0-1 programming is a special case of the integer programming, which is commonly encountered in many optimization problems. Neural network and its general energy function are presented for 0-1 optimization problem. The...0-1 programming is a special case of the integer programming, which is commonly encountered in many optimization problems. Neural network and its general energy function are presented for 0-1 optimization problem. Then, the 0-1 optimization problems are solved by a neural network model with transient chaotic dynamics (TCNN). Numerical simulations of two typical 0-1 optimization problems show that TCNN can overcome HNN's main drawbacks that it suffers from the local minimum and can search for the global optimal solutions in to solveing 0-1 optimization problems.展开更多
Chaos theory was introduced for water quality, prediction, and the model of water quality prediction was established by combining phase space reconstruction theory and BP neural network forecasting method. Through the...Chaos theory was introduced for water quality, prediction, and the model of water quality prediction was established by combining phase space reconstruction theory and BP neural network forecasting method. Through the phase space reconstruction, the one-dimensional water quality time series were mapped to be multi-dimensional sequence, which enriched the spatial information of water quality change and expanded mapping region of training samples of BP neural network. Established model of combining chaos theory and BP neural network were applied to forecast turbidity time series of a certain reservoir. Contrast to BP neural network method, the relative error and the mean squared error of the combined method had all varying degrees of lower. Results indicated the neural network model with chaos theory had the higher prediction accuracy, at the same time, it had better fault-tolerant capability and generalization performance .展开更多
In chaotic communication system, the useful signal is hidden in chaotic signal, so the general method does not work well. Due to the random feature of chaotic signal, a functional networkbased method is presented. In ...In chaotic communication system, the useful signal is hidden in chaotic signal, so the general method does not work well. Due to the random feature of chaotic signal, a functional networkbased method is presented. In this method, the neural functions are selected from some complete function set for the functional network to reconstruct the chaotic signal, so the useful signal hidden in chaotic background is extracted. In addition, its learning algorithm is presented here and the example proves its good preformance.展开更多
A laboratory leaching experiment with samples of different grades was carried out, and an analytical method of concentration of leaching solution was put forward. For each sample, respectively, by applying phase space...A laboratory leaching experiment with samples of different grades was carried out, and an analytical method of concentration of leaching solution was put forward. For each sample, respectively, by applying phase space reconstruction for time series of monitoring data, the saturated embedding dimension and the correlation dimension were obtained, and the evolution laws between neighboring points in the reconstructed phase space were revealed. With BP neural network, a prediction model of concentration of leaching solution was set up and the maximum error of which was less than 2%. The results show that there exist chaotic characteristics in leaching system, and samples of different grades have different nonlinear dynamic features; the higher the grade of sample, the smaller the correlation dimension; furthermore, the maximum Lyapunov index, energy dissipation and chaotic extent of the leaching system increase with grade of the sample; by phase space reconstruction, the subtle change features of concentration of leaching solution can be magnified and the inherent laws can be fully demonstrated. According to the laws, a prediction model of leaching cycle period has been established to provide a theoretical foundation for solution mining.展开更多
近年来,医疗数据泄露频发,严重威胁患者隐私与健康安全,亟需有效的解决方案以保护医疗数据在传输过程中的隐私与安全性。该文提出了一种基于双忆阻类脑混沌神经网络的医疗物联网(Internet of Medical Things,IoMT)数据隐私保护方法,以...近年来,医疗数据泄露频发,严重威胁患者隐私与健康安全,亟需有效的解决方案以保护医疗数据在传输过程中的隐私与安全性。该文提出了一种基于双忆阻类脑混沌神经网络的医疗物联网(Internet of Medical Things,IoMT)数据隐私保护方法,以应对这一挑战。首先,利用忆阻器的突触仿生特性,构建了一种基于Hopfield神经网络的双忆阻类脑混沌神经网络模型,并通过分岔图、Lyapunov指数谱、相图、时域图及吸引盆等非线性动力学工具,深入揭示了模型的复杂混沌动力学特性。研究结果表明,该网络不仅展现出复杂的网格多结构混沌吸引子特性,还具有平面初值位移调控能力,从而显著增强了其密码学应用潜力。为了验证其实用性与可靠性,基于微控制器单元(MCU)搭建了硬件平台,并通过硬件实验进一步确认了模型的复杂动力学行为。基于此模型,该文设计了一种结合双忆阻类脑混沌神经网络复杂混沌特性的高效IoMT数据隐私保护方法。在此基础上,对彩色医疗图像数据的加密效果进行了全面的安全性分析。实验结果表明,该方法在关键性能指标上表现优异,包括大密钥空间、低像素相关性、高密钥敏感性,以及对噪声与数据丢失攻击的强鲁棒性。该研究为IoMT环境下的医疗数据隐私保护提供了一种创新且有效的解决方案,为未来的智能医疗安全技术发展奠定了坚实基础。展开更多
基金This project was supported by the National Natural Science Foundation of China (79970042).
