The paper presents the analysis of a human evacuation from a higher education building located in Iassy,Romania,by means of engineering techniques to approach fire safety.Because in Romania(as in other European countr...The paper presents the analysis of a human evacuation from a higher education building located in Iassy,Romania,by means of engineering techniques to approach fire safety.Because in Romania(as in other European countries)fire safety design of buildings is prescriptive and not performance-based,a fire safety engineering approach arouse great interest in many countries such as the U.S.A.,Australia,New Zealand,England,Sweden,Finland,etc.This paper is based on the assumption of starting a fire in the space of a hall for festivities,located on the ground floor of the building,near two human evacuation routes;We consider two building evacuation scenarios:two exits and,respectively,just one exit(assuming that the second would be accidentally blocked).展开更多
With growing urban areas,the climate continues to change as a result of growing populations,and hence,the demand for better emergency response systems has become more important than ever.Human Behaviour Classi.cation(...With growing urban areas,the climate continues to change as a result of growing populations,and hence,the demand for better emergency response systems has become more important than ever.Human Behaviour Classi.cation(HBC)systems have started to play a vital role by analysing data from di.erent sources to detect signs of emergencies.These systems are being used inmany critical areas like healthcare,public safety,and disastermanagement to improve response time and to prepare ahead of time.But detecting human behaviour in such stressful conditions is not simple;it o.en comes with noisy data,missing information,and the need to react in real time.This review takes a deeper look at HBC research published between 2020 and 2025.and aims to answer.ve speci.c research questions.These questions cover the types of emergencies discussed in the literature,the datasets and sensors used,the e.ectiveness of machine learning(ML)and deep learning(DL)models,and the limitations that still exist in this.eld.We explored 120 papers that used di.erent types of datasets,some were based on sensor data,others on social media,and a few used hybrid approaches.Commonly used models included CNNs,LSTMs,and reinforcement learning methods to identify behaviours.Though a lot of progress has been made,the review found ongoing issues in combining sensors properly,reacting fast enough,and using more diverse datasets.Overall,from the.ndings we observed,the focus should be on building systems that use multiple sensors together,gather real-time data on a large scale,and produce results that are easier to interpret.Proper attention to privacy and ethical concerns needs to be addressed as well.展开更多
The frequency of natural and man-made disasters has increased over the past few decades,which has doubled the significance of evacuation planning because it directly affects people’s lives and properties.How evacuees...The frequency of natural and man-made disasters has increased over the past few decades,which has doubled the significance of evacuation planning because it directly affects people’s lives and properties.How evacuees behave during a disaster and the methodologies to assess their behaviour are vital factors in managing any emergency scenario.For example,during the evacuation of a transportation network,users’amount of information and how they react are imperative to achieve a resilient response to a disaster.Even though there are numerous approaches for assessing evacuee behaviour,further research is needed to determine how and when each methodology should be employed.This paper intends to evaluate and classify the methodologies that have been presented up to date to create a more consistent approach to interpreting human behaviour during an evacuation process.The majority of studies focus on how people behave during an evacuation of a building,with less attention paid to how they behave during a transport evacuation.Among the proposed methodologies in this paper,the virtual reality approach,in individual behaviour,and agent-based models,in crowd behaviour,have more advantages than other approaches.Overall,a comparison between the proposed approaches is made in the discussion part.The output of this study provides the classifications and suggestions for researchers to pick an appropriate approach based on the types of problems,and some direction for future studies are introduced.To reach the research goal,177 papers have been reviewed between 1954 and 2022.展开更多
During emergency evacuation,it is crucial to accurately detect and classify different groups of evacuees based on their behaviours using computer vision.Traditional object detection models trained on standard image da...During emergency evacuation,it is crucial to accurately detect and classify different groups of evacuees based on their behaviours using computer vision.Traditional object detection models trained on standard image databases often fail to recognise individuals in specific groups such as the elderly,disabled individuals and pregnant women,who require additional assistance during emergencies.To address this limitation,this study proposes a novel image dataset called the Human Behaviour Detection Dataset(HBDset),specifically collected and anno-tated for public safety and emergency response purposes.This dataset