Geographic location of nodes is very useful in a sensor network. Previous localization algorithms assume that there exist some anchor nodes in this kind of network, and then other nodes are estimated to create their c...Geographic location of nodes is very useful in a sensor network. Previous localization algorithms assume that there exist some anchor nodes in this kind of network, and then other nodes are estimated to create their coordinates. Once there are not anchors to be deployed, those localization algorithms will be invalidated. Many papers in this field focus on anchor-based solutions. The use of anchors introduces many limitations, since anchors require external equipments such as global position system, cause additional power consumption. A novel positioning algorithm is proposed to use a virtual coordinate system based on a new concept--virtual anchor. It is executed in a distributed fashion according to the connectivity of a node and the measured distances to its neighbors. Both the adjacent member information and the ranging distance result are combined to generate the estimated position of a network, one of which is independently adopted for localization previously. At the position refinement stage the intermediate estimation of a node begins to be evaluated on its reliability for position mutation; thus the positioning optimization process of the whole network is avoided falling into a local optimal solution. Simulation results prove that the algorithm can resolve the distributed localization problem for anchor-free sensor networks, and is superior to previous methods in terms of its positioning capability under a variety of circumstances.展开更多
Topography effects on the vertical vibration responses of pile group are revealed though numerical analysis and model tests.First,a series of model tests with different topography of ground and bedrock are conducted.T...Topography effects on the vertical vibration responses of pile group are revealed though numerical analysis and model tests.First,a series of model tests with different topography of ground and bedrock are conducted.The results indicate that displacement amplitude of the pile head in sloping ground topography is larger than in horizontal ground.Differential displacement at various positions of the pile cap is observed in non-horizontal topography.Afterwards,a numerical algorithm is employed to further explore the essential response characteristics in group piles of different topography configurations,which has been verified by the test results.The lengths of the exposed and frictional segment,together with the thickness of the subsoil layer,are the dominant factors which cause non-axisymmetric vibration at the pile cap.展开更多
Background:The relationship between the regression and prognosis of melanoma has been debated for years.When competing-risk events are present,using traditional survival analysis methods may induce bias in the identif...Background:The relationship between the regression and prognosis of melanoma has been debated for years.When competing-risk events are present,using traditional survival analysis methods may induce bias in the identified prognostic factors that affect patients with regressive melanoma.Methods:Data on patients diagnosed with regressive melanoma were extracted from the Surveillance,Epidemiology,and End Results(SEER)database during 2000-2019.Cumulative incidence function and Gray's test were used for the univariate analysis,and the Cox proportional-hazards model and the Fine-Gray model were used for the multivariate analysis.Results:A total of 1442 eligible patients were diagnosed with regressive melanoma,including 529 patients who died:109 from regressive melanoma and 420 from other causes.The multivariate analysis using the Fine-Gray model revealed that SEER stage,surgery status,and marital status were important factors that affected the prognosis of regressive melanoma.Due to the existence of competing-risk events,the Cox model may have induced biases in estimating the effect values,and the competing-risks model was more advantageous in the analysis of multipleendpoint clinical survival data.Conclusion:The findings of this study may help clinicians to better understand regressive melanoma and provide reference data for clinical decisions.展开更多
The present study examines the impact of short-term public opinion sentiment on the secondary market,with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment ...The present study examines the impact of short-term public opinion sentiment on the secondary market,with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment risk.The quantification of investment sentiment indicators and the persistent analysis of their impact has been a complex and significant area of research.In this paper,a structured multi-head attention stock index prediction method based adaptive public opinion sentiment vector is proposed.The proposedmethod utilizes an innovative approach to transform numerous investor comments on social platforms over time into public opinion sentiment vectors expressing complex sentiments.It then analyzes the continuous impact of these vectors on the market through the use of aggregating techniques and public opinion data via a structured multi-head attention mechanism.The experimental results demonstrate that the public opinion sentiment vector can provide more comprehensive feedback on market sentiment than traditional sentiment polarity analysis.Furthermore,the multi-head attention mechanism is shown to improve prediction accuracy through attention convergence on each type of input information separately.Themean absolute percentage error(MAPE)of the proposedmethod is 0.463%,a reduction of 0.294% compared to the benchmark attention algorithm.Additionally,the market backtesting results indicate that the return was 24.560%,an improvement of 8.202% compared to the benchmark algorithm.These results suggest that themarket trading strategy based on thismethod has the potential to improve trading profits.展开更多
Imbalanced data classification is the task of classifying datasets where there is a significant disparity in the number of samples between different classes.This task is prevalent in practical scenarios such as indust...Imbalanced data classification is the task of classifying datasets where there is a significant disparity in the number of samples between different classes.This task is prevalent in practical scenarios such as industrial fault diagnosis,network intrusion detection,cancer detection,etc.In imbalanced classification tasks,the focus is typically on achieving high recognition accuracy for the minority class.However,due to the challenges presented by imbalanced multi-class datasets,such as the scarcity of samples in minority classes and complex inter-class relationships with overlapping boundaries,existing methods often do not perform well in multi-class imbalanced data classification tasks,particularly in terms of recognizing minority classes with high accuracy.Therefore,this paper proposes a multi-class imbalanced data classification method called CSDSResNet,which is based on a cost-sensitive dualstream residual network.Firstly,to address the issue of limited samples in the minority class within imbalanced datasets,a dual-stream residual network backbone structure is designed to enhance the model’s feature extraction capability.Next,considering the complexities arising fromimbalanced inter-class sample quantities and imbalanced inter-class overlapping boundaries in multi-class imbalanced datasets,a unique cost-sensitive loss function is devised.This loss function places more emphasis on the minority class and the challenging classes with high interclass similarity,thereby improving the model’s classification ability.Finally,the effectiveness and generalization of the proposed method,CSDSResNet,are evaluated on two datasets:‘DryBeans’and‘Electric Motor Defects’.The experimental results demonstrate that CSDSResNet achieves the best performance on imbalanced datasets,with macro_F1-score values improving by 2.9%and 1.9%on the two datasets compared to current state-of-the-art classification methods,respectively.Furthermore,it achieves the highest precision in single-class recognition tasks for the minority cl展开更多
