A Study on the Active Vector Model for Object Tracking

In this thesis we propose a new active vector model which is able to track objects with an algorithm. First of all we classified a few basic shapes as the modes of the tracking object, which were learned by the principle components analysis, and then we extracted the representative feature vector and the minimum shape parameters. And we reorganize the sequence of basic shape change to the shape change based on the feature point vector. We modeled the object of target tracking and its moving using both the feature position vector and shape change vector obtained by the above process. The proposed method generates parameterized values based on the moving pattern of the object, provides better stability of the local structure than other models, and decreases the cost of convergence duration, which is the weakness of model-based tracking algorithms.

Spatiotemporal Identification of Moving Patterns on a Fingertip-based Electro-Tactile Display Array

An electro-tactile display can be used to stimulate sensations in the skin. The ultimate achievement in this area is to open a new information communication channel using this sensory substitution system. One of the requirement of such communication channel is to deliver meaningful commands to the user. The sensations should be distinctive enough to be readily understandable for the operator.<br>This study is perusing the feasibility of generating identifiable moving patterns in the electro-tactile display. Then, the degree of identification performed by the users will be validated.<br><br>An electro-tactile display is built using an array of sixteen contacts to form a moving pattern by delivering electrical signal to the fingertip skin.<br>This signal can have varying voltages, frequencies or duty cycles to form the most comfortable sensation.<br>Moving patterns can be generated by individually or collectively toggling the electrical contacts on the electro-tactile display. This will achieve a stimulation of a moving pattern. In this regard, a moving pattern can be compared to a set of frame-by-frame pictures that construct a movie. Similarly, by toggling the contacts in a specific order, a moving pattern can be achieved.<br><br>In this study, eight subjects participated. A questionnaire was used to assess the sensation of the corresponding movement.<br>The results of these reports were analyzed and a conclusion regarding the identification of the direction of the movement was drawn. It became clear that the direction of the movement had a significant impact on the recognition of the patterns.<br><br>Furthermore, an analysis of the detection threshold (DT) voltage and current mapping was performed to evaluate the effect of the internal structure of the skin for each user on the assessment performance.<br>Based on the mapping results, it became clear that the DT voltage is vastly different for each contact and the resulting spatial map is also unique to each user.

Spatiotemporal Identification of Moving Patterns on a Fingertip-based Electro-Tactile Display Array

An electro-tactile display can be used to stimulate sensations in the skin. The ultimate achievement in this area is to open a new information communication channel using this sensory substitution system. One of the requirement of such communication channel is to deliver meaningful commands to the user. The sensations should be distinctive enough to be readily understandable for the operator.<br>This study is perusing the feasibility of generating identifiable moving patterns in the electro-tactile display. Then, the degree of identification performed by the users will be validated.<br><br>An electro-tactile display is built using an array of sixteen contacts to form a moving pattern by delivering electrical signal to the fingertip skin.<br>This signal can have varying voltages, frequencies or duty cycles to form the most comfortable sensation.<br>Moving patterns can be generated by individually or collectively toggling the electrical contacts on the electro-tactile display. This will achieve a stimulation of a moving pattern. In this regard, a moving pattern can be compared to a set of frame-by-frame pictures that construct a movie. Similarly, by toggling the contacts in a specific order, a moving pattern can be achieved.<br><br>In this study, eight subjects participated. A questionnaire was used to assess the sensation of the corresponding movement.<br>The results of these reports were analyzed and a conclusion regarding the identification of the direction of the movement was drawn. It became clear that the direction of the movement had a significant impact on the recognition of the patterns.<br><br>Furthermore, an analysis of the detection threshold (DT) voltage and current mapping was performed to evaluate the effect of the internal structure of the skin for each user on the assessment performance.<br>Based on the mapping results, it became clear that the DT voltage is vastly different for each contact and the resulting spatial map is also unique to each user.

Prediction of Design Team Performance on a Conceptual Design Task Using an Automatable, Topic-Independent Analysis of Language Use

In this research, starting with an established metric called the Language Style Matching (LSM) measure [1] we show that some new LSM-based measures can predict team performance on an open-ended design task. We call these Style Entrainment Signal (SES) measures. Using them, two conversational patterns are newly identified, which we call “dwelling” and “forward-moving.” We show that a forward-moving pattern is associated with better-rated results produced by teams in 30-minute long conceptual design meetings with significant brainstorming activity. Through this, we gain insight into some of the interpersonal dynamics that contribute to a design team’s success. These results are founded on previous work in psycholinguistics, where it has been shown that analysis of language use can be used in several ways to predict a team’s performance on short, well-defined tasks. By expanding the research to more open-ended design tasks, and identifying two newly-measurable conversational patterns, we contribute back to psycholinguistic theory. The analysis developed for this work is automatable and topic-independent, and so it has potential to be applied widely.

Artificial Neural Network Algorithms based Nonlinear Data Analysis for Forecasting in the Finance Sector

The involvement of big populace in the quantitative trading has been increased remarkably since the wired and wireless systems have become quite ubiquitous in the fields of finance and economics. Statistical, mathematical and technical analysis in parallel with machine learning and artificial intelligence are frequently being applied to perceive prices moving pattern and forecasting. However stock price do not follow any deterministic regulatory function, factor or circumstances rather than many considerations such as economy and finance, political environments, demand and supply, buying and selling tendency, trading and investment, etc. Historical data assist remarkably for prices forecasting as an important option for mathematicians and researchers. In this paper, we have followed backpropagation and radial basis function neural network for predicting future prices by modifying these techniques as per requirements. We have also performed a comparative analysis of the two ANN techniques for existing and our modified models.