Publications without Fulltext

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3

Browse

Filters

2006 - 200922010 - 20141

Advanced Search

Filter by

Settings

Indexed at: search.filters.indexed.PubMedSubject: search.filters.subject.Electrical electronic engineering

Search Results

Now showing 1 - 3 of 3
  • Placeholder
    PublicationMetadata only
    Discriminative analysis of lip motion features for speaker identification and speech-reading
    (Ieee-Inst Electrical Electronics Engineers Inc, 2006) N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Çetingül, Hasan Ertan; Yemez, Yücel; Erzin, Engin; Tekalp, Ahmet Murat; Master Student; Faculty Member; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; 107907; 34503; 26207
    There have been several studies that jointly use audio, lip intensity, and lip geometry information for speaker identification and speech-reading applications. This paper proposes using explicit lip motion information, instead of or in addition to lip intensity and/or geometry information, for speaker identification and speech-reading within a unified feature selection and discrimination analysis framework, and addresses two important issues: 1) Is using explicit lip motion information useful, and, 2) if so, what are the best lip motion features for these two applications? The best lip motion features for speaker identification are considered to be those that result in the highest discrimination of individual speakers in a population, whereas for speech-reading, the best features are those providing the highest phoneme/word/phrase recognition rate. Several lip motion feature candidates have been considered including dense motion features within a bounding box about the lip, lip contour motion features, and combination of these with lip shape features. Furthermore, a novel two-stage, spatial, and temporal discrimination analysis is introduced to select the best lip motion features for speaker identification and speech-reading applications. Experimental results using an hidden-Markov-model-based recognition system indicate that using explicit lip motion information provides additional performance gains in both applications, and lip motion features prove more valuable in the case of speech-reading application.
  • Placeholder
    PublicationMetadata only
    LoC sensor array platform for real-time coagulation measurements
    (Institute of Electrical and Electronics Engineers (IEEE), 2014) Yaralıoğlu, Göksenin G.; N/A; Department of Electrical and Electronics Engineering; Department of Mechanical Engineering; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Department of Electrical and Electronics Engineering; Çakmak, Onur; Kılınç, Necmettin; Ermek, Erhan; Mostafazadeh, Aref; Elbüken, Çağlar; Ürey, Hakan; PhD Student; Researcher; Other; Researcher; Researcher; Faculty Member; Department of Mechanical Engineering; Department of Electrical and Electronics Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Sciences; College of Engineering; College of Engineering; College of Engineering; N/A; 59959; N/A; N/A; N/A; 8579
    This paper reports a MEMS-based sensor array enabling multiple clot-time tests in one disposable microfluidic cartridge using plasma. The versatile LoC (Lab-on-Chip) platform technology is demonstrated here for real-time coagulation tests (activated Partial Thrompoblastin Time (aPTT) and Prothrombin Time (PT)). The system has a reader unit and a disposable cartridge. The reader has no electrical connections to the cartridge, which consists of multiple microfluidic channels and MEMS microcantilevers placed in each channel. Microcantilevers are made of electro-plated nickel and actuated remotely using an external electro-coil. The read-out is also conducted remotely by a laser and the phase of the MEMS oscillator is monitored real-time. The system is capable of monitoring coagulation time with a precision estimated at 0.1sec.
  • Placeholder
    PublicationMetadata only
    Measuring local RF heating in MRI: simulating perfusion in a perfusionless phantom
    (Wiley-Blackwell, 2007) Atalar, Ergin; Güney, Sevin; Akça, İmran B; Yeung, Christopher J.; Taşçı, T. Onur; N/A; Ferhanoğlu, Onur; PhD Student; Graduate School of Sciences and Engineering; 205198
    Purpose: To overcome conflicting methods of local RF heating measurements by proposing a simple technique for predicting in vivo temperature rise by using a gel phantom experiment. Materials and Methods: In vivo temperature measurements are difficult to conduct reproducibly; fluid phantoms introduce convection, and gel phantom lacks perfusion. In the proposed method the local temperature rise is measured in a gel phantom at a timepoint that the phantom temperature would be equal to the perfused body steady-state temperature value. The idea comes from the fact that the steady-state temperature rise in a perfused body is smaller than the steady-state temperature increase in a perfusionless phantom. Therefore, when measuring the temperature on a phantom there will be the timepoint that corresponds to the perfusion time constant of the body part. Results: The proposed method was tested with several phantom and in vivo experiments. Instead, an overall average of 30.8% error can be given as the amount of underestimation with the proposed method. This error is within the variability of in vivo experiments (45%). Conclusion: With the aid of this reliable temperature rise prediction the amount of power delivered by the scanner can be controlled, enabling safe MRI examinations of patients with implants. © 2007 Wiley-Liss, Inc.