contains eight types of human behaviour categories,i.e.the normal adult,child,holding a crutch,holding a baby,using a wheelchair,pregnant woman,lugging luggage and using a mobile phone.The dataset comprises more than 1,5o0 images collected from various public scenarios,with more than 2,9oo bounding box annotations.The images were carefully selected,cleaned and subsequently manually annotated using the Labellmg tool.To demonstrate the effectiveness of the dataset,classical object detection algorithms were trained and tested based on the HBDset,and the average detection accuracy exceeds 90%,highlighting the robustness and universality of the dataset.The developed open HBDset has the potential to enhance public safety,provide early disaster warnings and prioritise the needs of vulnerable individuals during emergency evacuation.展开更多
This paper deals with the human adaptability to its built environment. The built environment as we know it rarely finds itself adapting to its surrounding context, whether it be on the level of interaction with humans...This paper deals with the human adaptability to its built environment. The built environment as we know it rarely finds itself adapting to its surrounding context, whether it be on the level of interaction with humans or the climate. Humans and nature both are in a constant state of flux;moving, changing, sensing, and reacting to their context and information they gather and perceive. A barrier is formed between the built environment and humans and nature due to the fact that their inherent characteristics are utterly contrasting. It is commonly estimated that persons in urban areas spend at least 80% of their time indoors. This suggests that the quality of the indoor environment can have a significant impact on comfort, health, and overall sense of well being. The indoor environment of buildings should thus be designed and controlled, as to provide a comfortable and healthy space for occupants. In order to maintain the quality of the indoor environment, we mechanically condition our buildings to achieve constant, uniform and comfortable environments. The maintenance of thermal equilibrium between the human body and its environment is one of the primary requirements. History of thermal comfort and climate design shows a definite relation between them and research is needed to know “What are comfort conditions?” and “How buildings could adapt themselves to these conditions”.展开更多
Many studies have looked at how dogs respond to human communicative information. Here, we examined which human communicative factors were important in influencing dogs’ responses. Eleven healthy pet dogs with no appa...Many studies have looked at how dogs respond to human communicative information. Here, we examined which human communicative factors were important in influencing dogs’ responses. Eleven healthy pet dogs with no apparent aggressive behaviour toward people were recruited. Five sensory conditions (all cues presented;either a visual, an auditory, or an olfactory cue presented;no cues presented) were provided three times randomly to each dog during the tests. All tests were video recorded, and both the dogs’ behaviour and time taken to reach the person when she presented each of the sensory cue conditions were observed. Total rates of reaching the person were as follows: 97.0% (all cues), 87.9% (auditory cues), 84.4% (visual cues), 84.4% (olfactory cues), and 69.7% (no cues). The time taken for the dog to notice the person in the box and then obtain a reward from her differed among the five conditions: all cues (6.00 ± 0.32 s) and visual cues (6.02 ± 0.91 s) were significantly faster than auditory cues (18.56 ± 9.57 s) and no cues (26.55 ± 11.72 s). Thus the type of information input was important in recognition of the person by the dogs and influenced the dogs’ response times;visual cues appeared advantageous in confirming the person’s presence.展开更多
[目的]了解上海市男男性行为人群(men who have sex with men,MSM)人类免疫缺陷病毒(HIV)感染相关行为学特征,并分析与男男无保护性行为相关的影响因素。[方法]利用信息网络中的上海市男男活动小组和男男论坛,共招募符合筛选条件的调查...[目的]了解上海市男男性行为人群(men who have sex with men,MSM)人类免疫缺陷病毒(HIV)感染相关行为学特征,并分析与男男无保护性行为相关的影响因素。[方法]利用信息网络中的上海市男男活动小组和男男论坛,共招募符合筛选条件的调查对象121名。采用中-加项目全球课题设计的统一表格对121人进行面对面问卷调查。[结果]调查对象平均年龄为(27.99±5.93)岁;大学及以上教育程度者占74.4%;月均收入≥3000元人民币者占62.9%;单身者占86.0%。121名MSM初次和男性发生性行为的平均年龄为(22.14±5.32)岁;过去半年内受访者的平均性伴数为(3.27±2.77)人。目前有固定男友的受访者占56.14%,但和固定男友之间在性关系上相互忠诚的仅占其中的36.84%。16人在过去半年内和女性有性行为,其中62.8%的受访者曾和女性发生过无保护性行为。45.45%的受访者曾与男性有过无保护性行为,受访者和固定男友间发生无保护性行为的比例高于和多次男性伴间发生无保护性行为的比例(χ2=4.32,P<0.05),也明显高于和偶遇男性伴间发生无保护性行为的比例(χ2=10.13,P<0.01)。77.7%的受访者认为自己有感染HIV的风险。多因素分析表明,与男性发生无保护性行为相关的影响因素为受教育程度、半年内性伴数量和HIV感染自我风险评估情况。[结论]受教育程度越低、性伴数量越多的MSM发生无保护性行为的概率越高。认为自己有HIV感染风险的受访者更有可能发生过无保护性行为。因此在今后对存在上述情况的MSM更应加强健康干预。展开更多
文摘The paper presents the analysis of a human evacuation from a higher education building located in Iassy,Romania,by means of engineering techniques to approach fire safety.Because in Romania(as in other European countries)fire safety design of buildings is prescriptive and not performance-based,a fire safety engineering approach arouse great interest in many countries such as the U.S.A.,Australia,New Zealand,England,Sweden,Finland,etc.This paper is based on the assumption of starting a fire in the space of a hall for festivities,located on the ground floor of the building,near two human evacuation routes;We consider two building evacuation scenarios:two exits and,respectively,just one exit(assuming that the second would be accidentally blocked).
