FIGURE 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Because of toxic gases and fast propagation speed, smoke causes the major injuries and deaths than burns in the fire. Deploying IoT enabled smoke sensors can help to sense, collect, and transmit the smoke data to the control station, it enables a dynamic and real-time evacuation approach to increase the evacuation success probability. In this paper...
Contexts in source publication
Context 1
... is a wellknown fire simulation software which is developed by the National Institute of Standards and Technology (NIST) of the United States Department of Commerce [32]. Figure 1 shows the layout of the Taipei 101 mall, and the fire colored in red starts at the first floor in the building. The blue color region indicates the staircase to the emergency exit at the first floor. ...
Context 2
... to Figure 3, at 80 seconds simulation time, the smoke does not cover the exit (1, 1, 1). Five evacuees start at (3, 5, 2) and five evacuees start at (4, 3, 3) will evacuate the exit (1, 1, 1). After six time slots (i.e., 180 seconds), these two groups will all arrive at node (1, 1, 2) and there are ten evacuees at node (1, 1, 2). ...
Context 3
... the methane is the main energy source in cooking and PVC conduit is used to protect the electrical wires in the building, two fire ignitors (methane and PVC) are simulated in Taipei 101 mall and the configuration files of two fire ignitors in FDS are shown in Table 1. Note that the fire origin at the first floor and the location of the fire origin is shown in Figure 1. Figure 7, we show the ratio of the sensors that are over the FED 0.3 threshold and FED 0.5 threshold at methane fire smoke and PVC fire smoke for 30 minutes simulation time in Taipei 101 mall. ...
Context 4
... the case of no sprinklers and the number of evacuees is more than 500, it results in tragedy that the evacuation success probability is below 50% for SIEP algorithm under í µí± CDE =0.3. In Figure 10, we show the last evacuation time at methane fire smoke. It shows that the last evacuee's evacuation time is almost a linear function with respect to the number of evacuees for SGEP algorithm with or without sprinklers. ...
Context 5
... indicates that, when the number of evacuees is more than 400, evacuation congestion problems rise for the SIEP algorithm. In Figure 11, we show the evacuation success probability comparisons between SGEP algorithm and SIEP algorithm at PVC fire smoke. At 1000 evacuees and í µí± CDE =0.3, the evacuation success probability for SGEP algorithm is 73% with sprinklers and 61% without sprinklers. ...
Context 6
... reason is because PVC is more toxic than the methane, which is consistent with the results in Figure 7. In Figure 12, we show the last evacuation time at PVC fire. The last evacuee's evacuation time for both SGEP algorithm and SIEP algorithm is much smaller than the methane fire in Figure 10. ...
Context 7
... Figure 12, we show the last evacuation time at PVC fire. The last evacuee's evacuation time for both SGEP algorithm and SIEP algorithm is much smaller than the methane fire in Figure 10. When the last evacuee's evacuation time is smaller than the simulation time (i.e., 1800 seconds), the last evacuee's evacuation time is the evacuation window time for the evacuees. ...
Context 8
... í µí± CDE =0.3 and without sprinklers, the evacuation window time for SIEP algorithm and SGEP algorithm is 864 seconds and 837 seconds, respectively. Note that, according to Figure 11, the evacuation success problem for SGEP is higher than SIEP. This shows that SGEP algorithm can not only evacuate more evacuees but also can evacuate faster than the SIEP algorithm. ...
Context 9
... last evacuee's evacuation time in the simulation results implies the evacuation window time, where no evacuees can be evacuated after the last evacuee's evacuation time. From the results in Figure 10 and Figure 12, evacuation window time depends on the total number of evacuees. The number of occupants in the Taipei 101 mall is random and it is difficult to tell exactly how many occupants are still in the building when at fire. ...
Context 10
... last evacuee's evacuation time in the simulation results implies the evacuation window time, where no evacuees can be evacuated after the last evacuee's evacuation time. From the results in Figure 10 and Figure 12, evacuation window time depends on the total number of evacuees. The number of occupants in the Taipei 101 mall is random and it is difficult to tell exactly how many occupants are still in the building when at fire. ...
Citations
... The urgency of evacuating quickly and safely is paramount in scenarios such as fires, natural disasters, or security threats. An effective evacuation plan is designed to minimize panic and chaos, offering clear guidance through well-defined pathways and signage to facilitate an orderly exit process, thereby reducing the risk of injuries and confusion [4]. Accessibility to emergency exits is a key consideration, demanding clear identification and regular maintenance to prevent obstructions or malfunctions. ...
... Researchers perform this investigation to examine the functionality of the suggested LCA. Following that, the LCA ��� ⃗ P 1 , ��� ⃗ T 1 are equal to (1,2,4,6) and the LCA ��� ⃗ P 2 , ��� ⃗ T 1 are equal to (1,4,7). Since LCA ��� ⃗ P 1 , ��� ⃗ T 1 has a greater number of nodes than LCA ��� ⃗ P 2 , ��� ⃗ T 1 , it is now the LCA that makes the decision about the trip of T1 along ��� ⃗ P 1 . ...
