loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Affiliation

Carnegie Mellon University, United States
Context (please use complete words only)
Field
Sort by

23 Papers

Graph Convolutional Matrix Completion for Bipartite Edge Prediction

Topics: Machine Learning; Collaborative Filtering

Authors: Yuexin Wu , Hanxiao Liu and Yiming Yang

Affiliation: Carnegie Mellon University, 5000 Forbes Ave, 15213, Pittsburgh, PA and U.S.A.

Digital Object Identifier: 10.5220/0006900000510060

Proceedings of KDIR 2018/IC3K, ISBN: 978-989-758-330-8

Collapse Button Quick Abstract
Leveraging intrinsic graph structures in data to improve bipartite edge prediction has become an increasingly important topic in the recent machine learning area. Existing methods, however, are facing open challenges in how to enrich model expressiveness and reduce computational complexity for scalability. This paper addresses both challenges with a novel approach that uses a multi-layer/hop neural network to model a hidden space, and the first-order Chebyshev approximation to reduce training time complexity. Our experiments on benchmark datasets for collaborative filtering, citation network analysis, course prerequisite prediction and drug-target interaction prediction show the advantageous performance of the proposed approach over several state-of-the-art methods.
Collapse Button Related Ontology Subjects/Areas/Topics (9)
Artificial Intelligence

Evolutionary Computing

Machine Learning

Collaborative Filtering

Knowledge Discovery and Information Retrieval

Soft Computing

Computational Intelligence

Knowledge-Based Systems

Symbolic Systems

A Kinect-based Monitoring System for Stroke Rehabilitation

Authors: Min Hun Lee 1 , Daniel Siewiorek 1 , Asim Smailagic 1 , Alexandre Bernardino 2 and Sergi Bermúdez I Badia 3

Affiliations: 1 Carnegie Mellon University, United States , 2 Instituto Superior Técnico, Portugal , 3 Madeira Interactive Technology Institute and Faculdade de Ciências Exatas e da Engenharia and Universidade da Madeira, Portugal

Proceedings of AHA 2017

Collapse Button Quick Abstract
Therapists monitor and evaluate stroke patient’s motor abilities with clinical tests to individualize clinical interventions. After a clinical session, a therapist designs task-oriented exercises for a patient and requests self-reporting of patient’s adherence on exercise regimen. However, outpatients, who cannot receive feedback, often show low adherence [1], leading to sparse self-reports. It is difficult for therapists to follow patient’s progress. To address this challenge, this paper describes a Kinect-based monitoring system that evaluates performance and provides real-time feedback for four stroke rehabilitation exercises. Our preliminary study showed that this monitoring system can accurately monitor in-home stroke rehabilitation exercises.

Brain Race - An Educational Mobile Game for an Adult English Literacy Program

Topics: Mobile Learning; Game-Based and Simulation-Based Learning; Smart Devices as Collaborative Learning Tools; Tools for Educational Communication and Collaboration

Authors: Nada Soudy 1 , Silvia Pessoa 1 , M. Bernardine Dias 2 , Swapnil Joshi 1 , Haya Thowfeek 1 and Ermine Teves 2

Affiliations: 1 Carnegie Mellon University in Qatar, Qatar , 2 Carnegie Mellon University, United States

Digital Object Identifier: 10.5220/0005410400340045

Proceedings of CSEDU 2015, ISBN: 978-989-758-108-3

Collapse Button Quick Abstract
This paper investigates the role and impact of Brain Race (BR), a customized mobile game-based learning tool, on the learning and teaching experiences of teachers and learners in a community adult English literacy program in Qatar. Relying on observations, formal interviews, and surveys with teachers and learners, this paper examines the implementation process of introducing BR in a classroom, the interaction of teachers and learners with BR and their opinions on BR, and BR’s perceived impact on learner motivation, engagement, and learning outcomes. Results indicate that although BR motivates learners and allows them to practice English concepts, certain issues, such as equipment used, scheduling, and content relevance, must be addressed in order to make the experience more efficient and valuable to both teachers and learners. The paper argues that learners and teachers have a variety of preferences, and thus it is important that they are able to decide for themselves how they want to include game-based learning tools, such as BR, into their classrooms. We conclude with recommendations to improve the implementation process so that learners can benefit more from BR and similar games.
Collapse Button Related Ontology Subjects/Areas/Topics (10)
Computer-Supported Education

