Fire detection has held stringent importance in computer vision for over half a century.The development of early fire detection strategies is pivotal to the realization of safe and smart cities,inhabitable in the futu...Fire detection has held stringent importance in computer vision for over half a century.The development of early fire detection strategies is pivotal to the realization of safe and smart cities,inhabitable in the future.However,the development of optimal fire and smoke detection models is hindered by limitations like publicly available datasets,lack of diversity,and class imbalance.In this work,we explore the possible ways forward to overcome these challenges posed by available datasets.We study the impact of a class-balanced dataset to improve the fire detection capability of state-of-the-art(SOTA)vision-based models and propose the use of generative models for data augmentation,as a future work direction.First,a comparative analysis of two prominent object detection architectures,You Only Look Once version 7(YOLOv7)and YOLOv8 has been carried out using a balanced dataset,where both models have been evaluated across various evaluation metrics including precision,recall,and mean Average Precision(mAP).The results are compared to other recent fire detection models,highlighting the superior performance and efficiency of the proposed YOLOv8 architecture as trained on our balanced dataset.Next,a fractal dimension analysis gives a deeper insight into the repetition of patterns in fire,and the effectiveness of the results has been demonstrated by a windowing-based inference approach.The proposed Slicing-Aided Hyper Inference(SAHI)improves the fire and smoke detection capability of YOLOv8 for real-life applications with a significantly improved mAP performance over a strict confidence threshold.YOLOv8 with SAHI inference gives a mAP:50-95 improvement of more than 25%compared to the base YOLOv8 model.The study also provides insights into future work direction by exploring the potential of generative models like deep convolutional generative adversarial network(DCGAN)and diffusion models like stable diffusion,for data augmentation.展开更多
To explore the technical solution for independently-developed wireless synchronous control of locomotives based on 5G-R,this study investigates the service demands of such control and analyzes the insufficiency of the...To explore the technical solution for independently-developed wireless synchronous control of locomotives based on 5G-R,this study investigates the service demands of such control and analyzes the insufficiency of the existing communication system of China's heavy-haul railway.Giving full consideration of the high bandwidth,low delay,IP-based links,packet domain transmission,quality of service priority guarantee and other characteristics of the 5G-R network,an overall technical solution is proposed,focusing on the implementation of functions such as master-slave locomotive data transmission,controllable end-of-train data transmission,marshaling requests,and multi-driver calls.The findings contribute to enhancing the advancement of the independently-developed wireless synchronous control system of locomotives,ensuring its reliable operation in complex environments,providing valuable guidance for improving the safety and efficiency of heavy-haul railway transportation,and offering robust technical support for the modernization and intelligence development of heavy-haul railway.展开更多
Prognostics and Health Management(PHM)technology is a critical component in establishing a precision-based Operation and Management(O&M)system for EMUs.This technology is essential for enhancing life cycle managem...Prognostics and Health Management(PHM)technology is a critical component in establishing a precision-based Operation and Management(O&M)system for EMUs.This technology is essential for enhancing life cycle management and advancing manufacturing and repair processes of EMUs.Through the analysis on O&M requirements of EMUs,this paper proposes the intelligent O&M objectives of EMUs based on PHM technology,as well as the system design architecture incorporating functions such as condition monitoring,fault prediction,health assessment,decision support and O&M analysis;and constructs a PHM-based standardized system for intelligent O&M of EMUs.The study also explores aspects such as the data lifecycle of EMUs,the development of PHM models,high-frequency streaming computation methods,unified management of heterogeneous models,and PHM-driven O&M production organization technologies.The PHM-based intelligent O&M system has been implemented across the railway network,achieving seamless information flow throughout the entire process of monitoring,decision-making and execution.展开更多
In this study,we consider a multi-cell millimeter-wave(mmWave)massive multiple-input multiple-output(MIMO)system with a mixed analog-to-digital converter(mixed-ADC)and hybrid beamforming architecture,in which antenna ...In this study,we consider a multi-cell millimeter-wave(mmWave)massive multiple-input multiple-output(MIMO)system with a mixed analog-to-digital converter(mixed-ADC)and hybrid beamforming architecture,in which antenna selection is applied to achieve intelligent assignment of high-and low-resolution ADCs.Both exact and approximate closed-form expressions for the uplink achievable rate are derived in the case of maximum-ratio combining reception.The impacts on the achievable rate of user transmit power,number of radio frequency chains at a base station,ratio of high-resolution ADCs,number of propagation paths,and number of quantization bits are analyzed.It is shown that the user transmit power can be scaled down inversely proportional to the number of antennas at the base station.We propose an efficient power allocation scheme by solving a complementary geometric programming problem.In addition,the energy efficiency is investigated,and an optimal tradeoff between the achievable rate and power consumption is discussed.Our results will provide a useful reference for the study of mixed-ADC multi-cell mmWave massive MIMO systems with antenna selection.展开更多
