Decision fusion for the classification of hyperspectral data: Outcome of the 2008 GRS-S data fusion contest

The 2008 Data Fusion Contest organized by the IEEE Geoscience and Remote Sensing Data Fusion Technical Committee deals with the classification of high-resolution hyperspectral data from an urban area. Unlike in the previous issues of the contest, the goal was not only to identify the best algorithm but also to provide a collaborative effort: The decision fusion of the best individual algorithms was aiming at further improving the classification performances, and the best algorithms were ranked according to their relative contribution to the decision fusion. This paper presents the five awarded algorithms and the conclusions of the contest, stressing the importance of decision fusion, dimension reduction, and supervised classification methods, such as neural networks and support vector machines.

Measurement with an automated oscillometric wrist device with position sensor leads to lower values than measurements obtained with an automated oscillometric arm device from the same manufacturer in elderly persons.

OBJECTIVE: Home blood pressure (BP) monitoring is recommended by several clinical guidelines and has been shown to be feasible in elderly persons. Wrist manometers have recently been proposed for such home BP measurement, but their accuracy has not been previously assessed in elderly patients. METHODS: Forty-eight participants (33 women and 15 men, mean age 81.3±8.0 years) had their BP measured with a wrist device with position sensor and an arm device in random order in a sitting position. RESULTS: Average BP measurements were consistently lower with the wrist than arm device for systolic BP (120.1±2.2 vs. 130.5±2.2 mmHg, P<0.001, means±SD) and diastolic BP (66.0±1.3 vs. 69.7±1.3 mmHg, P<0.001). Moreover, a 10 mmHg or greater difference between the arm and wrist device was observed in 54.2 and 18.8% of systolic and diastolic measures, respectively. CONCLUSION: Compared with the arm device, the wrist device with position sensor systematically underestimated systolic as well as diastolic BP. The magnitude of the difference is clinically significant and questions the use of the wrist device to monitor BP in elderly persons. This study points to the need to validate BP measuring devices in all age groups, including in elderly persons.

The NLRP3 inflammasome: a sensor for metabolic danger?

Interleukin-1beta (IL-1beta), reactive oxygen species (ROS), and thioredoxin-interacting protein (TXNIP) are all implicated in the pathogenesis of type 2 diabetes mellitus (T2DM). Here we review mechanisms directing IL-1beta production and its pathogenic role in islet dysfunction during chronic hyperglycemia. In doing so, we integrate previously disparate disease-driving mechanisms for IL-1beta, ROS, and TXNIP in T2DM into one unifying model in which the NLRP3 inflammasome plays a central role. The NLRP3 inflammasome also drives IL-1beta maturation and secretion in another disease of metabolic dysregulation, gout. Thus, we propose that the NLRP3 inflammasome contributes to the pathogenesis of T2DM and gout by functioning as a sensor for metabolic stress.

Risk Evaluation for Spoofing against a Sensor Supplied with Liveness Detection

The aim of this paper is to evaluate the risks associated with the use of fake fingerprints on a livescan supplied with a method of liveness detection. The method is based on optical properties of the skin. The sensor uses several polarizations and illuminations to capture the information of the different layers of the human skin. These experiments also allow for the determination under which conditions the system is deceived and if there is an influence respectively of the nature of the fake, the mould used for the production or the individuals involved in the attack. These experiments showed that current multispectral sensors can be deceived by the use of fake fingerprints created with or without the cooperation of the subject. Fakes created from direct casts perform better than those produced by fakes created from indirect casts. The results showed that the success of the attack is influenced by two main factors. The first is the quality of the fakes, and by extension the quality of the original fingerprint. The second is the combination of the general patterns involved in the attacks since an appropriate combination can strongly increase the rates of successful attacks.

A novel method for automated classification of epileptiform activity in the human electroencephalogram-based on independent component analysis.

Diagnosis of several neurological disorders is based on the detection of typical pathological patterns in the electroencephalogram (EEG). This is a time-consuming task requiring significant training and experience. Automatic detection of these EEG patterns would greatly assist in quantitative analysis and interpretation. We present a method, which allows automatic detection of epileptiform events and discrimination of them from eye blinks, and is based on features derived using a novel application of independent component analysis. The algorithm was trained and cross validated using seven EEGs with epileptiform activity. For epileptiform events with compensation for eyeblinks, the sensitivity was 65 +/- 22% at a specificity of 86 +/- 7% (mean +/- SD). With feature extraction by PCA or classification of raw data, specificity reduced to 76 and 74%, respectively, for the same sensitivity. On exactly the same data, the commercially available software Reveal had a maximum sensitivity of 30% and concurrent specificity of 77%. Our algorithm performed well at detecting epileptiform events in this preliminary test and offers a flexible tool that is intended to be generalized to the simultaneous classification of many waveforms in the EEG.

Measurement of the dynamics in ski jumping using a wearable inertial sensor-based system.

