An Improved Vehicle Parking Mechanism To Reduce Parking Space Searching Time Using Firefly Algorithm And Feed Forward Back Propagation Method

ABSTRACT

An issue of finding parking space is a serious concern in some locations, especially shopping complexes, hospitals, buildings, malls and other premises requires large parking space for vehicles. The parking scenario becomes worst on special occasions like festivals, fiesta and weekends. The conventional developed techniques using installation of sensors in parking zone for parking vehicles becomes costly. Therefore, a reliable method is required that works for long time to manage traffic congestion that occurs while searching for parking space. In this paper, a novel method is proposed for parking vehicles using metaheuristic approaches. The developed approach provides consistent results considering two parameters, parking efficiency and parking space search time. The parking efficiency is improved and parking space search time is reduced using the Firefly Algorithm (FA) and Feed Forward Back Propagation Neural Network (NN) approach.

CHAPTER ONE

1.0  INTRODUCTION

1.1  BACKGROUND OF THE STUDY

There is a general problem of finding free space for parking vehicles in crowded cities, particularly at shopping centres, theatres, sports venues, wedding places, hospitals and other tourist destinations [1]. There is a great complexity for the beginners to park a vehicle in peak hours, such as holidays, weekends etc. The problem of parking occurs due to inadequate space for parking which in turn leads to congestion and people often gets frustrated because of not finding available space for parking. Meanwhile, the problem of parking becomes worst as more population is migrating from towns to cities. So, automated parking methods were developed to access the parking spaces. These methods include implementation of Light Emitting Diode (LED) boards for counting parked vehicles, but it is not successful as detecting vacant locations is not possible. In addition, the installation and maintenance process of LED boards is costly and cumbersome as parking lot ceiling require wires for connecting parking sensors. Thus, a lot of research has been conducted for smart parking solutions in an affordable cost [2] but some cities does not have spatial resources to meet the need. Thus, alternative ways are suggested to solve the problem of parking. Researchers attempted to remove unnecessary parking sites for better planning of parking management. Though, if visitors have real time information about the location of parking spaces, then waiting time can be reduced with the adjustment of travelling schedule [3]. Smart parking solutions and intelligent systems provide a way to access information about the efficient parking lots. The main objective of adopting intelligent systems is to efficiently manage available resources, more specifically; parking facilities were enhanced to increase the space for parking using parking rotary systems. But these methods still needs more advancement for finding the best solution. The real time information accessed by predictive approach based on neural network provides the best solution [4]. Prediction model analyze the strengths of learning methods using prediction features. Furthermore, Support vector regression model was proposed to access vacant spaces for a specific time. The experiments were conducted to predict the available parking spaces. The proposed model was evaluated using different machine optimization algorithms [5]. In this paper, an improved model has been proposed to determine the vacant parking spaces using Firefly Algorithm which has been used with Feed Forward Back Propagation Neural Network method (FA-NN).

1.2                                    PROBLEM STATEMENT

Because of the advancement in technological worlds, people often use cars and vehicles in daily life to meet their routine needs. The parking scenario comes in concern due to the traffic congestion and jamming problems. The problem becomes worst, when drivers wait for the long time, which results in wastage of fuel and time. More specifically, there were many solutions proposed in the literature. Some were sensor based, which increases the cost while other relies on individual needs. Therefore, to resolve the issue of vehicle parking in a parking lot, an improved novel firefly algorithm based detection system has been developed. The developed method has been evaluated using feed forward back propagation method, a neural network technique.

1.3                       AIM /OBJECTIVES OF THE PROJECT

The aim of this project is to solve these problems of car parking using automatic car parking slot indicator using microcontroller. The microcontroller serves as a programming tool to run the whole operation, to  reduce  the  cost  in  terms  of  requirement  such  as  job opportunity  and to increase security. Moreover, this system is faster, flexible and can meet market needs. The system also has software which fulfils the following objectives:

1. To indicate Reserve parking space
2. To solve car congestion problem

• Generates bar code after payment

1.4                               PURPOSE OF THE PROJECT

The purpose is to control the number of the car inside it, how to monitor the movement in/out side of the parking lot, how to check whether there is a place inside for more cars or not and the safety to park.

1.5                                  SCOPE OF THE PROJECT

The scope of this project covers “improved Car Parking System” which controls parking spaces. The novel approach includes the Firefly Algorithm which has been used with Feed Forward Back Propagation Neural Network method (FA-NN). The effectiveness of proposed approach has been evaluated using the parameters parking efficiency and parking space search timing measurement.

1.6     SIGNIFICANCE OF THE PROJECT

It will enable the drivers at the exit gate to enter if there is any empty space in the parking and disable them to enter when there is no empty space. It will manage the main parking spaces by alerting the drivers if there are spaces to park in or not. It will provide an automated system that whenever there is no space no one can access the parking and when there is space drivers can access the parking.

In terms of money, this project has two things in   general; namely: It will reduce the number of people needed at the gate to guide drivers.

It will provide a way of getting money for any institution that has this system because it can be put on the market and people use it for their interest like in a commercial sector where an institution has movement of clients that have vehicles and the institution cannot support them at the same time; hence this automated system can be a solution.

1.7                          APPLICATIONS OF THE PROJECT

This device is used in public places such as:

1. Garage
2. Worshipping centres

• Industries

1. Business areas

To provide ease, and sense of safety and security of the vehicle in the crowded areas

1.8                            LIMITATION OF THE PROJECT

1. There is a greater construction cost per space
2. Use of redundant systems will result in a greater cost.

• It may be a bit confusing for unfamiliar users.

1. There may be a fear of breakdown. The system might malfunction if a sensor gets damaged

1.9                                BENEFIT OF THE PROJECT

1. There is a greater sense of security due to the fact that patrons do not actually walk to and from their own space.
2. It is highly feasible for extremely small sites that are unable to accommodate a conventional ramped parking structure.

iii. There is high parking efficiency

1. There is no need for driving while looking for an available space.
2. Emissions are greatly brought down and reduced.

• The patrons wait for their car in a highly controlled environment.
• There are less chances for vehicle vandalism.

1. There is a minimal staff requirement if it is used by known parkers.