intelligent escalator passenger safety management

Project Title

intelligent escalator passenger safety management

Project Area of Specialization Artificial IntelligenceProject Summary

This Project addresses an approach to intelligent safety control of passengers on escalators. The aim is to improve the accuracy of detecting threatening situations on escalators in the subway to make decisions to prevent threats and eliminate the consequences. The novelty of the approach lies in the complex processing of information from three types of sources (video, audio, sensors) using machine learning methods and recurrent neural networks with controlled elements. The conditions and indicators of safety assurance efficiency are clarified. New methods and algorithms for managing the safety of passengers on escalators are proposed. The architecture of a promising safety software system is developed, and implementation of its components for cloud and fog computing environments is provided. Modeling results confirm the capabilities and advantages of the proposed technological solutions for enhancing the safety of escalator passengers, efficiency of control decision making, and system usability. Due to the proposed solutions, it has become possible to increase the speed of identifying situations 3.5 times and increase the accuracy of their determination by 26%. The efficiency of decision making has increased by almost 30%.

Project Objectives

The Objectives are as follows:

Ensuring safety of the passenger in case of malfunction of escalator equipment or its parts (electricity, mechanics, etc.).

Detect defect/fault in Escalator.

Measures to prevent a threat or eliminate its  consequences.

Overload Alert.

Provision of timely assistance to the passenger in case of a sharp deterioration of health.

Timely assistance to low-mobility passengers (disabled persons).

Project Implementation Method

The proposed  system has a three-level architecture:

1. End user application is installed on smartphones under iOS or Android.

2. The program for data processing control is deployed in a fog computing environment.

3. Data processing program is deployed in the cloud.

Processing of all types of data takes place in the cloud using the high-performance system Microsoft Azure;

obtaining data characteristics necessary for control and carrying necessary data prepossessing is performed in

a fog environment, and the result is delivered to the safety operator’s smartphone or tablet. Cloud technologies

involve the use of the control console (through a website or command line), which simplifies to a large extent the

deployment of applications. Options for selection and configuration of different versions of operation systems

(Windows, Linux, Mac, FreeBSD, CentOS, etc.), necessary software (various web servers, machine learning

libraries, network administration programs, remote control, etc.) are provided via control console. At the fog

level, virtual machines are used, which, unlike the traditional VMware Workstation (https://www.vmware. com),

Virtual PC from Microsoft, can be adapted to certain technical means (taking into account storage parameters

and systems, chip-sets, central and graphics processors). Adaptation to hardware parameters enhances the efficiency of virtual machine resources by the users of applications.

Ready-made servers can be adapted to solve certain problems in the fog environment. For example, a Cisco

UCS C480 ML M5 server that differs from a user home computer by price (20 or even 30 times more expensive)

and by preinstalled software, necessary drivers, components (discrete and analog input boards for video, audio,

sensors), has a processor with a powerful NVIDIA Tesla V100 RAM graphics core, 96GB of RAM, a control

console that optimizes the resource consumption of a fog computing environment, is offered for use for solving

tasks using machine learning and neural networks. Servers that are adapted for other tasks (production process

control, banking operations, etc.) are also provided.

Benefits of the Project

Intelligent escalator passenger safety management will be used by subways and train stations, shopping malls, underground

passages and other objects of public infrastructure.

Improve the accuracy of detecting threatening situations on escalators in the subway to make decisions to prevent threats and eliminate the consequences.

Registration of a chronology of events in case of an emergency.

Ensuring safety of the passenger in case of malfunction of escalator equipment or its parts (electricity, mechanics, etc.)

Technical Details of Final Deliverable

Call an operator to assist a disabled person in case of his inability to move independently and absence of an

accompanying specialist.

• Stop the escalator in case of items stuck, in particular shoes, clothes or body parts in escalator equipment

mechanisms (comb, side parts of balustrade, handrails, etc.).

• Call an ambulance if the passenger falls from the escalator and is injured.

• Call the police and special services in case of a terrorist threat.

• Call the fire fighter, stop the escalator, turn on the fire prevention system, de-energize the escalator in case

of smoke, fire or open burning, previously persuading in the high degree of danger of the situation that has

arisen, i.e., making sure that the smoke is not the result of cigarette smoking or the actions of a minor bully

who has set fire to an article or other objects.

• De-energize the escalator and call emergency services in case of electrostatic failure.

• Switch on the backup brake system in case of failure of the main brakes or damage of the escalator engine or

side handrails

Final Deliverable of the Project Hardware SystemCore Industry ITOther Industries Security Core Technology Augmented & Virtual RealityOther Technologies Artificial Intelligence(AI)Sustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	80000
documents in hard copy	Miscellaneous	5	2000	10000
Autonic BJ1M-DDT	Equipment	2	11500	23000
Escalator sensor	Equipment	1	12000	12000
Drive machine	Equipment	2	5000	10000
Gear Reducer	Equipment	1	10000	10000
Handrail System	Equipment	1	15000	15000