To enhance the Young’s modulus(E)and strength of titanium alloys,we designed titanium matrix composites with intercon-nected microstructure based on the Hashin-Shtrikman theory.According to the results,the in-situ re...To enhance the Young’s modulus(E)and strength of titanium alloys,we designed titanium matrix composites with intercon-nected microstructure based on the Hashin-Shtrikman theory.According to the results,the in-situ reaction yielded an interconnected microstructure composed of Ti_(2)C particles when the Ti_(2)C content reached 50vol%.With widths of 10 and 230 nm,the intraparticle Ti lamellae in the prepared composite exhibited a bimodal size distribution due to precipitation and the unreacted Ti phase within the grown Ti_(2)C particles.The composites with interconnected microstructure attained superior properties,including E of 174.3 GPa and ultimate flexural strength of 1014 GPa.Compared with that of pure Ti,the E of the composite was increased by 55% due to the high Ti_(2)C content and interconnected microstructure.The outstanding strength resulted from the strong interfacial bonding,load-bearing capacity of interconnected Ti_(2)C particles,and bimodal intraparticle Ti lamellae,which minimized the average crack driving force.Interrupted flexural tests revealed preferential crack initiation along the{001}cleavage plane and grain boundary of Ti_(2)C in the region with the highest tensile stress.In addition,the propagation can be efficiently inhibited by interparticle Ti grains,which prevented the brittle fracture of the composites.展开更多
Systematic Review and Meta-analysis are techniques which attempt to associate the findings from similar studies and deliver quantitative summaries of the research literature [1]. The Systematic review of research...Systematic Review and Meta-analysis are techniques which attempt to associate the findings from similar studies and deliver quantitative summaries of the research literature [1]. The Systematic review of research literature identifies the common research methods, research design, sample size, parameters used, survey instruments, etc. used by the group of researchers. This study intends to fulfill this purpose in order to identify common research mythologies, dependent variables, sample sizes, moderators and mediators used in the field of analysing technology adoption based studies that utilizes the UTAUT2 model. This research collected over 59 published articles and conducted descriptive analytics. The results have revealed performance expectancy/perceived usefulness, trust and habit as the best predictors of consumer behavioural intentions towards the adoption of mobile application. Behavioural intention was the best predictor of use behaviour among the 57 articles selected. 274 was the mean sample size of research with 25 mean questionnaire items. SPSS and AMOS were the most common softwares used in all 57 studies, and 32 of those studies used UTAUT1 model while 14 researches incorporated the UTAUT2 model. There were also two promising predictors such as perceived risk on behavioural intention and habit on use behaviour.展开更多
The use of freely-available multi-source imagery for mapping vegetation in montane terrain is important for many developing countries that do not have the funding for high-resolution data capture.Radar images are also...The use of freely-available multi-source imagery for mapping vegetation in montane terrain is important for many developing countries that do not have the funding for high-resolution data capture.Radar images are also now freely available and include Sentinel-1 in dual polarisation,and PALSAR-2.These images can penetrate cloud cover and provide the advantage of acquiring data in a cloudy tropical region.This research evaluated whether the addition of radar with optical and topographic data improves classification accuracy in a montane region in Sri Lanka.Six classification experiments were designed based on different combinations of image data to test whether radar data improved land cover classification accuracy compared with optical data alone.Random forest classifier in the Google Earth Engine has been utilised to classify the tropical montane vegetation.The results indicate that radar or optical data alone cannot obtain satisfactory results.However,when combining radar with optical data the overall accuracy increased by approximately 5%,and by an additional 2%when topography data were added.The highest accuracy(92%)was achieved with multiple imagery,and adding the vegetation indices improved the model slightly by 0.3%.In addition,feature importance analysis showed that radar data makes a significant contribution to the classification.These positive outcomes demonstrate that freely-accessible multi-source remotely-sensed data have impressive capability for vegetation mapping,and support the monitoring and managing of forest ecological resources in tropical montane regions.展开更多
Using a recent stock market liberalization reform policy in China—the Stock Connect—as a quasi-natural experiment,this study examines the effect of stock market liberalization on market efficiency.Employing a datase...Using a recent stock market liberalization reform policy in China—the Stock Connect—as a quasi-natural experiment,this study examines the effect of stock market liberalization on market efficiency.Employing a dataset of 17,086 Chinese listed firms covering 2009 to 2018,we find that stock market liberalization improves the market efficiency of the Chinese mainland stock market.We further explore the potential channels through which the Stock Connect can enhance the efficiency of the A-share(A-shares refer to shares issued by Chinese companies incorporated in China's Mainland,traded in the Shanghai Stock Exchange and the Shenzhen Stock Exchange.They are denominated in Chinese RMB(the local currency).A-shares were restricted to local Chinese investors before 2003,are open to foreign investors via the Qualified Foreign Institutional Investor,RMB Qualified Foreign Institutional Investor,or the Stock Connect programs.)market.The findings show that liberalizing capital markets could benefit local market efficiency by increasing stock price informational efficiency and improving corporate governance quality.The additional analysis shows that stock market liberalization has a significant and positive impact on local market efficiency,enhancing firm value and reducing stock crash risk.We conduct various robustness checks to corroborate our findings.This study provides important policy implications for emerging countries liberalizing capital markets for foreign investors.展开更多
Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes over...Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more complex.The existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s performance.We analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream classification.Precision, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority classes.The study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.展开更多
