SciTePress - Affiliation Profile

Affiliation

Select a Subject
Refine Ontology Subject

School of Computer Science at Carnegie Mellon University, United States

Context (please use complete words only)

Field

Sort by

34 Papers

Advanced Multi-parametric Monitoring and Analysis for Diagnosis and Optimal Management of Epilepsy and Related Brain Disorders: The ARMOR Project

Authors: Wilhelm Stork ¹ , André Bideaux ² , Nikolaos S. Voros ³ , Christos P. Antonopoulos ³ , Stefan Hey ² and Panagiota Anastasopoulou ²

Affiliations: ¹ Institut für Technik der Informationsverarbeitung, Universität Karlsruhe, Germany , ² Karlsruhe Institute of Technology, Institute for Information Processing Technologies, Engesserstr. 5, 76131 Karlsruhe, Germany , ³ Technological Educational Institute of Western Greece, Computer and Informatics Engineering Department, Embedded System Design and Applications Lab, National Road Antiriou-Ioanninon, 30020, Antirio, Greece

Digital Object Identifier: 10.5220/0006144500340055

Proceedings of EPS Vienna 2014, ISBN: 978-989-758-101-4

Quick Abstract

The ARMOR project addresses the needs of the epileptic patient and healthcare professional, aiming at the design and development of a nonintrusive Personal Health System (PHS) for the monitoring and analysis of epilepsy- relevant multi-parametric data, (i.e. EEG, EOG, EMG, EKG, skin conductance data) and the documentation of the epilepsy related symptoms. ARMOR platform incorporates models derived from data analysis based on already existing state-of-the-art communication platform solutions emphasizing on security issues and required adaptations to meet ARMOR specifications. In this context, this chapter aims to provide an extensive description of the main aspects and issues addressed in the project as well as the main characteristics of the developed platform.

On Metrics for Measuring Fragmentation of Federation over SPARQL Endpoints

Topics: System Integration; Distributed and Parallel Applications; Ontology and the Semantic Web

Authors: Nur Aini Rakhmawati , Marcel Karnstedt , Michael Hausenblas and Stefan Decker

Affiliation: National University of Ireland, Ireland

Digital Object Identifier: 10.5220/0004858000990106

Proceedings of WEBIST 2014, ISBN: 978-989-758-024-6

Quick Abstract

Processing a federated query in Linked Data is challenging because it needs to consider the number of sources, the source locations as well as heterogeneous system such as hardware, software and data structure and distri- bution. In this work, we investigate the relationship between the data distribution and the communication cost in a federated SPARQL query framework. We introduce the spreading factor as a dataset metric for computing the distribution of classes and properties throughout a set of data sources. To observe the relationship between the spreading factor and the communication cost, we generate 9 datasets by using several data fragmentation and allocation strategies. Our experimental results showed that the spreading factor is correlated with the com- munication cost between a federated engine and the SPARQL endpoints . In terms of partitioning strategies, partitioning triples based on the properties and classes can minimize the communication cost. However, such partitioning can also reduce the performance of SPARQL endpoint within the federation framework.

On Metrics for Measuring Fragmentation of Federation over SPARQL Endpoints

Topics: System Integration; Distributed and Parallel Applications; Databases and Datawarehouses; Ontology and the Semantic Web

Authors: Nur Aini Rakhmawati , Marcel Karnstedt , Michael Hausenblas and Stefan Decker

Affiliation: National University of Ireland, Ireland

Digital Object Identifier: 10.5220/0004760101190126

Proceedings of WEBIST 2014, ISBN: 978-989-758-023-9

Quick Abstract

Processing a federated query in Linked Data is challenging because it needs to consider the number of sources, the source locations as well as heterogeneous system such as hardware, software and data structure and distribution. In this work, we investigate the relationship between the data distribution and the communication cost in a federated SPARQL query framework. We introduce the spreading factor as a dataset metric for computing the distribution of classes and properties throughout a set of data sources. To observe the relationship between the spreading factor and the communication cost, we generate 9 datasets by using several data fragmentation and allocation strategies. Our experimental results showed that the spreading factor is correlated with the communication cost between a federated engine and the SPARQL endpoints . In terms of partitioning strategies, partitioning triples based on the properties and classes can minimize the communication cost. However, such partitioning can also reduce the performance of SPARQL endpoint within the federation framework.

