A5068925981- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Remote Sensing and LiDAR Applications
- Remote Sensing and Land Use
- Advanced Algorithms and Applications
- Statistical Methods and Inference
- Image and Signal Denoising Methods
- Forest ecology and management
- Chinese history and philosophy
- Advanced SAR Imaging Techniques
- Advanced Statistical Methods and Models
- Robotic Path Planning Algorithms
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced Measurement and Detection Methods
- Advanced X-ray and CT Imaging
- Radiation Dose and Imaging
- Advanced Computational Techniques and Applications
- Image and Object Detection Techniques
- Forest Management and Policy
- Smart Agriculture and AI
- Spectroscopy and Chemometric Analyses
- Advanced Sensor and Control Systems
- Mathematical Analysis and Transform Methods
- Lung Cancer Diagnosis and Treatment
Institute of Forest Resource Information Techniques
2014-2024
Chinese Academy of Forestry
1993-2024
National University of Defense Technology
2011-2024
Yunnan Normal University
2024
iQIYI (China)
2024
Dongguan University of Technology
2023-2024
Yunnan University of Finance And Economics
2007-2023
Xi'an Jiaotong University
2008-2023
Xi'an Honghui Hospital
2020-2023
State Forestry and Grassland Administration
2019-2022
In this paper, the classification via sprepresentation and multitask learning is presented for target recognition in SAR image. To capture characteristics of image, a multidimensional generalization analytic signal, namely monogenic employed. The original signal can be then orthogonally decomposed into three components: 1) local amplitude; 2) phase; 3) orientation. Since components represent different kinds information, it beneficial by jointly considering them unifying framework. However,...
To describe in detail a dataset consisting of serial four-dimensional computed tomography (4DCT) and 4D cone beam CT (4DCBCT) images acquired during chemoradiotherapy 20 locally advanced, nonsmall cell lung cancer patients we have collected at our institution shared publicly with the research community.As part an NCI-sponsored study 82 4DCT 507 4DCBCT were population advanced undergoing radiation therapy. All subjects underwent concurrent radiochemotherapy to total dose 59.4-70.2 Gy using...
We have developed a new four‐dimensional cone beam CT (4D‐CBCT) on Varian image‐guided radiation therapy system, which has treatment and imaging capabilities. adapted the speed of gantry rotation time CBCT to average breath cycle patient maintain same level image quality adjusted data sampling frequency keep similar exposure patient. Our design utilized real‐time positioning monitoring system record respiratory signal during acquisition data. used full‐fan bowtie filter acquisition, acquired...
Most of existing change detection methods could be classified into three groups, the traditional pixel-based (PBCD), object-based (OBCD), and hybrid (HCD). Nevertheless, both PBCD OBCD have disadvantages, classical HCD belong to intuitive decision-level fusion schemes OBCD. There is no optimum method as yet. Analyzing complementarities method, we propose a new unsupervised algorithm-level scheme (UAFS-HCD) in this paper improve accuracy using spatial context information through: 1) getting...
The combination of features from the convolutional layer and fully connected a neural network (CNN) provides an effective way to improve performance crime scene investigation (CSI) image classification. However, in existing work, as weights feature fusion do not change after training phase, it may produce inaccurate which affect classification results. To solve this problem, paper proposes adaptive method based on auto-encoder accuracy. includes following steps: Firstly, CNN model is trained...
AbstractFlood detection from synthetic aperture radar (SAR) images should be performed with accurate, stable, automated and time-efficient algorithms; however, few methods meet all these requirements. Recently, Giustarini et al. proposed an promising methodology, capable of providing satisfactory results in flood detection. The algorithm is based on the assumption that a image contains relatively high number pixels low backscatter values, exhibiting bimodal histogram. For case histogram not...
The algorithm which takes into account the effect of refraction sound wave paths for acoustic computer tomography (CT) is developed. Incorporating ordinary CT algorithms are based on Fourier transformation very difficult. In this paper, least-squares method, capable considering effect, employed to reconstruct two-dimensional temperature distribution. solved by writing a set differential equations derived from Fermat's theorem and calculus variations. It impossible carry out analysis...
Speech-language pathologists (SLPs) are trained to correct articulation of people diagnosed with motor speech disorders by analyzing articulators' motion and assessing outcome while patients speak. To assist SLPs in this task, we presenting the multimodal capture system (MSCS) that records displays kinematics key articulators, tongue lips, along voice, using unobtrusive methods. Collected modalities, motion, lips gestures, voice visualized not only real-time provide instant feedback but also...
Tongue tracking, which helps researchers gain valuable insights into speech mechanism, has many applications in therapy and language learning. The wireless localization technique, involves tracking a small magnetic tracer within the 3-D oral space, provides low cost convenient approach to capture tongue kinematics. In practice, this technique requires accurate calibration of three-axial sensors used system. data-driven depends on trajectories ambient noise, may change across time space.In...
Single-molecule localization microscopy (SMLM) is a powerful super-resolution imaging technique that offers resolution far beyond the optical diffraction limit. The commonly used high numerical-aperture (NA) objective lenses in SMLM can only provide nearly ideal point-spread function (PSF) at center of field-of-view (FOV), whereas off-axis PSF often distorted due to aberrations. Since precision and accuracy three-dimensional (3D) spatial single molecules heavily depend on system’s PSF, FOV...
Abstract In space teleoperation systems, the dynamics of controlled robots exhibit uncertainties, and communication involves time delays. To address these challenges, this paper proposes a bilateral controller based on two-layer architecture: master side employs radial basis function (RBF) neural network-based sliding mode control, while slave uses model-compensated PD control. The study investigates two-degree-of-freedom robot under fixed delay conditions. Independent channels connect each...
Purpose: Implanted markers are commonly used in radiotherapy for x‐ray based target localization. The projected marker position a series of cone‐beam CT (CBCT) projections can be to estimate the three dimensional (3D) trajectory during CBCT acquisition. This has important applications tumor motion management such as inclusive, gating, and tracking strategies. However, irregularly shaped markers, reliable segmentation is challenged by large variations shape with projection angle. purpose this...
In this study, an individual tree crown ratio (CR) model was developed with a data set from total of 3134 Mongolian oak (Quercus mongolica) trees within 112 sample plots allocated in Wangqing Forest Bureau northeast China. Because high correlation among the observations taken same sampling plots, random effects at levels both blocks defined as stands that have different site conditions and were into account to develop nested two-level nonlinear mixed-effect model. Various stand...