Microplastics in the air are becoming a concern,especially in indoor environments.Outdoor microplastics can travel from far spaces while indoor ones remain suspended and recirculate in the indoor environment.In this s...Microplastics in the air are becoming a concern,especially in indoor environments.Outdoor microplastics can travel from far spaces while indoor ones remain suspended and recirculate in the indoor environment.In this study,we collected air samples from the same buildings indoors and outdoors and observed the indoor microplastic concentrationwas 1.8 times higher than the outdoor.24-hour sampling was performed with a mini-volume air sampler at the rate of 5 L/min.In this study,along with a comparison of indoor and outdoor concentrations,we also studied the microplastics'type size,and shape.We found that fiber-type microplastics account for nearly 90%of the total and synthetic fibers.We also reported the 10 highest present microplastics are Polyethylene,Polyethersulfone,Polyamide,Polystyrene,Acrylic,Polyvinyl Chloride,Polytetrafluoroethylene,Alkyd,and Polyurethane.It is also observed the indoor ventilation rate plays a major role in the microplastic concentrations,long and periodic ventilation resulted in the lower concentration of the indoor microplastics.This study resulted in higher indoor air concentrations than outdoor and even in the outskirts of the metropolitan city which shows that indoor air concentrations are dependent on indoor sources and human activity.展开更多
This work attempts to understand how a customized bus(CB)operator decides to open or close a CB line.We look into the changes in the operation status of CB lines(i.e.reopening and closure)from one of the largest CB op...This work attempts to understand how a customized bus(CB)operator decides to open or close a CB line.We look into the changes in the operation status of CB lines(i.e.reopening and closure)from one of the largest CB operators in Shanghai,China,with a 22-month con secutive observation ranging from January 2019 to October 2020.As all CB services were totally suspended at the beginning of 2020 due to the COVID-19 travel restriction and then gradually recovered in March 2020,we utilize this study period as a naturalistic observa tion experiment to investigate the changes in the operation status of each CB line before and after the travel restriction.Using the operation status at each month as the binary alternatives,the mixed logit models and the tree-based models with explainable machine learning techniques are respectively adopted to explore the factors that influence the decision-making process.The findings from both types of models are in general consistent.The results show that the characteristics of each CB line including the ridership,the length of the line,the closeness to charging stations,and the overlap of CB lines significantly impact the decisions.In addition,the land-use types around the CB stops and the market competition from alternative travel modes also play a key role in making the decisions.展开更多
基金supported by a grant from R&D Program Development of Rail-Specific Digital Resource Technology Based on an AI-Enabled Rail Support Platform,grant number PK2401C1,of the Korea Railroad Research Institute.
文摘Fire detection has held stringent importance in computer vision for over half a century.The development of early fire detection strategies is pivotal to the realization of safe and smart cities,inhabitable in the future.However,the development of optimal fire and smoke detection models is hindered by limitations like publicly available datasets,lack of diversity,and class imbalance.In this work,we explore the possible ways forward to overcome these challenges posed by available datasets.We study the impact of a class-balanced dataset to improve the fire detection capability of state-of-the-art(SOTA)vision-based models and propose the use of generative models for data augmentation,as a future work direction.First,a comparative analysis of two prominent object detection architectures,You Only Look Once version 7(YOLOv7)and YOLOv8 has been carried out using a balanced dataset,where both models have been evaluated across various evaluation metrics including precision,recall,and mean Average Precision(mAP).The results are compared to other recent fire detection models,highlighting the superior performance and efficiency of the proposed YOLOv8 architecture as trained on our balanced dataset.Next,a fractal dimension analysis gives a deeper insight into the repetition of patterns in fire,and the effectiveness of the results has been demonstrated by a windowing-based inference approach.The proposed Slicing-Aided Hyper Inference(SAHI)improves the fire and smoke detection capability of YOLOv8 for real-life applications with a significantly improved mAP performance over a strict confidence threshold.YOLOv8 with SAHI inference gives a mAP:50-95 improvement of more than 25%compared to the base YOLOv8 model.The study also provides insights into future work direction by exploring the potential of generative models like deep convolutional generative adversarial network(DCGAN)and diffusion models like stable diffusion,for data augmentation.
文摘To explore the technical solution for independently-developed wireless synchronous control of locomotives based on 5G-R,this study investigates the service demands of such control and analyzes the insufficiency of the existing communication system of China's heavy-haul railway.Giving full consideration of the high bandwidth,low delay,IP-based links,packet domain transmission,quality of service priority guarantee and other characteristics of the 5G-R network,an overall technical solution is proposed,focusing on the implementation of functions such as master-slave locomotive data transmission,controllable end-of-train data transmission,marshaling requests,and multi-driver calls.The findings contribute to enhancing the advancement of the independently-developed wireless synchronous control system of locomotives,ensuring its reliable operation in complex environments,providing valuable guidance for improving the safety and efficiency of heavy-haul railway transportation,and offering robust technical support for the modernization and intelligence development of heavy-haul railway.
