The goal of this paper is to analyze content shared in social media by presidential candidates in the United States of America. In particular, Twitter posts are being inspected, using advanced methods of big data analysis. In this report we describe the usage of tools, such as Map Reduce, collaborative filtering, k-means clustering and others, to determine different features of candidates' communication. We also made an application for recommending ideas to candidates based on the their Twitter analysis. At the end we show overview of our findings and propose directions for further analysis.
Chu Pak Sum, Filip Strycko, Niclas Ogeryd, Zhao Che
This paper is a report of an assignment of a course Computational Intelligence. The main goal of the assignment is to apply computational intelligence techniques in a practical setting - building a controller for a race car in The Open Racing Car Simulator (TORCS) using artificial neural network and evolving that network with evolutionary algorithm techniques.
Keywords: computational intelligence, car controller, artificial neural network
Gesture recognition and its implementation that support Human Computer systems are becoming very popular mode of interaction now a days. It allows to interfacing the man machine commutative information flow naturally. Vision based gesture recognition has the potential that can provide intuitive and effective interaction between man and machine. However there are not adequate tools and techniques that support for developing, detecting or executing these tasks. In this paper we will implement a prototype that facilitates recording data during building some action based activities captured by the Kinect sensor. We analyze those recorded clips and visualize the user interactions by recognition the gestures objects based on depth, IR and skeletal data. Kinect tools include an analysis feature, a time-line-based approach that manually or automatically can mark the recording sequences of clips. We will implement both discrete and continuous gestures by using AdaBoast machine learning approach to detect hands activities. Our result suggest that the learning mechanism can achieve more than 98% of confidence level of given gestures.
Keywords: Gesture recognition, Kinect, HCI, Machine learning, AdaBoost, Computer vision
In this experiment, AP Psychology 5th period asked the question "Does having a Christmas environment make shoppers more likely to choose holiday items rather than year-round ones?" The objective of this experiment was to answer this question. Also, a purpose of this experiment was to see, if the Christmas environment did, indeed, influence purchases, then to what extent? Two JROTC groups from 5th period were randomly selected, made their way to the AP Psychology classroom, and went on a shopping trip. These groups were in two different environments, non-Christmas and Christmas. Each environment had both non-Christmas and Christmas items to choose from. Data was collected from observers, "food cards", as well as pre and post surveys. Their data was collected and analyzed to see if the Christmas environment had any impact on whether students chose the Christmas items. After deep analysis, it can be seen that the Christmas environment influenced student's "purchases" (they did not actually have to buy the items). Although the first group (neutral environment) did not solely choose year-round items and the second group (Christmas environment) did not solely choose Christmas items, differences in purchases between the groups can still be noted. During the discussion with the subjects, some feel as though they were directly influenced by the Christmas decorations or lack thereof, while others say that they chose subconsciously.
Indoor air quality (IAQ) is referred to as “the air quality within and around buildings and structures, especially as it relates to the health and comfort of building occupants” (US EPA, 2015). Indoor pollutant levels further determine the quality of indoor air, and one of the indicators used to measure IAQ is carbon dioxide (CO2). Drawing on data collected from a classroom, auditorium, and gym setting in the Mount Royal University campus, the aim of this report is to determine if CO2 levels present are within established margins substantial to result in adverse health effects. Environmental factors that are considered in this report include: room size, supply air, and occupant load in the specified spaces on the campus. The results of this study suggest that there are a myriad of factors that may affect IAQ and that CO2 is merely an indicator of poor air quality. Overall, peak indoor CO2 levels can further be used to determine appropriate ventilation rates in an indoor space.