Search

Highlights: [•] We present a strategy to create objectively labeled ground-truth set of videos. [•] Such a strategy mitigates the subjective biases of the annotation process. [•] Objective labels show superior consistency than subjective labels. [•] A classifier is trained to predict objective labels for 51K unlabeled videos. [ABSTRACT FROM AUTHOR]

Abstract: We consider two hypothesis testing problems with independent observations on a single -vector, when , and the observations on the random -vector are independently and identically distributed as multivariate normal with mean vector and covariance matrix , both unknown. In the first problem, the -vector is partitioned into two sub-vectors of dimensions and , respectively, and we propose two tests for the independence of the two sub-vectors that are valid as . The asymptotic distribution of the test statistics under the hypothesis of independence is shown to be standard normal, and the power examined by simulations. The proposed tests perform better than the likelihood ratio test, although the latter can only be used when is smaller than . The second problem addressed is that of testing the hypothesis that the covariance matrix is of the intraclass correlation structure. A statistic for testing this is proposed, and assessed via simulations; again the proposed test statistic compares favorably with the likelihood ratio test. [Copyright &y& Elsevier]

The shapes of plant leaves are important features to biologists, as they can help in distinguishing plant species, measuring their health, analyzing their growth patterns, and understanding relations between various species. Most of the methods that have been developed in the past focus on comparing the shape of individual leaves using either descriptors or finite sets of landmarks. However, descriptor-based representations are not invertible and thus it is often hard to map descriptor variability into shape variability. On the other hand, landmark-based techniques require automatic detection and registration of the landmarks, which is very challenging in the case of plant leaves that exhibit high variability within and across species. In this paper, we propose a statistical model based on the Squared Root Velocity Function (SRVF) representation and the Riemannian elastic metric of Srivastava et al. (2011) to model the observed continuous variability in the shape of plant leaves. We treat plant species as random variables on a non-linear shape manifold and thus statistical summaries, such as means and covariances, can be computed. One can then study the principal modes of variations and characterize the observed shapes using probability density models, such as Gaussians or Mixture of Gaussians. We demonstrate the usage of such statistical model for (1) efficient classification of individual leaves, (2) the exploration of the space of plant leaf shapes, which is important in the study of population-specific variations, and (3) comparing entire plant species, which is fundamental to the study of evolutionary relationships in plants. Our approach does not require descriptors or landmarks but automatically solves for the optimal registration that aligns a pair of shapes. We evaluate the performance of the proposed framework on publicly available benchmarks such as the Flavia, the Swedish, and the ImageCLEF2011 plant leaf datasets. [ABSTRACT FROM AUTHOR]

• We retrospectively classified PNES using four different classification systems. • The most common PNES semiology in our cohort was pseudosyncope/dialeptic/non-motor. • All PNES events were classified by the systems by Asadi-Pooya and Wadwekar et al. • 37 (7.5%) PNES events remained unclassified using the system by Hubsch et al. • 5 (1%) events remained unclassified using the system by Dhiman et al. Multiple classification systems for psychogenic nonepileptic seizures (PNES) based on semiological features have been described. We sought to compare the efficiency of four PNES classification systems. We retrospectively analyzed medical and video-electroencephalography (VEEG) records of patients with PNES with at least one typical event recorded on VEEG. Semiology of PNES events was stringently classified using Hubsch, Dhiman, Wadwekar, and Asadi-Pooya's classification systems. We studied 248 patients with PNES (78% females, mean age 23.1 ± 10.3 years) and reviewed 498 PNES events. Using Hubsch's scheme, we classified events into: dystonic attacks with primitive gestural activity (5.2%), paucikinetic attacks with preserved responsiveness (9.7%), pseudosyncope (59.8%), hyperkinetic prolonged attacks (16.2%) and axial dystonic prolonged attacks (1.6%), and unclassified (7.5%). Using Dhiman's classification, events were: abnormal motor (hypermotor [10.4%]/ partial motor [12.7%]), dialeptic type (58.6%), mixed patterns (17.3%), and unclassified (1%). Using Wadwekar's classification: dystonic attacks with primitive gestural activity (5.2%), paucikinetic attacks with preserved responsiveness (9.6%), pseudosyncope with/without hyperventilation (65.1%), hyperkinetic prolonged attacks involving limbs ± trunk (18.5%), and axial dystonic prolonged attacks (1.6%). Using Asadi-Pooya's classification, events were: hypermotor (30.1%), non-motor (62.9%), and mixed (7.0%). All events could be classified via Wadwekar and Asadi-Pooya systems. In our study, pseudosyncope/dialeptic/non-motor semiology emerged as most frequent. Most of our patients with PNES had stereotyped semiology. All events could be classified using the schemes by Asadi-Pooya and Wadweker et al. Dhiman et al. scheme could classify 99% and 7.5% remained unclassified using Hubsch et al. scheme. [ABSTRACT FROM AUTHOR]