The proliferation of internet communication channels has increased telecom fraud,causing billions of euros in losses for customers and the industry each year.Fraudsters constantly find new ways to engage in illegal ac...The proliferation of internet communication channels has increased telecom fraud,causing billions of euros in losses for customers and the industry each year.Fraudsters constantly find new ways to engage in illegal activity on the network.To reduce these losses,a new fraud detection approach is required.Telecom fraud detection involves identifying a small number of fraudulent calls from a vast amount of call traffic.Developing an effective strategy to combat fraud has become challenging.Although much effort has been made to detect fraud,most existing methods are designed for batch processing,not real-time detection.To solve this problem,we propose an online fraud detection model using a Neural Factorization Autoencoder(NFA),which analyzes customer calling patterns to detect fraudulent calls.The model employs Neural Factorization Machines(NFM)and an Autoencoder(AE)to model calling patterns and a memory module to adapt to changing customer behaviour.We evaluate our approach on a large dataset of real-world call detail records and compare it with several state-of-the-art methods.Our results show that our approach outperforms the baselines,with an AUC of 91.06%,a TPR of 91.89%,an FPR of 14.76%,and an F1-score of 95.45%.These results demonstrate the effectiveness of our approach in detecting fraud in real-time and suggest that it can be a valuable tool for preventing fraud in telecommunications networks.展开更多
The control of oxygen is paramount in achieving high-performance titanium(Ti)parts by powder metallurgy such as metal in-jection molding(MIM).In this study,we purposely selected the Ti and Ti-6Al-4V powders as the ref...The control of oxygen is paramount in achieving high-performance titanium(Ti)parts by powder metallurgy such as metal in-jection molding(MIM).In this study,we purposely selected the Ti and Ti-6Al-4V powders as the reference materials since these two are the most representative Ti materials in the industry.Herein,hydride-dehydride(HDH)Ti powders were pre-oxidized to examine the ef-fect of oxygen variation on the characteristics of oxide layer on the particle surface and its resultant color feature.The results indicate that the thickness and Ti oxide level(Ti^(0)→Ti^(4+))of the oxide layer on the HDH Ti powders increased as the oxygen content increased,lead-ing to the transition of color appearance from grey,brown to blue.This work aids in the powder feedstock selection at the initial stage in powder metallurgy.In addition,the development of oxygen content was comprehensively studied during the MIM process using the gas-atomized(GA)Ti-6Al-4V powders.Particularly,the oxygen variation in the form of oxide layer,the change of oxygen content in the powders,and the relevant parts were investigated during the processes of kneading,injection,debinding,and sintering.The oxygen vari-ation was mainly concentrated in the sintering stage,and the content increased with the increase of sintering temperature.The variation of oxygen content during the MIM process demonstrates the crucial role of powder feedstock and sintering stage in controlling oxygen con-tent.This work provides a piece of valuable information on oxygen detecting,control,and manipulation for the powder and processing in the industry of Ti and its alloys by powder metallurgy.展开更多
Probability assessment in some scenarios may involve unusual aspects such as requiring certain values for some events and extremely high or low probabilities in other cases.
AIM: To investigate the association of colorectal adenomas with both Helicobacter pylori (H. pylori) infection and metabolic syndrome. METHODS: Using a cross-sectional hospital-based study, we analyzed physical examin...AIM: To investigate the association of colorectal adenomas with both Helicobacter pylori (H. pylori) infection and metabolic syndrome. METHODS: Using a cross-sectional hospital-based study, we analyzed physical examination data from 9311 healthy subjects with overnight physical examinations performed between January 2004 and December 2006. Examined data included gender, age, life style, anthropometric measurements, blood pressure, biochemical and hematological studies, H. pylori infection detected by esophagogastroduodenoscopy and biopsy urease tests, and colorectal adenomas detected with a complete total colonoscopy. RESULTS: The prevalence values for H. pylori infection, metabolic syndrome, and colorectal adenoma were39.2%, 18.7%, and 20.7%, respectively. Colorectal adenoma risk factors included male gender [odd ratio (OR): 2.005, 95% conf idence interval (CI): 1.740-2.310, P < 0.001], advanced age (OR: 1.046, 95% CI: 1.040-1.052, P < 0.001), smoking (OR: 1.377, 95% CI: 1.146-1.654, P = 0.001), increased body fat (OR: 1.016, 95% CI: 1.007-1.026, P = 0.001), higher white blood cell count (OR: 1.038, 95% CI: 1.005-1.073, P = 0.025), H. pylori infection (OR: 1.366, 95% CI: 1.230-1.517, P < 0.001), and metabolic syndrome (OR: 1.408, 95% CI: 1.231-1.610, P < 0.001). In addition, concomitant H. pylori infection with metabolic syndrome further increased the probability of colorectal adenomas. CONCLUSION: Our study revealed H. pylori infection with concomitant metabolic syndrome might further increase the risk of colorectal adenomas.展开更多
The Cr, Zn, Cu, Cd, Pb contents were determined in Cyprinus carpio Linnaeus, Carassius auratus Linnaeus, Hypophthalmichthys molitrix and Aristichthys nobilis, which were caught from Meiliang Bay, Taihu Lake, a large, ...The Cr, Zn, Cu, Cd, Pb contents were determined in Cyprinus carpio Linnaeus, Carassius auratus Linnaeus, Hypophthalmichthys molitrix and Aristichthys nobilis, which were caught from Meiliang Bay, Taihu Lake, a large, shallow and eutrophic lake of China. The results showed that: (1) the Cr, Cu, Pb, Cd contents in the edible parts of the four fish species were much lower than Chinese Food Health Criterion (1994), but the Zn contents were higher than the Criterion; (2) Cd contents were the highest in the liver of fish, Pb contents were almost the same in all organs of fish, Cr contents mainly enriched in the skin and gonads, Zn contents were the highest in the gonad (♀), and Cu contents were the highest in the liver; (3) the total metal accumulation was the greatest in the liver and the lowest in the muscle. The total metal accumulation was the highest in C. auratus L. This investigation indicated that fish products in Taihu Lake were still safe for human consumption, but the amount consumed should be controlled under the Chinese Food Health Criterion to avoid excessive intake of Zn.展开更多
Using a logistic model,this paper empirically investigated farmers’perception of climate change and its determinants based on a field survey of 1 350 rural households across five major grain producing provinces in Ch...Using a logistic model,this paper empirically investigated farmers’perception of climate change and its determinants based on a field survey of 1 350 rural households across five major grain producing provinces in China.The results show:i)There is an apparent difference in perception levels for long-term temperature and precipitation changes.Specifically,57.4%of farmers perceived the long-term temperature change correctly,but only 29.7%of farmers perceived the long-term precipitation change correctly;ii)The factors influencing the farmers’perceptions are almost completely different between precipitation and temperature,the former are mostly agriculture related,while latter are mostly non-agriculture related,except for farm size;and iii)Farmers are not expected to pay more attention to long-term precipitation changes over the crop growing seasons,because less than 30%of farmers can correctly perceive long-term precipitation change.Therefore,to improve the accuracy of farmers’perceptions of climate change,the government is recommended to:i)enhance education and training programs;ii)speed up land transfer and expand household land farm size;iii)develop farmer cooperative organizations;iv)invest more in agricultural infrastructure,specifically in major grain producing regions;and v)improve the agricultural environment and increase farming income.展开更多
