keyword
MENU ▼
Read by QxMD icon Read
search

benchmark

keyword
https://www.readbyqxmd.com/read/28103555/robust-head-pose-estimation-based-on-partially-latent-mixture-of-linear-regressions
#1
Vincent Drouard, Radu Horaud, Antoine Deleforge, Sileye Ba, Georgios Evangelidis
Head-pose estimation has many applications, such as social event analysis, human-robot and human-computer interaction, driving assistance, and so forth. Head-pose estimation is challenging because it must cope with changing illumination conditions, variabilities in face orientation and in appearance, partial occlusions of facial landmarks, as well as bounding-box-to- face alignment errors. We propose tu use a mixture of linear regressions with partially-latent output. This regression method learns to map high-dimensional feature vectors (extracted from bounding boxes of faces) onto the joint space of head-pose angles and bounding-box shifts, such that they are robustly predicted in the presence of unobservable phenomena...
January 16, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
https://www.readbyqxmd.com/read/28103196/sensor-based-gait-parameter-extraction-with-deep-convolutional-neural-networks
#2
Julius Hannink, Thomas Kautz, Cristian Pasluosta, Karl-Gunter Gassmann, Jochen Klucken, Bjoern Eskofier
Measurement of stride-related, biomechanical parameters is the common rationale for objective gait impairment scoring. State-of-the-art double integration approaches to extract these parameters from inertial sensor data are, however, limited in their clinical applicability due to the underlying assumptions. To overcome this, we present a method to translate the abstract information provided by wearable sensors to context-related expert features based on deep convolutional neural networks. Regarding mobile gait analysis, this enables integration-free and data-driven extraction of a set of eight spatio-temporal stride parameters...
December 8, 2016: IEEE Journal of Biomedical and Health Informatics
https://www.readbyqxmd.com/read/28103193/comprehensive-use-of-curvature-for-robust-and-accurate-online-surface-reconstruction
#3
Damien Lefloch, Markus Kluge, Hamed Sarbolandi, Tim Weyrich, Andreas Kolb
Interactive real-time scene acquisition from hand-held depth cameras has recently developed much momentum, enabling applications in ad-hoc object acquisition, augmented reality and other fields. A key challenge to online reconstruction remains error accumulation in the reconstructed camera trajectory, due to drift-inducing instabilities in the range scan alignments of the underlying iterative-closest-point (ICP) algorithm. Various strategies have been proposed to mitigate that drift, including SIFT-based pre-alignment, color-based weighting of ICP pairs, stronger weighting of edge features, and so on...
January 5, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
https://www.readbyqxmd.com/read/28103192/audio-visual-speaker-diarization-based-on-spatiotemporal-bayesian-fusion
#4
Israel Gebru, Sileye Ba, Xiaofei Li, Radu Horaud
Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem...
January 5, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
https://www.readbyqxmd.com/read/28103189/dynamic-programming-for-instance-annotation-in-multi-instance-multi-label-learning
#5
Anh Pham, Raviv Raich, Xiaoli Fern
Labeling data for classification requires significant human effort. To reduce labeling cost, instead of labeling every instance, a group of instances (bag) is labeled by a single bag label. Computer algorithms are then used to infer the label for each instance in a bag, a process referred to as instance annotation. This task is challenging due to the ambiguity regarding the instance labels. We propose a discriminative probabilistic model for the instance annotation problem and introduce an expectation maximization framework for inference, based on the maximum likelihood approach...
January 5, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
https://www.readbyqxmd.com/read/28103026/benchmark-quality-atomization-energies-for-beh-and-beh2
#6
Monica Vasiliu, Kirk A Peterson, David A Dixon
The total atomization energies for BeH and BeH2 have been calculated using the Feller-Peterson-Dixon approach to better than ±1 kcal/mol. The calculations are based on CCSD(T) all electron calculations extrapolated to the complete limit and CCSDT and CCSDTQ corrections are included. A scalar relativistic correction and a diagonal Born-Oppenheimer correction are included. Accurate zero point energies are used. The total atomization energies at 0K are 47.7 kcal/mol for BeH and 140.0 kcal/mol for BeH2 with error bars of at most ±0...
January 19, 2017: Journal of Chemical Theory and Computation
https://www.readbyqxmd.com/read/28102953/air-kerma-strength-determination-of-an-hdr-192-ir-source-including-a-geometric-sensitivity-study-of-the-seven-distance-method
#7
Blake R Smith, John A Micka, Manik Aima, Larry A DeWerd, Wesley S Culberson
PURPOSE: To perform an in-air air-kerma strength (SK) calibration of the Bebig model Ir2.A85-2 192Ir high-dose rate (HDR) brachytherapy source manufactured by Mallinckrodt Medical (Westerduinweg, Germany) with the NIST-traceable seven-distance technique established by the University of Wisconsin. A comparison was made between the reference air-kerma rate (RAKR) reported on a certificate from the Physikalisch-Technische Bundesanstalt (Berlin, Germany) (PTB) primary laboratory and the SK determined at the University of Wisconsin Madison Radiation Research Center (UWMRRC)...