The anisotropic mechanical behavior of rocks under high-stress and high-temperature coupled conditions is crucial for analyzing the stability of surrounding rocks in deep underground engineering.This paper is devoted ...The anisotropic mechanical behavior of rocks under high-stress and high-temperature coupled conditions is crucial for analyzing the stability of surrounding rocks in deep underground engineering.This paper is devoted to studying the anisotropic strength,deformation and failure behavior of gneiss granite from the deep boreholes of a railway tunnel that suffers from high tectonic stress and ground temperature in the eastern tectonic knot in the Tibet Plateau.High-temperature true triaxial compression tests are performed on the samples using a self-developed testing device with five different loading directions and three temperature values that are representative of the geological conditions of the deep underground tunnels in the region.Effect of temperature and loading direction on the strength,elastic modulus,Poisson’s ratio,and failure mode are analyzed.The method for quantitative identification of anisotropic failure is also proposed.The anisotropic mechanical behaviors of the gneiss granite are very sensitive to the changes in loading direction and temperature under true triaxial compression,and the high temperature seems to weaken the inherent anisotropy and stress-induced deformation anisotropy.The strength and deformation show obvious thermal degradation at 200℃due to the weakening of friction between failure surfaces and the transition of the failure pattern in rock grains.In the range of 25℃ 200℃,the failure is mainly governed by the loading direction due to the inherent anisotropy.This study is helpful to the in-depth understanding of the thermal-mechanical behavior of anisotropic rocks in deep underground projects.展开更多
Formation of intermetallic compounds （IMCs） during friction stir welding （FSW） of alu- minum/magnesium （AI/Mg） alloys easily results in the pin adhesion and then deteriorates joint formation. The severe pin adhe...Formation of intermetallic compounds （IMCs） during friction stir welding （FSW） of alu- minum/magnesium （AI/Mg） alloys easily results in the pin adhesion and then deteriorates joint formation. The severe pin adhesion transformed the tapered-and-screwed pin into a tapered pin at a low welding speed of 30 mm/min. The pin adhesion problem was solved with the help of ultrasonic. The weldability of Al/Mg alloys was significantly improved due to the good material flow induced by mechanical vibration and the fragments of the IMCs on the surface of a rotating pin caused by acoustic streaming, respectively. A sound joint with ultrasonic contained long Al/Mg interface joining length and complex mixture of AI/Mg alloys in the stir zone, thereby achieving perfect metallurgical bonding and mechanical interlocking. The ultrasonic could broaden process window and then improve tensile properties. The tensile strength of the Al/Mg joint with ultrasonic reached 115 MPa.展开更多
Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has...Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.展开更多
Non-destructive testing of composites is an important issue in the modern aircraft industry.Composites are susceptible to the barely visible impact damage which can affect the residual strength of the material and occ...Non-destructive testing of composites is an important issue in the modern aircraft industry.Composites are susceptible to the barely visible impact damage which can affect the residual strength of the material and occurs both during production and operation.The continuum model for describing the damaged zone is presented.The slip theory relations used for a continuous distribution of slip planes are applied.At the initial stage,the isotropic background model is used.This model allows the material slippage along the fractures based on the Coulomb friction law with the small viscous addition.In this regime,the govern system of equations becomes rigid.To overcome this difficulty,the explicit-implicit grid-characteristic scheme is proposed.The standard ultrasound diagnostic procedure of damaged composite materials is successfully simulated.Compared with the trivial free-surface fracture model,different reactions on the compression and stretch waves are registered.This approach provided an effective way for the simulation of complex dynamic behavior of damage zones.展开更多
Objective To explore the correlations of high-density lipoprotein cholesterol(HDL-C)/low-density lipoprotein cholesterol(LDL-C)with myocardial infarction(MI),all-cause mortality,haemorrhagic stroke and ischaemic strok...Objective To explore the correlations of high-density lipoprotein cholesterol(HDL-C)/low-density lipoprotein cholesterol(LDL-C)with myocardial infarction(MI),all-cause mortality,haemorrhagic stroke and ischaemic stroke,as well as the joint association of genetic susceptibility and HDL-C/LDL-C with the MI risk.Methods and results This study selected 384093 participants from the UK Biobank(UKB)database.First,restricted cubic splines indicated non-linear associations of HDL-C/LDL-C with MI,ischaemic stroke and all-cause mortality.Second,a Cox proportional-hazards model indicated that compared with HDL-C/LDL-C=0.4-0.6,HDL-C/LDL-C<0.4 and>0.6 were correlated with all-cause mortality(HR=0.97 for HDL-C/LDL-C<0.4,95%CI=0.939 to 0.999,p<0.05;HR=1.21 for HDL-C/LDL-C>0.6,95%CI=1.16 to 1.26,p<0.001)after full multivariable adjustment.HDL-C/LDL-C<0.4 was correlated with a higher MI risk(HR=1.36,95%CI=1.28 to 1.44,p<0.05)and ischaemic stroke(HR=1.12,95%CI=1.02 to 1.22,p<0.05)after full multivariable adjustment.HDL-C/LDL-C>0.6 was associated with higher risk haemorrhagic stroke risk after full multivariable adjustment(HR=1.25,95%CI=1.03 to 1.52,p<0.05).Third,after calculating the coronary heart disease Genetic Risk Score(CHD-GRS)of each participant,the Cox proportional-hazards model indicated that compared with low CHD-GRS and HDL-C/LDL-C=0.4-0.6,participants with a combination of high CHD-GRS and HDL-C/LDL-C<0.4 were associated with the highest MI risk(HR=2.45,95%CI=2.15 to 2.8,p<0.001).Participants with HDL-C/LDL-C<0.4 were correlated with a higher MI risk regardless of whether they had a high,intermediate or low CHD-GRS.Conclusion In UKB participants,HDL-C/LDL-C ratio of 0.4-0.6 was correlated with lower MI risk,all-cause mortality,haemorrhagic stroke and ischaemic stroke.Participants with HDL-C/LDL-C<0.4 were correlated with a higher MI risk regardless of whether they had a high,intermediate or low CHD-GRS.The clinical significance and impact of HDL-C/LDL-C need to be further verified in future studies.展开更多
In recent years,government investments in implementing restrictive public policies on the treatment and discharge of effluents from the aquaculture industry have increased.Hence,efficient and cleaner methods for aquac...In recent years,government investments in implementing restrictive public policies on the treatment and discharge of effluents from the aquaculture industry have increased.Hence,efficient and cleaner methods for aquaculture production are needed.Recirculating aquaculture systems(RAS)offers water conservation by recycling the treated aquaculture water for reuse.RAS wastewater treatment using a moving bed bioreactors(MBBRs)process has been considered well suited for maintaining good water quality,thereby making fish farming more sustainable.Currently,improvements were achieved in tackling the influence of salinity,organic matter,disinfectant,and bioreactor start-up process on the MBBR performance efficiency.This review highlights an updated overview of recent development made using MBBR to treat the residual water from RAS.Precisely,nitrification and simultaneous nitrification-denitrification(SND),and other hybrid processes for nitrogen removal were elucidated.Finally,future challenges and prospects of MBBRs in RAS facilities that need to be considered were also proposed.展开更多
