A5100664392- Traditional Chinese Medicine Studies
- Cancer-related molecular mechanisms research
- Emotion and Mood Recognition
- Advanced Radiotherapy Techniques
- Network Security and Intrusion Detection
- Radiation Detection and Scintillator Technologies
- Anomaly Detection Techniques and Applications
- Radiation Therapy and Dosimetry
- EEG and Brain-Computer Interfaces
- COVID-19 diagnosis using AI
- Neurological disorders and treatments
- Carbon Dioxide Capture Technologies
- Brain Tumor Detection and Classification
- Chemical Looping and Thermochemical Processes
- Traditional Chinese Medicine Analysis
- Diverse Musicological Studies
- Phytochemical and Pharmacological Studies
- Quality Function Deployment in Product Design
- Morinda citrifolia extract uses
- Composite Structure Analysis and Optimization
- Multi-Criteria Decision Making
- Ocular Diseases and Behçet’s Syndrome
- Hand Gesture Recognition Systems
- Plant tissue culture and regeneration
- Natural Language Processing Techniques
Beijing University of Technology
2025
PowerChina (China)
2024
Soochow University
2023
Fudan University
2017-2022
Shanghai University of International Business and Economics
2022
East China Jiaotong University
2021-2022
East China University of Science and Technology
2021
Tianjin University
2020
Capital University of Economics and Business
2019
Harbin Medical University
2017
Geometric dimension significantly affects the stable configuration and thereby nonlinear dynamic response of bistable composite laminate. Previous studies have not focused on minimum snap-through excitation transformation. This paper aims to address this gap by taking into account effect curvature laminate with different geometric dimensions. The room-temperature equilibrium states unsymmetric plates are obtained cooling down from cured temperature variable curvatures. governing equations...
Integrated CO2 capture and conversion (ICCC) into valuable chemicals such as CH4 CO is a promising approach to mitigate anthropogenic emissions. In this work, we prepared series of metal oxide (MxOy, M = Mg, Al, Mn, Y, Zr, La, Ce)-doped Ni/CaO dual-function materials (DFMs) applied them the ICCC process. The property–performance relationship DFMs was studied, mechanism captured explored. For any DFM at cycle (20 cycles in total), carbonation stage completely released CH4, CO, stage. Among...
Nowadays, driver drowsiness and distraction is considered as a major risk for fatal road accidents around the world. As result, monitoring identifying emerging an essential function of automotive safety systems. Its basic features include head pose, gaze direction, yawning eye state analysis. However, existing work has investigated algorithms to detect these tasks separately was usually conducted under laboratory environments. To address this problem, we propose multi-task learning CNN...
Tongue diagnosis, one of the essential diagnostic methods Traditional Chinese Medicine (TCM), is considered an ideal candidate for remote diagnosis because its convenience and noninvasiveness. However, trade-off between accuracy efficiency variation tongue images pose great challenges in real-time image segmentation. To remedy these problems, this paper, a light weight architecture based on encoder-decoder structure proposed. The feature extraction (TIFE) module designed to generate features...
With the rapid adoption of smartphones and tablets, more remote medical diagnostic applications have mushroomed. Tongue Diagnosis (TD) is a kind noninvasive technique, which offers significant information for health conditions. However, it rather tough to extract tongue from high-quality image, in there definite large area tongue, say nothing extracting digital image captured by photographers who often lack necessary skills using different mobile front facing cameras. Fundamentally,...
Facial medical analysis, including the inspection of face and inner facial components, has always been a primary part diagnostic method in Traditional Chinese Medicine (TCM). The existing literature merely focus on detecting or segmenting single organs such as tongue, eyes, lips. In this paper, we make first attempt to deal with multiple simultaneously develop an end-to-end hybrid network context aggregation (named TCMINet) achieve parsing for Inspection (TCMI). Additionally, construct new...
Triptolide (TPL) is an active compound extracted from a Chinese herbal medicine tripterygium wilfordii Hook. f. (Celastraceae), which has been used as anti-inflammatory drug for years. It also inhibits the growth and proliferation of different types cancer cells. The inhibitory effect TPL on angiogenesis after chemical-induced corneal inflammation was studied in vivo. effects proliferation, apoptosis, migration, tube formation rat aortic endothelial cells (RAECs) were vitro. Cell apoptosis...
Tongue crack segmentation is an essential component of computer-aided diagnosis applied in Traditional Chinese Medicine (TCM). However, existing methods are inadequate when dealing with the vague boundary foreground and variation tongue images. To this end, we propose a P-shaped neural network architecture based on lightweight encoder-decoder structure: encoder transforms pixel position information into channel by aggregating adjacent values; decoder restores image size obtains refined...
In the conceptual design stage of new product development, one major challenges is how to effectively determine single best scheme from multiple alternatives. Based on Axiomatic Design Theory, this paper proposes a method analyze and compare alternative schemes, Markov function then used calculate cost optimization direction chosen scheme. The optimal solution estimated through calculations with utility functions. To add more details final design, it necessary consider both working...
Deep neural networks (DNNs) are widely used in many artificial intelligence applications; specialized DNN-inference accelerators have been proposed. However, existing DNN rely heavily on certain types of operations (such as Conv, FC, and ReLU, etc.), which either less or likely to become out date future, posing challenges flexibility compatibility work. This paper designs a flexible accelerator from more generic perspective rather than speeding up operations. Our proposed Nebula exploits the...
Sublingual vein segmentation is an essential yet challenging task in computer-aided Traditional Chinese Medicine (TCM) tongue diagnosis. The most intricate part of sublingual the strong diversity images (e.g., various exposure and complex background) natural connectivity veins. To this end, we propose a novel effective approach based on generative adversarial networks (GANs). Specifically, framework comprises two modules: generator network with multi-scale outputs scale-consistent...
Multitarget tracking with highly maneuver and crossing track under dense-clutter environment is an emphasis in target field. To effectively differentiate the measurement of cluster target, establish relation between measurement, data technologies are needed to keep consistency path tracking. When maneuvers happen a suitable motion model should be selected for self-adaptive With consideration these two points, we combine JPDA algorithm IMM according some certain way, multiple maneuvering...
The rapid expansion of the new generation communication technologies, such as fifth mobile technology (5G), has brought tremendous to people's lives. A growing number smart devices are connected electric Internet Things, it brings convenience development power things, but at same time inevitably security risks. Such a variety attacks. At time, application large amount data exchange, which makes traditional anomaly detection for Things face difficulties. To solve these problems, this paper...
Aiming to the problems of domestic database missing, strong universality with insufficient specificity in abroad and utilization sample information collected by enterprises, thesis studies how obtain accurate field failure rate equipment. Bayesian method is selected analyzing comparing various reliability data processing methods. applied modify a more practical equipment taking provided foreign as priori data, collecting related enterprises data. In this thesis, it proved that estimation...
In this paper, an on-demand Deep brain stimulation (DBS) device is designed to deliver current pulses according beta band power of local field potentials (LFPs). The LFPs are collected by signal processing module and analyzed in digital processor (DSP) with the Fast Fourier transform method calculate band. Then, it controls monitoring comparing a predefined threshold. And based on neural mass model, self-oscillation network composed two populations, real from basal ganglia simulated using...