Image recognition and empirical application of desert plant species based on convolutional neural network

In recent years,deep convolution neural network has exhibited excellent performance in computer vision and has a far-reaching impact.Traditional plant taxonomic identification requires high expertise,which is time-consuming.Most nature reserves have problems such as incomplete species surveys,inaccurate taxonomic identification,and untimely updating of status data.Simple and accurate recognition of plant images can be achieved by applying convolutional neural network technology to explore the best network model.Taking 24 typical desert plant species that are widely distributed in the nature reserves in Xinjiang Uygur Autonomous Region of China as the research objects,this study established an image database and select the optimal network model for the image recognition of desert plant species to provide decision support for fine management in the nature reserves in Xinjiang,such as species investigation and monitoring,by using deep learning.Since desert plant species were not included in the public dataset,the images used in this study were mainly obtained through field shooting and downloaded from the Plant Photo Bank of China(PPBC).After the sorting process and statistical analysis,a total of 2331 plant images were finally collected(2071 images from field collection and 260 images from the PPBC),including 24 plant species belonging to 14 families and 22 genera.A large number of numerical experiments were also carried out to compare a series of 37 convolutional neural network models with good performance,from different perspectives,to find the optimal network model that is most suitable for the image recognition of desert plant species in Xinjiang.The results revealed 24 models with a recognition Accuracy,of greater than 70.000%.Among which,Residual Network X_8GF(RegNetX_8GF)performs the best,with Accuracy,Precision,Recall,and F1(which refers to the harmonic mean of the Precision and Recall values)values of 78.33%,77.65%,69.55%,and 71.26%,respectively.Considering the demand factors of hardware equipment and inference time,Mobile NetworkV2 achieves the best balance among the Accuracy,the number of parameters and the number of floating-point operations.The number of parameters for Mobile Network V2(MobileNetV2)is 1/16 of RegNetX_8GF,and the number of floating-point operations is 1/24.Our findings can facilitate efficient decision-making for the management of species survey,cataloging,inspection,and monitoring in the nature reserves in Xinjiang,providing a scientific basis for the protection and utilization of natural plant resources.

Water-saving Technologies,Solar Green House and Ecological Rehabilitation in Minqin Oasis of Gansu Province,China

Land degradation and desertification have become severe environmental problems in arid areas due to excessive use of water resources. It is urgent to reduce agricultural water use for ecological rehabilitation, which may result in a decrease in agricultural production and farmer＇s welfare. This paper focused on the impacts of some main measures including extensions of watersaving irrigation, expanding solar green house and increasing off-farm employment, which are generally recognized to be important to alleviate water shortage and poverty. A bioconomic model is applied taking Minqin Oasis in Gansu Province as a case study site. Simulation results showed that the effect of expanding solar greenhouse was more positive than other ones so it drew more attention. On the view of the different effects between each irrigation zone, mixed policy patterns suitable for them are suggested. In Baqu, expanding solar greenhouse should be the most important, auxiliary with encouraging pipe irrigation. Inversely, with regard to Quanshan, the major attention should be paid to subsidy for pipe irrigation and it would be better to supply the off-farm employment opportunities to the households in Huqu, where the expanding of solar greenhouse should also be summoned. Finally, it should be noted that farmer＇s income would only resume to 90% of the current level in the short run by putting more effort into local policies. Thus, the ecological compensation is needed to ensure farmer＇s welfare.

Income Growth,Urbanization,Changing Life Style and Energy Requirements in China

This paper aims to estimate the effects of changing life style and consumption demands driven by income growth and urbanization on increase of energy requirements in China, and es-timate the impacts of improvement in household consumption on mitigating energy requirements towards 2020, based on input-out-put analysis and scenarios simulation approach. The result shows that energy requirement per capita has increased by 159% for urban residents and 147% for rural residents from 1995 to 2004. Growth in household consumption driven by income growth and urbanization may induce a successive increase in energy require-ments in future. Per capita energy requirements of urban residents will increase by 240% during 2002-2015 and 330% during 2002-2020. Urbanization might lead to 0.75 billion ton of increment of energy requirements in 2020. About 45%-48% of total energy requirements in China might be a consequence of residents' life styles and the economic activities to support consumption demands in 2020. Under low-carbon life style scenario, per capita energy requirements of urban residents may decline to 97% in 2015 and 92% in 2020 in contrast with baseline scenario. That implies that China needs to pay a great attention to developing green low-carbon life style in order to realize mitigation target towards 2020.

