute, monitor, report, etc. for the project documented in this case study.

scholarly journals Cognitive Service Virtualisation: A New Machine Learning-Based Virtualisation to Generate Numeric Values

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5664 ◽  
Author(s):  
Zeinab Farahmandpour ◽  
Mehdi Seyedmahmoudian ◽  
Alex Stojcevski ◽  
Irene Moser ◽  
Jean-Guy Schneider
Keyword(s):  
Machine Learning ◽  
Empirical Evaluation ◽  
Variable Number ◽  
Ease Of Use ◽  
Machine Learning Techniques ◽  
Data Sets ◽  
Ripple Effects ◽  
Learning Techniques ◽  
Continuous Delivery ◽  
Development Approach

Continuous delivery has gained increased popularity in industry as a development approach to develop, test, and deploy enhancements to software components in short development cycles. In order for continuous delivery to be effectively adopted, the services that a component depends upon must be readily available to software engineers in order to systematically apply quality assurance techniques. However, this may not always be possible as (i) these requisite services may have limited access and (ii) defects that are introduced in a component under development may cause ripple effects in real deployment environments. Service virtualisation (SV) has been introduced as an approach to address these challenges, but existing approaches to SV still fall short of delivering the required accuracy and/or ease-of-use to virtualise services for adoption in continuous delivery. In this work, we propose a novel machine learning based approach to predict numeric fields in virtualised responses, extending existing research that has provided a way to produce values for categorical fields. The SV approach introduced here uses machine learning techniques to derive values of numeric fields that are based on a variable number of pertinent historic messages. Our empirical evaluation demonstrates that the Cognitive SV approach can produce responses with the appropriate fields and accurately predict values of numeric fields across three data sets, some of them based on stateful protocols.

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.

scholarly journals Digital Transformation of Forest Services in Finland—A Case Study for Improving Business Processes

Forests ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 781
Author(s):  
Ville Kankaanhuhta ◽  
Tuula Packalen ◽  
Kari Väätäinen
Keyword(s):  
Business Processes ◽  
Innovation Process ◽  
Single Type ◽  
Stand Management ◽  
Young Stand ◽  
Commercial Viability ◽  
Soil Preparation ◽  
Knowledge Intensive ◽  
Agile Software

This case study introduces an innovation and development concept for agile software tools for the improvement of the productivity and customer experience of forest services. This need was recognized in the context of the opening of forest data and the development of service platforms for a forest-based bioeconomy in Finland. The forest services that were studied covered a continuum from a single type of work, e.g., soil preparation and young stand management through timber procurement, to comprehensive forest property management services. The study concentrated on the needs of micro-, small, and medium-sized enterprises (SMEs), which provide either retail- or business to business (B2B) services as sub-contractors. In addition, the challenges and bottlenecks in service processes detected by other stakeholders were considered. The prevailing service processes were conceptually modelled in order to search for opportunities for improvements in business and ecosystem services, i.e., agile software concepts. For example, we examined whether it would be possible to create opportunities for flexible operational models for precision, resilience, and protection of valuable microsites in forests. These software concepts were developed and evaluated in co-operation with the stakeholders in a co-creative workshop. The technological feasibility and commercial viability of the concepts, as well as the desirability for the customer were considered. The results of this business development process—i.e., agile software concepts and their anticipated benefits—were provided for further evaluation. In addition to the practical implications of this kind of innovation process tested, the potential of these kinds of agile tools for the further development of knowledge-intensive service processes was further discussed.

Sign in / Sign up

Export Citation Format

Share Document