Echo State Networks (ESNs) is a newly developed recurrent neural network model. It has a special echo state property which entitles it to model nonlinear dynamic systems whose outputs are determined by previous inputs...
详细信息
ISBN:
(纸本)9783642106767
Echo State Networks (ESNs) is a newly developed recurrent neural network model. It has a special echo state property which entitles it to model nonlinear dynamic systems whose outputs are determined by previous inputs and outputs. The ESN approach has so far been worked out almost exclusively using standard sigmoid networks. Here we will consider ESNs constructed by leaky integrator neurons, which incorporate a time constant and the dynamics can be slowed down. Furthermore, we optimized relevant parameters of the network by Particle Swarm Optimization (PSO) in order to get a higher modeling precision. Here the input signals are spikes distilled from the monkey's motor cortex in an experiment and the outputs are the moving trajectories of the wrist of a monkey in the experiment. The results show that this model can well translate the neuronal firing activities into the desired positions.
Owing to the weaknesses of existing correlation detection methods in digital fingerprint matching, such as difficult to determine the threshold and low matching accuracy rate, a method proposed in digital fingerprint ...
详细信息
In this paper, a semi-fragile watermark solution based on quantization index modulation in the wavelet region was proposed. The algorithm employs a compressed halftoned binary image as watermark and embeds it in the w...
详细信息
This paper presents an applied study of scheduling buses and drivers for the Beijing Bus Group (BJBUS), the largest bus company in China. This is pioneering research in China for bus transit scheduling using computers...
详细信息
This paper presents an applied study of scheduling buses and drivers for the Beijing Bus Group (BJBUS), the largest bus company in China. This is pioneering research in China for bus transit scheduling using computers based on a unified mode of operation. It is anticipated that the research fruits and experiences obtained would be of benefit to other bus operators in China. The bus transit scheduling problem in BJBUS is first presented in the paper. The particular characteristics are pointed out, which are different from those in developed countries, while many are common in China. After a brief review and analysis of the appropriateness of some currently successful approaches, the paper focuses on reporting the solution ideas and methods for BJBUS, especially those developed to solve the specific problems of BJBUS, such as scheduling buses with built-in meal periods, multi-type bus scheduling, restricting drivers to one or two particular buses, etc. Finally, the implementation and computational results are reported before the concluding remarks.
Base on the theory of computational methods of experiments and agent modeling technology, combining with sociology and psychology, the paper presents method of computational experiments for research of Urban Mass Pani...
详细信息
ISBN:
(纸本)9783642015120
Base on the theory of computational methods of experiments and agent modeling technology, combining with sociology and psychology, the paper presents method of computational experiments for research of Urban Mass Panic (UMP). The method proposed a panic-information transmitting, artificial system for computational experiments with agent modeling technology. The system planed two kinds of agents: social individual agents and panic alarming agents. Social individual agents are designed to simulate persons living common human society. These agents which contain the ability of panic information recognition, reflection and making different decision are simulated with some nonlinear methods, Such as fuzzy neural network. Panic alarming agents are designed to simulate circumstance which engenders panic information or panic phenomenon. These agents collect information about panic and release information to social individual agents by different transmitting methods we call image. The paper also discusses how to carry through measurement to check the level of UMP by the information entropy theory dynamically.
A novel PSO algorithm, the Migrant Particle Swarm Optimization (Migrant PSO), is presented to solve the trajectory optimization problem in the presence of constraints such as dynamic pressure and overload. Imitating t...
详细信息
ISBN:
(纸本)9781424438655
A novel PSO algorithm, the Migrant Particle Swarm Optimization (Migrant PSO), is presented to solve the trajectory optimization problem in the presence of constraints such as dynamic pressure and overload. Imitating the behaviour of a flock of migrant birds, the Migrant PSO algorithm employs stochastic search method and adaptive linear search method respectively for PSO search spaces including both continuous space and discrete space. In the example of the minimum peak heat rate reentry trajectory optimization for X-33 vehicle model with free terminal time, some key problems such as parameterized method are argued in detail. The simulation results indicate that the Migrant PSO algorithm proves to be able to generate a complete and optimal 3DOF reentry trajectory rapidly.
作者：
Zuo, Bo-XinMing, De-LieTian, Jin-WenHuazhong Univ Sci & Technol
Inst Pattern Recognit & Artificial Intelligence State Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Province Peoples R China Huazhong Univ Sci & Technol
Inst Recognit & Artificial Intelligence State Educ Commiss Lab Image Proc & Intelligence Wuhan 430074 Hubei Province Peoples R China
Linear space-invariant image restoration algorithms often introduce ringing effects near sharp intensity transitions. A ringing metric to evaluate the quality of images restored using iterative deconvolution algorithm...
详细信息
Linear space-invariant image restoration algorithms often introduce ringing effects near sharp intensity transitions. A ringing metric to evaluate the quality of images restored using iterative deconvolution algorithms is presented. According to the types of ringing artifacts, two ringing metrics are used to assess the restored images based on the analysis of ringing artifacts. An overall ringing metric is presented based on the two ringing metrics. The experimental results validate that the proposed method performs well over a wide range of restoration image ringing level assessments. Consequently, the proposed model has a good agreement with the ratings from an observer in subjective experiments. (C) 2009 Society of Photo-Optical Instrumentation Engineers. [DOI: 10.1117/1.3095766]
The SPIHT (set partitioning in hierarchical trees) algorithm has attracted great attention in recent years as a technique for image coding. Not only does it give good objective and subjective performance, it is also s...
详细信息
ISBN:
(纸本)9783642015090
The SPIHT (set partitioning in hierarchical trees) algorithm has attracted great attention in recent years as a technique for image coding. Not only does it give good objective and subjective performance, it is also simple and efficient. In this paper, we investigate the problem Of how to quantize the wavelet coefficients in the lowest frequency subband with multi-scalar method. A novel wavelet image coding algorithm using multi-scalar quantization based oil SPIHT is proposed. First, in the higher bit plane, this algorithm only quantizes the wavelet coefficients in the lowest frequency subband. Then it quantizs other ones by uniform scalar. Experiment results have shown the proposed scheme improves the performance of wavelet image coders. In particular. it will get better coding gain in the low bit rates image coding.
This paper presents a new affine registration approach for planar point pattern matching. A process of parameter space clustering is implemented to confirm a one-to-one mapping between the maximal subsets of feature p...
详细信息
Background/purpose Skin microrelief has been studied using various methods and devices. However, the long duration of time needed to process one sample or the expensive equipment hampered the use of those systems for ...
详细信息
Background/purpose Skin microrelief has been studied using various methods and devices. However, the long duration of time needed to process one sample or the expensive equipment hampered the use of those systems for routine diagnosis. Today, the emergence of new software and hardware technologies may allow this issue to be resolved. Methods To characterize objectively the skin surface, we introduced a new parameter SPm, namely, the area mean of superficial skin texture block formed by primary and secondary lines crossing each other. Based on the skin detector produced by the Boseview Technology Company, we developed a software for acquiring automatically skin images and calculating SPm. The relationship between SPm and age was studied on the dorsal and ventral midway of the forearm (sun-exposed and sun-protected areas) of 94 healthy volunteers without a history of smoking. Results The skin surface topography can be conveniently quantified with the new parameter SPm. The value of SPm of both sites increases with age, independent of sex, with the site more exposed to light being more affected. Conclusion With the software developed, the details of the skin surface can be observed. SPm appears to be a new valid parameter for characterizing the property of the skin surface. Our method, alone or in combination with other technologies of skin topography analysis may be applied in routine diagnosis for a quantified evaluation of skin aging.
暂无评论