The final goal of all industrial machine learning (ML) projects is to develop ML products and rapidly bring them into production. However, it is highly challenging to automate and operationalize ML products and thus many ML endeavors fail to deliver on their expectations. The paradigm of Machine Learning Operations (MLOps) addresses this issue. MLOps includes several aspects, such as best practices, sets of concepts, and development culture. However, MLOps is still a vague term and its consequences for researchers and professionals are ambiguous. To address this gap, we conduct mixed-method research, including a literature review, a tool review, and expert interviews. As a result of these investigations, we contribute to the body of knowledge by providing an aggregated overview of the necessary principles, components, and roles, as well as the associated architecture and workflows. Furthermore, we provide a comprehensive definition of MLOps and highlight open challenges in the field. Finally, this work provides guidance for ML researchers and practitioners who want to automate and operate their ML products with a designated set of technologies.

Machine Learning Operations (MLOps): Overview, Definition, and Architecture

Global trends and characteristics of ecological security research in the early 21st century: A literature review and bibliometric analysis

This review article focuses on use of an escape room as a didactic tool in teaching and learning, as identified in empirical studies that have examined the use of escape rooms in educational contex...

https://www.tandfonline.com/doi/pdf/10.1080/20004508.2020.1860284

A review on use of escape rooms in education – touching the void

In the post-pandemic era, we must value our cities as cultural and economic centres, that are socially and environmentally diverse. This requires a transformation in the way we plan and govern our cities, but what can be learnt from the current crisis about how cities should be managed? In this article, we report on a scoping review to help identify seven lessons learnt for cities from the COVID-19 pandemic. We build on these lessons through a synthesis, outlining three urban missions that will chart a green urban recovery. The missions are to accelerate the urban mobility transition; to attain regenerative urban development; and create resilient urban infrastructure. We expand on what these missions entail, by defining six pathways that supports transition of urban mobility, energy, food, housing, health and nature. These pathways, when implemented in an integrated manner, provides a roadmap for green recovery in cities, that also builds resilience.

Accelerating a green recovery of cities: Lessons from a scoping review and a proposal for mission-oriented recovery towards post-pandemic urban resilience

The COVID-19 pandemic caused a large and involuntary shift to work from home (WFH) or teleworking, and widespread adoption of web-based platforms. This study aims to uncover the attitude and perception of WFH and online education among students and employees of the University of Ljubljana. A web-based questionnaire survey was conducted in November 2020, and more than 1300 valid responses were received. The lack of daily commuting, improved eating habits, and more time available for a family were the main reported advantages of WFH. The main issues, highlighted by respondents, were higher stress levels, lower study/work efficiency, and poorer working environment at home. When comparing the online educational process with the traditional one, the absence of traditional laboratory work, inadequate social interactions, and limitations of online knowledge assessment were identified as drawbacks by both students and educators. A significant difference between students and educators was observed in their opinion on the efficiency of online lectures compared to traditional ones, with the former being significantly more favored by students than educators. Overall, the majority of the respondents from all groups wish for the pre-COVID-19 study/work mode to be established as soon as possible. This implies that the perceived drawbacks of online education outweigh its advantages.

https://www.mdpi.com/2071-1050/13/9/5118/pdf

Difference in the Attitude of Students and Employees of the University of Ljubljana towards Work from Home and Online Education: Lessons from COVID-19 Pandemic

Exit for success. Gamifying science and technology for university students using escape-room. A preliminary approach

The unprecedented urban growth of recent years requires improved urban planning and management to make urban spaces more inclusive, safe, resilient and sustainable. Additionally, humanity faces the COVID pandemic, which especially complicates the management of Smart Cities. A possible solution to address these two problems (environmental and health) in Smart Cities may be the use of Machine Learning techniques. One of the objectives of our work is to thoroughly analyze the link between the concepts of Smart Cities, Machine Learning techniques and their applicability. In this work, an exhaustive study of the relationship between Smart Cities and the applicability of Machine Learning (ML) techniques is carried out with the aim of optimizing sustainability. For this, the ML models, analyzed from the point of view of the models, techniques and applications, are studied. The areas and dimensions of sustainability addressed are analyzed, and the Sustainable Development Goals (SDGs) are discussed. The main objective is to propose a model (EARLY) that allows us to tackle these problems in the future. An inclusive perspective on applicability, sustainability scopes and dimensions, SDGs, tools, data types and Machine Learning techniques is provided. Finally, a case study applied to an Andalusian city is presented.

https://www.mdpi.com/2071-1050/12/22/9320/pdf

Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

Analysis of the evolution of the sharing economy towards sustainability. Trends and transformations of the concept

The management of mobility in large cities is a complex issue of great interest due to its economic, social, and environmental impact. In this work, the interurban mobility of engineering students from two campuses of the University of Seville is studied. Specifically, this work carries out an analysis of the preferences of students in terms of mobility to their study centres and determines the environmental impact of such mobility in terms of kg of CO2 per student. Three constructs can be found to describe the motivation for their choice of transport: those related to comfort and speed, those related to sustainability and price, and those related to safety. Based on the responses obtained, groups of students are established that enable the design of specific actions in accordance with each of the profiles. From the analysis of the results obtained, recommendations are made for policymakers, and a reflection is given on the impact of the COVID-19 pandemic on this issue.

https://www.mdpi.com/1660-4601/17/24/9348/pdf

Amalia Luque-Sendra

Papers

Exit for success. Gamifying science and technology for university students using escape-room. A preliminary approach

Machine Learning Technologies for Sustainability in Smart Cities in the Post-COVID Era

Analysis of the evolution of the sharing economy towards sustainability. Trends and transformations of the concept

Analysis of Interurban Mobility in University Students: Motivation and Ecological Impact.