... Researchers perform this investigation to examine the functionality of the suggested LCA. Following that, the LCA ��� ⃗ P 1 , ��� ⃗ T 1 are equal to (1,2,4,6) and the LCA ��� ⃗ P 2 , ��� ⃗ T 1 are equal to (1,4,7). Since LCA ��� ⃗ P 1 , ��� ⃗ T 1 has a greater number of nodes than LCA ��� ⃗ P 2 , ��� ⃗ T 1 , it is now the LCA that makes the decision about the trip of T1 along ��� ⃗ P 1 . ...
In academic institutions, the gathering of students within buildings significantly influences the ecological parameters of these spaces. Understanding and enhancing the environmental impact of academic buildings requires monitoring ecological parameters and crowd flow. The job of monitoring large-scale crowds and environmental conditions is a difficult one to do without difficulty. This study introduces reinforcement learning-based lightweight crowd flow measurement (RL-CFM) for real-time crowd flow tracking in institutional buildings. RL-CFM enables prompt responses to changes in crowd dynamics, enhancing its effectiveness during emergencies. The proposed RL-CFM periodically searches for smartphone-enabled requests, providing insights into crowd movement. Implemented and tested in an institutional building under real-world conditions, RL-CFM was installed in various locations, including the evacuation passage on the ground floor and two classrooms on the first floor. The study explores ecological parameters like temperature and CO2 concentration in the evacuation passage, considering various modes of smartphone operation that reflect people’s walking behavior. The RL-CFM’s performance is evaluated using different smartphone models with varying walking speeds, revealing a tracking accuracy of 94.32% in the Wi-Fi registered mode.
... In this paper, propose dynamic evacuation signage that can adapt to the fire's progression and d namically point to a safe emergency route. B. IoT-enabled Evacuation Sign Control Mechanism: In the IoT-enabled evacuation proaches in [8,9], the evacuation route is sent to the evacuees' phones. In other wor the evacuation route can only be sent to occupants who have installed the evacuat app. ...
... In this paper, we propose dynamic evacuation signage that can adapt to the fire's progression and dynamically point to a safe emergency route. B. IoT-enabled Evacuation Sign Control Mechanism: In the IoT-enabled evacuation approaches in [8,9], the evacuation route is sent to the evacuees' phones. In other words, the evacuation route can only be sent to occupants who have installed the evacuation app. ...
... The Fire Dynamics Simulator [33], developed by the United States Department of Commerce's NIST (National Institute of Standards and Technology), is a widely recognized tool in fire engineering for simulating the transport of smoke and heat in fires. In a study conducted by [8], it was confirmed that the smoke danger zone in a large shopping mall is more extensive than the heat danger zone, as demonstrated using FDS simulations. ...
In contemporary evacuation systems, the evacuation sign typically points fixedly towards the nearest emergency exit, providing guidance to evacuees. However, this static approach may not effectively respond to the dynamic nature of a rapidly evolving fire situation, in particular if the closest emergency exit is compromised by fire. This paper introduces an intelligent evacuation sign control mechanism that leverages smoke and temperature sensors to dynamically adjust the direction of evacuation signs, ensuring evacuees are guided to the quickest and safest emergency exit. The proposed mechanism is outlined through a rigorous mathematical formulation, and an ESP heuristic is devised to determine temperature-safe, smoke-safe, and congestion-aware evacuation paths for each sign. This algorithm then adjusts the direction light on the evacuation sign to align with the identified evacuation path. To validate the effectiveness of this approach, fire simulations using FDS software 6.7.1 were conducted in the Taipei 101 shopping mall. Temperature and smoke data from sensor nodes were utilized by the ESP algorithm, demonstrating superior performance compared to that of the existing FEL algorithm. Specifically, the ESP algorithm exhibited a notable increase in the probability of evacuation success, surpassing the FEL algorithm by up to 34% in methane fire scenarios and 14% in PVC fire scenarios. The significance of this improvement is more pronounced in densely congested evacuation scenarios.
Air quality degradation due to the release of toxic gases in the drainage system and sewage areas or septic tanks has led to the number of accidents increasing day by day. The manual scavengers risk their lives every day and die due to infections and diseases like fibrosis, lung cancer, typhoid, hepatitis, asthma, etc. caused by more prolonged exposure to hazardous gases. Gases like hydrogen Sulphide (H2S), Carbon Monoxide (CO), Methane (CH4), Ammonia (NH3), Sulphur Dioxide (SO2), etc. are released through the toxic waste produced due to the natural decomposition of the organic and inorganic wastes. These gases also lead to adverse effects on the central nervous system and immunity system. Some gases like hydrogen sulphide and methane are highly flammable and higher concentration of these gases can be explosive. Higher concentration of carbon monoxide in human body results in fatigue, headache, dizziness, and sometimes led to suffocation. Therefore, monitoring of the released toxic gases is important in such vulnerable areas for safeguarding the lives of workers. In this work, efforts have been made to design a system which can monitor toxic gasses released in the sewage and can also give alert signal if the quantity of any such gases is found to be greater than the hazard limit.