Bodyweight is a key indicator of broiler production as it measures the production efficiency and indicates the health of a flock.Currently,broiler weight(i.e.,bodyweight)is primarily weighed manually,which is timecons...Bodyweight is a key indicator of broiler production as it measures the production efficiency and indicates the health of a flock.Currently,broiler weight(i.e.,bodyweight)is primarily weighed manually,which is timeconsuming and labor-intensive,and tends to create stress in birds.This study aimed to develop an automatic and stress-free weighing platform for monitoring the weight of floor-reared broiler chickens in commercial production.The developed system consists of a weighing platform,a real-time communication terminal,computer software and a smart phone applet userinterface.The system collected weight data of chickens on the weighing platform at intervals of 6 s,followed by filtering of outliers and repeating readings.The performance and stability of this system was systematically evaluated under commercial production conditions.With the adoption of data preprocessing protocol,the average error of the new automatic weighing system was only 10.3 g,with an average accuracy 99.5%with the standard deviation of 2.3%.Further regression analysis showed a strong agreement between estimated weight and the standard weight obtained by the established live-bird sales system.The variance(an indicator of flock uniformity)of broiler weight estimated using automatic weighing platforms was in accordance with the standard weight.The weighing system demonstrated superior stability for different growth stages,rearing seasons,growth rate types(medium-and slow-growing chickens)and sexes.The system is applicable for daily weight monitoring in floor-reared broiler houses to improve feeding management,growth monitoring and finishing day prediction.Its application in commercial farms would improve the sustainability of poultry industry.展开更多
Multi-floor buildings for raising pigs have recently attracted widespread attention as an emerging form of intensive livestock production especially in eastern China,due to the fact that they can feed a much larger nu...Multi-floor buildings for raising pigs have recently attracted widespread attention as an emerging form of intensive livestock production especially in eastern China,due to the fact that they can feed a much larger number of animals per unit area of land and thus alleviate the shortage of land available for standard single-floor pig production facilities.However,this more intensive kind of pig building will pose new challenges to the local environment in terms of pollutant dispersion.To compare the dispersion air pollutants(ammonia as a representative)emitted from multi-versus single-floor pig buildings,ammonia dispersion distance and concentration gradients were investigated through three-dimensional simulations based on computational fluid dynamics.The validation of an isolated cubic model was made to ensure the simulation method was effective.The effects of wind direction,wind speed and emission source concentration at 1.5 m(approximate human inhalation height)during summer were investigated.The results showed that the ammonia dispersion distance of the multi-floor pig building was far greater than that of the single-floor building on a plane of Z=1.5 m.When the wind direction was 67.5°,the wind speed was 2 m·s^(−1) and the emission source concentration was 20 ppmv,the dispersion distance of the multi-floor pig building could reach 1380 m.Meanwhile,the ammonia could accumulate in the yard to 7.68 ppmv.Therefore,future site selection,wind speed and source concentration need to be given serious consideration.Based on the simulation used in this study with source concentration is 20 ppmv,the multi-floor pig buildings should be located 1.4 km away from residential areas to avoid affecting residents.The results of this study should guidance for any future development of multi-floor pig buildings.展开更多
Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increa...Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention.Considering the time-consuming empirical mode decomposition(EMD)method and the more efficient classification provided by the convolutional neural network(CNN)method,a novel classification method based on incomplete empirical mode decomposition(IEMD)and dual-input dual-channel convolutional neural network(DDCNN)composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approach–This paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient(MFCC)and a neural network model of DDCNN.First,the sound signal is decomposed by IEMD to get numerous intrinsic mode functions(IMFs)and a residual(RES).Several IMFs and one RES are then extracted by MFCC features.Ultimately,the obtained features are split into two channels(IMFs one channel;RES one channel)and input into DDCNN.Findings–The Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection(MIMII dataset)is used to verify the practicability of the method.Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis.Compared with EMD,51.52% of data preprocessing time,67.25% of network training time and 63.7%of test time are saved and also improve accuracy.Research limitations/implications–This method can achieve higher accuracy in fault diagnosis with a shorter time cost.Therefore,the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/value–This method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.展开更多
Despite the diverse roles of tripartite motif(Trim)-containing proteins in the regulation of autophagy,the innate immune response,and cell differentiation,their roles in skeletal diseases are largely unknown.We recent...Despite the diverse roles of tripartite motif(Trim)-containing proteins in the regulation of autophagy,the innate immune response,and cell differentiation,their roles in skeletal diseases are largely unknown.We recently demonstrated that Trim21 plays a crucial role in regulating osteoblast(OB)differentiation in osteosarcoma.However,how Trim21 contributes to skeletal degenerative disorders,including osteoporosis,remains unknown.First,human and mouse bone specimens were evaluated,and the results showed that Trim21 expression was significantly elevated in bone tissues obtained from osteoporosis patients.Next,we found that global knockout of the Trim21 gene(KO,Trim2^(1-/-))resulted in higher bone mass compared to that of the control littermates.We further demonstrated that loss of Trim21 promoted bone formation by enhancing the osteogenic differentiation of bone marrow mesenchymal stem cells(BMSCs)and elevating the activity of OBs;moreover,Trim21 depletion suppressed osteoclast(OC)formation of RAW264.7 cells.In addition,the differentiation of OCs from bone marrow-derived macrophages(BMMs)isolated from Trim21^(-/-)and Ctsk-cre;Trim21^(f/f)mice was largely compromised compared to that of the littermate control mice.Mechanistically,YAP1/β-catenin signaling was identified and demonstrated to be required for the Trim21-mediated osteogenic differentiation of BMSCs.More importantly,the loss of Trim21 prevented ovariectomy(OVX)-and lipopolysaccharide(LPS)-induced bone loss in vivo by orchestrating the coupling of OBs and OCs through YAP1 signaling.Our current study demonstrated that Trim21 is crucial for regulating OB-mediated bone formation and OC-mediated bone resorption,thereby providing a basis for exploring Trim21 as a novel dual-targeting approach for treating osteoporosis and pathological bone loss.展开更多
