Ali Mehmood Khan

Recognizing Emotion from Blood Volume Pulse and Skin Conductance Sensor Using Machine Learning Algorithms

Recognizing emotional states is becoming a major part of a user’s context for wearable computing applications. The system should be able to acquire a user’s emotional states by using physiological sensors. We want to develop a personal emotional states recognition system that is practical, reliable, and can be used for health-care related applications. We propose to use the eHealth platform [1] which is a ready-made, light weight, small and easy to use device for recognizing a few emotional states like ‘Sad’, ‘Dislike’, ‘Joy’, ‘Stress’, ‘Normal’, ‘No-Idea’, ‘Positive’ and ‘Negative’ using decision tree (J48) and IBK classifiers. In this chapter, we present an approach to build a system that exhibits this property and provides evidence based on data for 8 different emotional states collected from 24 different subjects. Our results indicate that the system has an accuracy rate of approximately 92%. In our work, we used two physiological sensors (i.e. ‘Blood Volume Pulse’ and ‘Galvanic Skin Response’) in order to recognize emotional states (i.e. stress, joy/happy, sad, normal/neutral, dislike, no-idea, positive and negative).

Wearable Recognition System for Physical Activities

Physical activity is a major part of a users context for wearable computing applications. The system should be able to acquire the users physical activities by using body worn sensors. We want to develop a personal activity recognition system that is practical, reliable, and can be used for health-care related applications. We propose to use the axivity device [1] which is a ready-made, light weight, small and easy to use device for identifying basic physical activities like lying, sitting, walking, standing, cycling, running, ascending and descending stairs using decision tree classifier. In this paper, we present an approach to build a system that exhibits this property and provides evidence based on data for 8 different activities collected from 12 different subjects. Our results indicate that the system has a good accuracy rate.

Recognizing Emotional States Using Physiological Devices

Emotional computing is a field of human computer interaction where a system has the ability to recognize emotions and react accordingly. Recognizing Emotional states is becoming a major part of a user’s context for wearable computing applications. The system should be able to acquire the user’s emotional states by using physiological sensors. We want to develop a personal emotional states recognition system that is practical, reliable, and can be used for health-care related applications. We propose to use the eHealth platform which is a ready-made, light weight, small and easy to use device for recognizing few Emotional states like Sad, Dislike, Joy, Stress, Normal, NoIdea, Positive and Negative using decision tree classifier. In this paper, we present an approach to build a system that exhibits this property and provides evidence based on data for 8 different emotional states collected from 24 different subjects. Our results indicate that the system has an accuracy rate of approximately 91 %. In our work, we used three physiological sensors (i.e. BVP, GSR and EMG) in order recognize Emotional states (i.e. Stress, joy/Happy, sad, normal/Neutral, dislike and no idea).

Wearable Health Monitoring System

One of the major scientific undertakings over the past few years has been exploring the interaction between humans and machines in mobile environments. In this work, we will examine how to utilize existing technology in order to build eHealth system for the heart patients. This system should be able to establish an interaction between patients and health physician so that patients don’t need to visit clinic every time.

Hardware and Software for Solving the Serious Game Challenge Using Commercial Off-the-Shelf Components and Open Source Software Frameworks

The purpose of this book chapter is to show how to solve the problem of selection of an appropriate hardware and software. This is a challenge for any non-standardized application domain and a problem any research project has when looking for a general purpose solution for a specific problem. Here we target the evaluation of a Reference Rehabilitation Platform (RRP) for Serious Games. One constraint in such a case is that all components should be commercial off-the-shelf during the runtime of the project. Components should be well tested, provide sufficient firmware and documentation for integration and have the potential of becoming a kind of standard in the market. This is essential, as the focus of any such project is the problem solution and its evaluation of the hardware and software. We propose a platform where different Serious Games can be deployed and input devices as bio sensors can be plugged in easily. We developed a solution where these components can be replaced by new components easily without changing the whole architecture. This book chapter addresses technical issues and provides an idea how to integrate Serious Games for rehabilitation purposes as described in the chapter four.

Recognizing Emotional States An Approach Using Physiological Devices

Recognizing emotional states is becoming a major part of user context for wearable computing applications. The approach presented here starts from the research hypothesis that a wearable system can acquire a user’s emotional state by using physiological sensors. The purpose is to develop a personal emotional states recognition system that is practical, reliable, and can be used for health-care related applications. We use, as book chapter three described, the eHealth platform [1] which is a ready-made, light weight, small and easy to use device. The intension is to recognize emotional states like ‘Sad’, ‘Dislike’, ‘Joy’, ‘Stress’, ‘Normal’, ‘No-Idea’, ‘Positive’ and ‘Negative’ using a decision tree classifier. In this chapter, we present an approach that exhibits this property and provides evidence based on data for eight different emotional states collected from 24 different subjects. Our results indicate that the system has an accuracy rate of approximately 98%.