We analyze correlations and patterns of oxidative activity of 3D DNA at DNA fluorescence in complete sets of chromosomes in neutrophils of peripheral blood. Fluorescence of DNA is registered by method of flow cytometr...We analyze correlations and patterns of oxidative activity of 3D DNA at DNA fluorescence in complete sets of chromosomes in neutrophils of peripheral blood. Fluorescence of DNA is registered by method of flow cytometry with nanometer spatial resolution. Experimental data present fluorescence of many ten thousands of cells, from different parts of body in each population, in various blood samples. Data is presented in histograms as frequency distributions of flashes in the dependence on their intensity. Normalized frequency distribution of information in these histograms is used as probabilistic measure for definition of Shannon entropy. Data analysis shows that for this measure of Shannon entropy common sum of entropy, i.e. total entropy E, for any histogram is invariant and has identical trends of changes all values of E (r) = lnr at reduction of rank r of histogram. This invariance reflects informational homeostasis of chromosomes activity inside cells in multi-scale networks of entropy, for varied ranks r. Shannon entropy in multi-scale DNA networks has much more dense packing of correlations than in “small world” networks. As the rule, networks of entropy differ by the mix of normal D 2 and abnormal D > 2 fractal dimensions for varied ranks r, the new types of fractal patterns and hinges for various topology (fractal dimension) at different states of health. We show that all distributions of information entropy are divided on three classes, which associated in diagnostics with a good health or dominants of autoimmune or inflammatory diseases. This classification based on switching of stability at transcritical bifurcation in homeostasis regulation. We defined many ways for homeostasis regulation, coincidences and switching patterns in branching sequences, the averages of Hölder for deviations of entropy from homeostasis at different states of health, with various saturation levels the noises of entropy at activity of all chromosomes in support regulation of homeostasis.展开更多
We analyze fluorescence due to oxidizing activity of DNA in neutrophils of peripheral blood in the large populations ~104 - 105 of cells. Fluorescence is registered by flow cytometry method. Spatial resolution is abou...We analyze fluorescence due to oxidizing activity of DNA in neutrophils of peripheral blood in the large populations ~104 - 105 of cells. Fluorescence is registered by flow cytometry method. Spatial resolution is about a few nanometers for varied complex three-dimensional (3D) DNA nanostructures of all non-coding and coding parts of DNA. It’s shown that oxidative activity of all 3D DNA in the full set of chromosomes inside cells is defined by new standards for complex networks of “exponentially small worlds”, with more dense packing than in the well known networks of “small worlds”. Analysis of various blood samples in vivo and during medical treatment shown that only two classes of Good and Bad Networks of DNA for a good and a bad health existed. This division is defined by any network to one from two classes of “n” or “s” shaped curves for typical deviations and from straight line in perfect networks of “exponentially small worlds”, as for two types of hysteresis curves at phase transitions or at switching of bistability. These deviations coincide with two types of positive and negative trends of changing fractal dimension by changing the scales of multi-scale networks of fluorescing DNA. These trends give the overall assessments of human immunity, including hidden and unidentified diseases, and as a sum of all kinds of health and illness of given person, from the point of view the inner life of neutrophils, living in different parts of human body in given time. Characteristics of deviations associated with type, level and complexity of illness in the dependence on展开更多
This paper studies the eigentime and related issues in the fractal network corresponding to the Sierpiński fractal antenna.The access time or hitting time H(i,j)is the expected number of steps before node j is visite...This paper studies the eigentime and related issues in the fractal network corresponding to the Sierpiński fractal antenna.The access time or hitting time H(i,j)is the expected number of steps before node j is visited,starting from node i.The eigentime of G is the expectation of H(i,j)for all i,j∈G.Classical eigenvalue method let H(i,i)=0.However,when studying the random walk behavior of electrons in fractal networks corresponding to fractal antennas,it is nec-essary to consider the time when electrons leave a certain node and first return to that node(self return time).This paper adopts two research methods-the eigenvalue method based on spectral theory and the Markov chain method based on stochastic process theory-to obtain the modified in-trinsic time,and demonstrates through an example that the difference between the classical intrin-sic time and the modified intrinsic time is precisely due to the self return time.This paper shows the applications of fractal networks in modern communications.The research results are expected to provide a theoretical basis for the design and performance optimization of fractal antennas.展开更多
Oriented attachment can be used as a good synthetic route to make highly anisotropic nanostructures including nanorod,nanowire,nanoplate,and nanosheets.In a typical growth of anisotropic nanostructures,coalescence and...Oriented attachment can be used as a good synthetic route to make highly anisotropic nanostructures including nanorod,nanowire,nanoplate,and nanosheets.In a typical growth of anisotropic nanostructures,coalescence and reshaping after attachment make dense nanostructures.In this report,we show the formation of Ag sheets having fractal network by oriented attachment at low reaction temperature of 30℃.The synthesized Ag sheets exhibited good crystalline nature despite of their network structure and low synthetic temperature.We also investigated the effect of reaction conditions for the formation of the Ag sheets.In addition,using the Ag sheets as a sacrificial template,we could make hollow Au sheets via galvanic replacement.展开更多
Symmetrical relationships between humans and their environment have been referred to as an extension of symmetries in the human geographical system and have drawn great attention.This paper explored the symmetry betwe...Symmetrical relationships between humans and their environment have been referred to as an extension of symmetries in the human geographical system and have drawn great attention.This paper explored the symmetry between physical and human systems through fractal analysis of the road and drainage networks in Wuling mountainous area.We found that both the road and drainage networks reflect weak clustering distributions.The evolution of the road network shared a significant self-organizing composition,while the drainage network showed obvious double fraetal characteristics.The geometric fractal dimension of the road network was larger than that of the drainage network.In addition,when assigned a weight relating to hierarchy or length,neither the road network nor drainage network showed a fractal property.These findings indicated that the fractal evolution of the road network shared certain similarities with fractal distribution of the drainage network.The symmetry between the two systems resulted from an interactive process of destroying symmetry at the lower order and reconstructing symmetry at the higher order.The relationships between the fractal dimensions of the rural-urban road network,the drainage network andthe urban system indicated that the development of this area was to achieve the symmetrical isomorphism of physical-human geographical systems.展开更多
Based on the natural characters of stratum,complicated geological mining conditions and the essence of mining rock mass destruction,the complexity of rock mass destruction caused by miningw as analyzed.The inner link ...Based on the natural characters of stratum,complicated geological mining conditions and the essence of mining rock mass destruction,the complexity of rock mass destruction caused by miningw as analyzed.The inner link between rock mass destruction phenomena caused by mining and nonlinear science was revealed.There are numerous cracks in natural rock mass.The cracks’distribution is irregular and is of statistical fractal structure.Self-organizational nonlinear evolution of the inner structure flaws leads to the rock mass destruction with external force.The evolution includes single fault’s fractal development,formation and evolution of fractal crack network and coordination of fractal crack network,etc.The law of fractal crack network’s evolution was introduced,at the same time,the coordination of fractal crack network was analyzed.Finally,based on coordination the principal equation of mining-caused subsidence of structural rock mass was established and its steady-state solution and unsteady-state solution were found.展开更多
The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characteriz...The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characterized by coupling the artificial fracture model and the natural fracture model.Based on an assisted history matching(AHM)using multiple-proxy-based Markov chain Monte Carlo algorithm(MCMC),an embedded discrete fracture modeling(EDFM)incorporated with reservoir simulator was used to predict productivity of shale gas well.When using the natural fracture generation method,the distribution of natural fracture network can be controlled by fractal parameters,and the natural fracture network generated coupling with artificial fractures can characterize the complex system of different-scale fractures in shale after fracturing.The EDFM,with fewer grids and less computation time consumption,can characterize the attributes of natural fractures and artificial fractures flexibly,and simulate the details of mass transfer between matrix cells and fractures while reducing computation significantly.The combination of AMH and EDFM can lower the uncertainty of reservoir and fracture parameters,and realize effective inversion of key reservoir and fracture parameters and the productivity forecast of shale gas wells.Application demonstrates the results from the proposed productivity prediction model integrating FDFN,EDFM and AHM have high credibility.展开更多
Image compression consists of two main parts: encoding and decoding. One of the important problems of the fractal theory is the long encoding implementation time, which hindered the acceptance of fractal image compres...Image compression consists of two main parts: encoding and decoding. One of the important problems of the fractal theory is the long encoding implementation time, which hindered the acceptance of fractal image compression as a practical method. The long encoding time results from the need to perform a large number of domain-range matches, the total encoding time is the product of the number of matches and the time to perform each match. In order to improve encoding speed, a hybrid method combining features extraction and self-organization network has been provided, which is based on the feature extraction approach the comparison pixels by pixels between the feature of range blocks and domains blocks. The efficiency of the new method was been proved by examples.展开更多
Based on the Ising spin, the phase transition on fractal scale-free networks with tree-like skeletons is studied, where the loops are generated by local links. The degree distribution of the tree-like skeleton satisfi...Based on the Ising spin, the phase transition on fractal scale-free networks with tree-like skeletons is studied, where the loops are generated by local links. The degree distribution of the tree-like skeleton satisfies the power-law form P（k）～ k^-δ.It is found that when δ≥3, the renormalized scale-free network will have the same degree distribution as the original network. For a special case of δ = 4.5, a ferromagnetic to paramagnetic transition is found and the critical temperature is determined by the box-covering renormalization method. By keeping the structure of the fractal scale-free network constant, the numerical relationship between the critical temperature and the network size is found, which is the form of power law.展开更多
Fractal and self similarity of complex networks have attracted much attention in recent years. The fractal dimension is a useful method to describe the fractal property of networks. However, the fractal features of mo...Fractal and self similarity of complex networks have attracted much attention in recent years. The fractal dimension is a useful method to describe the fractal property of networks. However, the fractal features of mobile social networks （MSNs） are inadequately investigated. In this work, a box-covering method based on the ratio of excluded mass to closeness centrality is presented to investigate the fractal feature of MSNs. Using this method, we find that some MSNs are fractal at different time intervals. Our simulation results indicate that the proposed method is available for analyzing the fractal property of MSNs.展开更多
The paper presents a novel hydraulic fracturing model for the characterization and simulation of the complex fracture network in shale gas reservoirs. We go beyond the existing method that uses planar or orthogonal co...The paper presents a novel hydraulic fracturing model for the characterization and simulation of the complex fracture network in shale gas reservoirs. We go beyond the existing method that uses planar or orthogonal conjugate fractures for representing the ＇＇complexity＇＇ of the network. Bifurcation of fractures is performed utilizing the Lindenmayer system based on fractal geometry to describe the fracture propagation pattern, density and network connectivity. Four controlling parameters are proposed to describe the details of complex fractures and stimulated reservoir volume（SRV）. The results show that due to the multilevel feature of fractal fractures, the model could provide a simple method for contributing reservoir volume calibration. The primary-and second-stage fracture networks across the overall SRV are the main contributions to the production, while the induced fracture network just contributes another 20% in the late producing period. We also conduct simulation with respect to different refracturing cases and find that increasing the complexity of the fracture network provides better performance than only enhancing the fracture conductivity.展开更多
Clustering algorithms in feature space are important methods in image segmentation. The choice of the effective feature parameters and the construction of the clustering method are key problems encountered with cluste...Clustering algorithms in feature space are important methods in image segmentation. The choice of the effective feature parameters and the construction of the clustering method are key problems encountered with clustering algorithms. In this paper, the multifractal dimensions are chosen as the segmentation feature parameters which are extracted from original image and wavelet-transformed image. SOM (Self-Organizing Map) network is applied to cluster the segmentation feature parameters. The experiment shows that the performance of the presented algorithm is very good.展开更多
Time series forecasting is important in the fields of finance,energy,and meteorology,but traditional methods often fail to cope with the complex nonlinear and nonstationary processes of real data.In this paper,we prop...Time series forecasting is important in the fields of finance,energy,and meteorology,but traditional methods often fail to cope with the complex nonlinear and nonstationary processes of real data.In this paper,we propose the FractalNet-LSTM model,which combines fractal convolutional units with recurrent long short-term memory(LSTM)layers to model time series efficiently.To test the effectiveness of the model,data with complex structures and patterns,in particular,with seasonal and cyclical effects,were used.To better demonstrate the obtained results and the formed conclusions,the model performance was shown on the datasets of electricity consumption,sunspot activity,and Spotify stock price.The result showed that the proposed model outperforms traditional approaches at medium forecasting horizons and demonstrates high accuracy for data with long-term and cyclical dependencies.However,for financial data with high volatility,the model’s efficiency decreases at long forecasting horizons,indicating the need for further adaptation.The findings suggest further adaptation.The findings suggest that integrating fractal properties into neural network architecture improves the accuracy of time series forecasting and can be useful for developing more accurate and reliable forecasting systems in various industries.展开更多
针对瓷砖色差检测中传统方法依赖主观目测导致的结果不稳定问题,提出一种融合纹理与颜色特征的瓷砖色差量化与分级方法。构建包含纹理与颜色双标签的大规模瓷砖数据集TILE-TCR(TILE Texture and Color Recognition),以提升模型对纹理与...针对瓷砖色差检测中传统方法依赖主观目测导致的结果不稳定问题,提出一种融合纹理与颜色特征的瓷砖色差量化与分级方法。构建包含纹理与颜色双标签的大规模瓷砖数据集TILE-TCR(TILE Texture and Color Recognition),以提升模型对纹理与颜色特征的表征能力;同时,构建色差分级数据集TILE-CAG(TILE Chromatic Aberration Grade),用于支持色差分类任务。在此基础上,改进分形编码网络(FENet)的网络结构,即引入空间金字塔池化(SPP)与SE(Squeeze-and-Excitation)模块,从而实现多任务特征提取与关键区域聚焦。然后,通过聚类算法自适应确定色差分级阈值,从而实现色差分级的客观量化。实验结果表明,所提改进方法在瓷砖纹理分类任务中的准确率达到92.82%,较FENet提升了1.84个百分点;在色差分级任务中所提方法的准确率、精确率、召回率和F1分数均超过90%。此外,还搭建了模拟生产流水线,以完成模型的工业部署与实时性测试。而所提方法在常见规格瓷砖上的平均检测时间低于3 s,满足工业传送带在线检测的实时性要求。展开更多
文摘We analyze correlations and patterns of oxidative activity of 3D DNA at DNA fluorescence in complete sets of chromosomes in neutrophils of peripheral blood. Fluorescence of DNA is registered by method of flow cytometry with nanometer spatial resolution. Experimental data present fluorescence of many ten thousands of cells, from different parts of body in each population, in various blood samples. Data is presented in histograms as frequency distributions of flashes in the dependence on their intensity. Normalized frequency distribution of information in these histograms is used as probabilistic measure for definition of Shannon entropy. Data analysis shows that for this measure of Shannon entropy common sum of entropy, i.e. total entropy E, for any histogram is invariant and has identical trends of changes all values of E (r) = lnr at reduction of rank r of histogram. This invariance reflects informational homeostasis of chromosomes activity inside cells in multi-scale networks of entropy, for varied ranks r. Shannon entropy in multi-scale DNA networks has much more dense packing of correlations than in “small world” networks. As the rule, networks of entropy differ by the mix of normal D 2 and abnormal D > 2 fractal dimensions for varied ranks r, the new types of fractal patterns and hinges for various topology (fractal dimension) at different states of health. We show that all distributions of information entropy are divided on three classes, which associated in diagnostics with a good health or dominants of autoimmune or inflammatory diseases. This classification based on switching of stability at transcritical bifurcation in homeostasis regulation. We defined many ways for homeostasis regulation, coincidences and switching patterns in branching sequences, the averages of Hölder for deviations of entropy from homeostasis at different states of health, with various saturation levels the noises of entropy at activity of all chromosomes in support regulation of homeostasis.
文摘We analyze fluorescence due to oxidizing activity of DNA in neutrophils of peripheral blood in the large populations ~104 - 105 of cells. Fluorescence is registered by flow cytometry method. Spatial resolution is about a few nanometers for varied complex three-dimensional (3D) DNA nanostructures of all non-coding and coding parts of DNA. It’s shown that oxidative activity of all 3D DNA in the full set of chromosomes inside cells is defined by new standards for complex networks of “exponentially small worlds”, with more dense packing than in the well known networks of “small worlds”. Analysis of various blood samples in vivo and during medical treatment shown that only two classes of Good and Bad Networks of DNA for a good and a bad health existed. This division is defined by any network to one from two classes of “n” or “s” shaped curves for typical deviations and from straight line in perfect networks of “exponentially small worlds”, as for two types of hysteresis curves at phase transitions or at switching of bistability. These deviations coincide with two types of positive and negative trends of changing fractal dimension by changing the scales of multi-scale networks of fluorescing DNA. These trends give the overall assessments of human immunity, including hidden and unidentified diseases, and as a sum of all kinds of health and illness of given person, from the point of view the inner life of neutrophils, living in different parts of human body in given time. Characteristics of deviations associated with type, level and complexity of illness in the dependence on
基金supported by the Young Talent Fund of Association for Science and Technology in Shaanxi,China,un-der grant No.20230513.
文摘This paper studies the eigentime and related issues in the fractal network corresponding to the Sierpiński fractal antenna.The access time or hitting time H(i,j)is the expected number of steps before node j is visited,starting from node i.The eigentime of G is the expectation of H(i,j)for all i,j∈G.Classical eigenvalue method let H(i,i)=0.However,when studying the random walk behavior of electrons in fractal networks corresponding to fractal antennas,it is nec-essary to consider the time when electrons leave a certain node and first return to that node(self return time).This paper adopts two research methods-the eigenvalue method based on spectral theory and the Markov chain method based on stochastic process theory-to obtain the modified in-trinsic time,and demonstrates through an example that the difference between the classical intrin-sic time and the modified intrinsic time is precisely due to the self return time.This paper shows the applications of fractal networks in modern communications.The research results are expected to provide a theoretical basis for the design and performance optimization of fractal antennas.
基金This research was supported by the Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Science,ICT,&Future Planning(2014R1A5A1009799)by a National Research Foundation of Korea grant funded by the Korean government(MSIP)(NRF-2015R1C1A1A01054109 and NRF-2016M3D1A1021140).
文摘Oriented attachment can be used as a good synthetic route to make highly anisotropic nanostructures including nanorod,nanowire,nanoplate,and nanosheets.In a typical growth of anisotropic nanostructures,coalescence and reshaping after attachment make dense nanostructures.In this report,we show the formation of Ag sheets having fractal network by oriented attachment at low reaction temperature of 30℃.The synthesized Ag sheets exhibited good crystalline nature despite of their network structure and low synthetic temperature.We also investigated the effect of reaction conditions for the formation of the Ag sheets.In addition,using the Ag sheets as a sacrificial template,we could make hollow Au sheets via galvanic replacement.
基金supported by the National Natural Science Foundation of China project(Grant Nos.41201130,41101361,and 41371183)
文摘Symmetrical relationships between humans and their environment have been referred to as an extension of symmetries in the human geographical system and have drawn great attention.This paper explored the symmetry between physical and human systems through fractal analysis of the road and drainage networks in Wuling mountainous area.We found that both the road and drainage networks reflect weak clustering distributions.The evolution of the road network shared a significant self-organizing composition,while the drainage network showed obvious double fraetal characteristics.The geometric fractal dimension of the road network was larger than that of the drainage network.In addition,when assigned a weight relating to hierarchy or length,neither the road network nor drainage network showed a fractal property.These findings indicated that the fractal evolution of the road network shared certain similarities with fractal distribution of the drainage network.The symmetry between the two systems resulted from an interactive process of destroying symmetry at the lower order and reconstructing symmetry at the higher order.The relationships between the fractal dimensions of the rural-urban road network,the drainage network andthe urban system indicated that the development of this area was to achieve the symmetrical isomorphism of physical-human geographical systems.
基金Foundatinitem Project(50274044)supported by the National Natural Science Foundation of China.
文摘Based on the natural characters of stratum,complicated geological mining conditions and the essence of mining rock mass destruction,the complexity of rock mass destruction caused by miningw as analyzed.The inner link between rock mass destruction phenomena caused by mining and nonlinear science was revealed.There are numerous cracks in natural rock mass.The cracks’distribution is irregular and is of statistical fractal structure.Self-organizational nonlinear evolution of the inner structure flaws leads to the rock mass destruction with external force.The evolution includes single fault’s fractal development,formation and evolution of fractal crack network and coordination of fractal crack network,etc.The law of fractal crack network’s evolution was introduced,at the same time,the coordination of fractal crack network was analyzed.Finally,based on coordination the principal equation of mining-caused subsidence of structural rock mass was established and its steady-state solution and unsteady-state solution were found.
基金Supported by the National Science and Technology Major Project(2017ZX05063-005)Science and Technology Development Project of PetroChina Research Institute of Petroleum Exploration and Development(YGJ2019-12-04)。
文摘The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characterized by coupling the artificial fracture model and the natural fracture model.Based on an assisted history matching(AHM)using multiple-proxy-based Markov chain Monte Carlo algorithm(MCMC),an embedded discrete fracture modeling(EDFM)incorporated with reservoir simulator was used to predict productivity of shale gas well.When using the natural fracture generation method,the distribution of natural fracture network can be controlled by fractal parameters,and the natural fracture network generated coupling with artificial fractures can characterize the complex system of different-scale fractures in shale after fracturing.The EDFM,with fewer grids and less computation time consumption,can characterize the attributes of natural fractures and artificial fractures flexibly,and simulate the details of mass transfer between matrix cells and fractures while reducing computation significantly.The combination of AMH and EDFM can lower the uncertainty of reservoir and fracture parameters,and realize effective inversion of key reservoir and fracture parameters and the productivity forecast of shale gas wells.Application demonstrates the results from the proposed productivity prediction model integrating FDFN,EDFM and AHM have high credibility.
文摘Image compression consists of two main parts: encoding and decoding. One of the important problems of the fractal theory is the long encoding implementation time, which hindered the acceptance of fractal image compression as a practical method. The long encoding time results from the need to perform a large number of domain-range matches, the total encoding time is the product of the number of matches and the time to perform each match. In order to improve encoding speed, a hybrid method combining features extraction and self-organization network has been provided, which is based on the feature extraction approach the comparison pixels by pixels between the feature of range blocks and domains blocks. The efficiency of the new method was been proved by examples.
基金Project supported by the Natural Science Foundation of Shandong Province,China(Grant No.ZR2014EL002)
文摘Based on the Ising spin, the phase transition on fractal scale-free networks with tree-like skeletons is studied, where the loops are generated by local links. The degree distribution of the tree-like skeleton satisfies the power-law form P（k）～ k^-δ.It is found that when δ≥3, the renormalized scale-free network will have the same degree distribution as the original network. For a special case of δ = 4.5, a ferromagnetic to paramagnetic transition is found and the critical temperature is determined by the box-covering renormalization method. By keeping the structure of the fractal scale-free network constant, the numerical relationship between the critical temperature and the network size is found, which is the form of power law.
基金Supported by the National Natural Science Foundation of China under Grant Nos 61501217,61363015,61501218 and 61262020the Natural Science Foundation of Jiangxi Province under Grant No 20142BAB206026
文摘Fractal and self similarity of complex networks have attracted much attention in recent years. The fractal dimension is a useful method to describe the fractal property of networks. However, the fractal features of mobile social networks （MSNs） are inadequately investigated. In this work, a box-covering method based on the ratio of excluded mass to closeness centrality is presented to investigate the fractal feature of MSNs. Using this method, we find that some MSNs are fractal at different time intervals. Our simulation results indicate that the proposed method is available for analyzing the fractal property of MSNs.
基金supported by National Natural Science Foundation of China(No.51674279)China Postdoctoral Science Foundation(No.2016M602227)a grant from National Science and Technology Major Project(No.2017ZX05049-006)
文摘The paper presents a novel hydraulic fracturing model for the characterization and simulation of the complex fracture network in shale gas reservoirs. We go beyond the existing method that uses planar or orthogonal conjugate fractures for representing the ＇＇complexity＇＇ of the network. Bifurcation of fractures is performed utilizing the Lindenmayer system based on fractal geometry to describe the fracture propagation pattern, density and network connectivity. Four controlling parameters are proposed to describe the details of complex fractures and stimulated reservoir volume（SRV）. The results show that due to the multilevel feature of fractal fractures, the model could provide a simple method for contributing reservoir volume calibration. The primary-and second-stage fracture networks across the overall SRV are the main contributions to the production, while the induced fracture network just contributes another 20% in the late producing period. We also conduct simulation with respect to different refracturing cases and find that increasing the complexity of the fracture network provides better performance than only enhancing the fracture conductivity.
文摘Clustering algorithms in feature space are important methods in image segmentation. The choice of the effective feature parameters and the construction of the clustering method are key problems encountered with clustering algorithms. In this paper, the multifractal dimensions are chosen as the segmentation feature parameters which are extracted from original image and wavelet-transformed image. SOM (Self-Organizing Map) network is applied to cluster the segmentation feature parameters. The experiment shows that the performance of the presented algorithm is very good.
文摘Time series forecasting is important in the fields of finance,energy,and meteorology,but traditional methods often fail to cope with the complex nonlinear and nonstationary processes of real data.In this paper,we propose the FractalNet-LSTM model,which combines fractal convolutional units with recurrent long short-term memory(LSTM)layers to model time series efficiently.To test the effectiveness of the model,data with complex structures and patterns,in particular,with seasonal and cyclical effects,were used.To better demonstrate the obtained results and the formed conclusions,the model performance was shown on the datasets of electricity consumption,sunspot activity,and Spotify stock price.The result showed that the proposed model outperforms traditional approaches at medium forecasting horizons and demonstrates high accuracy for data with long-term and cyclical dependencies.However,for financial data with high volatility,the model’s efficiency decreases at long forecasting horizons,indicating the need for further adaptation.The findings suggest further adaptation.The findings suggest that integrating fractal properties into neural network architecture improves the accuracy of time series forecasting and can be useful for developing more accurate and reliable forecasting systems in various industries.
文摘针对瓷砖色差检测中传统方法依赖主观目测导致的结果不稳定问题,提出一种融合纹理与颜色特征的瓷砖色差量化与分级方法。构建包含纹理与颜色双标签的大规模瓷砖数据集TILE-TCR(TILE Texture and Color Recognition),以提升模型对纹理与颜色特征的表征能力;同时,构建色差分级数据集TILE-CAG(TILE Chromatic Aberration Grade),用于支持色差分类任务。在此基础上,改进分形编码网络(FENet)的网络结构,即引入空间金字塔池化(SPP)与SE(Squeeze-and-Excitation)模块,从而实现多任务特征提取与关键区域聚焦。然后,通过聚类算法自适应确定色差分级阈值,从而实现色差分级的客观量化。实验结果表明,所提改进方法在瓷砖纹理分类任务中的准确率达到92.82%,较FENet提升了1.84个百分点;在色差分级任务中所提方法的准确率、精确率、召回率和F1分数均超过90%。此外,还搭建了模拟生产流水线,以完成模型的工业部署与实时性测试。而所提方法在常见规格瓷砖上的平均检测时间低于3 s,满足工业传送带在线检测的实时性要求。