January 2017: Medical Physics
https://www.readbyqxmd.com/read/28102672/coupled-cluster-studies-of-ionization-potentials-and-electron-affinities-of-single-walled-carbon-nanotubes
#8
Bo Peng, Niranjan Govind, Edoardo Aprà, Michael Klemm, Jeff R Hammond, Karol Kowalski
In this paper we apply the equation-of-motion coupled cluster (EOM-CC) methods in the studies of the vertical ionization potentials (IPs) and electron affinities (EAs) for a series of single walled carbon nanotubes (SWCNT). The EOM-CC formulations for IPs and EAs employing excitation manifolds spanned by single and double excitations (IP/EA-EOM-CCSD) are used to study the IPs and EAs of the SWCNTs as a func- tion of the nanotube length. Several armchair nanotubes corresponding to C20nH20 models with n = 2 - 6 have been used in benchmark calculations...
January 19, 2017: Journal of Physical Chemistry. A
https://www.readbyqxmd.com/read/28102448/development-of-a-new-assessment-tool-for-cervical-myelopathy-using-hand-tracking-sensor-part-1-validity-and-reliability
#9
M Abdulhadi Alagha, Mahmoud A Alagha, Eleanor Dunstan, Olaf Sperwer, Kate A Timmins, Bronek M Boszczyk
PURPOSE: To assess the reliability and validity of a hand motion sensor, Leap Motion Controller (LMC), in the 15-s hand grip-and-release test, as compared against human inspection of an external digital camera recording. METHODS: Fifty healthy participants were asked to fully grip-and-release their dominant hand as rapidly as possible for two trials with a 10-min rest in-between, while wearing a non-metal wrist splint. Each test lasted for 15 s, and a digital camera was used to film the anterolateral side of the hand on the first test...
January 19, 2017: European Spine Journal
https://www.readbyqxmd.com/read/28100175/do-experiences-with-pregnancy-birth-and-postnatal-care-in-norway-vary-by-the-women-s-geographic-origin-a-comparison-of-cross-sectional-survey-results
#10
Ingeborg S Sjetne, Hilde H Iversen
BACKGROUND: A national survey was conducted to measure and benchmark women's experiences with pregnancy, birth and postnatal care in Norway. The purpose of this secondary analysis is to explore potential variation in these experiences with regard to the survey respondents' geographic origin. METHODS: Data were collected in a national observational cross-sectional study, by a self-administered questionnaire and from registries. The questionnaire collects patient reported experience measures (PREMS) of mainly nontechnical aspects of the health-care services...
January 18, 2017: BMC Pregnancy and Childbirth
https://www.readbyqxmd.com/read/28100157/characterization-of-planned-and-unplanned-30-day-readmissions-following-vascular-surgical-procedures
#11
Georges Tahhan, Alik Farber, Nishant K Shah, Brianna M Krafcik, Teviah E Sachs, Jeffrey A Kalish, Matthew R Peacock, Jeffrey J Siracuse
OBJECTIVE: Thirty-day readmission is increasingly used as a quality of care indicator. Patients undergoing vascular surgery have historically been at high risk for readmission. We analyzed hospital readmission details to identify patients at high risk for readmission in order to better understand these readmissions and improve resource utilization in this patient population. METHODS: A retrospective review and analysis of our medical center's admission and discharge data were conducted from October 2012 to March 2015...
January 2017: Vascular and Endovascular Surgery
https://www.readbyqxmd.com/read/28100145/chronic-health-conditions-among-incoming-canadian-federally-sentenced-women
#12
Amanda M Nolan, Lynn A Stewart
Over a 13-month period, health data on all consecutive incoming Canadian federally sentenced women offenders were collected and analyzed ( N = 280). The most common health conditions cited were back pain, head injury, hepatitis C virus (HCV), and asthma. Rates of chronic health problems were generally similar to those of their male offender counterparts, with the notable exception of HCV, which was higher for women. Aboriginal women offenders had particularly high rates of HCV. The study provides valuable information on the self-reported physical health status of federally sentenced women offenders that can be used as a benchmark to examine health trends over time...
January 2017: Journal of Correctional Health Care
https://www.readbyqxmd.com/read/28099489/acute-inactivation-of-primary-auditory-cortex-causes-a-sound-localisation-deficit-in-ferrets
#13
Katherine C Wood, Stephen M Town, Huriye Atilgan, Gareth P Jones, Jennifer K Bizley
The objective of this study was to demonstrate the efficacy of acute inactivation of brain areas by cooling in the behaving ferret and to demonstrate that cooling auditory cortex produced a localisation deficit that was specific to auditory stimuli. The effect of cooling on neural activity was measured in anesthetized ferret cortex. The behavioural effect of cooling was determined in a benchmark sound localisation task in which inactivation of primary auditory cortex (A1) is known to impair performance. Cooling strongly suppressed the spontaneous and stimulus-evoked firing rates of cortical neurons when the cooling loop was held at temperatures below 10°C, and this suppression was reversed when the cortical temperature recovered...
