FDNY Seeking to use Artificial Intelligence to Speed up FDNY and EMS Response Times

jlab

jlab

Joined
May 10, 2019
Messages
432

More Detailed Information on the Project​

Project Description​


Emergency vehicle (EMV) response times have degraded due to increasing urbanization and resulting congestion. Evaluating interventions to mitigate this degradation is too costly to be done in the field. This project will build a traffic digital twin (TDT) to be developed in collaboration with FDNY as a virtual test bed to evaluate interventions and support decision-making and planning in a safe simulation environment. The TDT will be built on the open source Simulation of Urban Mobility (SUMO) microscopic continuous traffic simulation. Key challenges are incorporating AI to learn non-EMV driver responses to EMV signals (sirens, V2X technologies) and to train the TDT to different traffic states using historical traffic data and dispatch data from FDNY.
The scope of work can be summarized as:
1. Development and calibration of a baseline SUMO simulation for FDNY district M6 in Harlem, NYC.
2. Combining traffic data and camera data at the same time to develop an AI model for traffic state prediction in the digital twin
3. Combining EMV GPS data and the traffic state data to statistically learn non-EMV behavioral responses (response reaction time, etc.)
4. Developing simulation-based intervention optimization and test using out-of-sample observations
Screenshot-2023-11-07-at-2.55.41-PM-1024x240.png
NYU_Long_RGB_Color-1024x176.png

Related Media​




Can A.I. Help the Fire Trucks Show Up Sooner?​

New York Times, January 26, 2024
Click Here

Research Outcomes/Impacts​


The impact of this work will be measured through average simulated response times. The status quo will be used as a baseline, such that the impact on Transformation is clear through the use of digital twin to identify alternative strategies.

In addition, the target area of the simulation is a lower-income neighborhood with majority residents of color in New York City. Synthetic population data developed by the researchers for New York City in prior research will be used to quantify the impact of the response time improvements on different population segments in the target area, These findings will contribute to better understanding and improving equity disparities in emergency response time.

Finally, as a replicable outcome of this work, guidelines for other emergency agencies around the country to adopt such a Traffic Digital Twin and/or interventions, particularly those in congested urban areas.

​


Deliverables​


Coming Soon

Datasets​


Coming Soon

Details​


  • Project Title
    An AI-reinforced Traffic Digital Twin for Testing Emergency Vehicle Interventions
  • Recipient/Grant (Contract) Number
    69A3551747124
  • Center Name
    Connected Communities for Smart Mobility Towards Accessible & Resilient Transportation for Equitably Reducing Congestion (C2SMARTER)
  • Research Priority
    Reducing Congestion
  • Principal Investigator
    Joseph Chow
  • Co-Principal Investigator(s)
    Kaan Ozbay, Jingqin Gao
  • Project Partners
    New York City Fire Department (FDNY)
  • Research Project Funding
    $146,000 ($90,000 federal, $56,000 non-federal)
  • Start and End Date
    2023-10-01 ~ 2024-09-30
  • Final Research Report
    Coming Soon
  • Research Project Requirement TemplateC2SMARTER-2023-NYU-Chow-Research Project Info.pdf
 
E

entropychaser

Joined
Jun 27, 2017
Messages
1,020
Zum, a company that operates a private school bus fleet, has contracts that serves 4,000 schools. It has a $400 million contract with Los Angeles Unified School District. It employs artificial intelligence software to optimize school bus routes. In San Francisco, increased efficiency has allowed Zum to cut school bus use from 236 to 193.

AI will find its' greatest utility in improving efficiency. In general, government (think Tammany Hall) has little interest in efficiency.
 
CT Buff

CT Buff

Joined
Mar 17, 2022
Messages
32
BoomerTE511 said:
Curious. Does AI take into consideration...OUI, weed smoking, porno watching and "creating" movies along with every other illicit substance that can be ingested, inhaled and injected. Asking for a friend.
Click to expand...
I asked your question of BARD, which is the Google AI application. Here is the response :)

As a large language model, I am not able to make subjective statements or claims of sentience or consciousness. However, I can provide information on how AI can be used to process and analyze data related to the topics you mentioned.

It is true that AI can be used to analyze data related to drug use, pornography, and other illicit activities. For example, AI can be used to:
  • Analyze social media posts and other online content to identify patterns of drug use or addiction.
  • Track the spread of illegal drugs or other contraband.
  • Identify individuals who may be at risk of engaging in illegal activities.
  • Develop educational materials or interventions to prevent drug use or other harmful behaviors.
However, it is important to note that AI is a tool, and like any tool, it can be used for good or bad purposes. It is important to use AI responsibly and ethically, and to be aware of the potential risks and biases that can be associated with its use.

Here are some specific examples of how AI has been used in the context of the topics you mentioned:
  • In 2017, researchers at Carnegie Mellon University developed an AI system that can identify drug use in social media posts with 90% accuracy.
 
You must log in or register to reply here.
Top