6 Works

Recognising the actions during cooking task (Cooking task dataset)

Frank Krüger, Albert Hein, Kristina Yordanova & Thomas Kirste
The dataset contains the data of acceleration sensors attached to a person during the execution of a kitchen task. It consists of 7 datasets that describe the execution of preparing and having a meal: preparing the ingredients, cooking, serving the meal, having a meal, cleaning the table, and washing the dishes. The aim of the experiment is to investigate the ability of activity recognition approaches to recognise fine-grained user activities based on acceleration data. The...

Detecting high-level team intentions (Three person meeting dataset)

Thomas Kirste
The dataset contains 20 recordings of scripted meetings and an annotation of the performed activities. Three persons (A, B and C) attend the meeting. Each member holds a presentation, and the meeting concludes with a common discussion. This dataset contains the individual team members positions as recorded by an indoor positioning systems.

Time series from textual instructions for causal relations discovery (Causal relations dataset)

Kristina Yordanova
One aspect of ontology learning methods is the discovery of relations in textual data. One kind of such relations are causal relations. Our aim is to discover causations described in texts such as recipes and manuals. There is a lot of research on causal relations discovery that is based on grammatical patterns. These patterns are, however, rarely discovered in textual instructions (such as recipes) with short and simple sentence structure. Therefore we use time series...

Anonymous activity recognition in an office environment (office tasks dataset)

Thomas Kirste
This datasets contains measurements of pressure mats generated by users performing tasks in a faked office environment. Annotation describe the real activities performed by the users. One, two or three persons enter an office room and two tasks to perform: get some coffee, and print a paper. The coffee machine requires water and ground coffee, paper is required for printing. These resources may already be at the coffee machine or the printer, or must be...

Probabilistic action selection - Tracking multiple persons in indoor environments

Martin Kasparick & Frank Krüger
Sensor data recording of multiple (1-7) interacting persons in indoor environments by use passive infrared sensors. The dataset was recorded in the context of the diploma thesis of Martin Kasparick.

Evaluation of Requirements for Human Behaviour Modelling for Activity Recognition (Questionnaire Dataset)

Kristina Yordanova
The study took place during the PhD thesis of Kristina Yordanova. 17 study participants were asked to answer the questions concerning the importance of 18 requirements for activity recognition. Each of the requirements was evaluated according to software engineering features. The requirements and their features are formally described in the PhD thesis "Methods for Engineering Computational Causal Behaviour Models" by Kristina Yordanova. Apart from the requirements, the following data was gathered: suitable modelling formalism according...

Registration Year

  • 2015
    6

Resource Types

  • Dataset
    6