Evaluation of regional energy security in eastern coastal China based on the DPSIR model

The DPSIR assessment method, which implies the relationships among driving force （D）, pressure （P）, status （S）, impact （I）, and response （R）, is widely applied by scholars. This paper aims to establish a comprehensive assessment system for regional energy security in eastern coastal China based on the above model using different indicators. Factor analysis and the SPSS statistical analysis software were used to carry out scientific and quantitative assessments. The results indicated that con- tradictions of energy supply and demand as well as environmental pollution are the critical factors that present great challenges to regional energy security in this area. The authors argued that a sustainable, stable, and safe supply energy supply is crucial in solving the aforesaid dilemma, and improving the energy use efficiency is one of the best choices. Some countermeasures and suggestions regarding regional energy supply stability and utilization security were pointed out.

Pyramid scheme model for consumption rebate frauds

There are various types of pyramid schemes that have inflicted or are inflicting losses on many people in the world.We propose a pyramid scheme model which has the principal characters of many pyramid schemes that have appeared in recent years: promising high returns, rewarding the participants for recruiting the next generation of participants, and the organizer takes all of the money away when they find that the money from the new participants is not enough to pay the previous participants interest and rewards.We assume that the pyramid scheme is carried out in the tree network, Erd?s–Réney(ER) random network, Strogatz–Watts(SW) small-world network, or Barabasi–Albert(BA) scale-free network.We then give the analytical results of the generations that the pyramid scheme can last in these cases.We also use our model to analyze a pyramid scheme in the real world and we find that the connections between participants in the pyramid scheme may constitute a SW small-world network.

Pyramid scheme in stock market:A kind of financial market simulation

Artificial stock market simulation based on agent is an important means to study financial market.Based on the assumption that the investors are composed of a main fund,small trend and contrarian investors characterized by four parameters,we simulate and research a kind of financial phenomenon with the characteristics of pyramid schemes.Our simulation results and theoretical analysis reveal the relationships between the rate of return of the main fund and the proportion of the trend investors in all small investors,the small investors'parameters of taking profit and stopping loss,the order size of the main fund and the strategies adopted by the main fund.Our work is helpful to explain the financial phenomenon with the characteristics of pyramid schemes in financial markets,design trading rules for regulators and develop trading strategies for investors.

A study of benef its compensation mechanism for agricultural water rights trading under the restriction of ecological reconstruction:a case study of Shiyang River basin

Agricultural water allocation system based on priority rights has caused regional conflicts and downstream ecological degradation. It is the urgent need to introduce the concept of the initial water rights and establish benefits compensation mechanism to resolve such problems. This paper takes the Shiyang River basin as an example to calculate the opportunity cost of 0.97×10^8 m^3 of agricultural water encroached by the middle reach based on initial water right allocation system under which water is allocated in accordance with the ratio between agricultural population of two different regions concerning the downstream ecological reconstruction needs with Bio-economic model （BEM）. The results suggest that the total economic loss of Minqin County for ecological reconstruction amounts to 2.5 7×10^8 yuan, of which 1.68×10^8 yuan is ecological compensation, representing the economic loss Minqin suffered for ecological reconstruction which shouM burden beneficial groups of ecological reconstruction and 0.89 ×10^8 yuan is the economic loss Minqin suffered due to Liangzhou＇s encroachment behavior which should be compensated by Liangzhou.