With the development of the Internet of Things(IoT),the massive data sharing between IoT devices improves the Quality of Service(QoS)and user experience in various IoT applications.However,data sharing may cause serio...With the development of the Internet of Things(IoT),the massive data sharing between IoT devices improves the Quality of Service(QoS)and user experience in various IoT applications.However,data sharing may cause serious privacy leakages to data providers.To address this problem,in this study,data sharing is realized through model sharing,based on which a secure data sharing mechanism,called BP2P-FL,is proposed using peer-to-peer federated learning with the privacy protection of data providers.In addition,by introducing the blockchain to the data sharing,every training process is recorded to ensure that data providers offer high-quality data.For further privacy protection,the differential privacy technology is used to disturb the global data sharing model.The experimental results show that BP2P-FL has high accuracy and feasibility in the data sharing of various IoT applications.展开更多
To improve the light environment and welfare of the turtle cultured indoors,the effects of lighting mode on growth performance,cortisol level,and oxidative stress of juvenile Chinese three-keeled pond turtle,Chinemys ...To improve the light environment and welfare of the turtle cultured indoors,the effects of lighting mode on growth performance,cortisol level,and oxidative stress of juvenile Chinese three-keeled pond turtle,Chinemys reevesii,were investigated in this study.The experimental turtles with an initial weight of 5.61±0.09 g were reared in tanks under four different lighting modes:three groups with light(lighting the basking area and water area,LBW;lighting the water area only,LW;lighting the basking area only,LB)and control group(no light,NL).The experiment was conducted for more than six months,with each group having three replicates.After 203 d of the experiment,the turtle in the LW group exhibited higher weight gain rate(WGR)and a specific growth rate(SGR,%/d)compared to other treatments.Also,results showed that the final body weight of the turtle exposed to LW was higher than that exposed to other treatments.On the physiological level,serum cortisol level in turtles exposed to LW was significantly lower than that in other treatments.Regarding oxidative stress,the level of catalase(CAT)in turtles exposed to LW and LB was significantly lower than that exposed to LBW and NL.The malonaldehyde(MDA)activity in turtles exposed to LW was significantly lower than other treatments.Based on the growth performance and health status,it is suggested that lighting the water area only is the optimal lighting mode for the juvenile threekeeled pond turtle cultured indoors.展开更多
Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational fiel...Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational field struggles with two challenges:the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage;the other is the lack of specialized educational QG datasets.To address the challenges,a specialized QG dataset,reading comprehension dataset from examinations for QG(named RACE4QG),is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE dataset.Further,an end-to-end QG model,which can exploit the intra-and inter-sentence information to generate better questions,is proposed.In our model,the encoder utilizes a Gated Recurrent Units(GRU)network,which takes the concatenation of word embedding,answer tagging,and Graph Attention neTworks(GAT)embedding as input.The hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation,which will be fed to the decoder.Results show that our model outperforms baselines on automatic metrics and human evaluation.Consequently,the model improves the baseline by 0.44,1.32,and 1.34 on BLEU-4,ROUGE-L,and METEOR metrics,respectively,indicating the effectivity and reliability of our model.Its gap with human expectations also reflects the research potential.展开更多
Rule-based portfolio construction strategies are rising as investmentdemand grows, and smart beta strategies are becoming a trend amonginstitutional investors. Smart beta strategies have high transparency, lowmanageme...Rule-based portfolio construction strategies are rising as investmentdemand grows, and smart beta strategies are becoming a trend amonginstitutional investors. Smart beta strategies have high transparency, lowmanagement costs, and better long-term performance, but are at the risk ofsevere short-term declines due to a lack of Risk Control tools. Although thereare some methods to use historical volatility for Risk Control, it is still difficultto adapt to the rapid switch of market styles. How to strengthen the RiskControl management of the portfolio while maintaining the original advantagesof smart beta has become a new issue of concern in the industry. Thispaper demonstrates the scientific validity of using a probability prediction forposition optimization through an optimization theory and proposes a novelnatural gradient boosting (NGBoost)-based portfolio optimization method,which predicts stock prices and their probability distributions based on non-Bayesian methods and maximizes the Sharpe ratio expectation of positionoptimization. This paper validates the effectiveness and practicality of themodel by using the Chinese stock market, and the experimental results showthat the proposed method in this paper can reduce the volatility by 0.08 andincrease the expected portfolio cumulative return (reaching a maximum of67.1%) compared with the mainstream methods in the industry.展开更多
To improve the operation efficiency of the photovoltaic power station complementary power generation system,an optimal allocation model of the photovoltaic power station complementary power generation capacity based o...To improve the operation efficiency of the photovoltaic power station complementary power generation system,an optimal allocation model of the photovoltaic power station complementary power generation capacity based on PSO-BP is proposed.Particle Swarm Optimization and BP neural network are used to establish the forecasting model,the Markov chain model is used to correct the forecasting error of the model,and the weighted fitting method is used to forecast the annual load curve,to complete the optimal allocation of complementary generating capacity of photovoltaic power stations.The experimental results show that thismethod reduces the average loss of photovoltaic output prediction,improves the prediction accuracy and recall rate of photovoltaic output prediction,and ensures the effective operation of the power system.展开更多
基金the National Natural Science Foundation of China (60673054, 60773129)theExcellent Youth Science and Technology Foundation of Anhui Province of China.
文摘Geographic location of nodes is very useful in a sensor network. Previous localization algorithms assume that there exist some anchor nodes in this kind of network, and then other nodes are estimated to create their coordinates. Once there are not anchors to be deployed, those localization algorithms will be invalidated. Many papers in this field focus on anchor-based solutions. The use of anchors introduces many limitations, since anchors require external equipments such as global position system, cause additional power consumption. A novel positioning algorithm is proposed to use a virtual coordinate system based on a new concept--virtual anchor. It is executed in a distributed fashion according to the connectivity of a node and the measured distances to its neighbors. Both the adjacent member information and the ranging distance result are combined to generate the estimated position of a network, one of which is independently adopted for localization previously. At the position refinement stage the intermediate estimation of a node begins to be evaluated on its reliability for position mutation; thus the positioning optimization process of the whole network is avoided falling into a local optimal solution. Simulation results prove that the algorithm can resolve the distributed localization problem for anchor-free sensor networks, and is superior to previous methods in terms of its positioning capability under a variety of circumstances.