文摘With growing urban areas,the climate continues to change as a result of growing populations,and hence,the demand for better emergency response systems has become more important than ever.Human Behaviour Classi.cation(HBC)systems have started to play a vital role by analysing data from di.erent sources to detect signs of emergencies.These systems are being used inmany critical areas like healthcare,public safety,and disastermanagement to improve response time and to prepare ahead of time.But detecting human behaviour in such stressful conditions is not simple;it o.en comes with noisy data,missing information,and the need to react in real time.This review takes a deeper look at HBC research published between 2020 and 2025.and aims to answer.ve speci.c research questions.These questions cover the types of emergencies discussed in the literature,the datasets and sensors used,the e.ectiveness of machine learning(ML)and deep learning(DL)models,and the limitations that still exist in this.eld.We explored 120 papers that used di.erent types of datasets,some were based on sensor data,others on social media,and a few used hybrid approaches.Commonly used models included CNNs,LSTMs,and reinforcement learning methods to identify behaviours.Though a lot of progress has been made,the review found ongoing issues in combining sensors properly,reacting fast enough,and using more diverse datasets.Overall,from the.ndings we observed,the focus should be on building systems that use multiple sensors together,gather real-time data on a large scale,and produce results that are easier to interpret.Proper attention to privacy and ethical concerns needs to be addressed as well.
文摘The frequency of natural and man-made disasters has increased over the past few decades,which has doubled the significance of evacuation planning because it directly affects people’s lives and properties.How evacuees behave during a disaster and the methodologies to assess their behaviour are vital factors in managing any emergency scenario.For example,during the evacuation of a transportation network,users’amount of information and how they react are imperative to achieve a resilient response to a disaster.Even though there are numerous approaches for assessing evacuee behaviour,further research is needed to determine how and when each methodology should be employed.This paper intends to evaluate and classify the methodologies that have been presented up to date to create a more consistent approach to interpreting human behaviour during an evacuation process.The majority of studies focus on how people behave during an evacuation of a building,with less attention paid to how they behave during a transport evacuation.Among the proposed methodologies in this paper,the virtual reality approach,in individual behaviour,and agent-based models,in crowd behaviour,have more advantages than other approaches.Overall,a comparison between the proposed approaches is made in the discussion part.The output of this study provides the classifications and suggestions for researchers to pick an appropriate approach based on the types of problems,and some direction for future studies are introduced.To reach the research goal,177 papers have been reviewed between 1954 and 2022.
基金funded by the Hong Kong Research Grants Council Theme-based Research Scheme(T22-505/19-N)the National Natural Science Foundation of China(52204232)MTR Research Fund(PTU-23005).
文摘During emergency evacuation,it is crucial to accurately detect and classify different groups of evacuees based on their behaviours using computer vision.Traditional object detection models trained on standard image databases often fail to recognise individuals in specific groups such as the elderly,disabled individuals and pregnant women,who require additional assistance during emergencies.To address this limitation,this study proposes a novel image dataset called the Human Behaviour Detection Dataset(HBDset),specifically collected and anno-tated for public safety and emergency response purposes.This dataset contains eight types of human behaviour categories,i.e.the normal adult,child,holding a crutch,holding a baby,using a wheelchair,pregnant woman,lugging luggage and using a mobile phone.The dataset comprises more than 1,5o0 images collected from various public scenarios,with more than 2,9oo bounding box annotations.The images were carefully selected,cleaned and subsequently manually annotated using the Labellmg tool.To demonstrate the effectiveness of the dataset,classical object detection algorithms were trained and tested based on the HBDset,and the average detection accuracy exceeds 90%,highlighting the robustness and universality of the dataset.The developed open HBDset has the potential to enhance public safety,provide early disaster warnings and prioritise the needs of vulnerable individuals during emergency evacuation.