Abstract Dynamics is a central aspect of ski jumping, particularly during take-off and stable flight. Currently, measurement systems able to measure ski jumping dynamics (e.g. 3D cameras, force plates) are complex and only available in few research centres worldwide. This study proposes a method to determine dynamics using a wearable inertial sensor-based system which can be used routinely on any ski jumping hill. The system automatically calculates characteristic dynamic parameters during take-off (position and velocity of the centre of mass perpendicular to the table, force acting on the centre of mass perpendicular to the table and somersault angular velocity) and stable flight (total aerodynamic force). Furthermore, the acceleration of the ski perpendicular to the table was quantified to characterise the skis lift at take-off. The system was tested with two groups of 11 athletes with different jump distances. The force acting on the centre of mass, acceleration of the ski perpendicular to the table, somersault angular velocity and total aerodynamic force were different between groups and correlated with the jump distances. Furthermore, all dynamic parameters were within the range of prior studies based on stationary measurement systems, except for the centre of mass mean force which was slightly lower.

Non-invasive and non-occlusive blood pressure estimation via a chest sensor.

The clinical demand for a device to monitor Blood Pressure (BP) in ambulatory scenarios with minimal use of inflation cuffs is increasing. Based on the so-called Pulse Wave Velocity (PWV) principle, this paper introduces and evaluates a novel concept of BP monitor that can be fully integrated within a chest sensor. After a preliminary calibration, the sensor provides non-occlusive beat-by-beat estimations of Mean Arterial Pressure (MAP) by measuring the Pulse Transit Time (PTT) of arterial pressure pulses travelling from the ascending aorta towards the subcutaneous vasculature of the chest. In a cohort of 15 healthy male subjects, a total of 462 simultaneous readings consisting of reference MAP and chest PTT were acquired. Each subject was recorded at three different days: D, D+3 and D+14. Overall, the implemented protocol induced MAP values to range from 80 ± 6 mmHg in baseline, to 107 ± 9 mmHg during isometric handgrip maneuvers. Agreement between reference and chest-sensor MAP values was tested by using intraclass correlation coefficient (ICC = 0.78) and Bland-Altman analysis (mean error = 0.7 mmHg, standard deviation = 5.1 mmHg). The cumulative percentage of MAP values provided by the chest sensor falling within a range of ±5 mmHg compared to reference MAP readings was of 70%, within ±10 mmHg was of 91%, and within ±15mmHg was of 98%. These results point at the fact that the chest sensor complies with the British Hypertension Society (BHS) requirements of Grade A BP monitors, when applied to MAP readings. Grade A performance was maintained even two weeks after having performed the initial subject-dependent calibration. In conclusion, this paper introduces a sensor and a calibration strategy to perform MAP measurements at the chest. The encouraging performance of the presented technique paves the way towards an ambulatory-compliant, continuous and non-occlusive BP monitoring system.

A combined ear sensor for pulse oximetry and carbon dioxide tension monitoring: accuracy in critically ill children.

IMPLICATIONS: A new combined ear sensor was tested for accuracy in 20 critically ill children. It provides noninvasive and continuous monitoring of arterial oxygen saturation, arterial carbon dioxide tension, and pulse rate. The sensor proved to be clinically accurate in the tested range.

HAMAP in 2015: updates to the protein family classification and annotation system.

HAMAP (High-quality Automated and Manual Annotation of Proteins-available at http://hamap.expasy.org/) is a system for the automatic classification and annotation of protein sequences. HAMAP provides annotation of the same quality and detail as UniProtKB/Swiss-Prot, using manually curated profiles for protein sequence family classification and expert curated rules for functional annotation of family members. HAMAP data and tools are made available through our website and as part of the UniRule pipeline of UniProt, providing annotation for millions of unreviewed sequences of UniProtKB/TrEMBL. Here we report on the growth of HAMAP and updates to the HAMAP system since our last report in the NAR Database Issue of 2013. We continue to augment HAMAP with new family profiles and annotation rules as new protein families are characterized and annotated in UniProtKB/Swiss-Prot; the latest version of HAMAP (as of 3 September 2014) contains 1983 family classification profiles and 1998 annotation rules (up from 1780 and 1720). We demonstrate how the complex logic of HAMAP rules allows for precise annotation of individual functional variants within large homologous protein families. We also describe improvements to our web-based tool HAMAP-Scan which simplify the classification and annotation of sequences, and the incorporation of an improved sequence-profile search algorithm.

