Fine-tuning of a deep convolutional neural network (CNN) is o‰en desired. Œis paper provides an overview of our publicly available py-faster-rcnn-… so‰ware library that can be used to €ne-tune the VGG CNN M 1024 model on custom subsets of the Microso‰ Common Objects in Context (MS COCO) dataset. For example, we improved the procedure so that the user does not have to look for suitable image €le...

In the database field, while very strong mathematical and engineering work has been done, the scientific approach has been much less prominent. The deep understanding of query optimizers obtained through the scientific approach can lead to better engineered designs. Unlike other domains, there have been few DBMS-dedicated laboratories, focusing on such scientific investigation. In this demonstr...

Swimming pool surveillance systems plays an essential role in safeguarding the premises. The main purpose of this project is to design a safety swimming pool. We present in this paper human movement approach to detection of drowning incidents in swimmingpools at the earliest possible stage.This is done by preventing the children from drowning in the swimming pool by lifting the iron plate.The p...

Cognitive diagnosis is aimed at inferring the degree of cognitive state from observations. This paper considers cognitive diagnosis as an instance of model-based diagnosis, which has been studied in artificial intelligence for many years. The model-based cognitive diagnosis we present runs on a model of students’ courses in terms of knowledge items that they may learn, tests them and helps them...

This paper supports the demo of LXListQuestion, a Web Question Answering System that exploit the redundancy of information available in the Web to answer List Questions in the form of Word Cloud.

Transition-based dependency parsers are widely used in the Natural Language Processing community but they are normally treated as black boxes, assuming that they provide the dependency parsing of a set of examples. We present MaltDiver, a tool developed to visualize the transitions performed by the transition-based parsers included in MaltParser and to show how the parsers interact with the sen...

Despite advances in the field of workflow flexibility, there is still insufficient support for dealing with unforeseen exceptions. In particular, it is challenging to find a solution which preserves the intent of the process as much as possible when such exceptions are encountered. This challenge can be alleviated by making the connection between a process and its objectives more explicit. This...

The assessment of variations in maternal behavior in laboratory rodents is challenging yet may provide an essential tool for understanding the mechanisms linking early life experiences to individual differences in stress responsivity and behavioral indices of depression and anxiety. In this chapter, the methodology for characterizing the quality and quantity of mother–pup interactions in mice a...

This paper demonstrates so-called sentinels in the TARGIT BI Suite. Sentinels are a novel type of rules that can warn a user if one or more measure changes in a multi-dimensional data cube are expected to cause a change to another measure critical to the user. We present the concept of sentinels, and we explain how sentinels represent stronger and more specific rules than sequential patterns an...