文摘0-1 programming is a special case of the integer programming, which is commonly encountered in many optimization problems. Neural network and its general energy function are presented for 0-1 optimization problem. Then, the 0-1 optimization problems are solved by a neural network model with transient chaotic dynamics (TCNN). Numerical simulations of two typical 0-1 optimization problems show that TCNN can overcome HNN's main drawbacks that it suffers from the local minimum and can search for the global optimal solutions in to solveing 0-1 optimization problems.
文摘Chaos theory was introduced for water quality, prediction, and the model of water quality prediction was established by combining phase space reconstruction theory and BP neural network forecasting method. Through the phase space reconstruction, the one-dimensional water quality time series were mapped to be multi-dimensional sequence, which enriched the spatial information of water quality change and expanded mapping region of training samples of BP neural network. Established model of combining chaos theory and BP neural network were applied to forecast turbidity time series of a certain reservoir. Contrast to BP neural network method, the relative error and the mean squared error of the combined method had all varying degrees of lower. Results indicated the neural network model with chaos theory had the higher prediction accuracy, at the same time, it had better fault-tolerant capability and generalization performance .
文摘In chaotic communication system, the useful signal is hidden in chaotic signal, so the general method does not work well. Due to the random feature of chaotic signal, a functional networkbased method is presented. In this method, the neural functions are selected from some complete function set for the functional network to reconstruct the chaotic signal, so the useful signal hidden in chaotic background is extracted. In addition, its learning algorithm is presented here and the example proves its good preformance.
基金Project(51374035)supported by the National Natural Science Foundation of ChinaProject(2012BAB08B02)supported by the National“Twelfth Five”Science and Technology,ChinaProject(NCET-13-0669)supported by New Century Excellent Talents in University of Ministry of Education of China
文摘A laboratory leaching experiment with samples of different grades was carried out, and an analytical method of concentration of leaching solution was put forward. For each sample, respectively, by applying phase space reconstruction for time series of monitoring data, the saturated embedding dimension and the correlation dimension were obtained, and the evolution laws between neighboring points in the reconstructed phase space were revealed. With BP neural network, a prediction model of concentration of leaching solution was set up and the maximum error of which was less than 2%. The results show that there exist chaotic characteristics in leaching system, and samples of different grades have different nonlinear dynamic features; the higher the grade of sample, the smaller the correlation dimension; furthermore, the maximum Lyapunov index, energy dissipation and chaotic extent of the leaching system increase with grade of the sample; by phase space reconstruction, the subtle change features of concentration of leaching solution can be magnified and the inherent laws can be fully demonstrated. According to the laws, a prediction model of leaching cycle period has been established to provide a theoretical foundation for solution mining.
文摘近年来,医疗数据泄露频发,严重威胁患者隐私与健康安全,亟需有效的解决方案以保护医疗数据在传输过程中的隐私与安全性。该文提出了一种基于双忆阻类脑混沌神经网络的医疗物联网(Internet of Medical Things,IoMT)数据隐私保护方法,以应对这一挑战。首先,利用忆阻器的突触仿生特性,构建了一种基于Hopfield神经网络的双忆阻类脑混沌神经网络模型,并通过分岔图、Lyapunov指数谱、相图、时域图及吸引盆等非线性动力学工具,深入揭示了模型的复杂混沌动力学特性。研究结果表明,该网络不仅展现出复杂的网格多结构混沌吸引子特性,还具有平面初值位移调控能力,从而显著增强了其密码学应用潜力。为了验证其实用性与可靠性,基于微控制器单元(MCU)搭建了硬件平台,并通过硬件实验进一步确认了模型的复杂动力学行为。基于此模型,该文设计了一种结合双忆阻类脑混沌神经网络复杂混沌特性的高效IoMT数据隐私保护方法。在此基础上,对彩色医疗图像数据的加密效果进行了全面的安全性分析。实验结果表明,该方法在关键性能指标上表现优异,包括大密钥空间、低像素相关性、高密钥敏感性,以及对噪声与数据丢失攻击的强鲁棒性。该研究为IoMT环境下的医疗数据隐私保护提供了一种创新且有效的解决方案,为未来的智能医疗安全技术发展奠定了坚实基础。