Introducing a new MRI classification of lumbar spinal stenosis based on cross-sectional morphology of the dural sac : 37

Introduction: Measures of the degree of lumbar spinal stenosis (LSS) such as antero-posterior diameter of the canal, and dural sac cross sectional area vary, and do not correlate with symptoms or results of surgery. We created a grading system, comprised of seven categories, based on the morphology of the dural sac and its contents as seen on T2 axial images. The categories take into account the ratio of rootlet/ CSF content. Grade A indicates no significant compression, grade D is equivalent to a total myelograhic block. We compared this classification with commonly used criteria of severity of stenosis. Methods: Fifty T2 axial MRI images taken at disc level from 27 symptomatic LSS patients undergoing decompressive surgery were classified twice by two radiologists and three spinal surgeons working at different institutions and countries. Dural sac cross-sectional surface area and AP diameter of the canal were measured both at disc and pedicle level from DICOM images using OsiriX software. Intraand inter-observer reliability were assessed using Cohen's, Fleiss' kappa statistics, and t test. Results: For the morphological grading the average intra-and inter observer kappas were 0.76 and 0.69+, respectively, for physicians working in the study originating country. Combining all observers the kappa values were 0.57 ± 0.19. and 0.44 ± 0.19, respectively. AP diameter and dural sac cross-sectional area measurements showed no statistically significant differences between observers. No correlation between morphological grading and AP diameter or dural sac crosssectional areawas observed in 13 (26%) and 8 cases (16%), respectively. Discussion: The proposed morphological grading relies on the identification of the dural sac and CSF better seen on full MRI series. This was not available to the external observers, which might explain the lower overall kappa values. Since no specific measurement tools are needed the grading suits everyday clinical practice and favours communication of degree of stenosis between practising physicians. The absence of a strict correlation with the dural sac surface suggests that measuring the surface alone might be insufficient in defining LSS as it is essentially a mismatch between the spinal canal and its contents. This grading is now adopted in our unit and further studies concentrating on relation between morphology, clinical symptoms and surgical results are underway.

Event-related potential analyses via single-subject topographic classification.

Introduction: Responses to external stimuli are typically investigated by averaging peri-stimulus electroencephalography (EEG) epochs in order to derive event-related potentials (ERPs) across the electrode montage, under the assumption that signals that are related to the external stimulus are fixed in time across trials. We demonstrate the applicability of a single-trial model based on patterns of scalp topographies (De Lucia et al, 2007) that can be used for ERP analysis at the single-subject level. The model is able to classify new trials (or groups of trials) with minimal a priori hypotheses, using information derived from a training dataset. The features used for the classification (the topography of responses and their latency) can be neurophysiologically interpreted, because a difference in scalp topography indicates a different configuration of brain generators. An above chance classification accuracy on test datasets implicitly demonstrates the suitability of this model for EEG data. Methods: The data analyzed in this study were acquired from two separate visual evoked potential (VEP) experiments. The first entailed passive presentation of checkerboard stimuli to each of the four visual quadrants (hereafter, "Checkerboard Experiment") (Plomp et al, submitted). The second entailed active discrimination of novel versus repeated line drawings of common objects (hereafter, "Priming Experiment") (Murray et al, 2004). Four subjects per experiment were analyzed, using approx. 200 trials per experimental condition. These trials were randomly separated in training (90%) and testing (10%) datasets in 10 independent shuffles. In order to perform the ERP analysis we estimated the statistical distribution of voltage topographies by a Mixture of Gaussians (MofGs), which reduces our original dataset to a small number of representative voltage topographies. We then evaluated statistically the degree of presence of these template maps across trials and whether and when this was different across experimental conditions. Based on these differences, single-trials or sets of a few single-trials were classified as belonging to one or the other experimental condition. Classification performance was assessed using the Receiver Operating Characteristic (ROC) curve. Results: For the Checkerboard Experiment contrasts entailed left vs. right visual field presentations for upper and lower quadrants, separately. The average posterior probabilities, indicating the presence of the computed template maps in time and across trials revealed significant differences starting at ~60-70 ms post-stimulus. The average ROC curve area across all four subjects was 0.80 and 0.85 for upper and lower quadrants, respectively and was in all cases significantly higher than chance (unpaired t-test, p<0.0001). In the Priming Experiment, we contrasted initial versus repeated presentations of visual object stimuli. Their posterior probabilities revealed significant differences, which started at 250ms post-stimulus onset. The classification accuracy rates with single-trial test data were at chance level. We therefore considered sub-averages based on five single trials. We found that for three out of four subjects' classification rates were significantly above chance level (unpaired t-test, p<0.0001). Conclusions: The main advantage of the present approach is that it is based on topographic features that are readily interpretable along neurophysiologic lines. As these maps were previously normalized by the overall strength of the field potential on the scalp, a change in their presence across trials and between conditions forcibly reflects a change in the underlying generator configurations. The temporal periods of statistical difference between conditions were estimated for each training dataset for ten shuffles of the data. Across the ten shuffles and in both experiments, we observed a high level of consistency in the temporal periods over which the two conditions differed. With this method we are able to analyze ERPs at the single-subject level providing a novel tool to compare normal electrophysiological responses versus single cases that cannot be considered part of any cohort of subjects. This aspect promises to have a strong impact on both basic and clinical research.