Water availability is a major constraint on grain production in China, therefore, improving irrigation efficiency is particularly important when agriculture faces extreme weather events. This paper first calculates ir...Water availability is a major constraint on grain production in China, therefore, improving irrigation efficiency is particularly important when agriculture faces extreme weather events. This paper first calculates irrigation efficiency with a translog stochastic frontier production function and then investigates what happens when extreme weather events occur via a Tobit model. The estimated results reveal several important features of irrigation practices: i) irrigation efficiency is lower when extreme weather events occur; ii) large variations in irrigation efficiency occur across irrigation facilities; iii) the farm plots exhibit an extreme distribution across efficiency levels; and iv) water-saving techniques, technology adoption, and the maintenance of farmers’ economic resilience are major determinants of irrigation efficiency. Based on these results we propose the following recommendations: i) farmers should balance crop yield and water use; undertake relevant training programs and adopt water-saving techniques; ii) local governments and researchers should help farmers to find the optimal level of irrigation water use based on their own circumstances and provide better water-saving techniques and training programs rather than simply encouraging farmers to invest in irrigation facilities in the most extreme weather years; and iii) the income level of farm households should be increased so as to improve their resilience to natural disasters.展开更多
The Tarim Basin is a representative example of the basins developed in the northwest China that are characterized by multiple stages of heating and cooling.In order to better understand its complex thermal history,apa...The Tarim Basin is a representative example of the basins developed in the northwest China that are characterized by multiple stages of heating and cooling.In order to better understand its complex thermal history,apatite fission track (AFT) thermochronology was applied to borehole samples from the Tazhong Uplift Zone (TUZ).Twelve sedimentary samples of Silurian to Triassic depositional ages were analyzed from depths coinciding with the apatite partial annealing zone (~60-120 ℃).The AFT ages,ranging from 132 ± 7 Ma (from a Triassic sample) to 25 ± 2 Ma (from a Carboniferous sample),are clearly younger than their depositional ages and demonstrate a total resetting of the AFT thermometer after deposition.The AFT ages vary among different tectonic belts and decrease from the No.Ten Faulted Zone (133-105 Ma) in the northwest,the Central Horst Zone in the middle (108-37 Ma),to the East Buried Hill Zone in the south (51 25 Ma).Given the low magnitude of post-Triassic burial heating evidenced by low vitrinite reflectance values (Ro < 0.7%),the total resetting of the AFT system is speculated to result from the hot fluid flow along the faults.Thermal effects along the faults are well documented by younger AFT ages and unimodal single grain age distributions in the vicinity of the faults.Permian-early Triassic basaltic volcanism may be responsible for the early Triassic total annealing of those samples lacking connectivity with the fault.The above arguments are supported by thermal modeling results.展开更多
Purpose We compared running economy(RE)and 3-km time-trial(TT)variables of runners wearing Nike Vaporfly 4%(VP4),Saucony Endorphin lightweight racing flats(FLAT),and their habitual running(OWN)footwear.Methods Eightee...Purpose We compared running economy(RE)and 3-km time-trial(TT)variables of runners wearing Nike Vaporfly 4%(VP4),Saucony Endorphin lightweight racing flats(FLAT),and their habitual running(OWN)footwear.Methods Eighteen male recreational runners(age=33.5±11.9 year(mean±SD),peak oxygen uptake(VO_(2peak))=55.8±4.4 mL/kg·min)attended 4 sessions approximately 7 days apart.The first session consisted of a VO_(2peak) test to inform subsequent RE speeds set at 60%,70%,and 80%of the speed eliciting VO2peak.In subsequent sessions,treadmill RE and 3-km TTs were assessed in the 3 footwear conditions in a randomized,counterbalanced crossover design.Results Oxygen consumption(mL/kg·min)was less in VP4(from 4.3%to 4.4%,p≤0.002)and FLAT(from 2.7%to 3.4%,p≤0.092)vs.OWN across intensities,with a non-significant difference between VP4 and FLAT(1.0%-1.7%,p≥0.292).Findings related to energy cost(W/kg)and energetics cost of transport(J/kg·m)were comparable.VP43-km TT performance(11:07.6±0:56.6 mm:ss)was enhanced vs.OWN by 16.6 s(2.4%,p=0.005)and vs.FLAT by 13.0 s(1.8%,p=0.032).The 3-km times between OWN and FLAT(0.5%,p=0.747)were similar.Most runners(n=11,61%)ran their fastest TT in VP4.Conclusion Overall,VP4 improved laboratory-based RE measures in male recreational runners at relative speeds compared to OWN,but the RE improvements in VP4 were not significant vs.FLAT.More runners exhibited better treadmill TT performances in VP4(61%)vs.FLAT(22%)and OWN(17%).The variability in RE(-10.3%to 13.3%)and TT(-4.7%to 9.3%)improvements suggests that responses to different types of shoes are individualized and warrant further investigation.展开更多
Purpose:The aim of this study was to evaluate the efficacy of a 17-week,3-component lifestyle intervention for enhancing health behaviors during the coronavirus disease 2019(COVID-19)pandemic.Methods:A parallel-group(...Purpose:The aim of this study was to evaluate the efficacy of a 17-week,3-component lifestyle intervention for enhancing health behaviors during the coronavirus disease 2019(COVID-19)pandemic.Methods:A parallel-group(intervention and control)study was conducted amongst 79 airline pilots over a 17-week period during the COVID-19 pandemic.The intervention group(n=38)received a personalized sleep,dietary,and physical activity(PA)program.The control group(n=41)received no intervention.Outcome measures for sleep,fruit and vegetable intake,PA,and subjective health were measured though an online survey before and after the 17-week period.The changes in outcome measures were used to determine the efficacy of the intervention.Results:Significant main effects for time£group were found for International Physical Activity Questionnaire-walk(p=0.02)and for all other outcome measures(p<0.01).The intervention group significantly improved in sleep duration(p<0.01;d=1.35),Pittsburgh Sleep Quality Index score(p<0.01;d=1.14),moderate-to-vigorous PA(p<0.01;d=1.44),fruit and vegetable intake(p<0.01;d=2.09),Short Form 12v2 physical score(p<0.01;d=1.52),and Short Form 12v2 mental score(p<0.01;d=2.09).The control group showed significant negative change for sleep duration,Pittsburgh Sleep Quality Index score,and Short Form 12v2 mental score(p<0.01).Conclusion:Results provide preliminary evidence that a 3-component healthy sleep,eating,and PA intervention elicit improvements in health behaviors and perceived subjective health in pilots and may improve quality of life during an unprecedented global pandemic.展开更多