Related Ontology Subjects/Areas/Topics (7)

Databases and Datawarehouses	Ontology and the Semantic Web	Web Information Systems and Technologies
Distributed and Parallel Applications	System Integration	Web Interfaces and Applications
Internet Technology

Array-based Electromyographic Silent Speech Interface

Topics: Speech Recognition; Pattern Recognition; Wearable Sensors and Systems; Physiological Processes and Bio-Signal Modeling, Non-Linear Dynamics

Authors: Michael Wand , Christopher Schulte , Matthias Janke and Tanja Schultz

Affiliation: Karlsruhe Institute of Technology, Germany

Digital Object Identifier: 10.5220/0004252400890096

Proceedings of BIOSIGNALS 2013/BIOSTEC, ISBN: 978-989-8565-36-5

Quick Abstract

An electromygraphic (EMG) Silent Speech Interface is a system which recognizes speech by capturing the electric potentials of the human articulatory muscles, thus enabling the user to communicate silently. This study is concerned with introducing an EMG recording system based on multi-channel electrode arrays. We first present our new system and introduce a method to deal with undertraining effects which emerge due to the high dimensionality of our EMG features. Second, we show that Independent Component Analysis improves the classification accuracy of the EMG array-based recognizer by up to 22.9% relative, which is a first example of an EMG signal processing method which is specifically enabled by our new array-based system. We evaluate our system on recordings of audible speech; achieving an optimal average word error rate of 10.9% with a training set of less than 10 minutes on a vocabulary of 108 words.

Related Ontology Subjects/Areas/Topics (18)

Artificial Intelligence	Health Information Systems	Physiological Computing Systems
Biomedical Engineering	Human-Computer Interaction	Physiological Processes and Bio-Signal Modeling, Non-Linear Dynamics
Biomedical Signal Processing	Methodologies and Methods	Sensor Networks
Data Manipulation	Neurocomputing	Soft Computing
Devices	Neurotechnology, Electronics and Informatics	Speech Recognition
Health Engineering and Technology Applications	Pattern Recognition	Wearable Sensors and Systems

DECISION-TREE BASED ANALYSIS OF SPEAKING MODE DISCREPANCIES IN EMG-BASED SPEECH RECOGNITION

Topics: Speech Recognition; Pattern Recognition; Wearable Sensors and Systems

Authors: Michael Wand , Matthias Janke and Tanja Schultz

Affiliation: Karlsruhe Institute of Technology, Germany

Digital Object Identifier: 10.5220/0003787201010109

Proceedings of BIOSIGNALS 2012/BIOSTEC, ISBN: 978-989-8425-89-8

Quick Abstract

This study is concerned with the impact of speaking mode variabilities on speech recognition by surface electromyography (EMG). In EMG-based speech recognition, we capture the electric potentials of the human articulatory muscles by surface electrodes, so that the resulting signal can be used for speech processing. This enables the user to communicate silently, without uttering any sound. Previous studies have shown that the processing of silent speech creates a new challenge, namely that EMG signals of audible and silent speech are quite distinct. In this study we consider EMG signals of three speaking modes: audibly spoken speech, whispered speech, and silently mouthed speech. We present an approach to quantify the differences between these speaking modes by means of phonetic decision trees and show that this measure correlates highly with differences in the performance of a recognizer on the different speaking modes. We furthermore reinvestigate the spectral mapping algorithm, which reduces the discrepancy between different speaking modes, and give an evaluation of its effectiveness.

Related Ontology Subjects/Areas/Topics (17)

Artificial Intelligence	Health Information Systems	Physiological Computing Systems
Biomedical Engineering	Human-Computer Interaction	Sensor Networks
Biomedical Signal Processing	Methodologies and Methods	Soft Computing
Data Manipulation	Neurocomputing	Speech Recognition
Devices	Neurotechnology, Electronics and Informatics	Wearable Sensors and Systems
Health Engineering and Technology Applications	Pattern Recognition

