A5101654483- Advancements in Battery Materials
- Advanced Battery Materials and Technologies
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Photopolymerization techniques and applications
- AI in cancer detection
- Digital Media and Visual Art
- Supercapacitor Materials and Fabrication
- Advanced Polymer Synthesis and Characterization
- Advanced MIMO Systems Optimization
- Domain Adaptation and Few-Shot Learning
- Neuroscience and Neural Engineering
- Image Processing Techniques and Applications
- Astronomical Observations and Instrumentation
- Nanofabrication and Lithography Techniques
- COVID-19 diagnosis using AI
- Cooperative Communication and Network Coding
- Advanced Manufacturing and Logistics Optimization
- Extraction and Separation Processes
- Advanced Battery Technologies Research
- Cell Image Analysis Techniques
- Advanced Neural Network Applications
- Energy Harvesting in Wireless Networks
- Assembly Line Balancing Optimization
- Radiomics and Machine Learning in Medical Imaging
Hunan University of Science and Engineering
2024
Beijing University of Posts and Telecommunications
2022-2024
Beihang University
2022-2024
Xiamen University
2013-2024
Soochow University
2024
Beijing University of Technology
2024
Amazon (Germany)
2024
Chongqing University
2024
Collaborative Innovation Center of Chemistry for Energy Materials
2013-2024
Tan Kah Kee Innovation Laboratory
2024
The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer. routine HER2 conducted with immunohistochemical techniques (IHC), which very expensive. Therefore, the first time, we propose cancer (BCI) benchmark attempting synthesize IHC data directly paired hematoxylin and eosin (HE) stained images. dataset contains 4870 registered image pairs, covering variety levels.Based on BCI, as minor contribution, further...
This work provides a facile one-step sol-gel route to synthesize high-quality resorcinol-formaldehyde (RF) resin coated nanocomposites that can be further used fabricate desired carbon nanostructures. Colloidal particles with different morphologies and sizes RF shells by the proposed cationic surfactant assisted coating strategy. The as-synthesized are ideal candidates for selective synthesis of core-shell, hollow, yolk-shell Based on carboxylic functional coating, graphitic nanostructures...
A thick and dense flakelike LiCoO2 with exposed {010} active facets is synthesized using Co(OH)2 nanoflake as a self-sacrificial template obtained from simple coprecipitation method, served cathode material for lithium ion batteries. When operated at high cutoff voltage up to 4.5 V, the resultant exhibits an outstanding rate capability, delivering reversible discharge capacity 179, 176, 168, 116, 96 mA h g(-1) 25 °C under current of 0.1, 0.5, 1, 5, 10 C, respectively. charge/discharge...
One-dimensional LiNi<sub>0.8</sub>Co<sub>0.15</sub>Al<sub>0.05</sub>O<sub>2</sub> microrods are synthesized through chemical lithiation of mixed Ni, Co, and Al oxalate microrod. The rod-like morphology together with structural stability endows it superior rate capability cycle performance for highly reversible lithium storage.
Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing (NLP), where data samples exhibit explicit spatial or semantic dependencies. However, applying these to tabular is challenging due the less pronounced dependencies among samples. In this paper, we address limitation by introducing SwitchTab, a novel self-supervised method specifically designed capture latent data. SwitchTab leverages an asymmetric...
Graph neural networks (GNNs) can improve the efficiency of learning wireless policies by leveraging their permutation properties and topology prior. While mismatched property to a policy may degrade performance overlooked permutations incurs low sample efficiency, there is still lacking systematical approach for modeling graph designing structure GNNs harness all properties. Moreover, information input feature lose during updating hidden representations with GNNs, which leads poor...
Abstract Ternary layered LiNi 0.5 Co 0.2 Mn 0.3 O 2 microspheres are functionally surface‐modified with a fast‐Li + ‐conductive Li ZrO 3 ‐based shell through facile synthetic strategy based on an infiltrative pre‐coating treatment combined single‐step post‐sintering process. Owing to the complete nanoscale coating, which has 3D diffusion path for , resultant coated manifest remarkably enhanced rate capability and cycling performance as cathode materials both at room elevated temperature when...
Objective. White matter tissue takes up approximately 50% of the human brain volume and it is widely known as a messenger conducting information between areas central nervous system. However, characteristics white neural activity whether recordings can contribute to movement decoding are often ignored still remain largely unknown. In this work, we make quantitative analyses investigate these two important questions using invasive recordings. Approach. We recorded...
Deep learning based on convolutional neural networks (CNN) has achieved success in brain-computer interfaces (BCIs) using scalp electroencephalography (EEG). However, the interpretation of so-called 'black box' method and its application stereo-electroencephalography (SEEG)-based BCIs remain largely unknown. Therefore, this paper, an evaluation is performed decoding performance deep methods SEEG signals.Thirty epilepsy patients were recruited, a paradigm including five hand forearm motion...
The prevalence of electronic defects has not been successfully demonstrated in nonreducible oxides. This work presents a straightforward approach to the preparation yellow alumina rich F-centers (oxygen vacancies containing free electrons), which is well characterized by systematic spectral methods. surface electron density as-prepared F-center enriched sample was estimated be approximately 0.35 mmol·g
Abstract Objective. Brain–computer interfaces (BCIs) have the potential to bypass damaged neural pathways and restore functionality lost due injury or disease. Approaches decoding kinematic information are well documented; however, of kinetic has received less attention. Additionally, possibility using stereo-electroencephalography (SEEG) for during hand grasping tasks is still largely unknown. Thus, objective this paper demonstrate parameter SEEG in patients performing a task with two...
Stereo-electroencephalography (SEEG) utilizes localized and penetrating depth electrodes to directly measure electrophysiological brain activity. The implanted generally provide a sparse sampling of multiple regions, including both cortical subcortical structures, making the SEEG neural recordings potential source for brain-computer interface (BCI) purpose in recent years. For signals, data cleaning is an essential preprocessing step removing excessive noises further analysis. However,...
Based on a practical application, this paper proposes the design and implementation to build an embedded-Linux downloading server network proxy, which is mainly applied download resources such as movies music from Internet via various protocols (http, ftp, bittorrent, emule, etc.) well be proxy. As proxy instead of computers (PC), prototype proved more available effective protect environment save energy.
Thanks to the rapid development of vehicle-to-everything (V2X) and sensor technology, states vehicles can be accurately measured stored jointly in cloud. These viewed as a set infinite attributes, such density around motor vehicle, signal strength so on. As such, vehicle moving object. The state measured, its entropy is large. In networking, unicast communications between must encrypted. previous approach was negotiate session key through Diffie-Hellman algorithm then use encrypt...
Hybrid precoding in millimeter wave systems can support high spectral efficiency with affordable cost. With deep learning, fairly good solutions that are robust to imperfect chan-nels be obtained low complexity from the non-convex optimization problems. Yet previous works for hybrid cost training neural networks because mathe-matical properties of problems not taken into account. In this paper, we show exhibit a multi-set permutation equivariance (PE) property and phase invariance property....
<p>For invasive breast cancer, immunohistochemical (IHC) techniques are often used to detect the expression level of human epidermal growth factor receptor-2 (HER2) in tissue formulate a precise treatment plan. From perspective saving manpower, material and time costs, directly generating IHC-stained images from hematoxylin eosin (H&E) stained is valuable research direction. Therefore, we held cancer image generation challenge, aiming explore novel ideas deep learning technology...