The Songliao Basin is famous for the Daqing Oilfield, the biggest in China. However, no economic hydrocarbon reservoir has been found in the northeastern Binbei district. Its thermal history, which is of great importa...The Songliao Basin is famous for the Daqing Oilfield, the biggest in China. However, no economic hydrocarbon reservoir has been found in the northeastern Binbei district. Its thermal history, which is of great importance for hydrocarbon generation and migration, is studied with apatite fission track (AFT) thermochronology. Samples with depositional ages of the late Cretaceous (-108-73 Ma) are analyzed. The AFT ages of the samples from reservoir rock (depositional age 〉 76.1 Ma) fall between the late Cretaceous (724-5 Ma) and the early Eocene (414-3 Ma) period, indicating their total annealing after deposition. In contrast, two samples from the main seals of the Qingshankou (depositional age 〉 89.3 Ma) and the Nenjiang Formation (depositional age 〉 73.0 Ma) are not annealed or partially annealed (AFT ages of 974-9 Ma and 704-4 Ma, respectively). Because the maximum burial temperature (〈90 ℃) evidenced by low vitrinite reflectance (Ro〈0.7) is not high enough to account for the AFT total annealing (110-120 ℃), the transient thermal effect arising from the syntectonic fluid flow between the late Cretaceous and the early Eocene is proposed. Transient thermal effects from fluid flow explains the indicated temperature discrepancies between the AFT thermometer and the Ro thermometer because the transient thermal effect from the fluid flow with a temperature high enough (110-120 ℃) to anneal the AFT thermometer does not last long enough (104-105 yrs.) for an enhancement of the Ro (minimum 106- 107 yrs. under the same temperature). This indicates that dating thermal effect from fluid flow might be a new means to reconstruct the tectonic history. It also answers why the samples from the main seals are not annealed because the seals will prohibit fluid flow and supply good thermal insulation. The large-scale fluid flow in the Binbei district calls for a new idea to direct the hydrocarbon exploration.展开更多
From 1985, an increasing gap has emerged between the official statistical measures of meat production and meat consumption in China, which has raised concerns from many researchers using such data. In this paper we re...From 1985, an increasing gap has emerged between the official statistical measures of meat production and meat consumption in China, which has raised concerns from many researchers using such data. In this paper we report the results of 428 observations(survey of 107 urban and rural households×4 quarters) from 7 provinces conducted in 2010, and compare them with the official statistical data from the National Bureau of Statistics of China(NBSC). We conclude that the main reason for the discrepancy is due to the underreporting of consumption, which is due mainly to the omission of consumption away from home.展开更多
Multifaceted events in an organizational environment usually need to be assigned probabilities as a prerequisite to analytical decision-making. If the decision situation is unique, a lack of relevant historical freque...Multifaceted events in an organizational environment usually need to be assigned probabilities as a prerequisite to analytical decision-making. If the decision situation is unique, a lack of relevant historical frequency data may preclude use of traditional probability models such as the normal, binomial etc. In this case, an individual decision maker (DM) or an informed group of persons can input into a procedure as outlined here to determine a probability distribution that leads to the expected values of alternative actions or fair values of securities. The individual or group member must decide qualitatively on the extent to which one event is "more likely" than another where both events are ranked adjacent (i.e., closest to each other) in terms of likelihood. Even though the individual or group members may lack experience in orthodox probability assessment, these pairwise "more likely" judgments on the relative likelihood of events are not overly demanding for persons familiar with the possible outcomes in the situation under analysis.展开更多
The Greenland ice core from NorthGRIP (NGRIP) contains a proxy climate record across the Pleistocene-Holocene boundary of unprecedented clarity and resolution. Analysis of an array of physical and chemical parameter...The Greenland ice core from NorthGRIP (NGRIP) contains a proxy climate record across the Pleistocene-Holocene boundary of unprecedented clarity and resolution. Analysis of an array of physical and chemical parameters within the ice enables the base of the Holocene, as reflected in the first signs of climatic warming at the end of the Younger Dryas/Greenland Stadial 1 cold phase, to be located with a high degree of precision.展开更多
Land cover classification of mountainous environments continues to be a challenging remote sensing problem,owing to landscape complexities exhibited by the region.This study explored a multiple classifier system(MCS)a...Land cover classification of mountainous environments continues to be a challenging remote sensing problem,owing to landscape complexities exhibited by the region.This study explored a multiple classifier system(MCS)approach to the classification of mountain land cover for the Khumbu region in the Himalayas using Sentinel-2 images and a cloud-based model framework.The relationship between classification accuracy and MCS diversity was investigated,and the effects of different diversification and combination methods on MCS classification performance were comparatively assessed for this environment.We present ten MCS models that implement a homogeneous ensemble approach,using the high performing Random Forest(RF)algorithm as the selected classifier.The base classifiers of each MCS model were developed using different combinations of three diversity techniques:(1)distinct training sets,(2)Mean Decrease Accuracy feature selection,and(3)‘One-vs-All’problem reduction.The base classifier predictions of each RFMCS model were combined using:(1)majority vote,(2)weighted argmax,and(3)a meta RF classifier.All MCS models reported higher classification accuracies than the benchmark classifier(overall accuracy with 95% confidence interval:87.33%±0.97%),with the highest performing model reporting an overall accuracy(±95% confidence interval)of 90.95%±0.84%.Our key findings include:(1)MCS is effective in mountainous environments prone to noise from landscape complexities,(2)problem reduction is indicated as a stronger method over feature selection in improving the diversity of the MCS,(3)although the MCS diversity and accuracy have a positive correlation,our results suggest this is a weak relationship for mountainous classifications,and(4)the selected diversity methods improve the discriminability of MCS against vegetation and forest classes in mountainous land cover classifications and exhibit a cumulative effect on MCS diversity for this context.展开更多
基金financially supported by the National Key R&D Program of China(No.2021YFB3701203)the National Natural Science Foundation of China(Nos.U22A20113,52201116,52071116,and 52261135543)+1 种基金Heilongjiang Touyan Team ProgramChina Postdoctoral Science Foundation(No.2022M710939).
