权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

A Generalised Approach to Learning Models of Human Behaviour for Activity Recognition from Textual Instructions

从文本指令进行活动识别的人类行为学习模型的通用方法

基本信息

批准号：
314457946
负责人：
Professorin Dr.-Ing. Kristina Yordanova
金额：
--
依托单位：
Institut für Data Science
依托单位国家：
德国
项目类别：
Research Grants
财政年份：
2016
资助国家：
德国
起止时间：
2015-12-31 至 2018-12-31
项目状态：
已结题

来源：
https://gepris.dfg.de/gepris/projekt/314457946?language=en
关键词：
Generalised Approach Learning Models Human

项目摘要

Computational models for activity recognition aim at recognising the user actions and goals based on precondition-effect rules. One problem such approaches face, is how to obtain the model structure. To reduce the need of domain experts or sensor data during the model building, methods for learning models of human behaviour from textual data have been investigated. Existing approaches, however, make various simplifying assumptions during the learning process. This renders the model inapplicable for activity recognition problems. To address this problem, this project aims at developing a generalised methodology for learning the model structure from textual instructions. The methodology shall combine existing and novel methods for model learning.- A methodology for extracting the action semantics from text shall be developed. The methodology shall address the challenge of identifying causal relations between elements in texts with short and simple sentence structure.- To ensure the model generalisation and the incorporation of context information, methods for ontology learning shall be investigated. A core challenge here is the ontology extension based on causal, spatial, and functional properties of the entities in the problem domain.- To learn the model semantics, methods for language grounding shall be investigated. The semantics shall be represented in terms of precondition-effect rules. The resulting methodology shall address the issues associated with learning these rules and translating them into an appropriate for activity recognition format. It shall also address the problem of learning an optimal model through reinforcement learning methods.- To evaluate the methodology, the learned models shall be applied to various activity recognition tasks and their performance compared to that of handcrafted models.If successful, the methodology will reduce the time and resources needed for developing computational models of human behaviour for activity recognition.

活动识别的计算模型旨在基于前提-效果规则来识别用户行为和目标。这种方法面临的一个问题是如何获得模型结构。为了减少模型构建过程中对领域专家或传感器数据的需求，人们研究了从文本数据学习人类行为模型的方法。然而，现有方法在学习过程中做出了各种简化假设。这使得该模型不适用于活动识别问题。为了解决这个问题，该项目旨在开发一种从文本指令中学习模型结构的通用方法。该方法应结合现有的和新颖的模型学习方法。 - 应开发一种从文本中提取动作语义的方法。该方法应解决识别短句结构文本中元素之间因果关系的挑战。 - 为了确保模型泛化和上下文信息的纳入，应研究本体学习方法。这里的一个核心挑战是基于问题域中实体的因果、空间和功能属性的本体扩展。-为了学习模型语义，应研究语言基础的方法。语义应以前提-效果规则表示。由此产生的方法应解决与学习这些规则并将其转化为适合活动识别格式相关的问题。它还应解决通过强化学习方法学习最佳模型的问题。-为了评估该方法，学习的模型应应用于各种活动识别任务及其与手工模型相比的性能。如果成功，该方法将减少开发用于活动识别的人类行为计算模型所需的时间和资源。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Automatic Detection of Everyday Social Behaviours and Environments from Verbatim Transcripts of Daily Conversations

DOI：
10.1109/percom.2019.8767403
发表时间：
2019-03
期刊：
2019 IEEE International Conference on Pervasive Computing and Communications (PerCom
影响因子：
0
作者：
Kristina Yordanova;Burcu Demiray;M. Mehl;Mike Martin
通讯作者：
Kristina Yordanova;Burcu Demiray;M. Mehl;Mike Martin

Analysing Cooking Behaviour in Home Settings: Towards Health Monitoring †

DOI：
10.3390/s19030646
发表时间：
2019-02
期刊：
Sensors (Basel, Switzerland)
影响因子：
0
作者：
Kristina Yordanova;S. Lüdtke;Samuel Whitehouse;Frank Krüger;A. Paiement;M. Mirmehdi;I. Craddock;T. Kirste
通讯作者：
Kristina Yordanova;S. Lüdtke;Samuel Whitehouse;Frank Krüger;A. Paiement;M. Mirmehdi;I. Craddock;T. Kirste

Extracting Planning Operators from Instructional Texts for Behaviour Interpretation

DOI：
10.1007/978-3-030-00111-7_19
发表时间：
2018-09
期刊：
Geoderma
影响因子：
6.1
作者：
Kristina Yordanova
通讯作者：
Kristina Yordanova

Automatic Generation of Situation Models for Plan Recognition Problems

DOI：
10.26615/978-954-452-049-6_105
发表时间：
2017-11
期刊：
影响因子：
0
作者：
Kristina Yordanova
通讯作者：
Kristina Yordanova

Knowledge Extraction from Task Narratives

DOI：
10.1145/3134230.3134234
发表时间：
2017-09
期刊：
Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction
影响因子：
0
作者：
Kristina Yordanova;Carlos Monserrat Aranda;David Nieves;J. Hernández-Orallo
通讯作者：
Kristina Yordanova;Carlos Monserrat Aranda;David Nieves;J. Hernández-Orallo