WPI Worcester Polytechnic Institute

Computer Science Department

AIRG Topics - Spring 2014

Our group meets on Thursdays at 11:00 a.m., FL 246.

Jan 16

Jan 23

Jan 30

Feb 6

Feb 13

Feb 20
Academic Advising Appointment Day

Feb 27
Hao Wan
practice talk for upcoming bioinformatics conference
    Abstract: A new feature generation algorithm for sequence data sets, called Mutated Subsequence Generation (MSG), is presented. Given a data set of sequences, the MSG algorithm generates features from these sequences by incorporating mutative positions in subsequences. We compare this algorithm with other sequence-based feature generation algorithms, including position-based, #-grams, and #-gapped pairs. Our experiments show that the MSG algorithm outperforms these other algorithms in domains in which presence, not specific location, of sequential patterns.

March 6

Mar 13
Ugrad & Grad student break

Mar 20

Mar 27

Apr 03
Ben Suay
Experiences from the DARPA challenge
    In this work, we present our system design, operational procedure, testing process, field results, and lessons learned for the valve-turning task of the DARPA Robotics Challenge (DRC). We present a software framework for cooperative traded control that enables a team of operators to control a remote humanoid robot over an unreliable communication link. Our system, composed of software modules running on-board the robot and on a remote workstation, allows the operators to specify the manipulation task in a straightforward manner. In addition, we have defined a clear operational procedure for the operators to manage the teleoperation task, designed to improve situation awareness and expedite task completion. Our testing process, consisting of hands-on intensive testing, remote testing, and remote practice runs, demonstrates that our framework is able to perform reliably and is resilient to unreliable network conditions. We analyze our approach, field tests, and experience at the DRC Trials and discuss lessons learned which may be useful for others when designing similar systems.

Apr 10

Apr 17
Maryam Hasan
Research Qualifier talk: "Detecting Emotions in Short Text Messages"
    Detecting emotions in text messages has wide range of applications including, the diagnosis of psychological ailments such as anxiety or depression, gauge the sentiment of buyers which facilitates targeted product advertisement, and detecting public mood of a community. In this research we propose a new approach for automatically classifying text messages of individuals to infer their emotional states.
            To model the emotional states of users, we utilize the well-established model of human moods, known as the Circumplex model that characterizes affective experience along two dimensions: valence and arousal. We select twitter messages to be the input data set, as they provide very large, diverse and freely available ensemble of emotions. Using a hash-tag label based approach, our methodology trains supervised classifiers for even multi-class emotion detection on potentially huge data sets with no manual effort.
            We investigate the utility of several features for emotion detection, including unigrams, emoticons, punctuations, and negations. To tackle the problem of sparse and high dimensional feature vectors of messages, we utilize a lexicon of emotions. We compared the results of two affective lexicons including, LIWC and ANEW. We also compared the accuracy of several machine learning algorithms such as SVM, KNN, Decision Tree, and Naive Bayes for classifying Twitter messages. Our results confirm an accuracy of above 90%, while demonstrating robustness across learning algorithms.

    Advisor: Prof. Elke Rundensteiner;
    Co-Advisor: Prof. Emmanuel Agu.

Apr 24
Undergraduate Project Presentation Day

Tue May 1
(reserved for possible MS thesis presentations)

[Feedback] [Search Our Web] [Help & Index]

[Return to the WPI Homepage] [Return to the CS Homepage]

AIRG Coordinator / Thu Apr 3 19:00:51 EDT 2014