文摘To enhance the Young’s modulus(E)and strength of titanium alloys,we designed titanium matrix composites with intercon-nected microstructure based on the Hashin-Shtrikman theory.According to the results,the in-situ reaction yielded an interconnected microstructure composed of Ti_(2)C particles when the Ti_(2)C content reached 50vol%.With widths of 10 and 230 nm,the intraparticle Ti lamellae in the prepared composite exhibited a bimodal size distribution due to precipitation and the unreacted Ti phase within the grown Ti_(2)C particles.The composites with interconnected microstructure attained superior properties,including E of 174.3 GPa and ultimate flexural strength of 1014 GPa.Compared with that of pure Ti,the E of the composite was increased by 55% due to the high Ti_(2)C content and interconnected microstructure.The outstanding strength resulted from the strong interfacial bonding,load-bearing capacity of interconnected Ti_(2)C particles,and bimodal intraparticle Ti lamellae,which minimized the average crack driving force.Interrupted flexural tests revealed preferential crack initiation along the{001}cleavage plane and grain boundary of Ti_(2)C in the region with the highest tensile stress.In addition,the propagation can be efficiently inhibited by interparticle Ti grains,which prevented the brittle fracture of the composites.
文摘Systematic Review and Meta-analysis are techniques which attempt to associate the findings from similar studies and deliver quantitative summaries of the research literature [1]. The Systematic review of research literature identifies the common research methods, research design, sample size, parameters used, survey instruments, etc. used by the group of researchers. This study intends to fulfill this purpose in order to identify common research mythologies, dependent variables, sample sizes, moderators and mediators used in the field of analysing technology adoption based studies that utilizes the UTAUT2 model. This research collected over 59 published articles and conducted descriptive analytics. The results have revealed performance expectancy/perceived usefulness, trust and habit as the best predictors of consumer behavioural intentions towards the adoption of mobile application. Behavioural intention was the best predictor of use behaviour among the 57 articles selected. 274 was the mean sample size of research with 25 mean questionnaire items. SPSS and AMOS were the most common softwares used in all 57 studies, and 32 of those studies used UTAUT1 model while 14 researches incorporated the UTAUT2 model. There were also two promising predictors such as perceived risk on behavioural intention and habit on use behaviour.
文摘The use of freely-available multi-source imagery for mapping vegetation in montane terrain is important for many developing countries that do not have the funding for high-resolution data capture.Radar images are also now freely available and include Sentinel-1 in dual polarisation,and PALSAR-2.These images can penetrate cloud cover and provide the advantage of acquiring data in a cloudy tropical region.This research evaluated whether the addition of radar with optical and topographic data improves classification accuracy in a montane region in Sri Lanka.Six classification experiments were designed based on different combinations of image data to test whether radar data improved land cover classification accuracy compared with optical data alone.Random forest classifier in the Google Earth Engine has been utilised to classify the tropical montane vegetation.The results indicate that radar or optical data alone cannot obtain satisfactory results.However,when combining radar with optical data the overall accuracy increased by approximately 5%,and by an additional 2%when topography data were added.The highest accuracy(92%)was achieved with multiple imagery,and adding the vegetation indices improved the model slightly by 0.3%.In addition,feature importance analysis showed that radar data makes a significant contribution to the classification.These positive outcomes demonstrate that freely-accessible multi-source remotely-sensed data have impressive capability for vegetation mapping,and support the monitoring and managing of forest ecological resources in tropical montane regions.
基金funded by the China Scholarship Council(CSC Grant No.202108360133)the Social Science Foundation of Jiangxi Province(No.22GL13&22GL43)the Science and Technology Research Project of Jiangxi Province Education Department(No.GJJ210537).
文摘Using a recent stock market liberalization reform policy in China—the Stock Connect—as a quasi-natural experiment,this study examines the effect of stock market liberalization on market efficiency.Employing a dataset of 17,086 Chinese listed firms covering 2009 to 2018,we find that stock market liberalization improves the market efficiency of the Chinese mainland stock market.We further explore the potential channels through which the Stock Connect can enhance the efficiency of the A-share(A-shares refer to shares issued by Chinese companies incorporated in China's Mainland,traded in the Shanghai Stock Exchange and the Shenzhen Stock Exchange.They are denominated in Chinese RMB(the local currency).A-shares were restricted to local Chinese investors before 2003,are open to foreign investors via the Qualified Foreign Institutional Investor,RMB Qualified Foreign Institutional Investor,or the Stock Connect programs.)market.The findings show that liberalizing capital markets could benefit local market efficiency by increasing stock price informational efficiency and improving corporate governance quality.The additional analysis shows that stock market liberalization has a significant and positive impact on local market efficiency,enhancing firm value and reducing stock crash risk.We conduct various robustness checks to corroborate our findings.This study provides important policy implications for emerging countries liberalizing capital markets for foreign investors.
基金The authors would like to extend their gratitude to Universiti Teknologi PETRONAS (Malaysia)for funding this research through grant number (015LA0-037).
文摘Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more complex.The existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s performance.We analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream classification.Precision, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority classes.The study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.
基金This research work has been conducted in cooperation with members of DETSI project supported by BPI France and Pays de Loire and Auvergne Rhone Alpes.
文摘The proliferation of internet communication channels has increased telecom fraud,causing billions of euros in losses for customers and the industry each year.Fraudsters constantly find new ways to engage in illegal activity on the network.To reduce these losses,a new fraud detection approach is required.Telecom fraud detection involves identifying a small number of fraudulent calls from a vast amount of call traffic.Developing an effective strategy to combat fraud has become challenging.Although much effort has been made to detect fraud,most existing methods are designed for batch processing,not real-time detection.To solve this problem,we propose an online fraud detection model using a Neural Factorization Autoencoder(NFA),which analyzes customer calling patterns to detect fraudulent calls.The model employs Neural Factorization Machines(NFM)and an Autoencoder(AE)to model calling patterns and a memory module to adapt to changing customer behaviour.We evaluate our approach on a large dataset of real-world call detail records and compare it with several state-of-the-art methods.Our results show that our approach outperforms the baselines,with an AUC of 91.06%,a TPR of 91.89%,an FPR of 14.76%,and an F1-score of 95.45%.These results demonstrate the effectiveness of our approach in detecting fraud in real-time and suggest that it can be a valuable tool for preventing fraud in telecommunications networks.