Learning/Teaching Methodologies and Assessment

Smart Devices as Collaborative Learning Tools

e-Learning

Mobile Information Systems

Ubiquitous Learning

Game-Based and Simulation-Based Learning

Mobile Learning

Web Information Systems and Technologies
Information Technologies Supporting Learning

Improving Physiological Signal Classification Using Logarithmic Quantization and a Progressive Calibration Technique

Topics: Biosignal Acquisition, Analysis and Processing; Physiological Computing in Mobile Devices

Authors: Nick Merrill 1 , Thomas Maillart 1 , Benjamin Johnson 2 and John Chuang 1

Affiliations: 1 UC Berkeley, United States , 2 Carnegie Mellon University, United States

Digital Object Identifier: 10.5220/0005238800440051

Proceedings of PhyCS 2015, ISBN: 978-989-758-085-7

Collapse Button Quick Abstract
This paper exhibits two methods for decreasing the time associated with training a machine learning classifier on biometric signals. Using electroencephalography (EEG) data obtained from a consumer-grade headset with a single electrode, we show that these methods produce significant gains in the computational performance and calibration time of a simple brain-computer interface (BCI) without significantly decreasing accuracy. We discuss the relevance of reduced feature vector size to the design of physiological computing applications.
Collapse Button Related Ontology Subjects/Areas/Topics (8)
Applications

Methodologies and Methods

Physiological Computing Systems

Biosignal Acquisition, Analysis and Processing

Pattern Recognition

Software Engineering
Human-Computer Interaction

Physiological Computing in Mobile Devices

A Web-based System to Support Inquiry Learning - Towards Determining How Much Assistance Students Need

Topics: Intelligent Tutoring Systems; Web-Based Learning, Wikis and Blogs; Pedagogy Enhancement with E-Learning; Intelligent Learning and Teaching Systems; K-12 Students

Authors: Bruce M. McLaren 1 , Michael Timms 2 , Doug Weihnacht 3 , Daniel Brenner 4 , Kim Luttgen 4 , Andrew Grillo-Hill 4 and David H. Brown 5

Affiliations: 1 Carnegie Mellon University, United States , 2 Australian Council for Educational Research, Australia , 3 MW Productions and San Francisco, United States , 4 WestEd and San Francisco, United States , 5 D. H. Brown & Associates, United States

Digital Object Identifier: 10.5220/0004810100430052

Proceedings of CSEDU 2014, ISBN: 978-989-758-020-8

Collapse Button Quick Abstract
How much assistance should be provided to students as they learn with educational technology? Providing help allows students to proceed when struggling, yet can depress their motivation to learn independently. Assistance withholding encourages students to learn for themselves, yet can also lead to frustration. The web-based inquiry-learning program, \emph{Voyage to Galapagos (VTG)}, helps students ``follow’’ the steps of Darwin through a simulation of the Galapagos Island and his discovery of evolution. Students explore the islands, take pictures of animals, evaluate their characteristics and behavior, and use scientific methodology to discover evolution. A preliminary study with 48 middle school students examined three levels of assistance: (1) no support, (2) error flagging, text feedback on errors, and hints, and (3) pre-emptive hints with error flagging, error feedback, and hints. The results indicate that higher performing students gainfully use the program’s support more frequently than lower performing students, those who arguably have a greater need for it. We conjecture that this could be a product of the current \emph{VTG} program only supporting an early phase of the learning process and also that higher performers have better metacognition, particularly in knowing when (and when not) to ask for help. Lower performers may benefit at later phases of the program, which we will test in a future study.
Collapse Button Related Ontology Subjects/Areas/Topics (13)
Artificial Intelligence and Decision Support Systems

