SYSU-CMU International Joint Research Institute

The neurodegenerative disease has affected millions of people worldwide. Previous studies have shown that physical exercise for the short term or long term is beneficial for neurodegenerations diseases. However, physical exercise is quite boring. Digital serious games can be used as tools to help and encourage older adults to train physically and mentally. Baduanjin Qigong exercise has been observed to be beneficial for their health. In this work, to motivate older adults to practice more physical exercise, a gamification framework for the Bedaubing exercise is proposed, and based on this framework, a somatosensory parkour mobile game is proposed. The experimental testing shows that the Baduanjin Qigong exercise can be accurately recognized, and the results from the Game Experience Questionnaire (GEQ) indicate the game can increase elderly users’ motivation. During play, the game, the physical movement data, and the performance data in the game are collected for training the predictive model to evaluate the risk of neurodegenerative diseases.

Multimodal tasks are gradually attracting the attention of the research community, and the lack of multimodal event extraction datasets restricts the development of multimodal event extraction. We introduce the new Multimodal Event Extraction Dataset (MEED) to fill the gap, we define event types and argument roles that can be used on multimodal data, then use controllable text generation to generate the textual modality based on visual event extraction dataset. In this paper, we aim to make full use of multimodal resources in the event extraction task by constructing a large-scale and high-quality multimodal event extraction dataset and promote researches in the field of multimodal event extraction.

Abstract This article presents a quasi‐Yagi antenna operating with high gain at two frequency bands. Compared with a conventional Yagi antenna, the proposed antenna is designed by integrating a pair of printed split‐ring resonators (SRRs) into the antenna layout. The SRRs introduce a new resonant frequency band and the antenna gain remains high at both the bands. The simulated and measured results show that the antenna is well matched while the antenna gain is 6 and 5.80 dBi at the GSM1800 and ISM2450 bands, respectively. The proposed antenna is compact and efficient and achieves high gain so that it could be successfully used in various wireless communication and radio frequency energy harvesting applications.

Abstract: The National Park System pilot practiced in China has arose numerous discussion about the policy and the practice of national park management in China's context, however, tourism becomes one of the most controversial topics in national parks establishment, whether it is possible to develop tourism in national park, or what kind of "tourism" could be approved in national park, or we should use the term "tourism" or "recreation" in national park context. Based on the analysis of the connotation of "tourism" and "recreation", combined with the corresponding expressions in international national parks, this article discusses "recreation" and "tourism" in national parks within the context of China. The findings indicate that "recreation" is the other side of tourism. "Recreation" is appropriate for the functional positioning and planning of parks which reflects the public welfare goals of national parks. However, in the specific operation and management of national parks, it is more appropriate to use the term "ecotourism". When we talk about the contradiction between tourism and national parks, the use of "tourism development" is more in line with the facts.

Electric vehicles (EVs) have many fundamental advantages over internal combustion engine vehicles. The EV idea is not new. As early as 1891, William Morrison of Des Moines, Iowa, already built the first successful EV in the United States. However, internal combustion engines almost completely replaced electric powertrains in the production of vehicles for the past 100 years. Thanks to the recent evolution of lithium-ion batteries and strong demand for zero-emission vehicles, EVs have successfully repositioned, demonstrating commercial success. Nevertheless, EVs still have challenges in terms of the battery weight, fully charged driving range, costs, etc.

This letter reports on an electronic device that works as a self-driven impulse sensor with high sensitivity and ultra-low power consumption. It consists of a mechanical-field-coupled thin-film transistor (TFT) formed by integrating a piezoelectric transducer with a 3-D FIN-shaped dual-gate TFT. An analytical model is presented to intricate the variation of output current in the response of the human impulse force, and an experimental study is conducted to evaluate its sensitivity and capability of acquiring impulse waveforms as well as heart rate. The proposed impulse sensor is anticipated to be pragmatic in wearable medical devices for prevention against cardiovascular abnormalities, both continuously and non-invasively.

