In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation system.The growth of parking lots has raised the likelihood of spontaneous vehicle combus-ti...In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation system.The growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative step.However,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection technologies.This paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking lots.First,we develop a novel dataset to fill the gap,as there is a lack of publicly available data.This dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor conditions.Second,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing capabilities.Third,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency response.Experiments show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.展开更多
With the widespread use of machine learning(ML)technology,the operational efficiency and responsiveness of power grids have been significantly enhanced,allowing smart grids to achieve high levels of automation and int...With the widespread use of machine learning(ML)technology,the operational efficiency and responsiveness of power grids have been significantly enhanced,allowing smart grids to achieve high levels of automation and intelligence.However,tree ensemble models commonly used in smart grids are vulnerable to adversarial attacks,making it urgent to enhance their robustness.To address this,we propose a robustness enhancement method that incorporates physical constraints into the node-splitting decisions of tree ensembles.Our algorithm improves robustness by developing a dataset of adversarial examples that comply with physical laws,ensuring training data accurately reflects possible attack scenarios while adhering to physical rules.In our experiments,the proposed method increased robustness against adversarial attacks by 100%when applied to real grid data under physical constraints.These results highlight the advantages of our method in maintaining efficient and secure operation of smart grids under adversarial conditions.展开更多
Meteorological conditions have an important impact on changes of vegetation in ecologically fragile karst areas.This study aims to explore a method for quantitative evaluation of these meteorological conditions. We an...Meteorological conditions have an important impact on changes of vegetation in ecologically fragile karst areas.This study aims to explore a method for quantitative evaluation of these meteorological conditions. We analyzed the changing trend of vegetation during 2000–2018 and the correlations between vegetation changes and various meteorological factors in karst rocky areas of Guangxi Zhuang Autonomous Region, China. Key meteorological factors in vegetation areas with varying degrees of improvement were selected and evaluated at seasonal timescale. A quantitative evaluation model of comprehensive influences of meteorological factors on vegetation was built by using the partial least-square regression(PLS). About 91.45% of the vegetation tended to be improved, while only the rest 8.55% showed a trend of degradation from 2000 to 2018. Areas with evident vegetation improvement were mainly distributed in the middle and northeast, and those with obvious vegetation degradation were scattered. Meteorological factors affecting vegetation were significantly different among the four seasons. Overall, high air humidity, small temperature difference in spring and autumn, and low daily minimum temperature and air pressure were favorable conditions. Low temperature in winter as well as high temperature in summer and autumn were unfavorable conditions. The Climate Vegetation Index(CVI) model was established by PLS using the maximum, minimum, and average temperatures;vapor pressure;rainfall;and air pressure as key meteorological factors. The Enhanced Vegetation Index(EVI) was well fitted by the CVI model, with the average coefficient of determination(r2) and root mean square error(RMSE) of 0.856 and 0.042, respectively. Finally, an assessment model of comprehensive meteorological conditions was built based on the interannual differences in CVI. The meteorological conditions in the study area in 2014 were successfully evaluated by combining the model and selected seasonal key meteorological factors.展开更多
基金This work was supported byNatural Science Foundation of China(No.62362008,author Z.Z,https://www.nsfc.gov.cn/)Guizhou Provincial Science and Technology Projects(No.ZK[2022]149,author Z.Z,https://kjt.guizhou.gov.cn/)+2 种基金Guizhou Provincial Research Project(Youth)for Universities(No.[2022]104,author Z.Z,https://jyt.guizhou.gov.cn/)Natural Science Special Foundation of Guizhou University(No.[2021]47,author Z.Z,https://www.gzu.edu.cn/)GZU Cultivation Project of NSFC(No.[2020]80,author Z.Z,https://www.gzu.edu.cn/).
文摘In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation system.The growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative step.However,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection technologies.This paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking lots.First,we develop a novel dataset to fill the gap,as there is a lack of publicly available data.This dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor conditions.Second,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing capabilities.Third,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency response.Experiments show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.
基金This work was supported by Natural Science Foundation of China(Nos.62303126,62362008,62066006,authors Zhenyong Zhang and Bin Hu,https://www.nsfc.gov.cn/,accessed on 25 July 2024)Guizhou Provincial Science and Technology Projects(No.ZK[2022]149,author Zhenyong Zhang,https://kjt.guizhou.gov.cn/,accessed on 25 July 2024)+1 种基金Guizhou Provincial Research Project(Youth)forUniversities(No.[2022]104,author Zhenyong Zhang,https://jyt.guizhou.gov.cn/,accessed on 25 July 2024)GZU Cultivation Project of NSFC(No.[2020]80,author Zhenyong Zhang,https://www.gzu.edu.cn/,accessed on 25 July 2024).
文摘With the widespread use of machine learning(ML)technology,the operational efficiency and responsiveness of power grids have been significantly enhanced,allowing smart grids to achieve high levels of automation and intelligence.However,tree ensemble models commonly used in smart grids are vulnerable to adversarial attacks,making it urgent to enhance their robustness.To address this,we propose a robustness enhancement method that incorporates physical constraints into the node-splitting decisions of tree ensembles.Our algorithm improves robustness by developing a dataset of adversarial examples that comply with physical laws,ensuring training data accurately reflects possible attack scenarios while adhering to physical rules.In our experiments,the proposed method increased robustness against adversarial attacks by 100%when applied to real grid data under physical constraints.These results highlight the advantages of our method in maintaining efficient and secure operation of smart grids under adversarial conditions.
基金Supported by the Guangxi Zhuang Autonomous Region (GZAR) Science and Technology Project (AB20159022 and AB17292051)GZAR Natural Science Foundation (2018GXNSFAA281338)。
文摘Meteorological conditions have an important impact on changes of vegetation in ecologically fragile karst areas.This study aims to explore a method for quantitative evaluation of these meteorological conditions. We analyzed the changing trend of vegetation during 2000–2018 and the correlations between vegetation changes and various meteorological factors in karst rocky areas of Guangxi Zhuang Autonomous Region, China. Key meteorological factors in vegetation areas with varying degrees of improvement were selected and evaluated at seasonal timescale. A quantitative evaluation model of comprehensive influences of meteorological factors on vegetation was built by using the partial least-square regression(PLS). About 91.45% of the vegetation tended to be improved, while only the rest 8.55% showed a trend of degradation from 2000 to 2018. Areas with evident vegetation improvement were mainly distributed in the middle and northeast, and those with obvious vegetation degradation were scattered. Meteorological factors affecting vegetation were significantly different among the four seasons. Overall, high air humidity, small temperature difference in spring and autumn, and low daily minimum temperature and air pressure were favorable conditions. Low temperature in winter as well as high temperature in summer and autumn were unfavorable conditions. The Climate Vegetation Index(CVI) model was established by PLS using the maximum, minimum, and average temperatures;vapor pressure;rainfall;and air pressure as key meteorological factors. The Enhanced Vegetation Index(EVI) was well fitted by the CVI model, with the average coefficient of determination(r2) and root mean square error(RMSE) of 0.856 and 0.042, respectively. Finally, an assessment model of comprehensive meteorological conditions was built based on the interannual differences in CVI. The meteorological conditions in the study area in 2014 were successfully evaluated by combining the model and selected seasonal key meteorological factors.