Tarun Kumar

Tarun Kumar, Himanshu Sharad Bhatt

Existing metrics used to evaluate table structure recognition algorithms have shortcomings with regard to capturing text and empty cells alignment. In this paper, we build on prior work and propose a new metric - TEDS based IOU similarity (TEDS (IOU)) for table structure recognition which uses bounding boxes instead of text while simultaneously being robust against the above disadvantages. We demonstrate the effectiveness of our metric against previous metrics through various examples.

Yakup Koc, Abhishek Raman, Martijn Warnier et al.

Power grid outages cause huge economical and societal costs. Disruptions in the power distribution grid are responsible for a significant fraction of electric power unavailability to customers. The impact of extreme weather conditions, continuously increasing demand, and the over-ageing of assets in the grid, deteriorates the safety of electric power delivery in the near future. It is this dependence on electric power that necessitates further research in the power distribution grid security assessment. Thus measures to analyze the robustness characteristics and to identify vulnerabilities as they exist in the grid are of utmost importance. This research investigates exactly those concepts- the vulnerability and robustness of power distribution grids from a topological point of view, and proposes a metric to quantify them with respect to assets in a distribution grid. Real-world data is used to demonstrate the applicability of the proposed metric as a tool to assess the criticality of assets in a distribution grid.