MIT Solve

Solution Overview

Solution Name:

Infectious Disease Deep Detection

One-line solution summary:

A system that detects and tracks potential infectious disease carriers through surveillance cameras using deep learning techniques.

Pitch your solution.

We are facing a rapid spread of pandemic disease. Our solution is aimed to reduce the spread of pandemic disease; track and monitor the potential infector’s activity in a closed area. We proposed Infectious Disease Deep Detection (IDDD) system that detects and tracks potential infectious disease carriers through surveillance cameras using cloud computing and deep learning techniques. It can be used to perform tracking and recognising any potential infectious person in an effective way. With DLDPID, we can help the government to track the potential infectious person based on the previous place the infected person has visited, and find out the closed contact person to prevent the disease from spreading. This also can raise personal precaution by notifying them about the infected person

What specific problem are you solving?

The standard of operating procedure (SOP) to reduce the risk of COVID-19 infection rate includes the process of acquiring the body temperature of the visitors in every entrance of the building. This process requires laborious manpower and often causes congestion due to a long visitor queue. Hence, we propose a system that combines the surveillance camera with a thermal sensor to track the body temperature of visitors. The facial information and body temperature are uploaded to the online database through cloud services. Another issue faced during this pandemic is to accurately track the person who has closed contact with the COVID-19 carrier. Hence, the system employs several deep learning techniques to recognize the face of the infected person (subject) from the recorded video, track the paths where the subject travelled before, and determine the crowd of people who have close contact with the subject. Blind spot is the limitation of the surveillance camera system. We also implement deep learning techniques to predict the direction and footage of the subject when the subject enters the blind spot. This technique can avoid the misdetection of the person who might have closed contact with the COVID-19 carrier in the blind spot area.

What is your solution?

Infectious Disease Deep Detection (IDDD) is a system that detects and tracks potential infectious disease carriers through surveillance cameras using cloud computing and deep learning techniques. The surveillance camera system consists of a normal video camera, a thermal camera, and a microcontroller with WiFi features. In the microcontroller of the surveillance camera system, a deep learning method namely convolution neural network- long short term memory (CNN-LSTM) is implemented to track visitors’ facial information from the dynamic images (video). The deep learning technique will return the position of the visitor face and is used to localize the visitor’s human body temperature from the thermal images. Then, the visitor's facial information and his/her body temperature value will be uploaded to the online database using the WiFi IoT feature of the microcontroller. If the surveillance camera system detects a visitor’s body temperature is above normal level, the system will alert the authority and keep tracking the position of the detected subject. Besides, if any visitor who has visited a building claims that he/she is a positive COVID-19 carrier (subject), it is mandatory to find out people who have closed contact with the subject during his/her visit.

Who does your solution serve, and in what ways will the solution impact their lives?

The Infectious Disease Deep Detection (IDDD) system is used to perform tracking and recognising any potential infectious person in an effective way. With DLDPID, we can help the government to track and check the potential infectious person based on the previous place the infected person went, and the closed contact person to prevent the disease from spreading. This also can raise personal precaution by notifying them about the infected person. The current coronavirus 2019 disease (COVID-19) pandemic has greatly changed our perspective of the risk for infection from contact. Without any supervision, it can be hard to track the visited place and closed contact person with the potential cluster COVID-19. Therefore, surveillance cameras play an important role to supervise any potential cluster to prevent the spread of disease. The DLDPID system can predict the path that will be taken by the user if the user was not captured by the surveillance camera. With the help of deep learning, this system can identify and track a person, multi-person or people correctly. It can monitor continuously 24 hours per week without having a rest. In this way, the possibility of time taken to detect potential clusters can be reduced and prevent the spread of COVID-19. The IDDLD system can be used to perform tracking and recognising potential infectious persons in an effective way. With DLIDPI, we can help the government to track the potential infectious person based on the previous place the infected person has visited, and find out the closed contact person to prevent the disease from spreading.

Which dimension of the Challenge does your solution most closely address?

Prevent the spread of misinformation and inspire individuals to protect themselves and their communities, including through information campaigns and behavioral nudges.

Explain how the problem you are addressing, the solution you have designed, and the population you are serving align with the Challenge.

Identify (Determine & limit the disease risk pool & spill over risk): Surveillance cameras are commonly used for security purposes that help to ensure safety of a place. The IDDD is able to detect any person who may have close contact with the infected person, record the time and location that had gone by the infected person. The surveillance camera is powered by AI and able to monitor 24/7 without any help of manpower. An analysis of video data will be done by using crowded analysis, path prediction method with deep learning model

In what city, town, or region is your solution team headquartered?

Malacca, Malaysia

What is your solution’s stage of development?

Concept: An idea being explored for its feasibility to build a product, service, or business model based on that idea.

Explain why you selected this stage of development for your solution.

The Infectious Disease Deep Detection (IDDD) system is in the proof of concept stage. We have done a lot of reading and literature review on deep learning and computer vision. Besides, we also know that we can use thermal vision to extract the temperature based on current research. Moreover, multi-human tracking is also possible to be done by using deep learning models such as convolutional neural networks with long short term memory. The crowd analysis in deep learning is the most challenging part and most effective way to detect each person in a crowd. The crowd analysis has used localization and counting techniques. The localization technique can be used for localizing the crowded scenes by using density of the maps. The counting technique can estimate the number of people in a video or image. The main steps in recognition systems are pre-processing, feature extraction, object tracking and behaviour understanding.

Who is the Team Lead for your solution?

Prof Dr Ir Sim Kok Swee