A5003572308- DNA and Biological Computing
- Advanced biosensing and bioanalysis techniques
- Advanced Memory and Neural Computing
- Advanced Measurement and Detection Methods
- Modular Robots and Swarm Intelligence
- Image Retrieval and Classification Techniques
- Neural Networks and Applications
- Retinal Imaging and Analysis
- Medical Image Segmentation Techniques
- Advanced Image Fusion Techniques
- AI in cancer detection
- Advanced Vision and Imaging
- Neural Networks and Reservoir Computing
- Remote-Sensing Image Classification
- Cutaneous Melanoma Detection and Management
- Cellular Automata and Applications
- Infrared Target Detection Methodologies
- Prostate Cancer Diagnosis and Treatment
- Advanced Steganography and Watermarking Techniques
- Image and Signal Denoising Methods
- Image Processing Techniques and Applications
- Neural dynamics and brain function
- Remote Sensing and Land Use
- Industrial Vision Systems and Defect Detection
- Video Surveillance and Tracking Methods
Xihua University
2012-2024
Baoji City Central Hospital
2023-2024
Soochow University
2018
Sichuan Animal Science Academy
2014
Georgia Institute of Technology
2014
C3J Therapeutics (United States)
2003
Chongqing University
2002
This paper proposes a new variant of spiking neural P systems (in short, SNP systems), nonlinear NSNP systems). In systems, the state each neuron is denoted by real number, and configuration vector used to characterize whole system. A type rules, introduced handle neuron’s firing, where consumed generated amounts spikes are often expressed functions neuron. class distributed parallel nondeterministic computing systems. The computational power discussed. Specifically, it proved that as...
Coupled neural P (CNP) systems are a recently developed Turing-universal, distributed and parallel computing model, combining the spiking coupled mechanisms of neurons. This paper focuses on how to apply CNP handle fusion multi-modality medical images proposes novel image method. Based two with local topology, an framework in nonsubsampled shearlet transform (NSST) domain is designed, where used control low-frequency NSST coefficients. The proposed method evaluated 20 pairs compared seven...
Nonlinear spiking neural P (NSNP) systems are a class of neural-like computational models inspired from the nonlinear mechanism neurons. NSNP have distinguishing feature: mechanism. To handle edge detection images, this paper proposes variant, with two outputs (TO), termed as NSNP-TO systems. Based on system, an framework is developed, ED-NSNP detector. The ability detector relies convolutional kernels. obtain good performance, particle swarm optimization (PSO) used to optimize parameters...
Nonlinear spiking neural P (NSNP) systems are a recently developed theoretical model, which is abstracted by nonlinear mechanism of biological neurons. NSNP have structure and the potential to describe dynamic systems. Based on systems, novel time series forecasting approach in this paper. During training phase, first converted frequency domain using redundant wavelet transform, then according data, an system automatically constructed adaptively trained domain. Then, well-trained can...
Wearable and contextually aware technologies have great applicability in task guidance systems. Order picking is the of collecting items from inventory a warehouse sorting them for distribution; this process accounts about 60% total operational costs these warehouses. Current practice industry includes paper pick lists pick-by-light We evaluated order assisted by four approaches: head-up display (HUD); cart-mounted (CMD); pick-by-light; list. report accuracy, error types, time, subjective...
Particle swarm optimization algorithm is a branch of evolutionary computing and can search for better solution in given feature space. This paper introduces the particle greedy strategy defect detection location industrial components then proposes algorithm. employs sparse random projection to map vast high-dimensional information low-dimensional space while maintaining relative distance between data. employment helps accelerate training prediction speed model remove some unimportant...
P systems are a class of distributed parallel computing models; this paper presents novel clustering algorithm, which is inspired from mechanism tissue-like system with loop structure cells, called membrane algorithm. The objects the cells express candidate centers clusters and evolved by evolution rules. Based on structure, communication rules realize local neighborhood topology, helps coevolution improves diversity in system. can effectively search for optimal partitioning help its...
Objective To develop an accurate and automatic segmentation model based on convolution neural network to segment the prostate its lesion regions. Methods Of all 180 subjects, 122 healthy individuals 58 patients with cancer were included. For each subject, slices of comprised in DWIs. A novel DCNN is proposed automatically This inspired by U-Net encoding-decoding path as backbone, importing dense block, attention mechanism techniques, group norm-Atrous Spatial Pyramidal Pooling. Data...
Conventional feature detection algorithms are largely based on clustered two-dimensional (2D) blocks of information. However, corners located at the centre gradually greying information cannot be extracted using these algorithms. The edge points described by often affected background changes, leading to significant differences in descriptors for same feature. These issues detrimental subsequent matching processes. Therefore, we propose a new method that will provide more useful corner...
This paper proposes an extension of numerical P (NP) systems, called stochastic (StNP) systems. In StNP a novel production function-repartition protocol is developed to evolve the variables. Compared with usual in NP there are two differences protocol: (i) some stochastic/randomized factors introduced function and/or repartition protocol; (ii) data updating way relaxed and can be flexibly used. An system has nested structure contains variables group programs. The programs consist protocols...
Locating the vehicle license plate plays an important role in automatic recognition system, At present gray feature and texture were considered most location methods, however, these methods have weak adaptability different environment. To solve problems, based on singular value is proposed basis of plate. License plates non-plate regions can be distinguished by extracting feature, which described Hidden Markov Models (HMM). Experimental results show that accurate positioning licenses...