基金financially supported by the National Key Research and Development Program of China(No.2021 YFB3701900)the National Natural Science Foundation Program of China(No.51971036)the Open Research Fund of State Key Laboratory of Mesoscience and Engineering(No.MESO-23-D07).
文摘The control of oxygen is paramount in achieving high-performance titanium(Ti)parts by powder metallurgy such as metal in-jection molding(MIM).In this study,we purposely selected the Ti and Ti-6Al-4V powders as the reference materials since these two are the most representative Ti materials in the industry.Herein,hydride-dehydride(HDH)Ti powders were pre-oxidized to examine the ef-fect of oxygen variation on the characteristics of oxide layer on the particle surface and its resultant color feature.The results indicate that the thickness and Ti oxide level(Ti^(0)→Ti^(4+))of the oxide layer on the HDH Ti powders increased as the oxygen content increased,lead-ing to the transition of color appearance from grey,brown to blue.This work aids in the powder feedstock selection at the initial stage in powder metallurgy.In addition,the development of oxygen content was comprehensively studied during the MIM process using the gas-atomized(GA)Ti-6Al-4V powders.Particularly,the oxygen variation in the form of oxide layer,the change of oxygen content in the powders,and the relevant parts were investigated during the processes of kneading,injection,debinding,and sintering.The oxygen vari-ation was mainly concentrated in the sintering stage,and the content increased with the increase of sintering temperature.The variation of oxygen content during the MIM process demonstrates the crucial role of powder feedstock and sintering stage in controlling oxygen con-tent.This work provides a piece of valuable information on oxygen detecting,control,and manipulation for the powder and processing in the industry of Ti and its alloys by powder metallurgy.
文摘Probability assessment in some scenarios may involve unusual aspects such as requiring certain values for some events and extremely high or low probabilities in other cases.
基金Supported by Buddhist Dalin Tzu Chi General Hospital
文摘AIM: To investigate the association of colorectal adenomas with both Helicobacter pylori (H. pylori) infection and metabolic syndrome. METHODS: Using a cross-sectional hospital-based study, we analyzed physical examination data from 9311 healthy subjects with overnight physical examinations performed between January 2004 and December 2006. Examined data included gender, age, life style, anthropometric measurements, blood pressure, biochemical and hematological studies, H. pylori infection detected by esophagogastroduodenoscopy and biopsy urease tests, and colorectal adenomas detected with a complete total colonoscopy. RESULTS: The prevalence values for H. pylori infection, metabolic syndrome, and colorectal adenoma were39.2%, 18.7%, and 20.7%, respectively. Colorectal adenoma risk factors included male gender [odd ratio (OR): 2.005, 95% conf idence interval (CI): 1.740-2.310, P < 0.001], advanced age (OR: 1.046, 95% CI: 1.040-1.052, P < 0.001), smoking (OR: 1.377, 95% CI: 1.146-1.654, P = 0.001), increased body fat (OR: 1.016, 95% CI: 1.007-1.026, P = 0.001), higher white blood cell count (OR: 1.038, 95% CI: 1.005-1.073, P = 0.025), H. pylori infection (OR: 1.366, 95% CI: 1.230-1.517, P < 0.001), and metabolic syndrome (OR: 1.408, 95% CI: 1.231-1.610, P < 0.001). In addition, concomitant H. pylori infection with metabolic syndrome further increased the probability of colorectal adenomas. CONCLUSION: Our study revealed H. pylori infection with concomitant metabolic syndrome might further increase the risk of colorectal adenomas.
基金Projects supported by the National Natural Science Foundation of China(No.40673078,40203007).
文摘The Cr, Zn, Cu, Cd, Pb contents were determined in Cyprinus carpio Linnaeus, Carassius auratus Linnaeus, Hypophthalmichthys molitrix and Aristichthys nobilis, which were caught from Meiliang Bay, Taihu Lake, a large, shallow and eutrophic lake of China. The results showed that: (1) the Cr, Cu, Pb, Cd contents in the edible parts of the four fish species were much lower than Chinese Food Health Criterion (1994), but the Zn contents were higher than the Criterion; (2) Cd contents were the highest in the liver of fish, Pb contents were almost the same in all organs of fish, Cr contents mainly enriched in the skin and gonads, Zn contents were the highest in the gonad (♀), and Cu contents were the highest in the liver; (3) the total metal accumulation was the greatest in the liver and the lowest in the muscle. The total metal accumulation was the highest in C. auratus L. This investigation indicated that fish products in Taihu Lake were still safe for human consumption, but the amount consumed should be controlled under the Chinese Food Health Criterion to avoid excessive intake of Zn.
基金supported by the National Social Science Fund of China (14BGL093)the International Development Research Center (107093-001)+4 种基金the Specialized Research Fund for the Jointed Doctoral Program of Higher Education of China (20124105110006)the National Natural Science Foundation of China (71403082)the 2017 Annual Scientific and Technological Innovation of Henan Province Talent (Humanities and Social Sciences) Support Program, China (2017-cxrc-002)the Young Backbone Teachers Scheme of Henan Colleges and Universities, China (2015GGJS-085)the Henan Province Philosophy and Social Science Planning Project, China (2017BJJ033)
文摘Using a logistic model,this paper empirically investigated farmers’perception of climate change and its determinants based on a field survey of 1 350 rural households across five major grain producing provinces in China.The results show:i)There is an apparent difference in perception levels for long-term temperature and precipitation changes.Specifically,57.4%of farmers perceived the long-term temperature change correctly,but only 29.7%of farmers perceived the long-term precipitation change correctly;ii)The factors influencing the farmers’perceptions are almost completely different between precipitation and temperature,the former are mostly agriculture related,while latter are mostly non-agriculture related,except for farm size;and iii)Farmers are not expected to pay more attention to long-term precipitation changes over the crop growing seasons,because less than 30%of farmers can correctly perceive long-term precipitation change.Therefore,to improve the accuracy of farmers’perceptions of climate change,the government is recommended to:i)enhance education and training programs;ii)speed up land transfer and expand household land farm size;iii)develop farmer cooperative organizations;iv)invest more in agricultural infrastructure,specifically in major grain producing regions;and v)improve the agricultural environment and increase farming income.
