A5101990068- Geochemistry and Geologic Mapping
- Medical Image Segmentation Techniques
- Geological and Geochemical Analysis
- Heavy metals in environment
- AI in cancer detection
- Copper Interconnects and Reliability
- Nanofabrication and Lithography Techniques
- earthquake and tectonic studies
- Anodic Oxide Films and Nanostructures
- Dental Radiography and Imaging
- Remote-Sensing Image Classification
- Mineral Processing and Grinding
- Medical Imaging Techniques and Applications
- Visual Attention and Saliency Detection
- Geophysical and Geoelectrical Methods
- Face and Expression Recognition
- Advanced Neural Network Applications
- Heavy Metal Exposure and Toxicity
- Rock Mechanics and Modeling
- Industrial Vision Systems and Defect Detection
- Mine drainage and remediation techniques
- Image Retrieval and Classification Techniques
- Soil Geostatistics and Mapping
- Corrosion Behavior and Inhibition
- Image and Video Quality Assessment
Hefei University of Technology
2023-2024
Shanghai University of Electric Power
2023-2024
Shanghai Stock Exchange
2024
University of Naples Federico II
2020-2023
Guilin University of Technology
2018-2021
The University of Sydney
2012-2018
University of Technology Sydney
2016
Clustering is increasingly important for multiview data analytics and current algorithms are either based on the collaborative learning of local partitions or directly derived global clustering from multikernel learning. In this paper, we innovate a model that unifies in framework. We first construct common space set basis kernels to better reflect information each individual view. Then, considering joint would conform clustering, fuse guidance as single objective function accordance with...
The Chating area is situated within the Middle-Lower Yangtze River Metallogenic Belt, China. Several concealed skarn and porphyry-type deposits have been discovered in this area, indicating high potential for hosting hydrothermal deposits. However, due to complex geological structure, exploration risks significantly increase with increasing depth. To overcome challenge, three-dimensional mineral prospectivity modeling (3DMPM) has begun be widely applied mapping of deep-seated mineralization....
In the field of geosciences, integration artificial intelligence is transitioning from perceptual to cognitive intelligence. The simultaneous utilization knowledge and data in geoscience domain a universally addressed concern. this paper, based on interpretability deep learning models for rock images, features such as structure, texture, mineral macroscopic identification characteristics were selected extract subgraph petrographic graph carry out type similarity reasoning. Comparative...
The utilization of machine learning (ML) techniques in conjunction with multi-source geoscience datasets for comprehensive metallogenic prognosis (MP) has emerged as a novel means geological prospecting. Nevertheless, the representativeness features and composition employed constructing ML model MP may substantially impact prediction model's overall performance augment prediction's uncertainty. In this study, Ashele copper-zinc deposit was chosen to conduct case study resolve these...
The study deals with the spatio-temporal distribution of heavy metals in sediments Chagan lake, Northeast China. pollution history is studied simultaneously through 210Pb dating method by analyzing characteristic As, Hg, Cd, Cr, Ni, Cu, Pb, and Zn concentration-depth profiles. potential ecological risk index (RI) geo-accumulation (Igeo) were used to evaluate contamination degree. Principal component analysis (PCA), based on logarithmic transformation isometric log-ratio (ilr) transformed...
Demons has been well recognized for its deformable registration capability. However, it might lead to misregistration due the large spatial distance between expected corresponding contents or erroneous diffusion tendency. In this paper, we propose a new energy function with topology energy, and demons registration. The incorporates topological relationships guide correct deformation, contributes local rigidity preservation. pulling regions into accurate alignment despite of possible gap....
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Deformable registration is essential to map the radiotherapy plan onto treatment images of patient. However, deformable may introduce excessive deformation into tumor volume, shape and location. In this paper, our proposed method aims correct local on while retaining global correspondence by conventional method. To trace change, automatic landmark established basis genus zero surface conformal mapping recover information its surrounding structures. Our experimental validation clinical PET...
Defect-free blind copper surperfilling for high-density interconnected printed circuit board PCB is the primary technology to guarantee development and quality of boards. Due fact that leveling agents are a key regulatory factor in achieving top-down overfilling holes, developing efficient has become crucial electroplating hole process Here, two small molecule five-membered heterocyclic compounds with different side chains, namely 3-amino-5-mercapto-1,2,4-triazole (AMT) 2-...
The demons registration (DR) model is well recognized for its deformation capability. However, it might lead to misregistration due erroneous diffusion direction when there are no overlaps between corresponding regions. We propose a novel energy function, introducing topology energy, and incorporating local function into the DR in progressive scheme, address these shortcomings. that derived from topological information of images serves as inference guide transformation retain merits DR....
The measurement of residual thyroid tissue after thyroidectomy is crucial for the precise quantification cancer treatment. Accurate segmentation from CT images challenging due to indistinct boundary. We propose a vote-in & vote-out region propagation model which incorporates global and local constraints two voting strategies. were initially estimated given seeds adaptively adjusted during process. strategies developed decrease opportunities merging unexpected voxels around uncertain...
Prostate segmentation from MRI image is a challenging task due to the appearance variations of different patients and in particular feature density heterogeneity within same image. To address these challenges, we propose collaborative learning based model adaptively choose optimal features set candidates improve prostate boundary delineation. In our method, on basis weighted multi-view clustering, proposed new ranking selection scheme automatically determines unique for optimally contouring...
Widely accessible biomedical data provides new opportunities to discover knowledge for quality healthcare. However, optimal selection of the most informative, representative and non-redundant features from huge volume datasets are be better explored. To address this challenge, in paper we propose an integrative clustering supervised feature approach. In our framework, unsupervised contributes reducing redundancy by exploring correlation among features, while learning selects informative...
Saliency detection on images has experienced substantial progress in recent years the basis of deep neural network (DNN). However, there may exist secondary saliency background that distracts DNN learning and mistakes salient regions as saliency. To address this issue, we propose a dual-term energy to improve inference top estimation, where dense term smoothens pixel scale sparse extracts prior knowledge differentiate non-saliency superpixels. Our including extra- intra-region priors,...