The acquisition of standard planes is crucial for medical ultrasound (US) diagnosis. In this paper, we present a hierarchical supervised learning framework for automatically detecting standard plane in consecutive 2D ...
详细信息
The acquisition of standard planes is crucial for medical ultrasound (US) diagnosis. In this paper, we present a hierarchical supervised learning framework for automatically detecting standard plane in consecutive 2D US images. The technique is demonstrated by developing a system that localizes fetal abdominal standard plane (FASP) from US videos. We first propose a novel radial component-based model (RCM) to describe the geometric constrains of key anatomical structures (KAS). In order to enhance the detection accuracy, we further adopt random forests classifier for detection of KAS within the regions constrained by RCM. Finally, a second-level classifier combines the results of component detectors to identify a US image as a “FASP” or a “nonFASP”. Experimental results show that our method significantly outperforms both the full abdomen and the separate anatomy detection methods without geometric constrains.
The work described in this paper is part of a research program named ABV (Low Speed Automation) where the goal is the automation of road vehicle at low speed while ensuring the sharing of driving between the driver an...
详细信息
The work described in this paper is part of a research program named ABV (Low Speed Automation) where the goal is the automation of road vehicle at low speed while ensuring the sharing of driving between the driver and the assistance. This paper focuses on the problem of human-machine cooperation in the specific context of vehicle driving, with a view of shared control between driver and automation, considering the acceptability of the system and the driver distractions and drowsiness.
Sighted individuals often develop significant knowledge about their environment through what they can visually observe. In contrast, individuals who are visually impaired mostly acquire such knowledge about their envi...
详细信息
ISBN:
(纸本)9781450324052
Sighted individuals often develop significant knowledge about their environment through what they can visually observe. In contrast, individuals who are visually impaired mostly acquire such knowledge about their environment through information that is explicitly related to them. This paper examines the practices that visually impaired individuals use to learn about their environments and the associated challenges. In the first of our two studies, we uncover four types of information needed to master and navigate the environment. We detail how individuals' context impacts their ability to learn this information, and outline requirements for independent spatial learning. In a second study, we explore how individuals learn about places and activities in their environment. Our findings show that users not only learn information to satisfy their immediate needs, but also to enable future opportunities - something existing technologies do not fully support. From these findings, we discuss future research and design opportunities to assist the visually impaired in independent spatial learning.
Currently, research is actively being conducted on applying games to education. However, existing game-based learning systems mainly focus on how to increase learning motivation and enhance engagement, while achieving...
详细信息
In this paper, we analyse the emotion of children's stories in sentence level by considering the context information. We demonstrate that the emotion of a sentence is not only dependent on its content, but also af...
详细信息
ISBN:
(纸本)9781479942503
In this paper, we analyse the emotion of children's stories in sentence level by considering the context information. We demonstrate that the emotion of a sentence is not only dependent on its content, but also affected by its neighbours in a story. A Hidden Markov Model (HMM) based method is proposed to model the emotion sequence and to detect whether a sentence is neutral or not. We show the important features for emotion detection by studying a children's story corpus. An empirical evaluation is conducted to investigate the efficiency of the model. The results demonstrate that the proposed method can achieve competitive performance with the state-of-the-art methods, and it is affected more slightly by the training set than traditional classification methods. Classifier fusion is applied to combine different methods to achieve better results.
We investigate cognitive factors that are predictive of learning gains when students learn to solve equations by teaching a synthetic peer, called SimStudent. Previous empirical studies showed that prior knowledge is ...
详细信息
We investigate cognitive factors that are predictive of learning gains when students learn to solve equations by teaching a synthetic peer, called SimStudent. Previous empirical studies showed that prior knowledge is strongly predictive of post-test scores. However, in a recent study in the Philippines that replicated our previous study in the USA, there were students with low priorknowledge who tutored their SimStudent better than other equally low prior students. In this paper, we analyze both process data (tutoring interactions) and outcome data (test scores) to understand what makes learning by teaching more effective. The results imply a presence of individual behavioral differences beyond the difference in the prior knowledge that might have affected SimStudent's learning, which in turn had non-trivial influence on tutor learning.
ISO 9241 Ergonomics of human-System interaction Standard, which is also called as Ergonomic requirements for office work with visual display terminals, is a standard containing many parts about ergonomics of human com...
详细信息
We examine a large dataset collected by the Marmoset system in a CS2 course. The dataset gives us a richly detailed portrait of student behavior because it combines automatically collected program snapshots with unit ...
详细信息
ISBN:
(纸本)9781450320788
We examine a large dataset collected by the Marmoset system in a CS2 course. The dataset gives us a richly detailed portrait of student behavior because it combines automatically collected program snapshots with unit tests that can evaluate the correctness of all snapshots. We find that students who start earlier tend to earn better scores, which is consistent with the findings of other researchers. We also detail the overall work habits exhibited by students. Finally, we evaluate how students use release tokens, a novel mechanism that provides feedback to students without giving away the code for the test cases used for grading, and gives students an incentive to start coding earlier. We find that students seem to use their tokens quite effectively to acquire feedback and improve their project score, though we do not find much evidence suggesting that students start coding particularly early. Copyright 2013 ACM.
One common problem plaguing crowdsourcing tasks is tuning the set of worker responses: Depending on task requirements, requesters may want a large set of rich and varied worker responses (typically in subjective evalu...
详细信息
A new signal processing algorithm is developed for quantifying heel strike (HS) and toe-off (TO) event times solely from measured heel and toe coordinates during overground walking. It is based on a rough estimation o...
详细信息
A new signal processing algorithm is developed for quantifying heel strike (HS) and toe-off (TO) event times solely from measured heel and toe coordinates during overground walking. It is based on a rough estimation of relevant local 3D position signals. An original piecewise linear fitting method is applied to these local signals to accurately identify HS and TO times without the need of using arbitrary experimental coefficients. We validated the proposed method with nine healthy subjects and a total of 322 trials. The extracted temporal gait events were compared to reference data obtained from a force plate. HS and TO times were identified with a temporal accuracy ± precision of 0.3 ms ± 7.1 ms, and -2.8 ms ± 7.2 ms in comparison with reference data defined with a force threshold of 10 N. This algorithm improves the accuracy of the HS and TO detection. Furthermore, it can be used to perform stride-by-stride analysis during overground walking with only recorded heel and toe coordinates.
暂无评论