基金supported by the State Social Science Funds of China (14BGL093)the Specialized Research Fund for the Jointed Doctoral Program of Higher Education of China (20124105110006)the International Development Research Center (107093-001)
文摘Water availability is a major constraint on grain production in China, therefore, improving irrigation efficiency is particularly important when agriculture faces extreme weather events. This paper first calculates irrigation efficiency with a translog stochastic frontier production function and then investigates what happens when extreme weather events occur via a Tobit model. The estimated results reveal several important features of irrigation practices: i) irrigation efficiency is lower when extreme weather events occur; ii) large variations in irrigation efficiency occur across irrigation facilities; iii) the farm plots exhibit an extreme distribution across efficiency levels; and iv) water-saving techniques, technology adoption, and the maintenance of farmers’ economic resilience are major determinants of irrigation efficiency. Based on these results we propose the following recommendations: i) farmers should balance crop yield and water use; undertake relevant training programs and adopt water-saving techniques; ii) local governments and researchers should help farmers to find the optimal level of irrigation water use based on their own circumstances and provide better water-saving techniques and training programs rather than simply encouraging farmers to invest in irrigation facilities in the most extreme weather years; and iii) the income level of farm households should be increased so as to improve their resilience to natural disasters.
基金supported by the National Program on Key Basic Research Project(973 Program)(Grant Nos.2006CB202308 and 2011CB201100)the Major National Science&Technology Program(Grant Nos.2011ZX05006-005 and 2011ZX05006-006)the National Natural Science Foundation of China(Grant Nos.40872097 and41272161)
文摘The Tarim Basin is a representative example of the basins developed in the northwest China that are characterized by multiple stages of heating and cooling.In order to better understand its complex thermal history,apatite fission track (AFT) thermochronology was applied to borehole samples from the Tazhong Uplift Zone (TUZ).Twelve sedimentary samples of Silurian to Triassic depositional ages were analyzed from depths coinciding with the apatite partial annealing zone (~60-120 ℃).The AFT ages,ranging from 132 ± 7 Ma (from a Triassic sample) to 25 ± 2 Ma (from a Carboniferous sample),are clearly younger than their depositional ages and demonstrate a total resetting of the AFT thermometer after deposition.The AFT ages vary among different tectonic belts and decrease from the No.Ten Faulted Zone (133-105 Ma) in the northwest,the Central Horst Zone in the middle (108-37 Ma),to the East Buried Hill Zone in the south (51 25 Ma).Given the low magnitude of post-Triassic burial heating evidenced by low vitrinite reflectance values (Ro < 0.7%),the total resetting of the AFT system is speculated to result from the hot fluid flow along the faults.Thermal effects along the faults are well documented by younger AFT ages and unimodal single grain age distributions in the vicinity of the faults.Permian-early Triassic basaltic volcanism may be responsible for the early Triassic total annealing of those samples lacking connectivity with the fault.The above arguments are supported by thermal modeling results.
基金internally funded by Te Huataki Waiora School of Health,University of Waikato,New Zealandthe Running Clinic,Canada
文摘Purpose We compared running economy(RE)and 3-km time-trial(TT)variables of runners wearing Nike Vaporfly 4%(VP4),Saucony Endorphin lightweight racing flats(FLAT),and their habitual running(OWN)footwear.Methods Eighteen male recreational runners(age=33.5±11.9 year(mean±SD),peak oxygen uptake(VO_(2peak))=55.8±4.4 mL/kg·min)attended 4 sessions approximately 7 days apart.The first session consisted of a VO_(2peak) test to inform subsequent RE speeds set at 60%,70%,and 80%of the speed eliciting VO2peak.In subsequent sessions,treadmill RE and 3-km TTs were assessed in the 3 footwear conditions in a randomized,counterbalanced crossover design.Results Oxygen consumption(mL/kg·min)was less in VP4(from 4.3%to 4.4%,p≤0.002)and FLAT(from 2.7%to 3.4%,p≤0.092)vs.OWN across intensities,with a non-significant difference between VP4 and FLAT(1.0%-1.7%,p≥0.292).Findings related to energy cost(W/kg)and energetics cost of transport(J/kg·m)were comparable.VP43-km TT performance(11:07.6±0:56.6 mm:ss)was enhanced vs.OWN by 16.6 s(2.4%,p=0.005)and vs.FLAT by 13.0 s(1.8%,p=0.032).The 3-km times between OWN and FLAT(0.5%,p=0.747)were similar.Most runners(n=11,61%)ran their fastest TT in VP4.Conclusion Overall,VP4 improved laboratory-based RE measures in male recreational runners at relative speeds compared to OWN,but the RE improvements in VP4 were not significant vs.FLAT.More runners exhibited better treadmill TT performances in VP4(61%)vs.FLAT(22%)and OWN(17%).The variability in RE(-10.3%to 13.3%)and TT(-4.7%to 9.3%)improvements suggests that responses to different types of shoes are individualized and warrant further investigation.
文摘Purpose:The aim of this study was to evaluate the efficacy of a 17-week,3-component lifestyle intervention for enhancing health behaviors during the coronavirus disease 2019(COVID-19)pandemic.Methods:A parallel-group(intervention and control)study was conducted amongst 79 airline pilots over a 17-week period during the COVID-19 pandemic.The intervention group(n=38)received a personalized sleep,dietary,and physical activity(PA)program.The control group(n=41)received no intervention.Outcome measures for sleep,fruit and vegetable intake,PA,and subjective health were measured though an online survey before and after the 17-week period.The changes in outcome measures were used to determine the efficacy of the intervention.Results:Significant main effects for time£group were found for International Physical Activity Questionnaire-walk(p=0.02)and for all other outcome measures(p<0.01).The intervention group significantly improved in sleep duration(p<0.01;d=1.35),Pittsburgh Sleep Quality Index score(p<0.01;d=1.14),moderate-to-vigorous PA(p<0.01;d=1.44),fruit and vegetable intake(p<0.01;d=2.09),Short Form 12v2 physical score(p<0.01;d=1.52),and Short Form 12v2 mental score(p<0.01;d=2.09).The control group showed significant negative change for sleep duration,Pittsburgh Sleep Quality Index score,and Short Form 12v2 mental score(p<0.01).Conclusion:Results provide preliminary evidence that a 3-component healthy sleep,eating,and PA intervention elicit improvements in health behaviors and perceived subjective health in pilots and may improve quality of life during an unprecedented global pandemic.
