The positional information of objects is crucial to enable robots to perform grasping and pushing manipulations in *** effectively perform grasping and pushing manipu-lations,robots need to perceive the position infor...
详细信息
The positional information of objects is crucial to enable robots to perform grasping and pushing manipulations in *** effectively perform grasping and pushing manipu-lations,robots need to perceive the position information of objects,including the co-ordinates and spatial relationship between objects(e.g.,proximity,adjacency).The authors propose an end-to-end position-aware deep Q-learning framework to achieve efficient collaborative pushing and grasping in ***,a pair of conjugate pushing and grasping attention modules are proposed to capture the position information of objects and generate high-quality affordance maps of operating positions with features of pushing and grasping *** addition,the authors propose an object isolation metric and clutter metric based on instance segmentation to measure the spatial re-lationships between objects in cluttered *** further enhance the perception capacity of position information of the objects,the authors associate the change in the object isolation metric and clutter metric in cluttered environment before and after performing the action with reward function.A series of experiments are carried out in simulation and real-world which indicate that the method improves sample efficiency,task completion rate,grasping success rate and action efficiency compared to state-of-the-art end-to-end *** that the authors’system can be robustly applied to real-world use and extended to novel *** material is available at https://***/NhG\_k5v3NnM}{https://***/NhG\_k5v3NnM.
Biometrics plays a significant role in vision-based surveillance applications. Soft biometrics such as gait is widely used with face in surveillance tasks like person recognition and re-identification. Nevertheless, i...
Biometrics plays a significant role in vision-based surveillance applications. Soft biometrics such as gait is widely used with face in surveillance tasks like person recognition and re-identification. Nevertheless, in practical scenarios, classical fusion techniques respond poorly to the changes in individual users, external environment and varying contexts such as viewpoints. To this end, we propose a novel context-aware adaptive multi-biometric fusion strategy viz., ‘Adapt-FuseNet’ for the dynamic incorporation of gait and face biometric cues leveraging attention techniques. In particular, we investigate the impact of attention models such as parallel co-attention & keyless attention, along with various fusion strategies such as naïve fusion & adaptive fusion for human identification. Extensive experiments are carried out on two publically available large gait datasets i.e. CASIA-A and CASIA-B. Results show the superior performance of our proposed context-aware adaptive fusion model compared with the state-of-the-art models.
Big data is a concept that deals with large or complex data sets by using data analysis tools(e.g.,data mining,machine learning)to analyze information extracted from several sources *** data has attracted wide attenti...
详细信息
Big data is a concept that deals with large or complex data sets by using data analysis tools(e.g.,data mining,machine learning)to analyze information extracted from several sources *** data has attracted wide attention from academia,for example,in supporting patients and health professionals by improving the accuracy of decision-making,diagnosis and disease *** research aimed to perform a Bibliometric Performance and Network Analysis(BPNA)supported by a Scoping Review(SR)to depict the strategic themes,thematic evolution structure,main challenges and opportunities related to the concept of big data applied in the healthcare *** this goal in mind,4857 documents from the Web of Science covering the period between 2009 to June 2020 were analyzed with the support of SciMAT *** bibliometric performance showed the number of publications and citations over time,scientific productivity and the geographic distribution of publications and research *** strategic diagram yielded 20 clusters and their relative importance in terms of centrality and *** thematic evolution structure presented the most important themes and how it changes over ***,we presented the main challenges and future opportunities of big data in healthcare.
This paper proposes a Hardware-in-the-Loop sim-ulation (HiLs) tested via square Helmholtz coils as a relative magnetic field generator. In technical terms, the HiLs is an indispensable tool for engineering design duri...
This paper proposes a Hardware-in-the-Loop sim-ulation (HiLs) tested via square Helmholtz coils as a relative magnetic field generator. In technical terms, the HiLs is an indispensable tool for engineering design during rapid proto-typing of attitude determination and control algorithms for the turning parameters that control the attitude of the satellite, since most of the satellite's mission relies on its attitude, making this system one of the most essential to the satellite's operation. More-over, performing controlled experiments with the parameters for developing adaptive control algorithms improves the overall efficiency of the satellite's kinematic system. The conceptual design of a proposed system architecture can be composed of the electrical currents of 2.4-meter square Helmholtz coils produced by a low-level microcontroller equipped with a DC-motor driver by a pulse-width modulation (PWM) signal through real-time connection to an orbit propagator using a high-level computer. This research focuses on the attitude dynamic of satellites through the interaction between the Earth's magnetic field (EMF) and the magnetotorque in the satellite. To apply this phenomenon, the intensity and the direction of the magnetic field must be identified through Biot-Savart's law. Along with the EMF, the reference position is calculated using the standard general perturbations satellite orbit model (SGP4), and the intensity is modeled based on coefficients from the 13 th edition of the International Geo-magnetic Reference Field (IGRF). Therefore, this paper presents a detailed development of a HiLs testbed for distributed attitude determination and control systems (hardware and software co-design, protocol, and control theory). Furthermore, it discusses a classic cooperative control case for the output of magnetic field intensity and direction, which was undertaken to explain the integrated simulation process and validate the effectiveness of the co-simulation tested to be
Background: systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, ...
详细信息
This article's main contributions are twofold: 1) to demonstrate how to apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice for the domain of he...
详细信息
Background: Despite major advances in artificial intelligence (AI) research for healthcare, the deployment and adoption of AI technologies remain limited in clinical practice. In recent years, concerns have been raise...
详细信息
Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that parti...
详细信息
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We ...
详细信息
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad
International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from t...
International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.
暂无评论