ON-LINE ACTION RECOGNITION FROM SPARSE FEATURE FLOW

Topics: Event and Human Activity Recognition; Vision for Robotics

Authors: Hildegard Kuehne , Dirk Gehrig , Tanja Schultz and Rainer Stiefelhagen

Affiliation: Karlsruhe Institute of Technology (KIT), Germany

Digital Object Identifier: 10.5220/0003861506340639

Proceedings of VISAPP 2012/VISIGRAPP, ISBN: 978-989-8565-03-7

Quick Abstract

The fast and robust recognition of human actions is an important aspect for many video-based applications in the field of human computer interaction and surveillance. Although current recognition algorithms provide more and more advanced results, their usability for on-line applications is still limited. To bridge this gap a online video-based action recognition system is presented that combines histograms of sparse feature point flow with an HMM-based action recognition. The usage of feature point motion is computational more efficient than the more common histograms of optical flow (HoF) by reaching a similar recognition accuracy. For recognition we use low-level action units that are modeled by Hidden-Markov-Models (HMM). They are assembled by a context free grammar to recognize complex activities. The concatenation of small action units to higher level tasks allows the robust recognition of action sequences as well as a continuous on-line evaluation of the ongoing activity. The average runtime is around 34 ms for processing one frame and around 20 ms for calculating one hypothesis for the current action. Assuming that one hypothesis per second is needed, the system can provide a mean capacity of 25 fps. The systems accuracy is compared with state of the art recognition results on a common benchmark dataset as well as with a marker-based recognition system, showing similar results for the given evaluation scenario. The presented approach can be seen as a step towards the on-line evaluation and recognition of human motion directly from video data.

Related Ontology Subjects/Areas/Topics (4)

Applications		Robotics		Software Engineering
Pattern Recognition

PEDESTRIAN DEAD RECKONING AS A COMPLEMENTARY METHOD FOR WIRELESS SENSOR NETWORK AD-HOC PERSON LOCALIZATION

Topics: MEMS; Wifi, Zigbee, WIMAX, Bluetooth; Ad Hoc Networks; Sensor Data Fusion; Multi-Sensor Data Processing; Distributed and Collaborative Signal Processing; Energy Efficiency; Well-Being and Well-Working; Healthcare

Authors: Tobias Gädeke , Johannes Schmid , Wilhelm Stork and Klaus D. Mueller-Glaser

Affiliation: Karlsruhe Institute of Technology (KIT), Germany

Digital Object Identifier: 10.5220/0003804801390148

Proceedings of SENSORNETS 2012, ISBN: 978-989-8565-01-3

Quick Abstract

The problem of localization and navigation in areas without any or with only limited access to global navigation satellite systems (GNSS) is still not solved. This is especially the case for person localization applications as persons tend to spend a good part of their time in buildings or in cities (urban canyons). One possibility to approach this issue is to use wireless sensor network (WSN) technology. Especially scenarios that require ad-hoc person localization like firefighters that enter a burning building or similar setups, WSN seem to be a promising solution. However, if the node density is low or if the scenario also requires localization in uncovered areas, an additional localization method is required. Pedestrian dead reckoning (PDR) is an ideal complementary method to achieve short term accurate localization under these assumptions. In this paper, an approach to PDR with low processing power for the use in WSN with a hip mounted inertial measurement unit (IMU) is presented. The purpose of the system is to provide a localization and tracking solution if temporarily none or only few anchor nodes are within communication range. This is achieved by detecting steps, estimating the length of each step and determining the step direction in WSN coordinates. We experimentally evaluate the system under varying environmental conditions and show that the concept is a promising solution for the intended applications.

Related Ontology Subjects/Areas/Topics (23)

Ad Hoc Networks	Energy Efficiency and Green Manufacturing	Obstacles
Application Domains	Hardware	Sensor Data Fusion
Applications and Uses	Health Information Systems	Sensor Networks
Biomedical Engineering	Healthcare	Signal Processing
Biomedical Instruments and Devices	Industrial Engineering	Simulation and Modeling
Data Manipulation	Informatics in Control, Automation and Robotics	Well-Being and Well-Working
Distributed and Collaborative Signal Processing	MEMS	Wireless Information Networks
Energy Efficiency	Multi-Sensor Data Processing

THE IMPACT OF SOURCE CODE NORMALIZATION ON MAIN CONTENT EXTRACTION

Topic: Web Information Filtering and Retrieval

Authors: Hadi Mohammadzadeh ¹ , Thomas Gottron ² , Franz Schweiggert ¹ and Gholamreza Nakhaeizadeh ³

Affiliations: ¹ University of Ulm, Germany , ² Universität Koblenz-Landau, Germany , ³ University of Karlsruhe, Germany

Digital Object Identifier: 10.5220/0003931906770682

Proceedings of WEBIST 2012, ISBN: 978-989-8565-08-2

Quick Abstract

In this paper, we introduce AdDANAg, a language-independent approach to extract the main content of web documents. The approach combines best-of-breed techniques from recent content extraction approaches to yield better extraction results. This combination of techniques brings together two pre-processing steps, e.g. to normalize the document presentation and reduce the impact of certain syntactical structures, and four phases for the actual content extraction. We show that AdDANAg demonstrates a high performance in terms of effectiveness and efficiency and outperforms previous approaches.

