Search

Quadruped robots require robust and general locomotion skills to exploit their mobility potential in complex and challenging environments. In this work, we present an implementation of a robust end-to-end learning-based controller on the Solo12 quadruped. Our method is based on deep reinforcement learning of joint impedance references. The resulting control policies follow a commanded velocity reference while being efficient in its energy consumption and easy to deploy. We detail the learning procedure and method for transfer on the real robot. We show elaborate experiments. Finally, we present experimental results of the learned locomotion on various grounds indoors and outdoors. These results show that the Solo12 robot is a suitable open-source platform for research combining learning and control because of the easiness in transferring and deploying learned controllers., (© 2023. The Author(s).)

Ongoing cognition supports behavioral flexibility by facilitating behavior in the moment, and through the consideration of future actions. These different modes of cognition are hypothesized to vary with the correlation between brain activity and external input, since evoked responses are reduced when cognition switches to topics unrelated to the current task. This study examined whether these reduced evoked responses change as a consequence of the task environment in which the experience emerges. We combined electroencephalography (EEG) recording with multidimensional experience sampling (MDES) to assess the electrophysiological correlates of ongoing thought in task contexts which vary on their need to maintain continuous representations of task information for satisfactory performance. We focused on an event-related potential (ERP) known as the parietal P3 that had a greater amplitude in our tasks relying on greater external attention. A principal component analysis (PCA) of the MDES data revealed four patterns of ongoing thought: off-task episodic social cognition, deliberate on-task thought, imagery, and emotion. Participants reported more off-task episodic social cognition and mental imagery under low external demands and more deliberate on-task thought under high external task demands. Importantly, the occurrence of off-task episodic social cognition was linked to similar reductions in the amplitude of the P3 regardless of external task. These data suggest the amplitude of the P3 may often be a general feature of external task-related content and suggest attentional decoupling from sensory inputs are necessary for certain types of perceptually-decoupled, self-generated thoughts., (Copyright © 2022 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Mutations in the immunoglobulin superfamily, member 1 gene (IGSF1/Igsf1) cause an X-linked form of central hypothyroidism. The canonical form of IGSF1 is a transmembrane glycoprotein with 12 immunoglobulin (Ig) loops. The protein is co-translationally cleaved into two sub-domains. The carboxyl-terminal domain (CTD), which contains the last 7 Ig loops, is trafficked to the plasma membrane. Most pathogenic mutations in IGSF1 map to the portion of the gene encoding the CTD. IGSF1/Igsf1 encodes a variety of transcripts. A little studied, but abundant splice variant encodes a truncated form of the protein, predicted to contain the first 2 Ig loops of the full-length IGSF1. The protein (hereafter referred to as IGSF1 isoform 2 or IGSF1-2) is likely retained in most individuals with IGSF1 mutations. Here, we characterized basic biochemical properties of the protein as a foray into understanding its potential function. IGSF1-2, like the IGSF1-CTD, is a glycoprotein. In both mouse and rat, the protein is N-glycosylated at a single asparagine residue in the first Ig loop. Contrary to earlier predictions, neither the murine nor rat IGSF1-2 is secreted from heterologous or homologous cells. In addition, neither protein associates with the plasma membrane. Rather, IGSF1-2 appears to be retained in the endoplasmic reticulum. Whether the protein plays intracellular functions or is trafficked through the secretory pathway under certain physiologic or pathophysiologic conditions has yet to be determined.

We introduce an automated pathology classification system for medical volumetric brain image slices. Existing work often relies on handcrafted features extracted from automatic image segmentation. This is not only a challenging and time-consuming process, but it may also limit the adaptability and robustness of the system. We propose a novel approach to combine sparse Gabor-feature based classifiers in an ensemble classification framework. The unsupervised nature of this non-parametric technique can significantly reduce the time and effort for system calibration. In particular, classification of medical images in this framework does not rely on segmentation, nor semantic-based or annotation-based feature selection. Our experiments show very promising results in classifying computer tomography image slices into pathological classes for traumatic brain injury patients.