文摘Prognostics and Health Management(PHM)technology is a critical component in establishing a precision-based Operation and Management(O&M)system for EMUs.This technology is essential for enhancing life cycle management and advancing manufacturing and repair processes of EMUs.Through the analysis on O&M requirements of EMUs,this paper proposes the intelligent O&M objectives of EMUs based on PHM technology,as well as the system design architecture incorporating functions such as condition monitoring,fault prediction,health assessment,decision support and O&M analysis;and constructs a PHM-based standardized system for intelligent O&M of EMUs.The study also explores aspects such as the data lifecycle of EMUs,the development of PHM models,high-frequency streaming computation methods,unified management of heterogeneous models,and PHM-driven O&M production organization technologies.The PHM-based intelligent O&M system has been implemented across the railway network,achieving seamless information flow throughout the entire process of monitoring,decision-making and execution.
基金Project supported by the National Key R&D Program of China(No.2018YFB1801101)the National Natural Science Foundation of China(Nos.62071031 and 61960206006)+4 种基金the Beijing Municipal Natural Science Foundation,China(No.4212006)the Center of National Railway Intelligent Transportation System Engineering and Technology,China Academy of Railway Sciences(Nos.RITS2019KF01 and 2019YJ188)the Research Fund of the National Mobile Communications Research Laboratory,Southeast University,China(Nos.2020B01 and 2021D01)the Fundamental Research Funds for the Central Universities,China(No.2242020R30001)the Huawei Cooperation Project,China,and the EU H2020 RISE TESTBED2 Project(No.872172)。
文摘In this study,we consider a multi-cell millimeter-wave(mmWave)massive multiple-input multiple-output(MIMO)system with a mixed analog-to-digital converter(mixed-ADC)and hybrid beamforming architecture,in which antenna selection is applied to achieve intelligent assignment of high-and low-resolution ADCs.Both exact and approximate closed-form expressions for the uplink achievable rate are derived in the case of maximum-ratio combining reception.The impacts on the achievable rate of user transmit power,number of radio frequency chains at a base station,ratio of high-resolution ADCs,number of propagation paths,and number of quantization bits are analyzed.It is shown that the user transmit power can be scaled down inversely proportional to the number of antennas at the base station.We propose an efficient power allocation scheme by solving a complementary geometric programming problem.In addition,the energy efficiency is investigated,and an optimal tradeoff between the achievable rate and power consumption is discussed.Our results will provide a useful reference for the study of mixed-ADC multi-cell mmWave massive MIMO systems with antenna selection.
基金the Development of mobile direct carbon dioxide capture technology by the Korea Railroad Research Institute(KRRI),Under the project code(PK2402A4).
文摘Microplastics in the air are becoming a concern,especially in indoor environments.Outdoor microplastics can travel from far spaces while indoor ones remain suspended and recirculate in the indoor environment.In this study,we collected air samples from the same buildings indoors and outdoors and observed the indoor microplastic concentrationwas 1.8 times higher than the outdoor.24-hour sampling was performed with a mini-volume air sampler at the rate of 5 L/min.In this study,along with a comparison of indoor and outdoor concentrations,we also studied the microplastics'type size,and shape.We found that fiber-type microplastics account for nearly 90%of the total and synthetic fibers.We also reported the 10 highest present microplastics are Polyethylene,Polyethersulfone,Polyamide,Polystyrene,Acrylic,Polyvinyl Chloride,Polytetrafluoroethylene,Alkyd,and Polyurethane.It is also observed the indoor ventilation rate plays a major role in the microplastic concentrations,long and periodic ventilation resulted in the lower concentration of the indoor microplastics.This study resulted in higher indoor air concentrations than outdoor and even in the outskirts of the metropolitan city which shows that indoor air concentrations are dependent on indoor sources and human activity.
基金This work is supported by the National Natural Science Foundation of China(Grant Nos.52272321,71901164,52272335)the Fundamental Research Funds for the Central Universities.
文摘This work attempts to understand how a customized bus(CB)operator decides to open or close a CB line.We look into the changes in the operation status of CB lines(i.e.reopening and closure)from one of the largest CB operators in Shanghai,China,with a 22-month con secutive observation ranging from January 2019 to October 2020.As all CB services were totally suspended at the beginning of 2020 due to the COVID-19 travel restriction and then gradually recovered in March 2020,we utilize this study period as a naturalistic observa tion experiment to investigate the changes in the operation status of each CB line before and after the travel restriction.Using the operation status at each month as the binary alternatives,the mixed logit models and the tree-based models with explainable machine learning techniques are respectively adopted to explore the factors that influence the decision-making process.The findings from both types of models are in general consistent.The results show that the characteristics of each CB line including the ridership,the length of the line,the closeness to charging stations,and the overlap of CB lines significantly impact the decisions.In addition,the land-use types around the CB stops and the market competition from alternative travel modes also play a key role in making the decisions.