Information Technologies Supporting Learning

Learning/Teaching Methodologies and Assessment

Computer-Supported Education

Intelligent Learning and Teaching Systems

Pedagogy Enhancement with e-Learning

Domain Applications and Case Studies

Intelligent Tutoring Systems

Social Context and Learning Environments

e-Learning

K-12 Students

Web-Based Learning, Wikis and Blogs
Enterprise Information Systems

Effortless Scanning of 3D Object Models by Boundary Aligning and Stitching

Topics: Image Registration; Shape Representation and Matching

Authors: Susana Brandão 1 , João P. Costeira 2 and Manuela Veloso 3

Affiliations: 1 Instituto Superior Técnico, Universidade de Lisboa and Carnegie Mellon University, Portugal , 2 Instituto Superior Técnico and Universidade de Lisboa, Portugal , 3 Carnegie Mellon University, United States

Digital Object Identifier: 10.5220/0004746406670674

Proceedings of VISAPP 2014/VISIGRAPP, ISBN: 978-989-758-003-1

Collapse Button Quick Abstract
We contribute a novel algorithm for the digitation of complete 3D object models that requires little preparation effort from the user. Notably, the presented algorithm, Joint Alignment and Stitching of Non-Overlapping Meshes (JASNOM), completes 3D object models by aligning and stitching two 3D meshes by the boundaries and does not require any previous registration between them. JASNOM only requirement is the lack of overlap between meshes, which is simple to achieve in most man made object. JASNOM takes advantage that both meshes can only be connected by their boundary to reframe the alignment problem as a search of the best assignment between boundary vertices. To make the problem tractable, JASNOM reduces the search space considerably by imposing strong constraints on valid assignments that transform the original combinatorial problem into a discrete linear problem. By not requiring previous camera registration and by not depending on shape features, JASNOM contributions range from quick modeling of 3D objects to hole filling in meshes.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Computer Vision, Visualization and Computer Graphics

Image Registration

Shape Representation and Matching
Image and Video Analysis

Probabilistic Object Identification through On-demand Partial Views

Topics: Active and Robot Vision; Shape Representation and Matching; Vision for Robotics

Authors: Susana Brandão 1 , Manuela Veloso 2 and João P. Costeira 3

Affiliations: 1 Carnegie Mellon University and Universidade de Lisboa, United States , 2 Carnegie Mellon University, United States , 3 Universidade de Lisboa, Portugal

Digital Object Identifier: 10.5220/0004855507170722

Proceedings of VISAPP 2014/VISIGRAPP, ISBN: 978-989-758-009-3

Collapse Button Quick Abstract
The current paper addresses the problem of object identification from multiple 3D partial views, collected from different view angles with the objective of disambiguating between similar objects. We assume a mobile robot equipped with a depth sensor that autonomously grasps an object from different positions, with no previous known pattern. The challenge is to efficiently combine the set of observations into a single classification. We approach the problem with a sequential importance resampling filter that allows to combine the sequence of observations and that, by its sampling nature, allows to handle the large number of possible partial views. In this context, we introduce innovations at the level of the partial view representation and at the formulation of the classification problem. We provide a qualitative comparison to support our representation and illustrate the identification process with a case study.
Collapse Button Related Ontology Subjects/Areas/Topics (9)
Active and Robot Vision

Image and Video Analysis

Robotics

Applications

Motion, Tracking and Stereo Vision

Shape Representation and Matching

Computer Vision, Visualization and Computer Graphics

Pattern Recognition

Software Engineering

Stress Recognition - A Step Outside the Lab

Topics: Pattern Recognition; Biosignal Acquisition, Analysis and Processing; Processing of Multimodal Input

Authors: Julian Ramos , Jin-Hyuk Hong and Anind K. Dey

Affiliation: Carnegie Mellon University, United States

Digital Object Identifier: 10.5220/0004725701070118

Proceedings of PhyCS 2014, ISBN: 978-989-758-006-2

Collapse Button Quick Abstract
Despite the potential for stress and emotion recognition outside the lab environment, very little work has been reported that is feasible for use in the real world and much less for activities involving physical activity. In this work, we move a step forward towards a stress recognition system that works on a close to real world data set and shows a significant improvement over classification only systems. Our method uses clustering to separate the data into physical exertion levels and later performs stress classification over the discovered clusters. We validate our approach on a physiological stress dataset from 20 participants who performed 3 different activities of varying intensity under 3 different types of stimuli intended to cause stress. The results show an f-measure improvement of 130\% compared to using classification only.
Collapse Button Related Ontology Subjects/Areas/Topics (15)
Artificial Intelligence

