A5101807587- Advanced Memory and Neural Computing
- Metaheuristic Optimization Algorithms Research
- Ferroelectric and Negative Capacitance Devices
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Network Security and Intrusion Detection
- Neural Networks and Applications
- Neural dynamics and brain function
- Sparse and Compressive Sensing Techniques
- Neural and Behavioral Psychology Studies
- Advanced Algorithms and Applications
- Advanced SAR Imaging Techniques
- Advanced Multi-Objective Optimization Algorithms
- Microbial Fuel Cells and Bioremediation
- Optimization and Search Problems
- Radiomics and Machine Learning in Medical Imaging
- Optimization and Packing Problems
- Membrane-based Ion Separation Techniques
- Advanced Decision-Making Techniques
- Gait Recognition and Analysis
- Vehicle Routing Optimization Methods
- AI in cancer detection
- Fuzzy Logic and Control Systems
- IoT and GPS-based Vehicle Safety Systems
- Solar Thermal and Photovoltaic Systems
- Process Optimization and Integration
Xidian University
2024
CCCC Highway Consultants (China)
2024
Sun Yat-sen University
2008-2024
Shanghai Maritime University
2022-2024
Tsinghua University
2019-2023
Zhejiang University
2022
Fuzhou University
2020
Institute of Microelectronics
2019
Medical imaging is an important tool for accurate medical diagnosis, while state-of-the-art image reconstruction algorithms raise critical challenges in massive data processing high-speed and high-quality imaging. Here, we present a memristive reconstructor (MIR) to greatly accelerate with discrete Fourier transformation (DFT) by computing-in-memory (CIM) memristor arrays. A high-accuracy quasi-analogue mapping (QAM) method generic complex matrix transfer (CMT) scheme was proposed improve...
We demonstrate a monolithic 3D integration of Si-based CMOS logic, resistive random-access memory (RRAM) based computing-in-memory (CIM) and ternary content-addressable (TCAM) layers, namely M3D-LIME, to implement one-shot learning. The first layer Si MOSFETs was designed fabricated using standard process served as control logic. second 1 T1R array with HfAlOx-based analog RRAM low-temperature (≤ 300°C) back-end-of-line (BEOL) CIM for feature extractions. third 2T2R-based TCAM carbon...
For the first time, an energy-efficient hybrid precoding with computing-in-memory technology for 5G/6G MIMO communication system is demonstrated. To meet requirement of massive matrix multiplication signal processing, we realize fully-parallel large-scale (128K) analog resistive switching RRAM array. In order to address IR-drop issue caused by both interconnect resistance and peripheral circuit in arrays, a compact model corresponding compensation scheme are proposed. computation complexity...
Unconstrained binary quadratic programming problem (UBQP) consists in maximizing a 0-1 function. It is well known NP-hard and considered as unified model for variety of combinatorial optimization problems. Recently, multi-objective UBQP (mUBQP) defined set mUBQP instances proposed. This paper proposes directional-biased tabu search algorithm (DTS) problem. In the beginning search, DTS optimizes each objective function to obtain extreme solutions. If solution one cannot be further improved,...
Traditional network defense approaches are insufficient to deal with new types of threats. Active based on software-defined networks helps solve this problem, which includes random port-hopping technology. Existing have problems such as the inability completely hide service port and complicated hopping mechanism. What is more, there no strict demonstration security effectiveness evaluation its influencing factors. In paper, a hidden services approach several models proposed these existing...
Gastroscopy is the first method to check gastrointestinal cancer and related diseases. Traditional manual methods have disadvantages of time-consuming, high missed diagnosis misdiagnosis rates. Image recognition technology based on deep learning has great potential in improving efficiency accuracy. We summarize latest advances gastric from aspects data sets, image preprocessing, classification algorithms. Most research teams cooperate with hospitals build small preprocess images using...
Steam turbine blades may crack, break, or suffer other failures due to high temperatures, pressures, and high-speed rotation, which seriously threatens the safety reliability of equipment. The signal characteristics different fault types are slightly different, making it difficult accurately classify faults rotating directly through vibration signals. This method combines a one-dimensional convolutional neural network (1DCNN) channel attention mechanism (CAM). 1DCNN can effectively extract...
In recent years, super multi-lane expressways such as two-way ten lanes and twelve have become a new trend of highway reconstruction expansion in our country. Due to the limitations terrain conditions, land use scale investment expressway expansion, some adjacent interchange is set compound because small net distance between them. this paper, combination with auxiliary taken research scenario, by combining theory simulation analysis, length selection method weaving area composite (one-way...
Most of multiobjective optimization algorithms consider multiple objectives as a whole when solving problems (MOPs). However, in MOPs, different objective functions may possess properties. Hence, it can be beneficial to build objective-wise strategy for each separately. This paper presents single guided (SOGMO) framework solve continuous MOPs. In SOGMO framework, solution is first selected from archive, and then learning developed Finally, all the considered simultaneously optimized parallel...
Automatic target recognition in synthetic aperture radar (SAR) images is a challenging task due to the unique imaging mechanism of SAR images. To address speckle noise and intensity variations caused by different operating conditions, we propose novel approach that implemented via multi-scale perception (MSP) denoising representation (DR). Specifically, first design MSP method for feature extraction which takes advantage sparse random projections features. This sparsity allows us avoid...
Geothermal Aided Power Generation (GAPG) technology is a geothermal hybrid power system that energy has been integrated into the fossil fired plant to preheat feedwater, and displace extraction steam of plant. In such system, heat exchange process between geo-fluid occurs in between. When exchanger quench lower temperature for transfer purpose, silica scaling would occur system. The performance GAPG be influenced by configuration exchanger. For plant, it two possible configurations system:...
Among the basic functions of brain, associative memory is an important ability, as widely illustrated by Pavlov's dog experiment. In article number 1900155, employing electro-thermal modulation layer, Huaqiang Wu and co-workers optimize a multilevel memristor cell. A Hopfield neural network experimentally demonstrated on integrated 1 k array.
The study focuses on the flexible thermal connection joint in active fluid loop of spacecraft, conducting stress, stiffness, and fatigue analysis. A computational model - bellows was established simplified through ANSYS finite element analysis, analyzing its stiffness coefficient correction under yield limit. Based Miner linear damage theory data from N-code analysis software library, a carried out. results show: torque corresponding to limit is 132.06N, twist angle 259°; 1.238 when not...