Search

Establishing a human motion reconstruction system from very few constraints imposed on the body has been an interesting and important research topic because it significantly reduces the degrees of freedom to be managed. However, it is a well-known mathematically ill-posed problem as the dimension of constraints is much lower than that of the human pose to be determined. Therefore, it is challenging to directly reconstruct the whole body joint information from very few constraints due to many possible solutions. To address this issue, we present a novel deep learning framework with an attention mechanism using large-scale motion capture (mocap) data for mapping very few user-defined constraints into the human motion as realistically as possible. Our system is built upon the attention networks for looking back further to achieve better results. Experimental results show that our network model is capable of producing more accurate results compared with previous approaches. We also conducted several experiments to test all possible combinations of the features extracted from the mocap data, and found the best feature combination to generate high-quality poses.

Three-dimensional mesh post-processing is an important task because low-precision hardware and a poor capture environment will inevitably lead to unordered point clouds with unwanted noise and holes that should be suitably corrected while preserving the original shapes and details. Although many 3D mesh data-processing approaches have been proposed over several decades, the resulting 3D mesh often has artifacts that must be removed and loses important original details that should otherwise be maintained. To address these issues, we propose a novel 3D mesh completion and denoising system with a deep learning framework that reconstructs a high-quality mesh structure from input mesh data with several holes and various types of noise. We build upon SpiralNet by using a variational deep autoencoder with anisotropic filters that apply different convolutional filters to each vertex of the 3D mesh. Experimental results show that the proposed method enhances the reconstruction quality and achieves better accuracy compared to previous neural network systems.

The inertial measurement unit (IMU) and magnetic, angular rate, and gravity (MARG) sensor orientation and position are widely used in the medical, robotics, and other fields. In general, the orientations can be defined by the integration of angular velocity data, and the positions are also computed from the double integration of acceleration data. However, the acceleration and angular velocity data are often inaccurate due to measurement errors which arise when the sensor moves quickly. Therefore, the orientations and positions significantly differ from the actual values. To address these issues, several techniques are proposed for the accurate measurement of IMU and MARG sensor orientations and positions. The proposed optimization method is applied to raw sensor data to compute faithful orientations by stabilizing and accelerating the convergence of the optimization process. Furthermore, a deep neural network based on 1D convolutional neural network (CNN) layers is proposed to predict the desired velocity from raw acceleration data. The method is validated qualitatively and quantitatively with an optical motion capture (mocap) system. The experimental results show that the proposed method significantly improves orientation and position estimations compared to those of other approaches.

This article explores the Korean application of “mind-transmission” (K. chŏnsim, C. chuanxin) episodes to the intra-Sŏn (C. Chan) polemics. Korean Sŏn masters, unlike Chinese counterparts, sought for the religious meaning of the existence of multiple transmission episodes that circulated in East Asia from the Sŏn polemical perspective. In particular, Kagun and Paekp’a used the term “samch’ŏ chŏnsim” to promote their own visions of Sŏn within the situation in which different visions of Sŏn competed for dominance.

In this paper, we propose a robust low-cost mocap system (mocap) with sparse sensors. Although the sensor with an accelerometer, magnetometer, and gyroscope is cost-effective and offers the measured positions and rotations from these devices, it potentially suffers from noise, drift, and lost issues over time. The resulting character obtained from a sensor-based low-cost mocap system is thus generally not satisfactory. We address these issues by using a novel deep learning framework that consists of two networks, a motion estimator and a sensor data generator. When the aforementioned issues occur, the motion estimator feeds the newly synthesized sensor data obtained with the measured and predicted data from the sensor data generator until the issues have been resolved. Otherwise, the motion estimator receives the measured sensor data to accurately and continuously reconstruct the new character poses. In our examples, we show that our system outperforms the previous approach without the sensor data generator and we believe that it can be considered a handy and robust mocap system.

