This report focuses on improving classification accuracy and reducing computational complexity for human activity recognition problem on public datasets UCI and WISDM. We discussed the benefits of getting access to smartphones in the filed of HAR research. Our experiment indicates that combining AdaBoost M1 algorithm with C4.5 contributes to discriminating several common human activities. Moreover, we showed that it is feasible to reduce computational complexity and achieve high accuracy at the same time by applying correlation-based feature selection.
Digital publishing unarguably has brought about many advantages for the dissemination of research findings. The distribution of research papers --- a format which has been used to present original data during the past 350 years --- has become faster, more affordable, longer lasting and content can be customised by the reader as publications can be assessed individually.
Yet, these are incremental innovations --- a pdf remains a linear narrative, contextualised in a manner that demands human interpretation. This fundamental and largely unchanged workflow often leads to suboptimal presentation of data within publications or even omission of making data publicly available. In addition, the unique potentials of digital technologies in terms of enhancing, curating and commenting content are barely being tapped.
We will discuss the impact of collaborative and dynamic authoring and publishing technologies and contemplate on what we think of as scholarly output of individual researchers. At the same time we will embark on our own collaborative authoring project and produce live session notes using writelatex.com --- everyone’s input is more than welcome!
SpotOn London 2013 Session Participants