Enhancing cut selection through reinforcement learning

With the rapid development of artificial intelligence in recent years,applying various learning techniques to solve mixed-integer linear programming(MILP)problems has emerged as a burgeoning research domain.Apart from constructing end-to-end models directly,integrating learning approaches with some modules in the traditional methods for solving MILPs is also a promising direction.The cutting plane method is one of the fundamental algorithms used in modern MILP solvers,and the selection of appropriate cuts from the candidate cuts subset is crucial for enhancing efficiency.Due to the reliance on expert knowledge and problem-specific heuristics,classical cut selection methods are not always transferable and often limit the scalability and generalizability of the cutting plane method.To provide a more efficient and generalizable strategy,we propose a reinforcement learning(RL)framework to enhance cut selection in the solving process of MILPs.Firstly,we design feature vectors to incorporate the inherent properties of MILP and computational information from the solver and represent MILP instances as bipartite graphs.Secondly,we choose the weighted metrics to approximate the proximity of feasible solutions to the convex hull and utilize the learning method to determine the weights assigned to each metric.Thirdly,a graph convolutional neural network is adopted with a self-attention mechanism to predict the value of weighting factors.Finally,we transform the cut selection process into a Markov decision process and utilize RL method to train the model.Extensive experiments are conducted based on a leading open-source MILP solver SCIP.Results on both general and specific datasets validate the effectiveness and efficiency of our proposed approach.

Stage Division and Pattern Discovery of Complex Patient Care Processes

This paper studies the design of a clinical pathway that defines medical service activities within each stage of a patient care process. Much prior research has developed clinicM process models that consider the trajectory of services occurring in a care process, by using data mining techniques on process execution logs. A novel approach that provides a more efficient way of clinical pathway design is introduced in this paper. Based on the strategy of TEI@I methodology, the proposed approach integrates statistical methods, optimization techniques and data mining. With the preprocessed data, a complex care process is subsequently divided into several medical stages, and then the patterns of each stage are identified, and thus a clinical pathway is developed. Finally, the proposed method is applied to the real world, using archival data derived from a hospital in Beijing, about three diseases that involve various departments, with an average of 300 samples for each disease. The results of real- world applications demonstrate that the proposed method can automatically and efficiently facilitate clinical pathways design. The main contributions to the field in this paper include （a） a new application of TEI@I methodology in healthcare domain, （b） a novel method for complex processes analysis, （c） tangible evidence of automatic clinical pathways design in the real world.

Analysis on the Effect of Government Investment on Private Investment in Western China——Take Province A as an Example

Since China began reforming and opening up its economy,and especially since the launch of development projects in western China,province A has attracted an increasing amount of investment,which is the main driving force for provincial economic growth.Hence,this study uses a state space model to examine how government investment has affected economic growth in province A in western China,and explains whether there is a crowding-in effect or a crowding-out effect of local government investment on private investment.The findings indicate that both government and private investments have a positive,stimulating influence on economic growth in province A,with the latter being more impactful than the former.Productive and non-productive investments have different effects on province A’s economic growth.From the perspective of the trajectory of government investment elasticity,the elasticity of government and private investments in province A presents a very large spatio-temporal change.That is,from 1994 to 2009,government investment in province A had a crowding-in effect on private investment,but from 2010 to 2017,a crowding-out effect was observed.

Process-oriented knowledge-sharing platform for chemical engineering design projects

A process-oriented knowledge-sharing platform is studied to improve knowledge sharing and project management of chemical engineering design enterprises. First, problems and characteristics of knowledge sharing in multi-projects of chemical engineering design are analyzed. Then based on theories of project management, process management, and knowledge management, a process-oriented knowledge-sharing platform is proposed. The platform has three characteristics: knowledge is divided into professional knowledge and project management knowledge; knowledge sharing is integrated with the project process, which makes knowledge sharing a necessary part of the project process and ensures the quantity of knowledge shared; the platform provides quantitative measurements of incentive mechanisms for knowledge providers and users which ensures the quality of knowledge shared. This knowledge-sharing platform uses two knowledge management tools, a knowledge map and a knowledge base, to support the platform.