文摘This paper deals with the human adaptability to its built environment. The built environment as we know it rarely finds itself adapting to its surrounding context, whether it be on the level of interaction with humans or the climate. Humans and nature both are in a constant state of flux;moving, changing, sensing, and reacting to their context and information they gather and perceive. A barrier is formed between the built environment and humans and nature due to the fact that their inherent characteristics are utterly contrasting. It is commonly estimated that persons in urban areas spend at least 80% of their time indoors. This suggests that the quality of the indoor environment can have a significant impact on comfort, health, and overall sense of well being. The indoor environment of buildings should thus be designed and controlled, as to provide a comfortable and healthy space for occupants. In order to maintain the quality of the indoor environment, we mechanically condition our buildings to achieve constant, uniform and comfortable environments. The maintenance of thermal equilibrium between the human body and its environment is one of the primary requirements. History of thermal comfort and climate design shows a definite relation between them and research is needed to know “What are comfort conditions?” and “How buildings could adapt themselves to these conditions”.
文摘Many studies have looked at how dogs respond to human communicative information. Here, we examined which human communicative factors were important in influencing dogs’ responses. Eleven healthy pet dogs with no apparent aggressive behaviour toward people were recruited. Five sensory conditions (all cues presented;either a visual, an auditory, or an olfactory cue presented;no cues presented) were provided three times randomly to each dog during the tests. All tests were video recorded, and both the dogs’ behaviour and time taken to reach the person when she presented each of the sensory cue conditions were observed. Total rates of reaching the person were as follows: 97.0% (all cues), 87.9% (auditory cues), 84.4% (visual cues), 84.4% (olfactory cues), and 69.7% (no cues). The time taken for the dog to notice the person in the box and then obtain a reward from her differed among the five conditions: all cues (6.00 ± 0.32 s) and visual cues (6.02 ± 0.91 s) were significantly faster than auditory cues (18.56 ± 9.57 s) and no cues (26.55 ± 11.72 s). Thus the type of information input was important in recognition of the person by the dogs and influenced the dogs’ response times;visual cues appeared advantageous in confirming the person’s presence.
文摘[目的]了解上海市男男性行为人群(men who have sex with men,MSM)人类免疫缺陷病毒(HIV)感染相关行为学特征,并分析与男男无保护性行为相关的影响因素。[方法]利用信息网络中的上海市男男活动小组和男男论坛,共招募符合筛选条件的调查对象121名。采用中-加项目全球课题设计的统一表格对121人进行面对面问卷调查。[结果]调查对象平均年龄为(27.99±5.93)岁;大学及以上教育程度者占74.4%;月均收入≥3000元人民币者占62.9%;单身者占86.0%。121名MSM初次和男性发生性行为的平均年龄为(22.14±5.32)岁;过去半年内受访者的平均性伴数为(3.27±2.77)人。目前有固定男友的受访者占56.14%,但和固定男友之间在性关系上相互忠诚的仅占其中的36.84%。16人在过去半年内和女性有性行为,其中62.8%的受访者曾和女性发生过无保护性行为。45.45%的受访者曾与男性有过无保护性行为,受访者和固定男友间发生无保护性行为的比例高于和多次男性伴间发生无保护性行为的比例(χ2=4.32,P<0.05),也明显高于和偶遇男性伴间发生无保护性行为的比例(χ2=10.13,P<0.01)。77.7%的受访者认为自己有感染HIV的风险。多因素分析表明,与男性发生无保护性行为相关的影响因素为受教育程度、半年内性伴数量和HIV感染自我风险评估情况。[结论]受教育程度越低、性伴数量越多的MSM发生无保护性行为的概率越高。认为自己有HIV感染风险的受访者更有可能发生过无保护性行为。因此在今后对存在上述情况的MSM更应加强健康干预。