基金supported by the National Natural Science Foundation of China (Grant Nos.40872097 and 41272161)the Major National Science & Technology Program (Grant Nos.2011ZX05006-005 and 2011ZX05006-006)partly funded by the State Key Laboratory for Petroleum Resource and Prospecting (Grant No.KYJJ2012-01-12)
文摘The Songliao Basin is famous for the Daqing Oilfield, the biggest in China. However, no economic hydrocarbon reservoir has been found in the northeastern Binbei district. Its thermal history, which is of great importance for hydrocarbon generation and migration, is studied with apatite fission track (AFT) thermochronology. Samples with depositional ages of the late Cretaceous (-108-73 Ma) are analyzed. The AFT ages of the samples from reservoir rock (depositional age 〉 76.1 Ma) fall between the late Cretaceous (724-5 Ma) and the early Eocene (414-3 Ma) period, indicating their total annealing after deposition. In contrast, two samples from the main seals of the Qingshankou (depositional age 〉 89.3 Ma) and the Nenjiang Formation (depositional age 〉 73.0 Ma) are not annealed or partially annealed (AFT ages of 974-9 Ma and 704-4 Ma, respectively). Because the maximum burial temperature (〈90 ℃) evidenced by low vitrinite reflectance (Ro〈0.7) is not high enough to account for the AFT total annealing (110-120 ℃), the transient thermal effect arising from the syntectonic fluid flow between the late Cretaceous and the early Eocene is proposed. Transient thermal effects from fluid flow explains the indicated temperature discrepancies between the AFT thermometer and the Ro thermometer because the transient thermal effect from the fluid flow with a temperature high enough (110-120 ℃) to anneal the AFT thermometer does not last long enough (104-105 yrs.) for an enhancement of the Ro (minimum 106- 107 yrs. under the same temperature). This indicates that dating thermal effect from fluid flow might be a new means to reconstruct the tectonic history. It also answers why the samples from the main seals are not annealed because the seals will prohibit fluid flow and supply good thermal insulation. The large-scale fluid flow in the Binbei district calls for a new idea to direct the hydrocarbon exploration.
基金supported by the Earmarked Fund for Modern Agro-Industry Technology Research System,China(CARS-42-G24)the Agricultural Science and Technology Innovation Program,China(ASTIP-IAED-2015-01)+1 种基金the Project of Construction of Innovative Teams and Teacher Career Development for Universities and Colleges Under Beijing Municipality,China(IDHT20140510)the Project of Strategy of Ensuring China’s Animal Products Eatable Safety(13BGL098)
文摘From 1985, an increasing gap has emerged between the official statistical measures of meat production and meat consumption in China, which has raised concerns from many researchers using such data. In this paper we report the results of 428 observations(survey of 107 urban and rural households×4 quarters) from 7 provinces conducted in 2010, and compare them with the official statistical data from the National Bureau of Statistics of China(NBSC). We conclude that the main reason for the discrepancy is due to the underreporting of consumption, which is due mainly to the omission of consumption away from home.
文摘Multifaceted events in an organizational environment usually need to be assigned probabilities as a prerequisite to analytical decision-making. If the decision situation is unique, a lack of relevant historical frequency data may preclude use of traditional probability models such as the normal, binomial etc. In this case, an individual decision maker (DM) or an informed group of persons can input into a procedure as outlined here to determine a probability distribution that leads to the expected values of alternative actions or fair values of securities. The individual or group member must decide qualitatively on the extent to which one event is "more likely" than another where both events are ranked adjacent (i.e., closest to each other) in terms of likelihood. Even though the individual or group members may lack experience in orthodox probability assessment, these pairwise "more likely" judgments on the relative likelihood of events are not overly demanding for persons familiar with the possible outcomes in the situation under analysis.
文摘The Greenland ice core from NorthGRIP (NGRIP) contains a proxy climate record across the Pleistocene-Holocene boundary of unprecedented clarity and resolution. Analysis of an array of physical and chemical parameters within the ice enables the base of the Holocene, as reflected in the first signs of climatic warming at the end of the Younger Dryas/Greenland Stadial 1 cold phase, to be located with a high degree of precision.
文摘Land cover classification of mountainous environments continues to be a challenging remote sensing problem,owing to landscape complexities exhibited by the region.This study explored a multiple classifier system(MCS)approach to the classification of mountain land cover for the Khumbu region in the Himalayas using Sentinel-2 images and a cloud-based model framework.The relationship between classification accuracy and MCS diversity was investigated,and the effects of different diversification and combination methods on MCS classification performance were comparatively assessed for this environment.We present ten MCS models that implement a homogeneous ensemble approach,using the high performing Random Forest(RF)algorithm as the selected classifier.The base classifiers of each MCS model were developed using different combinations of three diversity techniques:(1)distinct training sets,(2)Mean Decrease Accuracy feature selection,and(3)‘One-vs-All’problem reduction.The base classifier predictions of each RFMCS model were combined using:(1)majority vote,(2)weighted argmax,and(3)a meta RF classifier.All MCS models reported higher classification accuracies than the benchmark classifier(overall accuracy with 95% confidence interval:87.33%±0.97%),with the highest performing model reporting an overall accuracy(±95% confidence interval)of 90.95%±0.84%.Our key findings include:(1)MCS is effective in mountainous environments prone to noise from landscape complexities,(2)problem reduction is indicated as a stronger method over feature selection in improving the diversity of the MCS,(3)although the MCS diversity and accuracy have a positive correlation,our results suggest this is a weak relationship for mountainous classifications,and(4)the selected diversity methods improve the discriminability of MCS against vegetation and forest classes in mountainous land cover classifications and exhibit a cumulative effect on MCS diversity for this context.