2017: PloS One
https://www.readbyqxmd.com/read/28099238/evaluation-of-the-new-north-carolina-burn-registry
#14
Lori Chrisco, Debbie Travers, Ernest J Grant
High-quality burn registries can facilitate best practices in burn treatment, patient education, and research. A new burn registry was designed and implemented at the North Carolina Jaycee Burn Center in June 2013. The primary goals for the design of the new North Carolina (NC) burn registry were to improve reporting to the American Burn Association's National Burn Repository while maintaining current functionality and preserving previously collected data. The objective of this evaluation was to review the literature for best practices in designing a disease registry, benchmark the design of the NC burn registry with the best practices identified in the literature, and compare data quality before and after implementation of the new NC burn registry...
January 10, 2017: Journal of Burn Care & Research: Official Publication of the American Burn Association
https://www.readbyqxmd.com/read/28097215/an-ambiguity-principle-for-assigning-protein-structural-domains
#15
Guillaume Postic, Yassine Ghouzam, Romain Chebrek, Jean-Christophe Gelly
Ambiguity is the quality of being open to several interpretations. For an image, it arises when the contained elements can be delimited in two or more distinct ways, which may cause confusion. We postulate that it also applies to the analysis of protein three-dimensional structure, which consists in dividing the molecule into subunits called domains. Because different definitions of what constitutes a domain can be used to partition a given structure, the same protein may have different but equally valid domain annotations...
January 2017: Science Advances
https://www.readbyqxmd.com/read/28097213/fully-automated-quantitative-cephalometry-using-convolutional-neural-networks
#16
Sercan Ö Arık, Bulat Ibragimov, Lei Xing
Quantitative cephalometry plays an essential role in clinical diagnosis, treatment, and surgery. Development of fully automated techniques for these procedures is important to enable consistently accurate computerized analyses. We study the application of deep convolutional neural networks (CNNs) for fully automated quantitative cephalometry for the first time. The proposed framework utilizes CNNs for detection of landmarks that describe the anatomy of the depicted patient and yield quantitative estimation of pathologies in the jaws and skull base regions...
January 2017: Journal of Medical Imaging
https://www.readbyqxmd.com/read/28096313/opportunities-to-reduce-ct-radiation-exposure-experience-over-5-years-at-the-nih-clinical-center
#17
William C Kovacs, Jianhua Yao, David A Bluemke, Les R Folio
Our current study was undertaken in order to compare CT exposures during various dose-reduction initiatives at the National Institutes of Health Clinical center, to show trends in exposure reduction over a 5-y period, and to provide benchmarks that other facilities may use. Using an in-house extraction tool (Radiation Exposure Extraction Engine), we derived CT exposure data from Digital Imaging and Communications in Medicine (DICOM) headers over 5 y. We present parameters used and compare most common exams between 2010 and 2015...
January 16, 2017: Radiation Protection Dosimetry
https://www.readbyqxmd.com/read/28096085/improved-orthology-inference-with-hieranoid-2
#18
Mateusz Kaduk, Erik Sonnhammer
MOTIVATION: The initial step in many orthology inference methods is the computationally demanding establishment of all pairwise protein similarities across all analysed proteomes. The quadratic scaling with proteomes has become a major bottleneck. A remedy is offered by the Hieranoid algorithm which reduces the complexity to linear by hierarchically aggregating ortholog groups from InParanoid along a species tree. RESULTS: We have further developed the Hieranoid algorithm in many ways...
January 17, 2017: Bioinformatics
https://www.readbyqxmd.com/read/28095772/empirical-assessment-of-analysis-workflows-for-differential-expression-analysis-of-human-samples-using-rna-seq
#19
Claire R Williams, Alyssa Baccarella, Jay Z Parrish, Charles C Kim
BACKGROUND: RNA-Seq has supplanted microarrays as the preferred method of transcriptome-wide identification of differentially expressed genes. However, RNA-Seq analysis is still rapidly evolving, with a large number of tools available for each of the three major processing steps: read alignment, expression modeling, and identification of differentially expressed genes. Although some studies have benchmarked these tools against gold standard gene expression sets, few have evaluated their performance in concert with one another...
January 17, 2017: BMC Bioinformatics
https://www.readbyqxmd.com/read/28095769/pcm-sabre-a-platform-for-benchmarking-and-comparing-outcome-prediction-methods-in-precision-cancer-medicine
#20
Noah Eyal-Altman, Mark Last, Eitan Rubin
BACKGROUND: Numerous publications attempt to predict cancer survival outcome from gene expression data using machine-learning methods. A direct comparison of these works is challenging for the following reasons: (1) inconsistent measures used to evaluate the performance of different models, and (2) incomplete specification of critical stages in the process of knowledge discovery. There is a need for a platform that would allow researchers to replicate previous works and to test the impact of changes in the knowledge discovery process on the accuracy of the induced models...
January 17, 2017: BMC Bioinformatics
keyword
keyword
120366
1
2
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read
×

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"