# About Intelligent Sensor Fusion Computer Science Essay

Published: Last Edited:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

Fuzzy Logic: Fuzzy logic is extensively used in machine control. The term itself inspires convinced incredulity, sounding equivalent to half baked logic or bogus logic, but the fuzzy part does not refer to a lack of firmness in the method, rather to the fact that the logic involved can deal with fuzzy concepts-concepts that cannot be expressed as true or false but rather as partially true is called fuzzy logic.

2) IRISNet: The IrisNet (Internet scale Resource intensive sensor network services) is a potentially global network of smart sensor nodes and organizing nodes. Which present the means to query latest and historical sensor based data. Irisnet has two main components, sensing agents (SAs) and organizing agents (OAs) which are described as follows

Sensing Agents (SAs): SAs are devices that consist of a smart sensor (microphone, webcam etc) are attached to PC or PDAs class device. SAs collect and process data from the attached sensors and pass them on the organizing agents.

Organizing Agents (OAs): OAs are PCs in the Internet that provide services for querying present and historical data.

The purpose of this course work is to design an irisnet car parking system considering three parameters using fuzzy logic approach, which will instruct users in making quality decisions having in mind, the average travelling time as provided. When a person is on the way to the destination, he queries the system online about the parking space. This system tells the nearest parking areas to the destination where free parking spaces are available. The purpose here is to guide the user about parking lots and help him to find the parking spaces in minimum time.

To complete this task, I have applied a fuzzy logic development tool such as MATLAB Fuzzy Logic Toolbox. My system consists of three inputs and one output member ship functions, which are explained as follows.

II. JUSTIFICATION OF RULES

Defining Input Membership Functions:

Three input member ship functions are described as follows.

Input 1: Average Traffic Intensity Factor (p):

Average intensity factor of traffic on roads is taken as fuzzy variable p, characterizing it with three different fuzzy values: Low (L), Medium (M) and High (H). Figure 1 shows the triangle and trapezoids representation of membership functions.

Figure 1: Average Traffic intensity factor

Input 2: Average Distance from the Parking lot (s):

Let the average distance to parking lots in the destination vicinity s may be a fuzzy variable. The member ship function here ranges from 0 to 1, characterizing it with three different (fuzzy) values: Short (S), Medium (M) and Large (L).Figure 2 shows the triangle and trapezoidal member ship functions.

Figure 2: Average Distance from parking lot

Input 3: Average Occupancy of car park (m):

Average occupancy factor of car parks is denoted by fuzzy variable m, characterizing it with three different values: Small (S), Very Small (VS) and Medium (M). Average occupancy describes here is the space occupied in the park. Here we are using member ship functions trapezoidal and triangular as shown below in figure 3 and ranges are from 0 to 1.

Figure 3: Average Occupancy factor

Defining Output Membership Function:

Output: Average Travel Time required to car to reach at the destination (n):

The average travel time required to car reach at destination is denoted as n, characterizing it with six different values: Very Small (VS), Small (S), Relatively Small (RS), Medium (M), Relatively Large (RL), Large (L) and Very Large (VL). The member ship function for output ranges from 0 to 1 as shown in figure 4.

Figure4: Average Travel time required to reach the destination

In our system the choice of rules are made on research by using If- Then rule of fuzzy logic. We have total of 3 Input membership functions and 1 output member ship function. The combination of these inputs and output are tabulated in appendix at the end of report.

For example in our first rule if traffic intensity is low (L), distance is short (S) and average occupancy is very small (VS), the output, average travel time to destination will be very small (VS). In our rules we have given almost the same priority to each rule. If any one of the parameter will affect, it will affect the output which is average time required to reach at destination. In second rule if traffic intensity is low (L), average distance is short (S) and occupancy factor is small (S), the output will be small (S). Here only occupancy factor increases the time.

We have to use just common sense in choice of our rules. The rules will be in such a way that system efficiency should increase.

III. CRITICAL VIEW OF FINAL DESIGN

Surface Viewer:

Surface viewer is a read only tool. Surface plots shown below are obtained by using rules in appendix 1 as shown at the end of the report. Plot shown below are the simulations with two inputs and one output.

Fig. 5: Simulation of Average Intensity with Average Distance Fig. 6: Simulation of Average Distance with Average Occupancy

Fig. 7: Simulation of Average Intensity with Average Occupancy

In these plots all inputs are at the same priority. For example in figure (a) if average distance and average intensity is minimum then the time taken is also minimum. If average distance and average intensity is medium the time taken is also medium. If average intensity is maximum and distance is minimum the time taken is medium and so on.