We introduce an automated, pathological class level annotation system for medical volumetric brain images. While much of the earlier work has mainly focused on annotating regions of interest in medical images, our system does not require annotated region level training data nor assumes perfect segmentation results for the regions of interest; the time and effort needed for acquiring training data are hence significantly reduced. This capability of handling high-dimensional noisy data, however, poses additional technical challenges, since statistical estimation of models for such data is prone to over-fitting. We propose a framework that combines a regularized logistic regression method and a kernel-based discriminative method to address these problems. Regularized methods provide a flexible selection mechanism that is well-suited for high dimensional noisy data. Our experiments show promising results in classifying computer tomography images of traumatic brain injury patients into pathological classes.

Background: It has been shown that if genetic relationships among individuals are not taken into account for genome wide association studies, this may lead to false positives. To address this problem, we used Genome-wide Rapid Association using Mixed Model and Regression and principal component stratification analyses. To account for linkage disequilibrium among the significant markers, principal components loadings obtained from top markers can be included as covariates. Estimation of Bayesian networks may also be useful to investigate linkage disequilibrium among SNPs and their relation with environmental variables.For the quantitative trait we first estimated residuals while taking polygenic effects into account. We then used a single SNP approach to detect the most significant SNPs based on the residuals and applied principal component regression to take linkage disequilibrium among these SNPs into account. For the categorical trait we used principal component stratification methodology to account for background effects. For correction of linkage disequilibrium we used principal component logit regression. Bayesian networks were estimated to investigate relationship among SNPs., Results: Using the Genome-wide Rapid Association using Mixed Model and Regression and principal component stratification approach we detected around 100 significant SNPs for the quantitative trait (p<0.05 with 1000 permutations) and 109 significant (p<0.0006 with local FDR correction) SNPs for the categorical trait. With additional principal component regression we reduced the list to 16 and 50 SNPs for the quantitative and categorical trait, respectively., Conclusions: GRAMMAR could efficiently incorporate the information regarding random genetic effects. Principal component stratification should be cautiously used with stringent multiple hypothesis testing correction to correct for ancestral stratification and association analyses for binary traits when there are systematic genetic effects such as half sib family structures. Bayesian networks are useful to investigate relationships among SNPs and environmental variables.

This paper proposes a generative model approach to automatically annotate medical images to improve the efficiency and effectiveness of image retrieval systems for teaching, research, and diagnosis. The generative model captures the probabilistic relationships among relevant classification tags, tentative lesion patterns, and selected input features. Operating on the imperfect segmentation results of input images, the probabilistic framework can effectively handle the inherent uncertainties in the images and insufficient information in the training data. Preliminary assessment in the ischemic stroke subtype classification shows that the proposed system is capable of generating the relevant tags for ischemic stroke brain images. The main benefit of this approach is its scalability; the method can be applied in large image databases as it requires only minimal manual labeling of the training data and does not demand high-precision segmentation of the images.

We have developed an approach to classify toxicants based upon their influence on profiles of mRNA transcripts. Changes in liver gene expression were examined after exposure of mice to 24 model treatments that fall into five well-studied toxicological categories: peroxisome proliferators, aryl hydrocarbon receptor agonists, noncoplanar polychlorinated biphenyls, inflammatory agents, and hypoxia-inducing agents. Analysis of 1200 transcripts using both a correlation-based approach and a probabilistic approach resulted in a classification accuracy of between 50 and 70%. However, with the use of a forward parameter selection scheme, a diagnostic set of 12 transcripts was identified that provided an estimated 100% predictive accuracy based on leave-one-out cross-validation. Expansion of this approach to additional chemicals of regulatory concern could serve as an important screening step in a new era of toxicological testing.

In patients with obstructive jaundice, biliary decompression can be achieved by an endoprosthesis inserted by a percutaneous transhepatic approach. The prosthesis sometimes becomes dislodged and thus additional percutaneous transhepatic procedures may be required. To avoid this problem, a nondislodgeable endoprosthesis has been developed. The prosthesis is constructed with a layer of biocompatible material (hydrogel) on its surface. The hydrogel is located in grooves around the endoprosthesis and has the ability to absorb liquid, which increases its size. By placing the rings of hydrogel on either side of the obstruction, dislodgement of the prosthesis can be prevented. The nondislodgeable endoprosthesis has been inserted into 11 patients with biliary obstructions due to malignant strictures. No dislodgement has occurred and the established internal drainage reduced serum bilirubin levels without any major complications.