基金National Science Foundation of China under Grant Nos.51622803 and 51778092Innovation Group Science Foundation of the Natural Science Foundation of Chongqing,China under Grant No.cstc2020jcyjcxttX0003China Scholarship Council(File No:201806050121)for financial support to visit Purdue University。
文摘Topography effects on the vertical vibration responses of pile group are revealed though numerical analysis and model tests.First,a series of model tests with different topography of ground and bedrock are conducted.The results indicate that displacement amplitude of the pile head in sloping ground topography is larger than in horizontal ground.Differential displacement at various positions of the pile cap is observed in non-horizontal topography.Afterwards,a numerical algorithm is employed to further explore the essential response characteristics in group piles of different topography configurations,which has been verified by the test results.The lengths of the exposed and frictional segment,together with the thickness of the subsoil layer,are the dominant factors which cause non-axisymmetric vibration at the pile cap.
基金Key Scientific Problems and Medical Technical Problems Research Project of China Medical Education Association(2022KTZ009)Guangdong Provincial Key Laboratory of Traditional Chinese Medicine Informatization(2021B1212040007).
文摘Background:The relationship between the regression and prognosis of melanoma has been debated for years.When competing-risk events are present,using traditional survival analysis methods may induce bias in the identified prognostic factors that affect patients with regressive melanoma.Methods:Data on patients diagnosed with regressive melanoma were extracted from the Surveillance,Epidemiology,and End Results(SEER)database during 2000-2019.Cumulative incidence function and Gray's test were used for the univariate analysis,and the Cox proportional-hazards model and the Fine-Gray model were used for the multivariate analysis.Results:A total of 1442 eligible patients were diagnosed with regressive melanoma,including 529 patients who died:109 from regressive melanoma and 420 from other causes.The multivariate analysis using the Fine-Gray model revealed that SEER stage,surgery status,and marital status were important factors that affected the prognosis of regressive melanoma.Due to the existence of competing-risk events,the Cox model may have induced biases in estimating the effect values,and the competing-risks model was more advantageous in the analysis of multipleendpoint clinical survival data.Conclusion:The findings of this study may help clinicians to better understand regressive melanoma and provide reference data for clinical decisions.
基金funded by the Major Humanities and Social Sciences Research Projects in Zhejiang higher education institutions,grant number 2023QN082,awarded to Cheng ZhaoThe National Natural Science Foundation of China also provided funding,grant number 61902349,awarded to Cheng Zhao.
文摘The present study examines the impact of short-term public opinion sentiment on the secondary market,with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment risk.The quantification of investment sentiment indicators and the persistent analysis of their impact has been a complex and significant area of research.In this paper,a structured multi-head attention stock index prediction method based adaptive public opinion sentiment vector is proposed.The proposedmethod utilizes an innovative approach to transform numerous investor comments on social platforms over time into public opinion sentiment vectors expressing complex sentiments.It then analyzes the continuous impact of these vectors on the market through the use of aggregating techniques and public opinion data via a structured multi-head attention mechanism.The experimental results demonstrate that the public opinion sentiment vector can provide more comprehensive feedback on market sentiment than traditional sentiment polarity analysis.Furthermore,the multi-head attention mechanism is shown to improve prediction accuracy through attention convergence on each type of input information separately.Themean absolute percentage error(MAPE)of the proposedmethod is 0.463%,a reduction of 0.294% compared to the benchmark attention algorithm.Additionally,the market backtesting results indicate that the return was 24.560%,an improvement of 8.202% compared to the benchmark algorithm.These results suggest that themarket trading strategy based on thismethod has the potential to improve trading profits.
基金supported by Beijing Municipal Science and Technology Project(No.Z221100007122003)。
文摘Imbalanced data classification is the task of classifying datasets where there is a significant disparity in the number of samples between different classes.This task is prevalent in practical scenarios such as industrial fault diagnosis,network intrusion detection,cancer detection,etc.In imbalanced classification tasks,the focus is typically on achieving high recognition accuracy for the minority class.However,due to the challenges presented by imbalanced multi-class datasets,such as the scarcity of samples in minority classes and complex inter-class relationships with overlapping boundaries,existing methods often do not perform well in multi-class imbalanced data classification tasks,particularly in terms of recognizing minority classes with high accuracy.Therefore,this paper proposes a multi-class imbalanced data classification method called CSDSResNet,which is based on a cost-sensitive dualstream residual network.Firstly,to address the issue of limited samples in the minority class within imbalanced datasets,a dual-stream residual network backbone structure is designed to enhance the model’s feature extraction capability.Next,considering the complexities arising fromimbalanced inter-class sample quantities and imbalanced inter-class overlapping boundaries in multi-class imbalanced datasets,a unique cost-sensitive loss function is devised.This loss function places more emphasis on the minority class and the challenging classes with high interclass similarity,thereby improving the model’s classification ability.Finally,the effectiveness and generalization of the proposed method,CSDSResNet,are evaluated on two datasets:‘DryBeans’and‘Electric Motor Defects’.The experimental results demonstrate that CSDSResNet achieves the best performance on imbalanced datasets,with macro_F1-score values improving by 2.9%and 1.9%on the two datasets compared to current state-of-the-art classification methods,respectively.Furthermore,it achieves the highest precision in single-class recognition tasks for the minority cl
基金This work was supported by Natural Science Foundation of China(Grant No.52278333)the Fundamental Research Funds for the Central Universities(Grant No.N2101021)The work is under the framework of the 111 Project(Grant No.B17009)and Sino-Franco Joint Research Laboratory on Multiphysics and Multiscale Rock Mechanics.