An automobile ball joint is the element for connecting the control arm and the knuckle arm, allowing rotational motion. The ball joint consists of the stud, plug, socket, and seat. These components are assembled through the caulking process that consists of plugging and spinning. In the existing research, the pull-out strength and gap stiffness were calculated, but we did not consider the uncertainties due to the numerical analysis and production. In this study, the uncertainties of material property and tolerance are considered to predict the distributions of pull-out strength and gap stiffness. Also, pull-out strength and gap stiffness are predicted as the a distribution rather than one deterministic value. Furthermore, a robust design applying the Taguchi method is suggested.

In the late Chosŏn period, Paekp'a Kŭngsŏn 白坡亘璇 (1767–1852) attempted to reestablish the identity of the Korean Sŏn tradition, which had been associated with the Linji school in its lineage and the Heze school in its practice. Paekp'a employed Linji's teaching of "three statements, three mysteries, and three essentials" as a link between the two different traditions. And based on Linji's teaching, Paekp'a laid out a three-fold taxonomy of Chan. In this taxonomy, he promoted the Linji school, with which the Korean Sŏn tradition claimed to be affiliated genealogically, as the supreme Chan school; he also unified the Korean Sŏn and Linji traditions soteriologically by placing the Heze scheme of Buddhist practice, the so-called "sudden awakening followed by gradual cultivation," in Linji's teaching. In so doing, Paekp'a not only redefined Chinese Linji Chan, but also completed the process of its assimilation into the Korean Sŏn tradition.

In this paper, we propose a novel method of denoising human motion using a bidirectional recurrent neural network (BRNN) with an attention mechanism. The corrupted motion that is captured from a single 3D depth sensor camera is automatically fixed in the well-established smooth motion manifold. Incorporating an attention mechanism into BRNN achieves better optimization results and higher accuracy because a higher weight value is selectively given to the more important input pose at a specific frame for encoding the input motion when compared to other deep learning frameworks. The results show that our approach efficiently handles various types of motion and noise. We also experiment with different features to find the best feature and believe that our method will be sufficiently desirable to be used in motion capture applications as a post-processing step after capturing human motion.

The biometrics based on resting state electroencephalography (EEG) is better than other EEG-based authentication protocols in terms of usability because it does not require any external stimuli and has a relatively short authentication time. Most of previous resting state EEG-based authentication systems have used a relatively long EEG data (e.g., > 1 min) measured once, and they were segmented to create many trials (e.g., > 100). In this case, however, it is difficult to reflect real-authentication situations in which a user repetitively uses an authentication system in different time points. Therefore, we propose to use single trials repetitively measured for short time (10 s). In the experiment, resting state EEGs were measured while fifteen subjects opened and closed their eyes 30 times for 10 s each. The measured EEG data were divided into three conditions, which are eyes open (EO), eyes closed (EC), and difference between EC and EO (Diff). We extracted power spectral density (PSD) ranging from 3 to 20 Hz as features for classification, with which a binary classification based on a 5×5-fold cross-validation was performed for each subject using linear discriminant analysis (LDA). The mean authentication accuracies of EC, EO, and Diff were 97.05 ± 5.4, 92.5 ± 8.2, and 85.3 ± 7.0 %, respectively, demonstrating the feasibility of single-trial-based EEG authentication. EC could be an optimal condition for developing a resting-state EEG authentication system based on single trial.

In this paper, we present a novel motion retargeting system by using the deep autoencoder combining the Deep Convolution Inverse Graphics Network (DC-IGN) ([Kulkarni et al. 2015]) and the U-Net ([Long et al. 2015]) to produce high-quality human motion. The retargeted motion is fully-automatically and naturally generated from the given input motion and bone length ratios. To validate the proposed motion retargeting system, we conduct several experiments and achieve more accuracy and less computational burden when compared with the conventional motion retargeting approach and other neural network architectures.