Health Engineering and Technology Applications

Pattern Recognition

Biomedical Engineering

Human-Computer Interaction

Physiological Computing Systems

Biomedical Signal Processing

Methodologies and Methods

Processing of Multimodal Input

Biosignal Acquisition, Analysis and Processing

Neurocomputing

Sensor Networks

Data Manipulation

Neurotechnology, Electronics and Informatics

Soft Computing

Efficient 3D Control for Needle Steering using Duty-cycled Rotation

Topics: Robot Design, Development and Control; Modeling, Simulation and Architecture

Authors: Xiao Li , Craig A. Lehocky and Cameron N. Riviere

Affiliation: Carnegie Mellon University, United States

Digital Object Identifier: 10.5220/0004456501920199

Proceedings of ICINCO 2013, ISBN: 978-989-8565-71-6

Collapse Button Quick Abstract
Bevel-tipped flexible needles can be steered to reach clinical targets along curvilinear paths in 3D while avoiding obstacles. Steering by duty-cycled rotation increases the versatility of this approach by providing proportional control of trajectory curvature. This paper presents computationally efficient techniques for path planning and path-following control for this application, using a 3D simulated brain environment. Path planning algorithms for this class of steerable needles have been developed using Rapidly-exploring Random Trees (RRTs). This paper expands on these methods, using quaternions for representation of rotation, and enhancing computational efficiency through use of interpolation, and by relaxing the entry constraint. For path-following, a look-ahead proportional controller for position and orientation is presented. Simulations in a 3D brain-like environment demonstrate the performance of the proposed planner and path-following controller. The look-ahead is seen to improve path-following performance.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Informatics in Control, Automation and Robotics

Robot Design, Development and Control

Robotics and Automation
Modeling, Simulation and Architectures

Knowledge Resource Development for Identifying Matching Image Descriptions

Topics: Ontology Engineering; Natural Language Processing; Knowledge Representation; Domain Analysis and Modeling

Authors: Alicia Sagae and Scott E. Fahlman

Affiliation: Carnegie Mellon University, United States

Digital Object Identifier: 10.5220/0004550601000108

Proceedings of KEOD 2013/IC3K, ISBN: 978-989-8565-81-5

Collapse Button Quick Abstract
Background knowledge resources contribute to the performance of many current systems for textual inference tasks (QA, textual entailment, summarization, retrieval, and others). However, it can be difficult to assess how additions to such a knowledge base will impact a system that relies on it. This paper describes the incremental, task-driven development of an ontology that provides features to a system that retrieves images based on their textual descriptions. We perform error analysis on a baseline system that uses lexical features only, then focus ontology development on reducing these errors against a development set. The resulting ontology contributes more to performance than domain-general resources like WordNet, even on a test set of previously unseen examples.
Collapse Button Related Ontology Subjects/Areas/Topics (14)
Applications

Information Systems Analysis and Specification

Ontologies and the Semantic Web

Artificial Intelligence

Knowledge Engineering and Ontology Development

Ontology Engineering

Data Engineering

Knowledge Representation

Pattern Recognition

Domain Analysis and Modeling

Knowledge-Based Systems

Symbolic Systems
Enterprise Information Systems

Natural Language Processing

Context (please use complete words only)
Field
Sort by

Topic(s):

Filter listed results, by

Publication date

From:
To:
Author
Locate Author in list below
Data pager
Data pager
12345678
 Page 1 of 8, items 1 to 10 of 78.
Add Author(s) to filter:
Conference
Locate Conference in list below
Data pager
Data pager
12
 Page 1 of 2, items 1 to 10 of 15.
Add Conference(s) to filter:

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic