BACKGROUND Congenital heart disease is most commonly seen in neonates and it is a major cause of pediatric illness and childhood morbidity and mortality.AIM To identify and build the best predictive model for predicti...BACKGROUND Congenital heart disease is most commonly seen in neonates and it is a major cause of pediatric illness and childhood morbidity and mortality.AIM To identify and build the best predictive model for predicting cyanotic and acyanotic congenital heart disease in children during pregnancy and identify their potential risk factors.METHODS The data were collected from the Pediatric Cardiology Department at Chaudhry Pervaiz Elahi Institute of Cardiology Multan,Pakistan from December 2017 to October 2019.A sample of 3900 mothers whose children were diagnosed with identify the potential outliers.Different machine learning models were compared,and the best-fitted model was selected using the area under the curve,sensitivity,and specificity of the models.RESULTS Out of 3900 patients included,about 69.5%had acyanotic and 30.5%had cyanotic congenital heart disease.Males had more cases of acyanotic(53.6%)and cyanotic(54.5%)congenital heart disease as compared to females.The odds of having cyanotic was 1.28 times higher for children whose mothers used more fast food frequently during pregnancy.The artificial neural network model was selected as the best predictive model with an area under the curve of 0.9012,sensitivity of 65.76%,and specificity of 97.23%.CONCLUSION Children having a positive family history are at very high risk of having cyanotic and acyanotic congenital heart disease.Males are more at risk and their mothers need more care,good food,and physical activity during pregnancy.The best-fitted model for predicting cyanotic and acyanotic congenital heart disease is the artificial neural network.The results obtained and the best model identified will be useful for medical practitioners and public health scientists for an informed decision-making process about the earlier diagnosis and improve the health condition of children in Pakistan.展开更多
The surge of large-scale models in recent years has led to breakthroughs in numerous fields,but it has also introduced higher computational costs and more complex network architectures.These increasingly large and int...The surge of large-scale models in recent years has led to breakthroughs in numerous fields,but it has also introduced higher computational costs and more complex network architectures.These increasingly large and intricate networks pose challenges for deployment and execution while also exacerbating the issue of network over-parameterization.To address this issue,various network compression techniques have been developed,such as network pruning.A typical pruning algorithm follows a three-step pipeline involving training,pruning,and retraining.Existing methods often directly set the pruned filters to zero during retraining,significantly reducing the parameter space.However,this direct pruning strategy frequently results in irreversible information loss.In the early stages of training,a network still contains much uncertainty,and evaluating filter importance may not be sufficiently rigorous.To manage the pruning process effectively,this paper proposes a flexible neural network pruning algorithm based on the logistic growth differential equation,considering the characteristics of network training.Unlike other pruning algorithms that directly reduce filter weights,this algorithm introduces a three-stage adaptive weight decay strategy inspired by the logistic growth differential equation.It employs a gentle decay rate in the initial training stage,a rapid decay rate during the intermediate stage,and a slower decay rate in the network convergence stage.Additionally,the decay rate is adjusted adaptively based on the filter weights at each stage.By controlling the adaptive decay rate at each stage,the pruning of neural network filters can be effectively managed.In experiments conducted on the CIFAR-10 and ILSVRC-2012 datasets,the pruning of neural networks significantly reduces the floating-point operations while maintaining the same pruning rate.Specifically,when implementing a 30%pruning rate on the ResNet-110 network,the pruned neural network not only decreases floating-point operations by 40.8%but also enhances the classification accuracy by 0.49%compared to the original network.展开更多
This study examined gender differences in modal choice among residents of coastal communities of Yenagoa metropolis in Bayelsa State, Nigeria. The Four-Step model of transportation planning and modal choice provided t...This study examined gender differences in modal choice among residents of coastal communities of Yenagoa metropolis in Bayelsa State, Nigeria. The Four-Step model of transportation planning and modal choice provided the theoretical basis for this study. A survey research design involving a stratified sampling technique was adopted. The descriptives on transport modes, amount and time spent revealed that 10 (76.9%) males and 3 (23.1%) females preferred bicycle as means of transportation, 7 (58.3%) males and 5 (41.7%) females preferred motorcycle, while a significant proportion 90 (53.9%) males and 77 (46.1%) females preferred tricycle, 80 (63.0%) males and 47 (37.0%) females preferred cars/taxis, and 12 (46.2%) males and 14 (53.8%) females preferred mass transit bus. However, 14 (46.7%) males and 16 (53.3%) females in marshy terrain and coastal locations preferred canoes and boats. The result of the logistic regression model revealed that gender modal preference is more likely to be influenced by mode of transportation with a beta weight of 1.140, safety considerations 1.139, ownership of transport 1.135 and distance to place of work 1.073. Hence, this study recommends that a combination of these factors should be incorporated into transport planning to achieve effective transport planning and sustainable development in the Yenagoa metropolis.展开更多
Bangladesh has a denser population in comparison with many other countries. Though the rate of population increase has been regarded as a concerning issue, estimation of the population instability in the upcoming year...Bangladesh has a denser population in comparison with many other countries. Though the rate of population increase has been regarded as a concerning issue, estimation of the population instability in the upcoming years may be useful for national planning. To predict Bangladesh’s future population, this study compares the estimated populations of two popular population models, the Malthusian and the logistic population models, with the country’s census population published by BBS. We also tried to find out which model gives a better approximation for forecasting the past, present, and future population between these two models.展开更多
Sustainable ecological development is key to enhancing the life satisfaction of indigenous populations.However,comprehensive studies on the impact of ecological protection policies on life satisfaction from the perspe...Sustainable ecological development is key to enhancing the life satisfaction of indigenous populations.However,comprehensive studies on the impact of ecological protection policies on life satisfaction from the perspective of the indigenous populations of national parks are lacking.This study investigated the impact of national park ecological protection policies on the life satisfaction of 496 indigenous households in the Qilian Mountain National Park through a questionnaire survey conducted in 2021,employing an ordered multicategorical logistic regression model.The results showed that overall life satisfaction was high and 17.34%of indigenous populations are very satisfied with their current standard of living,with the highest satisfaction of herding households,followed by nonfarming households,half-farming and half-herding households,and farming households.Livelihood capital components had different impacts on life satisfaction.Policy satisfaction,perceived importance,and participation willingness had different impacts on life satisfaction.Key ecological policy instruments,such as ecological compensation,livelihood skills training,eco-stewardship positions,specialty town development,and natural grassland/forest conservation,significantly enhanced life satisfaction.Therefore,emphasizing the interests of indigenous populations,enhancing their willingness to participate in ecological policies,and improving their nonagricultural and pastoral employment abilities can help to improve overall life satisfaction.展开更多
Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it o...Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3%of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.展开更多
Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ri...Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p 〈0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions p^1, p^2 and p^3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to cheek the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height （X1 ） and potential energy （X2 ） significantly impact （p 〈 0. 0001 ） the amplitude-based refleeted rate; the P-values for the deviance and Pearson are all 〉 0.05 （0.2839, 0.3438, respectively）. That is, the goodness-of-fit between ridge height （ X1 ） and potential energy （X2） can further predict parameters under the scenario of the best parsimonious model. Investigation of 6 predictive powers （ R2, Max-rescaled R^2, Sorners＇ D, Gamma, Tau-a, and c, respectively） indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model.展开更多
Fifty-three larch interspecific hybrid clones（Larix kaempferi × L.gmelini） and their parent clones were used for growth curve analysis of height variations.The growth curves of the 55 clones were ＇S＇-shaped a...Fifty-three larch interspecific hybrid clones（Larix kaempferi × L.gmelini） and their parent clones were used for growth curve analysis of height variations.The growth curves of the 55 clones were ＇S＇-shaped and 36 exhibited similar curves as the male parent.The coefficients of the logistic models were higher than 0.943,indicating that our results were effective in the simulation of the growth curves.ANOVA analysis showed significant differences in height of different clones （P／0.01）.Average date of maximum height growth was Day 173,and average duration of rapid growth lasted for 50 days.Annual average increase in height was 9.7cm d^（-1） and daily average increase was 0.2 cm.The ratio of GR to the total annual increase in height ranged from 51.2 to 68.8%,with the average being 59.8%.There was a positive correlation between k values and plant heights which benefited from the evaluation of early plant height.There was also a positive correlation between GR（growth stage）,GD（plant height） and annual increase in height.These results are informative to the evaluation of the elite clone selection and provide a theoretical basis for breeding and management.展开更多
We present and discuss the partial oscillation with respect to equilibrium state ofm-dimensional Logistic delay ecologic models, and obtain some simple criteria.
Based on the weekly closing price of Shenzhen Integrated Index, this article studies the volatility of Shenzhen Stock Market using three different models： Logistic, AR（1） and AR（2）. The time-variable parameters o...Based on the weekly closing price of Shenzhen Integrated Index, this article studies the volatility of Shenzhen Stock Market using three different models： Logistic, AR（1） and AR（2）. The time-variable parameters of Logistic regression model is estimated by using both the index smoothing method and the time-variable parameter estimation method. And both the AR（1） model and the AR（2） model of zero-mean series of the weekly dosing price and its zero-mean series of volatility rate are established based on the analysis results of zero-mean series of the weekly closing price, Six common statistical methods for error prediction are used to test the predicting results. These methods are： mean error （ME）, mean absolute error （MAE）, root mean squared error （RMSE）, mean absolute percentage error （MAPE）, Akaike＇s information criterion （AIC）, and Bayesian information criterion （BIC）. The investigation shows that AR（1） model exhibits the best predicting result, whereas AR（2） model exhibits predicting results that is intermediate between AR（1） model and the Logistic regression model.展开更多
The catch and effort data of Sillago sihama fishery in Pakistani waters were used to investigate the performance of two closely related stock assessment models: logistic and generalized surplus-production models. Comp...The catch and effort data of Sillago sihama fishery in Pakistani waters were used to investigate the performance of two closely related stock assessment models: logistic and generalized surplus-production models. Compared with the generalized production model, the logistic model produced more reasonable estimates for parameters such as maximum sustainable yield. The Akaike's Information Criterion values estimated at 4.265 and -51.152 respectively by the logistic and generalized models. Simulation analyses of the S. sihama fishery showed that the estimated and observed abundance indices for the logistic model were closer than those for the generalized production model. Standardized residuals were distributed closer for logistic model, but exhibited a slightly increasing trend for the generalized model. Statistical outliers were seen in 1989 and 1993 for the logistic model, and in 1981 and 1999 for the generalized model. Simulated results revealed that the logistic estimates were close to the true value for low CVs (coefficients of variation) but widely dispersed for high CVs. In contrast, the generalized model estimates were loose for all CV levels. The estimated production model curve parameter was not reasonable at all the tested levels of white noise. With the increase in white noise R2 for the catch per unit effort decreased. Therefore, we conclude that the logistic model performs more reasonably than the generalized production model.展开更多
This paper describes the real-time and the importance of the study about e-commerce logistics cost management ,analyzes the development status of today＇ s e-commerce logistics and compares it with the traditional log...This paper describes the real-time and the importance of the study about e-commerce logistics cost management ,analyzes the development status of today＇ s e-commerce logistics and compares it with the traditional logistics, defines the e-commerce logistics cost management .Based on this, it summarizes the cost structure of e-commerce logistics, proposes factors affecting the cost of logistics, builds the basic ideas of logistics cost management, and thus introducts the accounting methods about logistics cost .Finally, puts forward to the content and methods of logistics costs budget, controling the cost effectively.展开更多
Scheduling is one of the most difficult issues in t he planning and operations of the aircraft services industry. In this paper, t he various scheduling problems in ground support operation of an aircraft mainte nance...Scheduling is one of the most difficult issues in t he planning and operations of the aircraft services industry. In this paper, t he various scheduling problems in ground support operation of an aircraft mainte nance service company are addressed. The authors developed a set of vehicle rout ings to cover each schedule flights; the objectives pursued are the maximization of vehicle and manpower utilization and minimization of operation time. To obta in the goals, an integer-programming model with genetic algorithm is formulated . It is found that the company can produce an effective and efficient schedules to deploy the manpower and equipment resources. Simulation is used to verify the method and a MATLAB program is used to code the genetic algorithm. This model i s further illustrated by a case study in Hong Kong and the benefit elaborated. F inally, a conclusion is made to summarize the experience of this project and pro vide further improvement.展开更多
A mathematical model capable of providing a forecast of future consumption and import of natural gas is essential for the planning of the Brazilian energy matrix. The aim of this study is to compare three mathematical...A mathematical model capable of providing a forecast of future consumption and import of natural gas is essential for the planning of the Brazilian energy matrix. The aim of this study is to compare three mathematical models, logistic model or model of Verhulst, exponential model or the model of Malthus and the model of von Bertalanffy to analyze the possibilities of these models to describe the evolution of production, import and consumption of natural gas in Brazil, from data provided by the energy balance of the Ministry of Mines and Energy (MME) from 1970 to 2009. A projection of the production and the import of natural gas up to 2017 is made with the models studied in this article and compared with the Brazilian Ten-Year Plan for Expansion of Energy (PDE). At the end of this paper a comparison with the Hubbert model for Brazilian natural gas production is made. These data were adjusted to use the differential equations which describe the models of population growth. All the computer work used in this article: graphics, resolution of differential equations, calculations of linearization and the least squares fitting was prepared in the software MatLab. The results obtained by means of graphs show that the population dynamics models (logistic, exponential and von Bertalanffy) can be applied in modeling the production, import and consumption of natural gas in Brazil.展开更多
This study uses logistic and Poisson regression models to examine the factors influencing the adoption of sustain-able land management(SLM)practices in Mali using two rounds of the nationally representative survey Enq...This study uses logistic and Poisson regression models to examine the factors influencing the adoption of sustain-able land management(SLM)practices in Mali using two rounds of the nationally representative survey Enquête Agricole de Conjoncture Intégrée aux Conditions de Vie des Ménages.The SLMs considered include the applica-tion of organic fertilizers,the application of inorganic fertilizers,the use of improved seeds,and the practice of intercropping.On average the application of organic fertilizers(39.2%),and inorganic fertilizers(28.7%)are the most frequent SLM practices among Malian farmers,and between 2014 and 2017,we observe a decline in the practice of intercropping.The regression results show that farmers’adoption of different SLMs is significantly associated with biophysical factors(average temperature,climate type,plot size,plot shape,and location),de-mographic factors(age,gender,education,household size),and socioeconomic factors(number of cultivated plots,livelihood diversification,type of crop grown,market access,credit access,economic shocks,and social capital).Our findings suggest that policymakers and agricultural development agencies in Mali need to adopt a multidimensional policy framework to unlock the untapped potential of SLM practices in promoting sustainable agriculture and food security.展开更多
Regulating planting density and nitrogen(N)fertilization could delay chlorophyll(Chl)degradation and leaf senescence in maize cultivars.This study measured changes in ear leaf green area(GLA_(ear)),Chl content,the act...Regulating planting density and nitrogen(N)fertilization could delay chlorophyll(Chl)degradation and leaf senescence in maize cultivars.This study measured changes in ear leaf green area(GLA_(ear)),Chl content,the activities of Chl a-degrading enzymes after silking,and the post-silking dry matter accumulation and grain yield under multiple planting densities and N fertilization rates.The dynamic change of GLA_(ear)after silking fitted to the logistic model,and the GLA_(ear) duration and the GLAearat 42 d after silking were affected mainly by the duration of the initial senescence period(T_(1))which was a key factor of the leaf senescence.The average chlorophyllase(CLH)activity was 8.3 times higher than pheophytinase activity and contributed most to the Chl content,indicating that CLH is a key enzyme for degrading Chl a in maize.Increasing density increased the CLH activity and decreased the Chl content,T1,GLAear,and GLA_(ear) duration.Under high density,appropriate N application reduced CLH activity,increased Chl content,prolonged T1,alleviated high-density-induced leaf senescence,and increased post-silking dry matter accumulation and grain yield.展开更多
Malware is an ever-present and dynamic threat to networks and computer systems in cybersecurity,and because of its complexity and evasiveness,it is challenging to identify using traditional signature-based detection a...Malware is an ever-present and dynamic threat to networks and computer systems in cybersecurity,and because of its complexity and evasiveness,it is challenging to identify using traditional signature-based detection approaches.The study article discusses the growing danger to cybersecurity that malware hidden in PDF files poses,highlighting the shortcomings of conventional detection techniques and the difficulties presented by adversarial methodologies.The article presents a new method that improves PDF virus detection by using document analysis and a Logistic Model Tree.Using a dataset from the Canadian Institute for Cybersecurity,a comparative analysis is carried out with well-known machine learning models,such as Credal Decision Tree,Naïve Bayes,Average One Dependency Estimator,Locally Weighted Learning,and Stochastic Gradient Descent.Beyond traditional structural and JavaScript-centric PDF analysis,the research makes a substantial contribution to the area by boosting precision and resilience in malware detection.The use of Logistic Model Tree,a thorough feature selection approach,and increased focus on PDF file attributes all contribute to the efficiency of PDF virus detection.The paper emphasizes Logistic Model Tree’s critical role in tackling increasing cybersecurity threats and proposes a viable answer to practical issues in the sector.The results reveal that the Logistic Model Tree is superior,with improved accuracy of 97.46%when compared to benchmark models,demonstrating its usefulness in addressing the ever-changing threat landscape.展开更多
Population is an important strategic resource for national development, a fundamental element of socio-economic development. The coordinated development of population and economy is an effective way to achieve rapid e...Population is an important strategic resource for national development, a fundamental element of socio-economic development. The coordinated development of population and economy is an effective way to achieve rapid economic growth. Based on the population statistics data of counties (districts) in Henan Province, China, from 2006 to 2021. The paper firstly uses the logistic population growth mathematical model to calculate the resident population growth rate of counties (districts), then utilizes the hotspot analysis and spatial semi-variogram analysis, to research the spatial distribution characteristics of the resident population growth rate in Henan Province. The research results show that the evolution of the regional resident population in the province basically conforms to the logistic natural growth model. The resident population growth rate shows the characteristics of high in the north and low in the south, high in the center and low in the surrounding regions. The resident population growth rate is positively correlated with the level of economic development;the urban built-up areas, especially the new regions in urban planning, have a fast growth rate of resident population, which has a significant siphon effect on the population of surrounding regions. The hotspots of resident population growth rate in the province are mainly distributed in the urban built-up areas and surrounding regions of Zhengzhou, Luoyang, and Xinxiang, accounting for about 3.51% of the total area of the province. The cold spots are mainly distributed in the eastern part of the province, forming zonal distribution, which spans across Shangqiu City, Zhoukou City, and Zhumadian City, accounting for about 8.61% of the total area of the province. The area with negative growth of resident population accounts for approximately 53.47% of the total province. The spatial distribution of the growth rate of the resident population in the whole province basically conforms to the spherical model, with a small dispersion degree and a short range. In the range, there is a high degree of variability in resident population growth rate.展开更多
In view of the composition analysis and identification of ancient glass products, L1 regularization, K-Means cluster analysis, elbow rule and other methods were comprehensively used to build logical regression, cluste...In view of the composition analysis and identification of ancient glass products, L1 regularization, K-Means cluster analysis, elbow rule and other methods were comprehensively used to build logical regression, cluster analysis, hyper-parameter test and other models, and SPSS, Python and other tools were used to obtain the classification rules of glass products under different fluxes, sub classification under different chemical compositions, hyper-parameter K value test and rationality analysis. Research can provide theoretical support for the protection and restoration of ancient glass relics.展开更多
In this paper,we propose a Bayesian PG-INLA algorithm which is tailored to both one-dimensional and multidimensional 2-PL IRT models.The proposed PG-INLA algorithm utilizes a computationally efficient data augmentatio...In this paper,we propose a Bayesian PG-INLA algorithm which is tailored to both one-dimensional and multidimensional 2-PL IRT models.The proposed PG-INLA algorithm utilizes a computationally efficient data augmentation strategy via the Pólya-Gamma variables,which can avoid low computational efficiency of traditioanl Bayesian MCMC algorithms for IRT models with a logistic link function.Meanwhile,combined with the advanced and fast INLA algorithm,the PG-INLA algorithm is both accurate and computationally efficient.We provide details on the derivation of posterior and conditional distributions of IRT models,the method of introducing the Pólya-Gamma variable into Gibbs sampling,and the implementation of the PG-INLA algorithm for both onedimensional and multidimensional cases.Through simulation studies and an application to the data analysis of the IPIP-NEO personality inventory,we assess the performance of the PG-INLA algorithm.Extensions of the proposed PG-INLA algorithm to other IRT models are also discussed.展开更多
文摘BACKGROUND Congenital heart disease is most commonly seen in neonates and it is a major cause of pediatric illness and childhood morbidity and mortality.AIM To identify and build the best predictive model for predicting cyanotic and acyanotic congenital heart disease in children during pregnancy and identify their potential risk factors.METHODS The data were collected from the Pediatric Cardiology Department at Chaudhry Pervaiz Elahi Institute of Cardiology Multan,Pakistan from December 2017 to October 2019.A sample of 3900 mothers whose children were diagnosed with identify the potential outliers.Different machine learning models were compared,and the best-fitted model was selected using the area under the curve,sensitivity,and specificity of the models.RESULTS Out of 3900 patients included,about 69.5%had acyanotic and 30.5%had cyanotic congenital heart disease.Males had more cases of acyanotic(53.6%)and cyanotic(54.5%)congenital heart disease as compared to females.The odds of having cyanotic was 1.28 times higher for children whose mothers used more fast food frequently during pregnancy.The artificial neural network model was selected as the best predictive model with an area under the curve of 0.9012,sensitivity of 65.76%,and specificity of 97.23%.CONCLUSION Children having a positive family history are at very high risk of having cyanotic and acyanotic congenital heart disease.Males are more at risk and their mothers need more care,good food,and physical activity during pregnancy.The best-fitted model for predicting cyanotic and acyanotic congenital heart disease is the artificial neural network.The results obtained and the best model identified will be useful for medical practitioners and public health scientists for an informed decision-making process about the earlier diagnosis and improve the health condition of children in Pakistan.
基金supported by the National Natural Science Foundation of China under Grant No.62172132.
文摘The surge of large-scale models in recent years has led to breakthroughs in numerous fields,but it has also introduced higher computational costs and more complex network architectures.These increasingly large and intricate networks pose challenges for deployment and execution while also exacerbating the issue of network over-parameterization.To address this issue,various network compression techniques have been developed,such as network pruning.A typical pruning algorithm follows a three-step pipeline involving training,pruning,and retraining.Existing methods often directly set the pruned filters to zero during retraining,significantly reducing the parameter space.However,this direct pruning strategy frequently results in irreversible information loss.In the early stages of training,a network still contains much uncertainty,and evaluating filter importance may not be sufficiently rigorous.To manage the pruning process effectively,this paper proposes a flexible neural network pruning algorithm based on the logistic growth differential equation,considering the characteristics of network training.Unlike other pruning algorithms that directly reduce filter weights,this algorithm introduces a three-stage adaptive weight decay strategy inspired by the logistic growth differential equation.It employs a gentle decay rate in the initial training stage,a rapid decay rate during the intermediate stage,and a slower decay rate in the network convergence stage.Additionally,the decay rate is adjusted adaptively based on the filter weights at each stage.By controlling the adaptive decay rate at each stage,the pruning of neural network filters can be effectively managed.In experiments conducted on the CIFAR-10 and ILSVRC-2012 datasets,the pruning of neural networks significantly reduces the floating-point operations while maintaining the same pruning rate.Specifically,when implementing a 30%pruning rate on the ResNet-110 network,the pruned neural network not only decreases floating-point operations by 40.8%but also enhances the classification accuracy by 0.49%compared to the original network.
文摘This study examined gender differences in modal choice among residents of coastal communities of Yenagoa metropolis in Bayelsa State, Nigeria. The Four-Step model of transportation planning and modal choice provided the theoretical basis for this study. A survey research design involving a stratified sampling technique was adopted. The descriptives on transport modes, amount and time spent revealed that 10 (76.9%) males and 3 (23.1%) females preferred bicycle as means of transportation, 7 (58.3%) males and 5 (41.7%) females preferred motorcycle, while a significant proportion 90 (53.9%) males and 77 (46.1%) females preferred tricycle, 80 (63.0%) males and 47 (37.0%) females preferred cars/taxis, and 12 (46.2%) males and 14 (53.8%) females preferred mass transit bus. However, 14 (46.7%) males and 16 (53.3%) females in marshy terrain and coastal locations preferred canoes and boats. The result of the logistic regression model revealed that gender modal preference is more likely to be influenced by mode of transportation with a beta weight of 1.140, safety considerations 1.139, ownership of transport 1.135 and distance to place of work 1.073. Hence, this study recommends that a combination of these factors should be incorporated into transport planning to achieve effective transport planning and sustainable development in the Yenagoa metropolis.
文摘Bangladesh has a denser population in comparison with many other countries. Though the rate of population increase has been regarded as a concerning issue, estimation of the population instability in the upcoming years may be useful for national planning. To predict Bangladesh’s future population, this study compares the estimated populations of two popular population models, the Malthusian and the logistic population models, with the country’s census population published by BBS. We also tried to find out which model gives a better approximation for forecasting the past, present, and future population between these two models.
基金Fujian Provincial Department of Finance,Fujian Provincial Federation of Social Science Circles for its support of this study(Grant No.FJ2023B124)。
文摘Sustainable ecological development is key to enhancing the life satisfaction of indigenous populations.However,comprehensive studies on the impact of ecological protection policies on life satisfaction from the perspective of the indigenous populations of national parks are lacking.This study investigated the impact of national park ecological protection policies on the life satisfaction of 496 indigenous households in the Qilian Mountain National Park through a questionnaire survey conducted in 2021,employing an ordered multicategorical logistic regression model.The results showed that overall life satisfaction was high and 17.34%of indigenous populations are very satisfied with their current standard of living,with the highest satisfaction of herding households,followed by nonfarming households,half-farming and half-herding households,and farming households.Livelihood capital components had different impacts on life satisfaction.Policy satisfaction,perceived importance,and participation willingness had different impacts on life satisfaction.Key ecological policy instruments,such as ecological compensation,livelihood skills training,eco-stewardship positions,specialty town development,and natural grassland/forest conservation,significantly enhanced life satisfaction.Therefore,emphasizing the interests of indigenous populations,enhancing their willingness to participate in ecological policies,and improving their nonagricultural and pastoral employment abilities can help to improve overall life satisfaction.
文摘Gully erosion is a disruptive phenomenon which extensively affects the Iranian territory,especially in the Northern provinces.A number of studies have been recently undertaken to study this process and to predict it over space and ultimately,in a broader national effort,to limit its negative effects on local communities.We focused on the Bastam watershed where 9.3%of its surface is currently affected by gullying.Machine learning algorithms are currently under the magnifying glass across the geomorphological community for their high predictive ability.However,unlike the bivariate statistical models,their structure does not provide intuitive and quantifiable measures of environmental preconditioning factors.To cope with such weakness,we interpret preconditioning causes on the basis of a bivariate approach namely,Index of Entropy.And,we performed the susceptibility mapping procedure by testing three extensions of a decision tree model namely,Alternating Decision Tree(ADTree),Naive-Bayes tree(NBTree),and Logistic Model Tree(LMT).We dichotomized the gully information over space into gully presence/absence conditions,which we further explored in their calibration and validation stages.Being the presence/absence information and associated factors identical,the resulting differences are only due to the algorithmic structures of the three models we chose.Such differences are not significant in terms of performances;in fact,the three models produce outstanding predictive AUC measures(ADTree=0.922;NBTree=0.939;LMT=0.944).However,the associated mapping results depict very different patterns where only the LMT is associated with reasonable susceptibility patterns.This is a strong indication of what model combines best performance and mapping for any natural hazard-oriented application.
基金This paper was financially supported by NSC96-2628-E-366-004-MY2 and NSC96-2628-E-132-001-MY2
文摘Internal solitary wave propagation over a submarine ridge results in energy dissipation, in which the hydrodynamic interaction between a wave and ridge affects marine environment. This study analyzes the effects of ridge height and potential energy during wave-ridge interaction with a binary and cumulative logistic regression model. In testing the Global Null Hypothesis, all values are p 〈0.001, with three statistical methods, such as Likelihood Ratio, Score, and Wald. While comparing with two kinds of models, tests values obtained by cumulative logistic regression models are better than those by binary logistic regression models. Although this study employed cumulative logistic regression model, three probability functions p^1, p^2 and p^3, are utilized for investigating the weighted influence of factors on wave reflection. Deviance and Pearson tests are applied to cheek the goodness-of-fit of the proposed model. The analytical results demonstrated that both ridge height （X1 ） and potential energy （X2 ） significantly impact （p 〈 0. 0001 ） the amplitude-based refleeted rate; the P-values for the deviance and Pearson are all 〉 0.05 （0.2839, 0.3438, respectively）. That is, the goodness-of-fit between ridge height （ X1 ） and potential energy （X2） can further predict parameters under the scenario of the best parsimonious model. Investigation of 6 predictive powers （ R2, Max-rescaled R^2, Sorners＇ D, Gamma, Tau-a, and c, respectively） indicate that these predictive estimates of the proposed model have better predictive ability than ridge height alone, and are very similar to the interaction of ridge height and potential energy. It can be concluded that the goodness-of-fit and prediction ability of the cumulative logistic regression model are better than that of the binary logistic regression model.
基金supported by Grants from the National Science and Technology Pillar Program of China(No.2015DAD09B01)
文摘Fifty-three larch interspecific hybrid clones（Larix kaempferi × L.gmelini） and their parent clones were used for growth curve analysis of height variations.The growth curves of the 55 clones were ＇S＇-shaped and 36 exhibited similar curves as the male parent.The coefficients of the logistic models were higher than 0.943,indicating that our results were effective in the simulation of the growth curves.ANOVA analysis showed significant differences in height of different clones （P／0.01）.Average date of maximum height growth was Day 173,and average duration of rapid growth lasted for 50 days.Annual average increase in height was 9.7cm d^（-1） and daily average increase was 0.2 cm.The ratio of GR to the total annual increase in height ranged from 51.2 to 68.8%,with the average being 59.8%.There was a positive correlation between k values and plant heights which benefited from the evaluation of early plant height.There was also a positive correlation between GR（growth stage）,GD（plant height） and annual increase in height.These results are informative to the evaluation of the elite clone selection and provide a theoretical basis for breeding and management.
文摘We present and discuss the partial oscillation with respect to equilibrium state ofm-dimensional Logistic delay ecologic models, and obtain some simple criteria.
基金The research is supported by the National Natural Science Foundation of China (60574069)the Soft Science Foundation of Guangdong Province (2005B70101044)
文摘Based on the weekly closing price of Shenzhen Integrated Index, this article studies the volatility of Shenzhen Stock Market using three different models： Logistic, AR（1） and AR（2）. The time-variable parameters of Logistic regression model is estimated by using both the index smoothing method and the time-variable parameter estimation method. And both the AR（1） model and the AR（2） model of zero-mean series of the weekly dosing price and its zero-mean series of volatility rate are established based on the analysis results of zero-mean series of the weekly closing price, Six common statistical methods for error prediction are used to test the predicting results. These methods are： mean error （ME）, mean absolute error （MAE）, root mean squared error （RMSE）, mean absolute percentage error （MAPE）, Akaike＇s information criterion （AIC）, and Bayesian information criterion （BIC）. The investigation shows that AR（1） model exhibits the best predicting result, whereas AR（2） model exhibits predicting results that is intermediate between AR（1） model and the Logistic regression model.
基金supported by the special research fund of the Ocean University of China (No.201022001)
文摘The catch and effort data of Sillago sihama fishery in Pakistani waters were used to investigate the performance of two closely related stock assessment models: logistic and generalized surplus-production models. Compared with the generalized production model, the logistic model produced more reasonable estimates for parameters such as maximum sustainable yield. The Akaike's Information Criterion values estimated at 4.265 and -51.152 respectively by the logistic and generalized models. Simulation analyses of the S. sihama fishery showed that the estimated and observed abundance indices for the logistic model were closer than those for the generalized production model. Standardized residuals were distributed closer for logistic model, but exhibited a slightly increasing trend for the generalized model. Statistical outliers were seen in 1989 and 1993 for the logistic model, and in 1981 and 1999 for the generalized model. Simulated results revealed that the logistic estimates were close to the true value for low CVs (coefficients of variation) but widely dispersed for high CVs. In contrast, the generalized model estimates were loose for all CV levels. The estimated production model curve parameter was not reasonable at all the tested levels of white noise. With the increase in white noise R2 for the catch per unit effort decreased. Therefore, we conclude that the logistic model performs more reasonably than the generalized production model.
文摘This paper describes the real-time and the importance of the study about e-commerce logistics cost management ,analyzes the development status of today＇ s e-commerce logistics and compares it with the traditional logistics, defines the e-commerce logistics cost management .Based on this, it summarizes the cost structure of e-commerce logistics, proposes factors affecting the cost of logistics, builds the basic ideas of logistics cost management, and thus introducts the accounting methods about logistics cost .Finally, puts forward to the content and methods of logistics costs budget, controling the cost effectively.
文摘Scheduling is one of the most difficult issues in t he planning and operations of the aircraft services industry. In this paper, t he various scheduling problems in ground support operation of an aircraft mainte nance service company are addressed. The authors developed a set of vehicle rout ings to cover each schedule flights; the objectives pursued are the maximization of vehicle and manpower utilization and minimization of operation time. To obta in the goals, an integer-programming model with genetic algorithm is formulated . It is found that the company can produce an effective and efficient schedules to deploy the manpower and equipment resources. Simulation is used to verify the method and a MATLAB program is used to code the genetic algorithm. This model i s further illustrated by a case study in Hong Kong and the benefit elaborated. F inally, a conclusion is made to summarize the experience of this project and pro vide further improvement.
文摘A mathematical model capable of providing a forecast of future consumption and import of natural gas is essential for the planning of the Brazilian energy matrix. The aim of this study is to compare three mathematical models, logistic model or model of Verhulst, exponential model or the model of Malthus and the model of von Bertalanffy to analyze the possibilities of these models to describe the evolution of production, import and consumption of natural gas in Brazil, from data provided by the energy balance of the Ministry of Mines and Energy (MME) from 1970 to 2009. A projection of the production and the import of natural gas up to 2017 is made with the models studied in this article and compared with the Brazilian Ten-Year Plan for Expansion of Energy (PDE). At the end of this paper a comparison with the Hubbert model for Brazilian natural gas production is made. These data were adjusted to use the differential equations which describe the models of population growth. All the computer work used in this article: graphics, resolution of differential equations, calculations of linearization and the least squares fitting was prepared in the software MatLab. The results obtained by means of graphs show that the population dynamics models (logistic, exponential and von Bertalanffy) can be applied in modeling the production, import and consumption of natural gas in Brazil.
文摘This study uses logistic and Poisson regression models to examine the factors influencing the adoption of sustain-able land management(SLM)practices in Mali using two rounds of the nationally representative survey Enquête Agricole de Conjoncture Intégrée aux Conditions de Vie des Ménages.The SLMs considered include the applica-tion of organic fertilizers,the application of inorganic fertilizers,the use of improved seeds,and the practice of intercropping.On average the application of organic fertilizers(39.2%),and inorganic fertilizers(28.7%)are the most frequent SLM practices among Malian farmers,and between 2014 and 2017,we observe a decline in the practice of intercropping.The regression results show that farmers’adoption of different SLMs is significantly associated with biophysical factors(average temperature,climate type,plot size,plot shape,and location),de-mographic factors(age,gender,education,household size),and socioeconomic factors(number of cultivated plots,livelihood diversification,type of crop grown,market access,credit access,economic shocks,and social capital).Our findings suggest that policymakers and agricultural development agencies in Mali need to adopt a multidimensional policy framework to unlock the untapped potential of SLM practices in promoting sustainable agriculture and food security.
基金financially supported by the National Key Research and Development Program of China(2022YFD190160304)Natural Science Foundation of Sichuan Province(2022NSFSC0013)+1 种基金Sichuan Maize Innovation Team Construction Project(SCCXTD-2022-02)National Key Research and Development Program of China(2018YFD0301206)。
文摘Regulating planting density and nitrogen(N)fertilization could delay chlorophyll(Chl)degradation and leaf senescence in maize cultivars.This study measured changes in ear leaf green area(GLA_(ear)),Chl content,the activities of Chl a-degrading enzymes after silking,and the post-silking dry matter accumulation and grain yield under multiple planting densities and N fertilization rates.The dynamic change of GLA_(ear)after silking fitted to the logistic model,and the GLA_(ear) duration and the GLAearat 42 d after silking were affected mainly by the duration of the initial senescence period(T_(1))which was a key factor of the leaf senescence.The average chlorophyllase(CLH)activity was 8.3 times higher than pheophytinase activity and contributed most to the Chl content,indicating that CLH is a key enzyme for degrading Chl a in maize.Increasing density increased the CLH activity and decreased the Chl content,T1,GLAear,and GLA_(ear) duration.Under high density,appropriate N application reduced CLH activity,increased Chl content,prolonged T1,alleviated high-density-induced leaf senescence,and increased post-silking dry matter accumulation and grain yield.
基金This research work was funded by Institutional Fund Projects under Grant No.(IFPIP:211-611-1443).
文摘Malware is an ever-present and dynamic threat to networks and computer systems in cybersecurity,and because of its complexity and evasiveness,it is challenging to identify using traditional signature-based detection approaches.The study article discusses the growing danger to cybersecurity that malware hidden in PDF files poses,highlighting the shortcomings of conventional detection techniques and the difficulties presented by adversarial methodologies.The article presents a new method that improves PDF virus detection by using document analysis and a Logistic Model Tree.Using a dataset from the Canadian Institute for Cybersecurity,a comparative analysis is carried out with well-known machine learning models,such as Credal Decision Tree,Naïve Bayes,Average One Dependency Estimator,Locally Weighted Learning,and Stochastic Gradient Descent.Beyond traditional structural and JavaScript-centric PDF analysis,the research makes a substantial contribution to the area by boosting precision and resilience in malware detection.The use of Logistic Model Tree,a thorough feature selection approach,and increased focus on PDF file attributes all contribute to the efficiency of PDF virus detection.The paper emphasizes Logistic Model Tree’s critical role in tackling increasing cybersecurity threats and proposes a viable answer to practical issues in the sector.The results reveal that the Logistic Model Tree is superior,with improved accuracy of 97.46%when compared to benchmark models,demonstrating its usefulness in addressing the ever-changing threat landscape.
文摘Population is an important strategic resource for national development, a fundamental element of socio-economic development. The coordinated development of population and economy is an effective way to achieve rapid economic growth. Based on the population statistics data of counties (districts) in Henan Province, China, from 2006 to 2021. The paper firstly uses the logistic population growth mathematical model to calculate the resident population growth rate of counties (districts), then utilizes the hotspot analysis and spatial semi-variogram analysis, to research the spatial distribution characteristics of the resident population growth rate in Henan Province. The research results show that the evolution of the regional resident population in the province basically conforms to the logistic natural growth model. The resident population growth rate shows the characteristics of high in the north and low in the south, high in the center and low in the surrounding regions. The resident population growth rate is positively correlated with the level of economic development;the urban built-up areas, especially the new regions in urban planning, have a fast growth rate of resident population, which has a significant siphon effect on the population of surrounding regions. The hotspots of resident population growth rate in the province are mainly distributed in the urban built-up areas and surrounding regions of Zhengzhou, Luoyang, and Xinxiang, accounting for about 3.51% of the total area of the province. The cold spots are mainly distributed in the eastern part of the province, forming zonal distribution, which spans across Shangqiu City, Zhoukou City, and Zhumadian City, accounting for about 8.61% of the total area of the province. The area with negative growth of resident population accounts for approximately 53.47% of the total province. The spatial distribution of the growth rate of the resident population in the whole province basically conforms to the spherical model, with a small dispersion degree and a short range. In the range, there is a high degree of variability in resident population growth rate.
文摘In view of the composition analysis and identification of ancient glass products, L1 regularization, K-Means cluster analysis, elbow rule and other methods were comprehensively used to build logical regression, cluster analysis, hyper-parameter test and other models, and SPSS, Python and other tools were used to obtain the classification rules of glass products under different fluxes, sub classification under different chemical compositions, hyper-parameter K value test and rationality analysis. Research can provide theoretical support for the protection and restoration of ancient glass relics.
基金supported by theNationalNatural Science Foundation of China[grant number 12271168]the 111 Project of China[grant number B14019].
文摘In this paper,we propose a Bayesian PG-INLA algorithm which is tailored to both one-dimensional and multidimensional 2-PL IRT models.The proposed PG-INLA algorithm utilizes a computationally efficient data augmentation strategy via the Pólya-Gamma variables,which can avoid low computational efficiency of traditioanl Bayesian MCMC algorithms for IRT models with a logistic link function.Meanwhile,combined with the advanced and fast INLA algorithm,the PG-INLA algorithm is both accurate and computationally efficient.We provide details on the derivation of posterior and conditional distributions of IRT models,the method of introducing the Pólya-Gamma variable into Gibbs sampling,and the implementation of the PG-INLA algorithm for both onedimensional and multidimensional cases.Through simulation studies and an application to the data analysis of the IPIP-NEO personality inventory,we assess the performance of the PG-INLA algorithm.Extensions of the proposed PG-INLA algorithm to other IRT models are also discussed.
