The past two years I have conducted an extensive literature and tool review to answer the question: “What should software engineers learn about building production-ready machine learning systems?”. During my research I noted that because the discipline of building production-ready machine learning systems is so new, it is not so easy to get the terminology straight. People write about it from different perspectives and backgrounds and have not yet found each other to join forces. At the same time the field is moving fast and far from mature. My focus on material that is ready to be used with our bachelor level students (applied software engineers, profession-oriented education), helped me to consolidate everything I have found into a body of knowledge for building production-ready machine learning (ML) systems. In this post I will first define the discipline and introduce the terminology for AI engineering and MLOps.
LINK
The past two years I have conducted an extensive literature and tool review to answer the question: “What should software engineers learn about building production-ready machine learning systems?”. During my research I noted that because the discipline of building production-ready machine learning systems is so new, it is not so easy to get the terminology straight. People write about it from different perspectives and backgrounds and have not yet found each other to join forces. At the same time the field is moving fast and far from mature. My focus on material that is ready to be used with our bachelor level students (applied software engineers, profession-oriented education), helped me to consolidate everything I have found into a body of knowledge for building production-ready machine learning (ML) systems. In this post I will first define the discipline and introduce the terminology for AI engineering and MLOps.
LINK
Long-term care facilities are currently installing dynamic lighting systems with the aim to improve the well-being and behaviour of residents with dementia. The aim of this study was to investigate the implementation of dynamic lighting systems from the perspective of stakeholders and the performance of the technology. Therefore, a questionnaire survey was conducted with the management and care professionals of six care facilities. Moreover, light measurements were conducted in order to describe the exposure of residents to lighting. The results showed that the main reason for purchasing dynamic lighting systems lied in the assumption that the well-being and day/night rhythmicity of residents could be improved. The majority of care professionals were not aware of the reasons why dynamic lighting systems were installed. Despite positive subjective ratings of the dynamic lighting systems, no data were collected by the organizations to evaluate the effectiveness of the lighting. Although the care professionals stated that they did not see any large positive effects of the dynamic lighting systems on the residents and their own work situation, the majority appreciated the dynamic lighting systems more than the old situation. The light values measured in the care facilities did not exceed the minimum threshold values reported in the literature. Therefore, it seems illogical that the dynamic lighting systems installed in the researched care facilities will have any positive health effects.