Comparison of Average Occupancy, Intensity and Distance with Average Travel Time:

Comparisons of each input parameter with output are shown below. Inputs are defined almost at the same priority that's why these views are looking almost similar.

Fig.8: Comparison between Occupancy and Time Fig.9: Comparison between Intensity and Time

Fig.10: Comparison between Distance and Time

Rule Viewer:

In figure 11 if inputs for average intensity, average distance and average occupancy are 0.5 then the output we get is 0.5. In figure 12 if we decreases the all three input factors at 0.307 it will decrease the output to 0.453. In figure 13 if we increases the only distance factor from 0.5 to 0.765, it will increase the output (travel time) from 0.5 to 0.54. In figure 14 if we increase the two inputs i.e., average occupancy and average intensity from 0.5 to 0.789, it will increase the overall output from 0.5 to 0.617. This output from rule viewer shows that our results are up to expectations.

Fig.11: Showing inputs and output with no change Fig.12: Showing change in all inputs

Fig.13: Showing change in one input Fig.14: Showing change in two inputs

IV. CONCLUSIONS

From the above it can be observed that the system we design is giving result according to our expectations. The surface and rule viewers show the correctness of our system. All figures are looking almost the same because we have given equal priorities to all factors. Finally it can be observed from above details that our system is working fine and responding according to our requirements.

V. SUGGESTIONS FOR FURTHER WORK

From the above results we can further suggest the following improvements for the system.

By adding more inputs considering different factors in mind, for example any type of emergency, vehicle condition, road condition and weather conditions etc.

Appendix: Program code

[System]

Name='IRISnet_final_parking_datafinal'

Type='mamdani'

Version=2.0

NumInputs=3

NumOutputs=1

NumRules=27

AndMethod='min'

OrMethod='max'

ImpMethod='min'

AggMethod='max'

DefuzzMethod='centroid'

[Input1]

Name='Traffic_Intensity'

Range=[0 1]

NumMFs=3

MF1='LOW':'trapmf',[0 0 0.1 0.306]

MF2='MEDIUM':'trimf',[0.104 0.501 0.901]

MF3='HIGH':'trapmf',[0.697703703703703 0.957703703703704 1.0577037037037 1.0577037037037]

[Input2]

Name='Average_Distance'

Range=[0 1]

NumMFs=3

MF1='SHORT':'trapmf',[0 0 0.0622 0.36]

MF2='MEDIUM':'trimf',[0.102 0.507 0.903439153439153]

MF3='LARGE':'trapmf',[0.647936507936508 0.967936507936508 1.04793650793651 1.36793650793651]

[Input3]

Name='Average_Occupancy'

Range=[0 1]

NumMFs=3

MF1='VERY_SMALL':'trapmf',[0 0 0.08 0.36]

MF2='SMALL':'trimf',[0.104 0.498677248677249 0.898]

MF3='MEDIUM':'trapmf',[0.64 0.96 1.04 1.36]

[Output1]

Name='Average_Travel_Time'

Range=[0 1]

NumMFs=7

MF1='VS':'trapmf',[0 0 0.1 0.3]

MF2='S':'trimf',[0.137 0.252645502645503 0.4]

MF3='RS':'trimf',[0.244380952380952 0.382380952380952 0.509259259259259]

MF4='M':'trimf',[0.303 0.504 0.694]

MF5='RL':'trimf',[0.552 0.652116402116402 0.758]

MF6='L':'trimf',[0.599 0.728835978835979 0.9]

MF7='VL':'trapmf',[0.7 0.9 1 1]

[Rules]

1 1 1, 1 (1) : 1

1 1 2, 2 (1) : 1

1 1 3, 3 (1) : 1

1 2 1, 2 (1) : 1

1 2 2, 3 (1) : 1

1 2 3, 4 (1) : 1

1 3 1, 3 (1) : 1

1 3 2, 4 (1) : 1

1 3 3, 5 (1) : 1

2 1 1, 2 (1) : 1

2 1 2, 3 (1) : 1

2 1 3, 4 (1) : 1

2 2 1, 3 (1) : 1

2 2 2, 4 (1) : 1

2 2 3, 5 (1) : 1

2 3 1, 4 (1) : 1

2 3 2, 5 (1) : 1

2 3 3, 6 (1) : 1

3 1 1, 3 (1) : 1

3 1 2, 4 (1) : 1

3 1 3, 6 (1) : 1

3 2 1, 4 (1) : 1

3 2 2, 5 (1) : 1

3 2 3, 6 (1) : 1

3 3 1, 5 (1) : 1

3 3 2, 6 (1) : 1

3 3 3, 7 (1) : 1