文摘The anisotropic mechanical behavior of rocks under high-stress and high-temperature coupled conditions is crucial for analyzing the stability of surrounding rocks in deep underground engineering.This paper is devoted to studying the anisotropic strength,deformation and failure behavior of gneiss granite from the deep boreholes of a railway tunnel that suffers from high tectonic stress and ground temperature in the eastern tectonic knot in the Tibet Plateau.High-temperature true triaxial compression tests are performed on the samples using a self-developed testing device with five different loading directions and three temperature values that are representative of the geological conditions of the deep underground tunnels in the region.Effect of temperature and loading direction on the strength,elastic modulus,Poisson’s ratio,and failure mode are analyzed.The method for quantitative identification of anisotropic failure is also proposed.The anisotropic mechanical behaviors of the gneiss granite are very sensitive to the changes in loading direction and temperature under true triaxial compression,and the high temperature seems to weaken the inherent anisotropy and stress-induced deformation anisotropy.The strength and deformation show obvious thermal degradation at 200℃due to the weakening of friction between failure surfaces and the transition of the failure pattern in rock grains.In the range of 25℃ 200℃,the failure is mainly governed by the loading direction due to the inherent anisotropy.This study is helpful to the in-depth understanding of the thermal-mechanical behavior of anisotropic rocks in deep underground projects.
基金supported by the National Natural Science Foundation of China(No.51204111)the Program for Liaoning Excellent Talents in University(No.LJQ2015084)+1 种基金the China Postdoctoral Science Foundation(No.2016M590821)Guangdong Provincial Key Laboratory of Advanced Welding Technology for Ships(No.2017B030302010)
文摘Formation of intermetallic compounds （IMCs） during friction stir welding （FSW） of alu- minum/magnesium （AI/Mg） alloys easily results in the pin adhesion and then deteriorates joint formation. The severe pin adhesion transformed the tapered-and-screwed pin into a tapered pin at a low welding speed of 30 mm/min. The pin adhesion problem was solved with the help of ultrasonic. The weldability of Al/Mg alloys was significantly improved due to the good material flow induced by mechanical vibration and the fragments of the IMCs on the surface of a rotating pin caused by acoustic streaming, respectively. A sound joint with ultrasonic contained long Al/Mg interface joining length and complex mixture of AI/Mg alloys in the stir zone, thereby achieving perfect metallurgical bonding and mechanical interlocking. The ultrasonic could broaden process window and then improve tensile properties. The tensile strength of the Al/Mg joint with ultrasonic reached 115 MPa.
基金supported by Beijing Municipal Science and Technology Project(No.Z221100007122003).
文摘Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.
基金the financial support of the Russian Science Foundation(No.19-71-10060)。
文摘Non-destructive testing of composites is an important issue in the modern aircraft industry.Composites are susceptible to the barely visible impact damage which can affect the residual strength of the material and occurs both during production and operation.The continuum model for describing the damaged zone is presented.The slip theory relations used for a continuous distribution of slip planes are applied.At the initial stage,the isotropic background model is used.This model allows the material slippage along the fractures based on the Coulomb friction law with the small viscous addition.In this regime,the govern system of equations becomes rigid.To overcome this difficulty,the explicit-implicit grid-characteristic scheme is proposed.The standard ultrasound diagnostic procedure of damaged composite materials is successfully simulated.Compared with the trivial free-surface fracture model,different reactions on the compression and stretch waves are registered.This approach provided an effective way for the simulation of complex dynamic behavior of damage zones.
文摘Objective To explore the correlations of high-density lipoprotein cholesterol(HDL-C)/low-density lipoprotein cholesterol(LDL-C)with myocardial infarction(MI),all-cause mortality,haemorrhagic stroke and ischaemic stroke,as well as the joint association of genetic susceptibility and HDL-C/LDL-C with the MI risk.Methods and results This study selected 384093 participants from the UK Biobank(UKB)database.First,restricted cubic splines indicated non-linear associations of HDL-C/LDL-C with MI,ischaemic stroke and all-cause mortality.Second,a Cox proportional-hazards model indicated that compared with HDL-C/LDL-C=0.4-0.6,HDL-C/LDL-C<0.4 and>0.6 were correlated with all-cause mortality(HR=0.97 for HDL-C/LDL-C<0.4,95%CI=0.939 to 0.999,p<0.05;HR=1.21 for HDL-C/LDL-C>0.6,95%CI=1.16 to 1.26,p<0.001)after full multivariable adjustment.HDL-C/LDL-C<0.4 was correlated with a higher MI risk(HR=1.36,95%CI=1.28 to 1.44,p<0.05)and ischaemic stroke(HR=1.12,95%CI=1.02 to 1.22,p<0.05)after full multivariable adjustment.HDL-C/LDL-C>0.6 was associated with higher risk haemorrhagic stroke risk after full multivariable adjustment(HR=1.25,95%CI=1.03 to 1.52,p<0.05).Third,after calculating the coronary heart disease Genetic Risk Score(CHD-GRS)of each participant,the Cox proportional-hazards model indicated that compared with low CHD-GRS and HDL-C/LDL-C=0.4-0.6,participants with a combination of high CHD-GRS and HDL-C/LDL-C<0.4 were associated with the highest MI risk(HR=2.45,95%CI=2.15 to 2.8,p<0.001).Participants with HDL-C/LDL-C<0.4 were correlated with a higher MI risk regardless of whether they had a high,intermediate or low CHD-GRS.Conclusion In UKB participants,HDL-C/LDL-C ratio of 0.4-0.6 was correlated with lower MI risk,all-cause mortality,haemorrhagic stroke and ischaemic stroke.Participants with HDL-C/LDL-C<0.4 were correlated with a higher MI risk regardless of whether they had a high,intermediate or low CHD-GRS.The clinical significance and impact of HDL-C/LDL-C need to be further verified in future studies.
基金This study received support from the National Key R&D Program of China(No.2020YFD0900600)the Key Program of Science and Technology of Zhejiang Province(2019C02084).
文摘In recent years,government investments in implementing restrictive public policies on the treatment and discharge of effluents from the aquaculture industry have increased.Hence,efficient and cleaner methods for aquaculture production are needed.Recirculating aquaculture systems(RAS)offers water conservation by recycling the treated aquaculture water for reuse.RAS wastewater treatment using a moving bed bioreactors(MBBRs)process has been considered well suited for maintaining good water quality,thereby making fish farming more sustainable.Currently,improvements were achieved in tackling the influence of salinity,organic matter,disinfectant,and bioreactor start-up process on the MBBR performance efficiency.This review highlights an updated overview of recent development made using MBBR to treat the residual water from RAS.Precisely,nitrification and simultaneous nitrification-denitrification(SND),and other hybrid processes for nitrogen removal were elucidated.Finally,future challenges and prospects of MBBRs in RAS facilities that need to be considered were also proposed.