In this paper, we present a fully-automated subcortical and ventricular shape generation pipeline that acts on structural magnetic resonance images (MRIs) of the human brain. Principally, the proposed pipeline consists of three steps: (1) automated structure segmentation using the diffeomorphic multi-atlas likelihood-fusion algorithm; (2) study-specific shape template creation based on the Delaunay triangulation; (3) deformation-based shape filtering using the large deformation diffeomorphic metric mapping for surfaces. The proposed pipeline is shown to provide high accuracy, sufficient smoothness, and accurate anatomical topology. Two datasets focused upon Huntington's disease (HD) were used for evaluating the performance of the proposed pipeline. The first of these contains a total of 16 MRI scans, each with a gold standard available, on which the proposed pipeline's outputs were observed to be highly accurate and smooth when compared with the gold standard. Visual examinations and outlier analyses on the second dataset, which contains a total of 1,445 MRI scans, revealed 100% success rates for the putamen, the thalamus, the globus pallidus, the amygdala, and the lateral ventricle in both hemispheres and rates no smaller than 97% for the bilateral hippocampus and caudate. Another independent dataset, consisting of 15 atlas images and 20 testing images, was also used to quantitatively evaluate the proposed pipeline, with high accuracy having been obtained. In short, the proposed pipeline is herein demonstrated to be effective, both quantitatively and qualitatively, using a large collection of MRI scans.

Huntington's disease (HD) is a progressive inherited brain disorder that affects cognition, personality and physical abilities. Advanced statistical shape analysis pipelines have shown that region-specific shape abnormalities of the putamen and thalamus begin earlier than clinical onset ("premanifest" period), but the order and pattern of different subregions' abnormalities of those two structures are still unclear. In this paper, we applied a multivariate linear mixed-effects model, in combination with a novel shape diffeomorphometry technique, to identify the changepoints at which the shape morphometry abnormalities of different putamen and thalamus sub-regions start. Our experimental results revealed that the putamen was affected severely by HD whereas the thalamus was affected in a milder way. The putaminal subregion connected to the executive cortex and the thalamic subregion connected to the prefrontal cortex were found to be affected the earliest by HD. This study contributes to a better understanding of the temporal ordering of the putaminal and thalamic abnormalities of different functionally-distinct subregions.

In this study, we proposed and validated a novel and accurate automatic approach for ulcer area extraction from ocular staining images. We first segmented the corneal surface area with the help of four pre-defined key landmarks by modeling the corneal surface shape as an ellipse. Then the ulcer area was identified within the cornea by employing a combination of techniques: 1) iterative k-means based clustering to extract areas with similar color information; 2) morphological operations to polish results from the previous step, with the parameters employed in the morphological operators determined automatically via linear regression analysis; 3) region growing to select the true ulcer area among a number of separated areas. To validate this automatic approach, we compared its results with those from manual delineations using the Dice Overlap Score (DSC) and the automatic-versus-manual correlation in terms of the ulcer area size based on 48 ocular staining images with corneal ulcers. The automatic results showed strong and statistically significant positive correlations with the manual ones in terms of both the cornea size and the ulcer area size (cornea: PCC=0.842, p-value=6:890 x 10^-14; corneal ulcer area: PCC=0.969, p-value=1:119 x 10^-29). For cornea, the DSC between the proposed automatic results and the manual ones is on average 0.989, whereas the average DSC for the ulcer segmentation is 0.879. This suggests a high overlap between the automatic and the manual results for both the cornea and the corneal ulcer area. We also compared the proposed method with a classic segmentation approach (the active contour). Our results revealed a superior performance of the proposed automatic approach in corneal ulcer area identification relative to the active contour (0.879 versus 0.639 in terms of DSC).

In this brief, we study the problem of controller synthesis for time-delay systems with controller failures based on an input–output approach. First, the time-delay system with controller failure is modeled as an input–output form. Next, the stability condition of the system with controller failure is developed via scaled small gain theorem. Additionally, the proposed stability condition is also testified by the direct Lyapunov functional method. The merit of the proposed approach lies in its reduced conservatism, which is made possible by a new model of the investigated system, a new triangle inequality and a new Lyapunov–Krasovskii functional. The proposed stability condition is demonstrated to be less conservative than other existing results. Moreover, the problem of stabilization is further solved with admissible controller designed via convex optimizations. The effectiveness of the proposed method is also illustrated via a numerical example.