A Mobile sensing framework for audience emotion analysis

Kepucka, Eldjon
The main objective of this thesis is to develop a multi-modal framework which facilitates simple data collection using mobile sensing on smartphones from an audience, for the duration of an experimental study. Current solutions primarily rely on custom mobile sensing platforms which are expensive to develop and complicated to apply. While there are a number of mobile sensing platforms developed for smartphones targeting different domains, such as transportation and air pollution they are not designed to be used for simultaneous and synchronized data collection. The mobile sensing framework introduced in this study is focused primarily on addressing efficiency and reliability issues considering the limited resources of smartphone devices. The applicability of the framework spans cross research domains such as: emotion analysis, activity sensing, human body monitoring, and user-computer interaction. Moreover, as demonstrated in our pilot study, the introduced framework can find practical usage in industries such as advertisement and content evaluation. The applied design solution was based on the classical server-client architecture paradigm and the concrete implementation of the framework expresses high performance efficiency and comprehensive reach affirmed by our performance tests. The pilot study organized during FIFA World Cup 2014, where an audience of people was invited to watch two football matches, demonstrated the validity of our framework for real-life studies. Preliminary analysis exposes the potential of the acquired sensor data in targeted domains.


A Multi-perspective Analysis of Social Context and Personal Factors in Office Settings for the Design of an Effective Mobile Notification System
ÇAVDAR, ŞEYMA; Taşkaya Temizel, Tuğba; Musolesi, Mirco; Tino, Peter (2020-03-01)
In this study, we investigate the effects of social context, personal and mobile phone usage on the inference of work engagement/challenge levels of knowledge workers and their responsiveness to well-being related notifications. Our results show that mobile application usage is associated to the responsiveness and work engagement/challenge levels of knowledge workers. We also developed multi-level (within- and between-subjects) models for the inference of attentional states and engagement/challenge levels w...
A Multimodal sensor analysis framework for vehicular mobile applications
Orhan, Fatih; Eren, Pekin Erhan; Department of Information Systems (2013)
The sensing, computing and communicating capabilities of smart phones bring new possibilities for creating remarkable applications increasing the quality, safety, comfort, economy and other capabilities of cars. However, many challenges exist regarding the development of multimodal sensor analysis applications, such as proper collection of sensor values, integration of diverse libraries and tools for sharing the results. This study focuses on these challenges and aims to construct a framework that enables e...
A temporal neural network model for constructing connectionist expert system knowledge bases
Alpaslan, Ferda Nur (Elsevier BV, 1996-04-01)
This paper introduces a temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications.
A Study on quality assessment on mobile B2C applications
Yıldız, Ekrem; Bilgen, Semih; Department of Information Systems (2014)
This study aims to provide mechanisms to analyze the quality of the Business to Customer (B2C) mobile software products based on mobile-specific characteristics and quality factors, and sub-factors based on ISO 25010 product quality model which would help mobile software developers, designers and testers to develop more effective mobile applications. We aim to help development of more qualified and effective mobile applications from not only developers’ perspective but also endusers’ perspective. For this p...
A Hybrid geo-activity recommendation system using advanced feature combination and semantic activity similarity
Sattari, Masoud; Toroslu, İsmail Hakkı; Department of Computer Engineering (2013)
In this study, a new method for analyzing and representing the discriminative information, distributed in functional Magnetic Resonance Imaging (fMRI) data, is proposed. For this purpose, a local mesh with varying size is formed around each voxel, called the seed voxel. The relationships among each seed voxel and its neighbors are estimated using a linear regression equation by minimizing the expectation of the squared error. This squared error coming from linear regression is used to calculate various info...
Citation Formats
E. Kepucka, “A Mobile sensing framework for audience emotion analysis,” M.S. - Master of Science, Middle East Technical University, 2014.