基金funded by Zhejiang Provincial Key R&D Program(2021C02026)China Agriculture Research System(CARS-40).
文摘Bodyweight is a key indicator of broiler production as it measures the production efficiency and indicates the health of a flock.Currently,broiler weight(i.e.,bodyweight)is primarily weighed manually,which is timeconsuming and labor-intensive,and tends to create stress in birds.This study aimed to develop an automatic and stress-free weighing platform for monitoring the weight of floor-reared broiler chickens in commercial production.The developed system consists of a weighing platform,a real-time communication terminal,computer software and a smart phone applet userinterface.The system collected weight data of chickens on the weighing platform at intervals of 6 s,followed by filtering of outliers and repeating readings.The performance and stability of this system was systematically evaluated under commercial production conditions.With the adoption of data preprocessing protocol,the average error of the new automatic weighing system was only 10.3 g,with an average accuracy 99.5%with the standard deviation of 2.3%.Further regression analysis showed a strong agreement between estimated weight and the standard weight obtained by the established live-bird sales system.The variance(an indicator of flock uniformity)of broiler weight estimated using automatic weighing platforms was in accordance with the standard weight.The weighing system demonstrated superior stability for different growth stages,rearing seasons,growth rate types(medium-and slow-growing chickens)and sexes.The system is applicable for daily weight monitoring in floor-reared broiler houses to improve feeding management,growth monitoring and finishing day prediction.Its application in commercial farms would improve the sustainability of poultry industry.
基金supported by the National Key R&D Program of China(2022YFE0115600)the Key Research and Development Program of Zhejiang Province(2022C02045).
文摘Multi-floor buildings for raising pigs have recently attracted widespread attention as an emerging form of intensive livestock production especially in eastern China,due to the fact that they can feed a much larger number of animals per unit area of land and thus alleviate the shortage of land available for standard single-floor pig production facilities.However,this more intensive kind of pig building will pose new challenges to the local environment in terms of pollutant dispersion.To compare the dispersion air pollutants(ammonia as a representative)emitted from multi-versus single-floor pig buildings,ammonia dispersion distance and concentration gradients were investigated through three-dimensional simulations based on computational fluid dynamics.The validation of an isolated cubic model was made to ensure the simulation method was effective.The effects of wind direction,wind speed and emission source concentration at 1.5 m(approximate human inhalation height)during summer were investigated.The results showed that the ammonia dispersion distance of the multi-floor pig building was far greater than that of the single-floor building on a plane of Z=1.5 m.When the wind direction was 67.5°,the wind speed was 2 m·s^(−1) and the emission source concentration was 20 ppmv,the dispersion distance of the multi-floor pig building could reach 1380 m.Meanwhile,the ammonia could accumulate in the yard to 7.68 ppmv.Therefore,future site selection,wind speed and source concentration need to be given serious consideration.Based on the simulation used in this study with source concentration is 20 ppmv,the multi-floor pig buildings should be located 1.4 km away from residential areas to avoid affecting residents.The results of this study should guidance for any future development of multi-floor pig buildings.
基金At the same time,the authors also appreciate the support by the fund from the Network and Data Security Key Laboratory of Sichuan Province,UESTC(NO.NDS2021-7)Sichuan Province General Education Scientific Research(NO.2019514).
文摘Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water pumps.Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention.Considering the time-consuming empirical mode decomposition(EMD)method and the more efficient classification provided by the convolutional neural network(CNN)method,a novel classification method based on incomplete empirical mode decomposition(IEMD)and dual-input dual-channel convolutional neural network(DDCNN)composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approach–This paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient(MFCC)and a neural network model of DDCNN.First,the sound signal is decomposed by IEMD to get numerous intrinsic mode functions(IMFs)and a residual(RES).Several IMFs and one RES are then extracted by MFCC features.Ultimately,the obtained features are split into two channels(IMFs one channel;RES one channel)and input into DDCNN.Findings–The Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection(MIMII dataset)is used to verify the practicability of the method.Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis.Compared with EMD,51.52% of data preprocessing time,67.25% of network training time and 63.7%of test time are saved and also improve accuracy.Research limitations/implications–This method can achieve higher accuracy in fault diagnosis with a shorter time cost.Therefore,the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/value–This method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.
基金supported by the Natural Science Foundation with grants from the National Key R&D Program of China(2018YFC2002500)National Natural Science Foundation of China(81602360,82072470,82350003,92049201)+6 种基金Key Laboratory Construction Project of Guangzhou Science and Technology Bureau(202102100007)supported by the Clinical Frontier Technology Program of the First Affiliated Hospital of Jinan University,China(No.JNU1AF-CFTP-2022-a01221)Natural Science Foundation of Guangdong Province(2021A1515012154,2019A1515011082,2017A030313665,2018A030313544,2020B1515120038)Science and Technology Projects in Guangzhou(201707010493,202102010069)Macao Foundation for Development of Science and Technology(0029/2019/A)Youth Talent Support Project of Guangzhou Association for Science&Technology(X20200301018)pilot project of clinical collaboration from National Administration of Traditional Chinese Medicine and National Health Commission of the People’s Republic of China and Logistics Support Department of the Central Military Commission。
文摘Despite the diverse roles of tripartite motif(Trim)-containing proteins in the regulation of autophagy,the innate immune response,and cell differentiation,their roles in skeletal diseases are largely unknown.We recently demonstrated that Trim21 plays a crucial role in regulating osteoblast(OB)differentiation in osteosarcoma.However,how Trim21 contributes to skeletal degenerative disorders,including osteoporosis,remains unknown.First,human and mouse bone specimens were evaluated,and the results showed that Trim21 expression was significantly elevated in bone tissues obtained from osteoporosis patients.Next,we found that global knockout of the Trim21 gene(KO,Trim2^(1-/-))resulted in higher bone mass compared to that of the control littermates.We further demonstrated that loss of Trim21 promoted bone formation by enhancing the osteogenic differentiation of bone marrow mesenchymal stem cells(BMSCs)and elevating the activity of OBs;moreover,Trim21 depletion suppressed osteoclast(OC)formation of RAW264.7 cells.In addition,the differentiation of OCs from bone marrow-derived macrophages(BMMs)isolated from Trim21^(-/-)and Ctsk-cre;Trim21^(f/f)mice was largely compromised compared to that of the littermate control mice.Mechanistically,YAP1/β-catenin signaling was identified and demonstrated to be required for the Trim21-mediated osteogenic differentiation of BMSCs.More importantly,the loss of Trim21 prevented ovariectomy(OVX)-and lipopolysaccharide(LPS)-induced bone loss in vivo by orchestrating the coupling of OBs and OCs through YAP1 signaling.Our current study demonstrated that Trim21 is crucial for regulating OB-mediated bone formation and OC-mediated bone resorption,thereby providing a basis for exploring Trim21 as a novel dual-targeting approach for treating osteoporosis and pathological bone loss.