EXTRACTING THE MAIN CONTENT OF WEB DOCUMENTS BASED ON A NAIVE SMOOTHING METHOD

Topics: Web Mining; Information Extraction

Authors: Hadi Mohammadzadeh ¹ , Thomas Gottron ² , Franz Schweiggert ¹ and Gholamreza Nakhaeizadeh ³

Affiliations: ¹ University of Ulm, Germany , ² Universität Koblenz-Landau, Germany , ³ University of Karlsruhe, Germany

Digital Object Identifier: 10.5220/0003665304700475

Proceedings of KDIR 2011/IC3K, ISBN: 978-989-8425-79-9

Quick Abstract

Extracting the main content of web documents, with high accuracy, is an important challenge for researchers working on the web. In this paper, we present a novel language-independent method for extracting the main content of web pages. Our method, called DANAg, in comparison with other main content extraction approaches has high performance in terms of effectiveness and efficiency. The extraction process of data DANAg is divided into four phases. In the first phase, we calculate the length of content and code of fixed segments in an HTML file. The second phase applies a naive smoothing method to highlight the segments forming the main content. After that, we use a simple algorithm to recognize the boundary of the main content in an HTML file. Finally, we feed the selected main content area to our parser in order to extract the main content of the targeted web page.

Related Ontology Subjects/Areas/Topics (7)

Artificial Intelligence	Knowledge-Based Systems	Symbolic Systems
Information Extraction	Soft Computing	Web Mining
Knowledge Discovery and Information Retrieval

USING UTF-8 TO EXTRACT MAIN CONTENT OF RIGHT TO LEFT LANGUAGE WEB PAGES

Topic: Data and Information Retrieval

Authors: Hadi Mohammadzadeh ¹ , Franz Schweiggert ¹ and Gholamreza Nakhaeizadeh ²

Affiliations: ¹ University of Ulm, Germany , ² University of Karlsruhe, Germany

Digital Object Identifier: 10.5220/0003508502430249

Proceedings of ICSOFT 2011, ISBN: 978-989-8425-76-8

Quick Abstract

In this paper, we propose a new and simple approach to extract the main content of Right to Left language web pages. Independence to DOM tree and HTML tags is one of the most important features of the proposed algorithm. In practice, HTML tags have been written in English and we know that the English character set is located in the interval [0,127]. In most languages which are written from Right-to-Left (R2L) such as the Arabic language, however, a definite interval of the Unicode character set is used that is certainly not in this interval. In the first phase of our approach, we apply this distinction to separate the R2L characters from the English ones. Then for each HTML file, we determine the density of the R2L characters and the density of Non-R2L characters. That part of the HTML file with high density of the R2L characters and low density of the Non-R2L characters contains the main content of the web page with high accuracy. The proposed algorithm has been tested, evaluated and compared with the last main content extraction approach on 2166 selected web pages.

Related Ontology Subjects/Areas/Topics (3)

Business Analytics

Data and Information Retrieval

Data Engineering

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
1 2 3 4 5 6 7 Page 1 of 7, items 1 to 10 of 64.

Add Author(s) to filter:

Michael Decker (9)

Tanja Schultz (9)

W. Stork (7)

Michael Wand (5)

Johannes Britsch (4)

Gunther Schiefer (3)

K. D. Mueller-Glaser (3)

S. Heuer (3)

Gholamreza Nakhaeizadeh (3)

Hadi Mohammadzadeh (3)

Conference

Locate Conference in list below

Data pager
Data pager
1 2 Page 1 of 2, items 1 to 10 of 12.

Add Conference(s) to filter:

BIOSIGNALS(13)

ICE-B(6)

VISAPP(3)

WEBIST(3)

ICETE(2)

ICSOFT(1)

KDIR(1)

KEOD(1)

SENSORNETS(1)

ICEIS(1)

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject: