Fillia Makedon

University of Texas at Arlington, Arlington, Texas, United States

Are you Fillia Makedon?

Claim your profile

Publications (236)56.57 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: We present an Adaptive Dialogue System, able to make conversation in natural language with post-traumatic stress disorder (PTSD)-suffering users, and guide the way that allows eliciting information about their disorder and progress of their treatment. As the conversation unfolds, the system gathers information enabling us to calculate a PTSD score and perform an initial screening of the users. We generate the system's response in real time and continuously monitor an estimate of the user's emotional state. If a user becomes frustrated, angry, sad, etc., we provide encouragement and observe any changes in the dialogue. The system will be trained with data from real and simulated interactions, using automatic virtual agents. Last, we present our plans for evaluation with PTSD-suffering and non-PTSD-suffering users.
    Journal of Applied Biobehavioral Research 09/2014; 19(3).
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Drug compliance and adverse drug reactions (ADR) are two of the most important issues regarding patient safety throughout the worldwide healthcare sector. ADR prevalence is 6.7 % throughout hospitals worldwide, with an international death rate of 0.32 ...
    Personal and Ubiquitous Computing 01/2014; · 1.13 Impact Factor
  • Source
    Universal Access in the Information Society 01/2014; · 0.53 Impact Factor
  • Hua Wang, Heng Huang, Fillia Makedon
    [Show abstract] [Hide abstract]
    ABSTRACT: Human emotion detection is of substantial importance in a variety of pervasive applications in assistive environments. Because facial expressions provide a key mechanism for understanding and conveying emotion, automatic emotion detection through facial expression recognition has attracted increased attention in both scientific research and practical applications in recent years. Traditional facial expression recognition methods normally use only one type of facial expression data, either static data extracted from one single face image or motion-dependent data obtained from dynamic face image sequences, but seldom employ both. This work proposes to place the emotion detection problem under the framework of Discriminant Laplacian Embedding (DLE) to integrate these two types of facial expression data in a shared subspace, such that the advantages of both of them are exploited. Due to the reinforcement between the two types of facial features, the new data representation is more discriminative and easier to classify. Encouraging experimental results in empirical studies demonstrate the practical usage of the proposed DLE method for emotion detection.
    Universal Access in the Information Society 01/2014; · 0.53 Impact Factor
  • Source
    V. Metsis, F. Makedon, D. Shen, H. Huang
    [Show abstract] [Hide abstract]
    ABSTRACT: Array comparative genomic hybridization (aCGH) is a newly introduced method for the detection of copy number abnormalities associated with human diseases with special focus on cancer. Specific patterns in DNA copy number variations (CNVs) can be associated with certain disease types and can facilitate prognosis and progress monitoring of the disease. Machine learning techniques have been used to model the problem of tissue typing as a classification problem. Feature selection is an important part of the classification process, because many biological features are not related to the diseases and confuse the classification tasks. Multiple feature selection methods have been proposed in the different domains where classification has been applied. In this work, we will present a new feature selection method based on structured sparsity-inducing norms to identify the informative aCGH biomarkers which can help us classify different disease subtypes. To validate the performance of the proposed method, we experimentally compare it with existing feature selection methods on four publicly available aCGH data sets. In all empirical results, the proposed sparse learning based feature selection method consistently outperforms other related approaches. More important, we carefully investigate the aCGH biomarkers selected by our method, and the biological evidences in literature strongly support our results.
    IEEE/ACM Transactions on Computational Biology and Bioinformatics 01/2014; 11(1):168-181. · 1.62 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The monitoring of sleep patterns is of major importance for various reasons such as the detection and treatment of sleep disorders, the assessment of the effect of different medical conditions or medications on the sleep quality, and the assessment of mortality risks associated with sleeping patterns in adults and children. Sleep monitoring by itself is a difficult problem due to both privacy and technical considerations. The proposed system uses a combination of non-invasive sensors to assess and report sleep patterns: a contact-based pressure mattress and a non-contact 3D image acquisition device, which can complement each other. To evaluate our system, we used real data collected in Heracleia Lab’s assistive living apartment. Our system uses Machine Learning techniques to automatically analyze the collected data and recognize sleep patterns. It is non-invasive, as it does not disrupt the user’s usual sleeping behavior and it can be used both at the clinic and at home with minimal cost.
    Personal and Ubiquitous Computing 01/2014; · 1.13 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Automatic patient thought record categorization (TR) is important in cognitive behavior therapy, which is an useful augmentation of standard clinic treatment for major depressive disorder. Because both collecting and labeling TR data are expensive, it is usually cost prohibitive to require a large amount of TR data, as well as their corresponding category labels, to train a classification model with high classification accuracy. Because in practice we only have very limited amount of labeled and unlabeled training TR data, traditional semi-supervised learning methods and transfer learning methods, which are the most commonly used strategies to deal with the lack of training data in statistical learning, cannot work well in the task of automatic TR categorization. To address this challenge, we propose to tackle the TR categorization problem from a new perspective via self-taught learning, an emerging technique in machine learning. Self-taught learning is a special type of transfer learning. Instead of requiring labeled data from an auxiliary domain that are relevant to the classification task of interest as in traditional transfer learning methods, it learns the inherent structures of the auxiliary data and does not require their labels. As a result, a classifier achieves decent classification accuracy using the limited amount of labeled TR texts, with the assistance from the large amount of text data obtained from some inexpensive, or even no-cost, resources. That is, a cost-effective TR categorization system can be built that may be particularly useful for diagnosis of patients and training of new therapists. By further taking into account the discrete nature input text data, instead of using the traditional Gaussian sparse coding in self-taught learning, we use exponential family sparse coding to better simulate the distribution of the input data. We apply the proposed method to the task of classifying patient homework texts. Experimental results show the effectiveness of the proposed automatic TR classification framework.
    Personal and Ubiquitous Computing 01/2014; · 1.13 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the performance of our audio-visual speech recognition system in both English and Greek under the influence of audio noise. We present the architecture of our recently built system that utilizes information from three streams including 3-D distance measurements. The feature extraction approach used is based on the discrete cosine transform and linear discriminant analysis. Data fusion is employed using state-synchronous hidden Markov models. Our experiments were conducted on our recently collected database under a multi-speaker configuration and resulted in higher performance and robustness in comparison to an audio-only recognizer.
    Proceedings of the 15th international conference on Human-Computer Interaction: interaction modalities and techniques - Volume Part IV; 07/2013
  • International Conference on Multimedia and Human-Computer Interaction; 07/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a system which is able to interact through natural dialogue, with PTSD patients, as well as to guide the conversation aiming to elicit enough information to make an assessment of their condition, in a manner similar to a self assessment test. Our system is able to adapt to each individual patient and can operate in two modes: one that stores information about previous sessions with a patient to provide a sense of trust and relationship; and one that does not store information to preserve anonymity.
    Pervasive Technologies Related to Assistive Environments; 05/2013
  • 3rd Robotics in Assistive Environments; 05/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an intelligent wheelchair designed to be used as a development and evaluation platform for alternative, non-tactile power wheelchair controls. The system is designed to be highly modular such that new human-computer interface devices and methods can be quickly integrated and evaluated as necessary. The current configuration provides full proportional steering and speed control outputs using a combination of voice commands, video-occulography (eye tracking), and a single point electrode based electroencephalography (EEG) brain-computer interface.
    Pervasive Technologies Related to Assistive Environments; 05/2013
  • Paul Sassaman, Eric Becker, Fillia Makedon
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we describe several existing Augmented Reality projects that illustrate critical yet currently disparate applications of Augmented Reality. This paper then describes a partially implemented system (the Visually Pervasive Augmented World) that has begun work on merging all of these applications together in an attempt to provide as much functionality as possible, while keeping the hardware requirements as accessible to the general public as possible. Once completed, this system will offer complete customizability to users, allowing them to interact with and modify their augmented world through user-submitted static and animated 3D models, text, a custom scripting language, and location and object based Augmented Reality.
    Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we describe a novel methodology which employs machine learning as an alternative means to explore hospital characteristics and client satisfaction, for decision making and improved quality of care. We applied well known feature selection and data mining algorithms such as forward selection and Naïve Bayes respectively, to determine patient satisfaction, which is an important indicator of quality of care in hospital settings. Our dataset comprised of three types of data, (i) patient perception about received care, (ii) nurse perception about the working environment and (iii) organizational attributes of the hospital. Our experimental results exhibited high classification accuracy (87%), allowing valid conclusions to be reached about the organizational and workforce factors which attribute to patient satisfaction. Our findings were validated using traditional statistical methods such as binomial correlation and linear regression.
    Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a system targeted for assistive living environments, that is able to control the actuators of a robot and manipulate objects that lie on a table. An adaptive dialogue system is responsible for interacting with the user, retrieving his/her intentions and reacting accordingly. Our system is able to learn in real time how to solve complicated tasks by combining solutions to simpler ones, thus reusing previous knowledge. It is also able to effectively plan and execute table top object manipulation, which can have a great impact in the quality of life of an elderly, disabled or injured person.
    Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cerebral Palsy (CP) is a central nervous system disorder affecting 2 out of every 1000 births. CP limits a person's muscular function. Rehabilitative, touch-screen gaming promises to assist in developing muscle tone and dexterity for hemi-paretic CP patients as well as help therapists keep track of a patient's performance over time. However, most systems fail to take into account other factors of the disorder that could affect the scoring of a patient differently on various assessment days - specifically attention deficit or distraction. Cerebral Palsy is frequently associated with diagnosed Attention Deficit (Hyperactive) Disorder (ADD/ADHD), but even if a child does not fall within that definition, pediatric CP patients are often easily distracted. In this work we perform attention deficit simulation experiments with able-bodied users playing three rehabilitative games as well as similar computer generated data and propose a methodology to model and eliminate the effects of attention deficit or distraction from the scoring scheme used to evaluate the patient's motor abilities and progress over time.
    Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2013
  • Shawn N. Gieser, Eric Becker, Fillia Makedon
    [Show abstract] [Hide abstract]
    ABSTRACT: Rheumatoid Arthritis is a chronic disease that leads to swelling and inflammation of the joints and even spread to surrounding tissues and blood vessels. Physical therapy has been used successfully to slow the effects of this degenerative disease. Patients, however, do not want to do these exercises due to the fact they are boring and repetitive. In this paper, we introduce the first steps in creating a virtual environment using a CAVE System for the physical therapy sessions where the user will be engaged and motived to complete the exercises prescribed by his or her doctor.
    Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: A framework employing the Student-t pdf is introduced for offline map estimation and robot localization using visual loop closures. The framework uses the Student-t pdf (a) as an observation model of a Hidden Markov Model to represent a topological map (b) to represent the robot motion model. The map and the motion model are calculated in an expectation maximization (EM) framework. We show that the estimator converges at linear time and that the provided accuracy is higher compared to using a conventional Gaussian mixture pdf, due to higher noise resiliency, as well as compared to using a fixed robot motion model. The task is assisted by unsupervised landmark definition through the EM-based clustering of the observations and by scene representation using the complex Zernike moments, which provide rich rotation-invariant information. The validity of the method has been verified experimentally using the input from an omnidirectional camera.
    Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments; 05/2013
  • Alexandros Papangelis, Fillia Makedon
    ACES; 03/2013
  • Georgios Galatas, Fillia Makedon
    [Show abstract] [Hide abstract]
    ABSTRACT: Context-awareness constitutes a fundamental attribute of a smart environment. Our research aims at advancing the context-awareness capabilities of ambient intelligence environments by combining multi-modal information from both stationary and moving sensors. The collected data enables us to perform person identification and 3-D localization and recognize activities. In addition, we explore closed-loop feedback by integrating autonomous robots interacting with the users.
    Proceedings of the companion publication of the 2013 international conference on Intelligent user interfaces companion; 03/2013

Publication Stats

1k Citations
56.57 Total Impact Points

Institutions

  • 2007–2014
    • University of Texas at Arlington
      • Department of Computer Sciences & Engineering
      Arlington, Texas, United States
  • 2006
    • Southern Methodist University
      • Department of Computer Science and Engineering
      Dallas, TX, United States
  • 2005–2006
    • University of Massachusetts Dartmouth
      • Department of Computer and Information Science
      United States
  • 1992–2006
    • Dartmouth College
      • Department of Computer Science
      Hanover, NH, United States
  • 1997
    • University of Sydney
      Sydney, New South Wales, Australia
  • 1993
    • Massachusetts Institute of Technology
      Cambridge, Massachusetts, United States
  • 1989–1991
    • University of Texas at Dallas
      • Department of Computer Science
      Richardson, Texas, United States
  • 1982
    • Illinois Institute of Technology
      Chicago, Illinois, United States
  • 1970
    • UBS AG
      Zürich, Zurich, Switzerland