Samch’ŏ chŏnsim (Three places of the mind-transmission 三處傳心) is one of the best-known terms in the Korean Buddhist tradition. It refers to three different events in which the Buddha Śākyamuni transmitted the mind to his successor, Mahākāśyapa. These events include the Buddha sharing his seat, holding up a flower, and sticking his feet out of his coffin. Despite its popularity, the term has hardly attracted serious academic attention. Scholars have assumed that it originated from China to refer to those “historical” episodes that happened in India. However, textual evidence shows (a) that many mind-transmission episodes developed in medieval China to substantiate the Chan separation from the scriptural tradition and (b) that the term Samch’ŏ chŏnsim was first introduced in Korea to treat the three episodes of Samch’ŏ chŏnsim collectively and to attempt a new interpretation of the mind-transmission. The term first appears in the Koryŏ Sŏn master Kagun’s Sŏnmun yŏmsong sŏrhwa 禪門拈頌說話 to present the idea that the Buddha transmitted to Kāśyapa different minds or different aspects of the mind in different times and places .

We prove Amann type three solutions theorem for one dimensionalp-Laplacian problems with a singular weight function. To prove this theorem, we define a strong upper and lower solutions and compute the Leray-Schauder degree on a newly established weighted solution space. As an application, we consider the combustion model and show the existence of three positive radial solutions on an exterior domain.

Objectives The Surviving Sepsis Campaign has recommended that antibiotic therapy should be started within the first hour of recognizing severe sepsis. Procalcitonin has recently been proposed as a biomarker of bacterial infection, although the quantitative procalcitonin assay is often time consuming, and it is not always available in many emergency departments (EDs). Our aim is to evaluate usefulness of the semiquantitative procalcitonin fast kit as a guideline for starting antibiotic administration for patients with severe sepsis or septic shock that requires prompt antibiotic therapy in the ED. Methods We include those patients who were admitted to the ED and who were suspected of having infection. The procalcitonin concentration was determined by semiquantitative PCT-Q strips, and the points of the severity scoring system were calculated. The receiver operating characteristic curve was used to assess the diagnostic value of the PCT-Q strips to predict severe sepsis or septic shock. Results Of the 80 recruited patients, 33 patients were categorized as having severe sepsis or septic shock according to the definition. At a procalcitonin cutoff level of 2 ng/mL or greater, the sensitivity of the PCT-Q for detecting severe sepsis or septic shock was 93.94% and the specificity was 87.23. The receiver operating characteristic curve for PCT-Q to predict severe sepsis or septic shock had an area under the curve of 0.916. Conclusion PCT-Q is probably a fast, useful method for detecting severe sepsis in the ED, and it can be used as a guideline for antibiotic treatment.

Background: There are a plethora of literatures showing that high-intensity intensive care unit (ICU) physician staffing is associated with reduced ICU mortality. However, it is not widely used in ICUs because of limited budgets and resources. We created a critical care team (CCT) to improve outcomes in an open general ICU and evaluated its effectiveness based on patients` outcomes. Methods: We conducted this prospective, observational study in an open, general ICU setting, during a period ranging from March of 2009 to February of 2010. The CCT consisted of five teaching staffs. It provided rapid medical services within three hours after calls or consultation. Results: We analyzed the data of 830 patients (157 patients of the CCT group and 673 patients of the non-CCT one). Patients of the CCT group presented more serious conditions than those of the non-CCT group (acute physiologic and chronic health evaluation II [APACHE II] 20.2 vs. 15.8, p＜0.001; sequential organ failure assessment [SOFA] 5.5 vs. 4.6, p=0.003). The CCT group also had significantly more patients on mechanical ventilation than those in the non-CCT group (45.9% vs. 23.9%, p＜0.001). Success rate of weaning was significantly higher in the CCT group than that of the non-CCT group (61.1% vs. 44.7%, p=0.021). On a multivariate logistic regression analysis, the increased ICU mortality was associated with the older age, non-CCT, higher APACHE II score, higher SOFA score and mechanical ventilation (p＜0.05). Conclusion: Although the CCT did not provide full-time services in an open general ICU setting, it might be associated with a reduced ICU mortality. This is particularly the case with patients on mechanical ventilation.