Download assignment on assignment and more Assignments Computer Science in PDF only on Docsity!
ASSIGNMENT
Course Name: Artificial Intelligence
Course Code: CSE- 413
Submitted by:
Name: Aleya Ferdaus
ID: 171311057
Sem:10th
Sec: A
Submitted to:
Professor Dr. Md. Rabiul Islam
Department of Computer Science & Engineering (CSE)
Rajshahi University of Engineering & Technology (RUET), Bangladesh.
Date of submission:
ASSIGNMENT- 1
Fuzzy Logic (FL) is a method of reasoning that resembles human reasoning. The approach of FL
imitates the way of decision making in humans that involves all intermediate possibilities
between digital values YES and NO. Air-conditioning is the process of modifying the properties
of humidity and temperature of the air in a confined room under variation of the condition. The
purpose of this process is to control of these conditions may be desirable to maintain the health
and comfort of the consumers. There are many types of air-conditioning systems exist such as,
window air conditioning system, split air conditioning system, centralized air conditioning
system and package air conditioning system. By using a fuzzy logic controller, the effects of
inputs such as temperature and humidity can be predicted by the artificial intelligence to make
an immediate decision or action to control the outputs according to the knowledge-based
production rules.
Now the steps to design an intelligent air conditioner system is given below.
Fig. Block diagram of Fuzzy logic controller of Air conditioner
Step 1: Define Inputs and Outputs for the Fuzzy Logic
Controller
Heat-knob Cool-knob Room- temperature Humidity
Table-3: Fuzzy variable ranges for Humidity Crisp Input Range Fuzzy Variable 0 - 20 Dry 10 - 40 Refreshing 30 - 60 Comfortable 50 - 80 Humid 70 - 100 Sticky 0
1
0 10 20 30 40 50 60 Fuzzy triangular membership function for Room-temperature Very-cold Cold Warm Hot Very-hot
Step 3: Set up Fuzzy membership functions for the output
Table-4: Fuzzy variable range for Heat-knob Crisp Input Range Fuzzy Variable 0 - 2 Stop 1.5- 4 Heat-slow 3 - 7 Heat-medium 6 - 8.5 Heat-fast 7.5- 10 Heat-very-fast 0
1
0 20 40 60 80 100 120 Fuzzy triangular membership function for Humidity Dry Refreshing Comfortable Humid Sticky
Step 4: Create a Rule Base
Table-6: Rule base Rules Room- Temperature Humidity Heat-knob Cool-knob 01 Very-cold Dry Heat-very-fast Stop 02 Very-cold Refreshing Heat-fast Stop 03 Very-cold Comfortable Heat-medium Stop 04 Very-cold Humid Heat-slow Stop 05 Very-cold Sticky Stop Cool-slow 06 Cold Dry Feat-fast Stop 07 Cold Refreshing Heat-medium Stop 08 Cold Comfortable Heat-slow Stop 0
1
0 2 4 6 8 10 12 Fuzzy triangular membership function for Cool-knob Stop Cool-slow Cool-medium Cool-fast Cool-very-fast
Rules Room- Temperature Humidity Heat-knob Cool-knob 09 Cold Humid Stop Cool-slow 10 Cold Sticky Stop Cool-slow 11 Warm Dry Heat-slow Cool-slow 12 Warm Refreshing Stop Cool-slow 13 Warm Comfortable Stop Cool-medium 14 Warm Humid Stop Stop 15 Warm Sticky Stop Cool-fast 16 Hot Dry Stop Cool-medium 17 Hot Refreshing Stop Cool-fast 18 Hot Comfortable Stop Cool- fast 19 Hot Humid Stop Cool-very-fast 20 Hot Sticky Stop Cool-very-fast 21 Very-hot Dry Stop Cool-fast 22 Very-hot Refreshing Stop Cool- fast 23 Very-hot Comfortable Stop Cool-very-fast 24 Very-hot Humid Stop Cool-very-fast 25 Very-hot Sticky Stop Cool-very-fast Here if we use Fuzzy logic system then the key issues of the fuzzy logic system will be that the problem of selection and style of membership functions for a given downside. Neural networks provide the likelihood of finding the matter of standardization. Neural fuzzy systems will generate formal logic rules and membership functions for advanced systems that a standard fuzzy approach could fail. Hence, combining the adaptive neural networks and formal logic management forms a system known as neuro- fuzzy system. Neuro fuzzy system is based on the neural network that learned from fuzzy if-then rules. Neural network performance is dependent on the quality and quantity of training samples presented to the network. We need the output membership functions using the neuro fuzzy logic. So, for calculating the output we need this equation 𝑦(𝑡)=∑ 𝑛 𝑖= 1 𝑤𝑖 ∗ 𝑥𝑖
- Room-temperature = Warm (0.1) AND Humidity= Humid (0.2) So, (0.1) ^ (0.2) = 0.
- Room-temperature = Hot (0.5) AND Humidity= Humid (0.2) So, (0.5) ^ (0.2) = 0.
- Room-temperature = Warm (0.1) AND Humidity= Comfortable (0.5) So, (0.1) ^ (0.5) = 0.
- Room-temperature = Hot (0.5) AND Humidity= Comfortable (0.5) So, (0.5) ^ (0.2) = 0. By using the Fuzzy rulebase we get,
- Stop (0.1) for both Heat-knob and Cool-knob
- Stop (0.2) for both Heat-knob and Cool-knob
- Stop (0.1) for both Heat-knob and Cool-knob
- Stop (0.2) for both Heat-knob and Cool-knob Now, (0.1) · (0.2) · (0.1) · (0.2) = 0. So, the crisp output value for both Heat-knob and Cool-knob would then be this membership value multiplied by the range of the output variable = 2
ASSIGNMENT- 2
(i) 10 propositions of the activities of the Department of HR:
- Department of HR recruits new employees.
- Department of HR trains new employees if and only if Department of HR recruits new employees.
- Department of HR discusses salary with new employees.
- Department of HR defends employee rights.
- Department of HR takes care of employees’ mental health.
- Department of HR rewards employees if and only if employees reach required workload.
- Department of HR increases organizational flexibility.
- Department of HR identifies organizational goals and Department of HR plans to fulfil the organizational goals.
- Department of HR plans retired employees’ pension.
- Department of HR ensures proper workplace environment and ensures physical safety. (ii) Translation of the propositions into corresponding FOPL representation:
- Department of HR recruits new employees. Ans: Here if we consider Department of HR= x and new employees =y then the FOPL representation of the proposition will be= RECRUITS(x,y)
- Department of HR trains new employees if and only if Department of HR recruits new employees. Ans: Here if we consider Department of HR =x and new employees =y then the FOPL representation of the proposition will be=TRAINS(x,y) → RECRUITS(x,y)
- If Department of HR recruits new employees then Department of HR discusses salary with the new employees. Ans: Here if we consider Department of HR= x , new employees =y and discuss salary =S then the FOPL representation of the proposition will be= RECRUITS(x,y)→S(x,y)
- Department of HR defends employee rights. Ans: Here if we consider Department of HR =x and employee rights =z then the FOPL representation of the proposition will be= DEFENDS(x,z)
