Beneftis of modularity and module level tests

Many companies implement a modular architecture to support the need to create more variants with less effort. Although the modular architecture has many benefits, the tests to detect any defects become a major challenge. However, a modular architecture with defined functional elements seems beneficial to test at module level, so called MPV (Module Property Verification). This paper presents studies from 29 companies with the purpose of showing trends in the occurrence of defects and how these can support the MPV.

Can qualitative methods support the development of more flexible and energy saving thermal comfort?

This paper uses examples from a Swedish study to suggest some ways in which cultural variation could be included in studies of thermal comfort. It is shown how only a slight shift of focus and methodological approach could help us discover aspects of human life that add to previous knowledge within comfort research of how human beings perceive and handle warmth and cold. It is concluded that it is not enough for buildings, heating systems and thermal control devices to be energy-efficient in a mere technical sense. If these are to help to decrease, rather than to increase, energy consumption, they have to support those parts of already existing habits and modes of thought that have the potential for low energy use. This is one reason why culture-specific features and emotional cores need to be investigated and deployed into the study and development of thermal comfort.

Machine Learning Algorithms in Heavy Process Manufacturing

In a global economy, manufacturers mainly compete with cost efficiency of production, as the price of raw materials are similar worldwide. Heavy industry has two big issues to deal with. On the one hand there is lots of data which needs to be analyzed in an effective manner, and on the other hand making big improvements via investments in cooperate structure or new machinery is neither economically nor physically viable. Machine learning offers a promising way for manufacturers to address both these problems as they are in an excellent position to employ learning techniques with their massive resource of historical production data. However, choosing modelling a strategy in this setting is far from trivial and this is the objective of this article. The article investigates characteristics of the most popular classifiers used in industry today. Support Vector Machines, Multilayer Perceptron, Decision Trees, Random Forests, and the meta-algorithms Bagging and Boosting are mainly investigated in this work. Lessons from real-world implementations of these learners are also provided together with future directions when different learners are expected to perform well. The importance of feature selection and relevant selection methods in an industrial setting are further investigated. Performance metrics have also been discussed for the sake of completion.