Both Software Engineering and Machine Learning have become recognized disciplines. In this article I analyse the combination of the two: engineering of machine learning applications. I believe the systematic way of working for machine learning applications is at certain points different from traditional (rule-based) software engineering. The question I set out to investigate is “How does software engineering change when we develop machine learning applications”?. This question is not an easy to answer and turns out to be a rather new, with few publications. This article collects what I have found until now.
LINK
In the fall of 1999, an international integrated product development pilot project based on collaborative engineering was started with team members in two international teams from the United States, The Netherlands and Germany. Team members interacted using various Internet capabilities, including, but not limited to, ICQ (means: I SEEK YOU, an internet feature which immediately detects when somebody comes "on line"), web phones, file servers, chat rooms and Email along with video conferencing. For this study a control group with all members located in the USA only also worked on the same project.
From the article: This paper describes the external IT security analysis of an international corporate organization, containing a technical and a social perspective, resulting in a proposed repeatable approach and lessons learned for applying this approach. Part of the security analysis was the utilization of a social engineering experiment, as this could be used to discover employee related risks. This approach was based on multiple signals that indicated a low IT security awareness level among employees as well as the results of a preliminary technical analysis. To carry out the social engineering experiment, two techniques were used. The first technique was to send phishing emails to both the system administrators and other employees of the company. The second technique comprised the infiltration of the office itself to test the physical security, after which two probes were left behind. The social engineering experiment proved that general IT security awareness among employees was very low. The results allowed the research team to infiltrate the network and have the possibility to disable or hamper crucial processes. Social engineering experiments can play an important role in conducting security analyses, by showing security vulnerabilities and raising awareness within a company. Therefore, further research should focus on the standardization of social engineering experiments to be used in security analyses and further development of the approach itself. This paper provides a detailed description of the used methods and the reasoning behind them as a stepping stone for future research on this subject. van Liempd, D., Sjouw, A., Smakman, M., & Smit, K. (2019). Social Engineering As An Approach For Probing Organizations To Improve It Security: A Case Study At A Large International Firm In The Transport Industry. 119-126. https://doi.org/10.33965/es2019_201904l015
MULTIFILE
In the past decade additive manufacturing has gained an incredible traction in the construction industry. The field of 3D concrete printing (3DCP) has advanced significantly, leading to commercially viable housing projects. The use of concrete represents a challenge because of its environmental impact and CO2 footprint. Due to its material properties, structural capacity and ability to take on complex geometries with relative ease, concrete is and will remain for the foreseeable future a key construction material. The framework required for casting concrete, in particular non-orthogonal geometries, is in itself wasteful, not reusable, contributing to its negative environmental impact. Non-standard, complex geometries generally require the use of moulds and subsystems to be produced, leading to wasteful, material-intense manufacturing processes, with high carbon footprints. This research proposal bypasses the use of wasteful scaffolding and moulds, by exploring 3D printing with concrete on reusable substructures made of sand, clay or aggregate. Optimised material depositing strategies for 3DCP will be explored, by making use of algorithmic structural optimisation. This way, material is deposited only where structurally needed, allowing for further reduction of raw-material use. This collaboration between Neutelings Riedijk Architects, Vertico and the Architectural Design and Engineering Chair of the TU Eindhoven, investigates full-scale additive manufacturing of spatially complex 3D-concrete printed components using multi-material support systems (clay, sand and aggregates). These materials can be easily shaped multiple times into substrates with complex geometries, without generating material waste. The 3D concrete printed full-scale prototypes can be used as lightweight façade elements, screens or spatial dividers. To generate waterproof components, the cavities of the extruded lattices can be filled up with lightweight clay or cement. This process allows for the exploration of new aesthetic, creative and circular possibilities, complex geometries and new material expressions in architecture and construction, while reducing raw-material use and waste.
Human kind has a major impact on the state of life on Earth, mainly caused by habitat destruction, fragmentation and pollution related to agricultural land use and industrialization. Biodiversity is dominated by insects (~50%). Insects are vital for ecosystems through ecosystem engineering and controlling properties, such as soil formation and nutrient cycling, pollination, and in food webs as prey or controlling predator or parasite. Reducing insect diversity reduces resilience of ecosystems and increases risks of non-performance in soil fertility, pollination and pest suppression. Insects are under threat. Worldwide 41 % of insect species are in decline, 33% species threatened with extinction, and a co-occurring insect biomass loss of 2.5% per year. In Germany, insect biomass in natural areas surrounded by agriculture was reduced by 76% in 27 years. Nature inclusive agriculture and agri-environmental schemes aim to mitigate these kinds of effects. Protection measures need success indicators. Insects are excellent for biodiversity assessments, even with small landscape adaptations. Measuring insect biodiversity however is not easy. We aim to use new automated recognition techniques by machine learning with neural networks, to produce algorithms for fast and insightful insect diversity indexes. Biodiversity can be measured by indicative species (groups). We use three groups: 1) Carabid beetles (are top predators); 2) Moths (relation with host plants); 3) Flying insects (multiple functions in ecosystems, e.g. parasitism). The project wants to design user-friendly farmer/citizen science biodiversity measurements with machine learning, and use these in comparative research in 3 real life cases as proof of concept: 1) effects of agriculture on insects in hedgerows, 2) effects of different commercial crop production systems on insects, 3) effects of flower richness in crops and grassland on insects, all measured with natural reference situations