基金This work is supported by National Natural Science Foundation of China under Grant No.U1905211 and 61702103Natural Science Foundation of Fujian Province under Grant No.2020J01167 and 2020J01169.
文摘With the development of the Internet of Things(IoT),the massive data sharing between IoT devices improves the Quality of Service(QoS)and user experience in various IoT applications.However,data sharing may cause serious privacy leakages to data providers.To address this problem,in this study,data sharing is realized through model sharing,based on which a secure data sharing mechanism,called BP2P-FL,is proposed using peer-to-peer federated learning with the privacy protection of data providers.In addition,by introducing the blockchain to the data sharing,every training process is recorded to ensure that data providers offer high-quality data.For further privacy protection,the differential privacy technology is used to disturb the global data sharing model.The experimental results show that BP2P-FL has high accuracy and feasibility in the data sharing of various IoT applications.
基金supported by the Key Program of Science and Technology of Zhejiang Province(Grant No.2023 C02050)the Open Fund of Zhejiang Institute of Freshwater Fisheries(Grant No.ZJK201905)+2 种基金the Technology Program of Department of Agriculture and Rural of Zhejiang Province,China(Grant No.2020XTTGSC01)the Rural Revitalization Project of Huzhou(No.2021ZD2039)the Fundamental Research Funds for the Central Universities(Grant No.2019QNA6005).
文摘To improve the light environment and welfare of the turtle cultured indoors,the effects of lighting mode on growth performance,cortisol level,and oxidative stress of juvenile Chinese three-keeled pond turtle,Chinemys reevesii,were investigated in this study.The experimental turtles with an initial weight of 5.61±0.09 g were reared in tanks under four different lighting modes:three groups with light(lighting the basking area and water area,LBW;lighting the water area only,LW;lighting the basking area only,LB)and control group(no light,NL).The experiment was conducted for more than six months,with each group having three replicates.After 203 d of the experiment,the turtle in the LW group exhibited higher weight gain rate(WGR)and a specific growth rate(SGR,%/d)compared to other treatments.Also,results showed that the final body weight of the turtle exposed to LW was higher than that exposed to other treatments.On the physiological level,serum cortisol level in turtles exposed to LW was significantly lower than that in other treatments.Regarding oxidative stress,the level of catalase(CAT)in turtles exposed to LW and LB was significantly lower than that exposed to LBW and NL.The malonaldehyde(MDA)activity in turtles exposed to LW was significantly lower than other treatments.Based on the growth performance and health status,it is suggested that lighting the water area only is the optimal lighting mode for the juvenile threekeeled pond turtle cultured indoors.
基金This work was supported by the National Natural Science Foundation of China(No.62166050)Yunnan Fundamental Research Projects(No.202201AS070021)Yunnan Innovation Team of Education Informatization for Nationalities,Scientific Technology Innovation Team of Educational Big Data Application Technology in University of Yunnan Province,and Yunnan Normal University Graduate Research and innovation fund in 2020(No.ysdyjs2020006).
文摘Question Generation(QG)is the task of utilizing Artificial Intelligence(AI)technology to generate questions that can be answered by a span of text within a given passage.Existing research on QG in the educational field struggles with two challenges:the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage;the other is the lack of specialized educational QG datasets.To address the challenges,a specialized QG dataset,reading comprehension dataset from examinations for QG(named RACE4QG),is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE dataset.Further,an end-to-end QG model,which can exploit the intra-and inter-sentence information to generate better questions,is proposed.In our model,the encoder utilizes a Gated Recurrent Units(GRU)network,which takes the concatenation of word embedding,answer tagging,and Graph Attention neTworks(GAT)embedding as input.The hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation,which will be fed to the decoder.Results show that our model outperforms baselines on automatic metrics and human evaluation.Consequently,the model improves the baseline by 0.44,1.32,and 1.34 on BLEU-4,ROUGE-L,and METEOR metrics,respectively,indicating the effectivity and reliability of our model.Its gap with human expectations also reflects the research potential.
基金supported by the National Natural Science Foundation of China[Grant Number 61902349].
文摘Rule-based portfolio construction strategies are rising as investmentdemand grows, and smart beta strategies are becoming a trend amonginstitutional investors. Smart beta strategies have high transparency, lowmanagement costs, and better long-term performance, but are at the risk ofsevere short-term declines due to a lack of Risk Control tools. Although thereare some methods to use historical volatility for Risk Control, it is still difficultto adapt to the rapid switch of market styles. How to strengthen the RiskControl management of the portfolio while maintaining the original advantagesof smart beta has become a new issue of concern in the industry. Thispaper demonstrates the scientific validity of using a probability prediction forposition optimization through an optimization theory and proposes a novelnatural gradient boosting (NGBoost)-based portfolio optimization method,which predicts stock prices and their probability distributions based on non-Bayesian methods and maximizes the Sharpe ratio expectation of positionoptimization. This paper validates the effectiveness and practicality of themodel by using the Chinese stock market, and the experimental results showthat the proposed method in this paper can reduce the volatility by 0.08 andincrease the expected portfolio cumulative return (reaching a maximum of67.1%) compared with the mainstream methods in the industry.
文摘To improve the operation efficiency of the photovoltaic power station complementary power generation system,an optimal allocation model of the photovoltaic power station complementary power generation capacity based on PSO-BP is proposed.Particle Swarm Optimization and BP neural network are used to establish the forecasting model,the Markov chain model is used to correct the forecasting error of the model,and the weighted fitting method is used to forecast the annual load curve,to complete the optimal allocation of complementary generating capacity of photovoltaic power stations.The experimental results show that thismethod reduces the average loss of photovoltaic output prediction,improves the prediction accuracy and recall rate of photovoltaic output prediction,and ensures the effective operation of the power system.