When liver disease diagnosis encounters deep learning:Analysis,challenges,and prospects

The liver is the second-largest organ in the human body and is essential for digesting food and removing toxic substances.Viruses,obesity,alcohol use,and other factors can damage the liver and cause liver disease.The diagnosis of liver disease used to depend on the clinical experience of doctors,which made it subjective,difficult,and time-consuming.Deep learning has made breakthroughs in various fields;thus,there is a growing interest in using deep learning methods to solve problems in liver research to assist doctors in diagnosis and treatment.In this paper,we provide an overview of deep learning in liver research using 139 papers from the last 5 years.We also show the relationship between data modalities,liver topics,and applications in liver research using Sankey diagrams and summarize the deep learning methods used for each liver topic,in addition to the relations and trends between these methods.Finally,we discuss the challenges of and expectations for deep learning in liver research.

Forecasting Container Throughput of Qingdao Port with a Hybrid Model

This paper proposes a hybrid forecasting method to forecast container throughput of Qingdao Port.To eliminate the influence of outliers,local outlier factor(lof) is extended to detect outliers in time series,and then different dummy variables are constructed to capture the effect of outliers based on domain knowledge.Next,a hybrid forecasting model combining projection pursuit regression(PPR) and genetic programming(GP) algorithm is proposed.Finally,the hybrid model is applied to forecasting container throughput of Qingdao Port and the results show that the proposed method significantly outperforms ANN,SARIMA,and PPR models.

A grid-based clustering algorithm for wild bird distribution

Advanced satellite tracking technologies provide biologists with long-term location sequence data to understand movement of wild birds then to find explicit correlation between dynamics of migratory birds and the spread of avian influenza. In this paper, we propose a hierarchical clustering algorithm based on a recursive grid partition and kernel density estimation （KDE） to hierarchically identify wild bird habitats with different densities. We hierarchically cluster the GPS data by taking into account the following observations： 1） the habitat variation on a variety of geospatial scales; 2） the spatial variation of the activity patterns of birds in different stages of the migration cycle. In addition, we measure the site fidelity of wild birds based on clustering. To assess effectiveness, we have evaluated our system using a large-scale GPS dataset collected from 59 birds over three years. As a result, our approach can identify the hierarchical habitats and distribution of wild birds more efficiently than several commonly used algorithms such as DBSCAN and DENCLUE.

Improved twin support vector machine

We improve the twin support vector machine(TWSVM)to be a novel nonparallel hyperplanes classifier,termed as ITSVM(improved twin support vector machine),for binary classification.By introducing the diferent Lagrangian functions for the primal problems in the TWSVM,we get an improved dual formulation of TWSVM,then the resulted ITSVM algorithm overcomes the common drawbacks in the TWSVMs and inherits the essence of the standard SVMs.Firstly,ITSVM does not need to compute the large inverse matrices before training which is inevitable for the TWSVMs.Secondly,diferent from the TWSVMs,kernel trick can be applied directly to ITSVM for the nonlinear case,therefore nonlinear ITSVM is superior to nonlinear TWSVM theoretically.Thirdly,ITSVM can be solved efciently by the successive overrelaxation(SOR)technique or sequential minimization optimization(SMO)method,which makes it more suitable for large scale problems.We also prove that the standard SVM is the special case of ITSVM.Experimental results show the efciency of our method in both computation time and classification accuracy.

Supply Chain Engineering in China's Retailing Industry: A Case of Meiyijia

This paper addresses the supply chain engineering and its application in China’s retailing industry. Based on the approaches of systems engineering, we propose the concept of supply chain engineering, which applies the idea of supply chain management to the engineering practices through the advanced information and management technology, to integrate the supply chain system and optimize its operations. We then illustrate the application of the supply chain engineering in China’s retailing industry. In such practices, we developed the virtual retailing enterprise mode and the FROM-SCM system, and designed the sales assistant etc. Such theory and practices are successfully applied in Meiyijia, which has transformed Meiyijia from a traditional retailer to a modern service enterprise, and the profits are resulted from the service fees rather than the traditional surplus between buying and selling prices. Now Meiyijia has built an ecosystem with the retailer in the core, the headquarter as the service platform. The success of Meiyijia in recent years shows the effectiveness of the supply chain engineering.