Artificial Intelligence and its Application in Different Areas Group Research – BSCS Department of Computer Science – UBIT Summary

Artificial Intelligence and its Application in Different Areas
Group Research – BSCS
Department of Computer Science – UBIT
In this summary, we discuss about Artificial Intelligence and its impact on daily life and the research on it for upcoming technologies and its importance in future. We’ll also discuss about the applications of Artificial Intelligence in detail. In this research paper, we highlight about all the important terms mentioned above.

Abstract: Artificial intelligence is the intelligence exhibited by machines or software. It is the subfield of computer science.
Introduction: It is claimed that artificial intelligence is playing an increasing role in the research of management science and operational research areas. The various techniques applied in artificial intelligence are Neural Network, Fuzzy Logic, Evolutionary Computing, and Hybrid Artificial Intelligence.

Fig 1. Papers published on different Artificial Intelligence Techniques used
The Turing Test Approach: The Turing test was proposed Alan Turing (1950) .This test was designed to test that whether a particular machine can think or not.
AREAS OF ARTIFICIAL INTELLIGENCE: To translate from spoken language to a written form and to translate from one natural language to another natural language. The Representation Problem for Problem Solving Systems Modeling Natural Systems (Economic, Sociological, Ecological, Biological etc.) Learning and adaptive systems: The ability to adapt behavior bagged on previous experience, and to develop general rules concerning the world based on such experience.

Best services for writing your paper according to Trustpilot

Premium Partner
From $18.00 per page
4,8 / 5
Writers Experience
Recommended Service
From $13.90 per page
4,6 / 5
Writers Experience
From $20.00 per page
4,5 / 5
Writers Experience
* All Partners were chosen among 50+ writing services by our Customer Satisfaction Team

Applications of artificial intelligence: The PSS is an additional control system, which is often applied as a part of an excitation control system. They perform within the generator’s excitation system to create a part of electrical torque, called damping torque, proportional to speed change. In the field of power system operation computer programs are executed and modified frequently according to any variations. Radial basis function network (RBFN) has three layers: input layers, hidden layers, and output layers.

Fuzzy Logic (FL) in PSS: For the robustness of the FLPSS, five generator power systems were used and for designing a normalized sum-squared deviation index were used. The input signal to FLPSS is the speed deviation of the synchronous generator and its derivative. This A novel input signal based FLPSS was applied in the multi-machine environment. A design process for a fuzzy logic based PSS (FLPSS) was proposed for a multi-machine power system. In 1964, Lotfi Zadeh developed FL to address inaccuracy and uncertainty which usually exist in engineering problems.

Application of Artificial Intelligence Techniques in Network Intrusion Detection:
Intrusion Detection System (IDS) is the process of monitoring the events occurring in network and detecting the signs of intrusion. Intrusion Detection Systems (IDS) uses the various Artificial Intelligence techniques for protecting computer and communication networks from intruders.

a)Artificial Neural Network in IDS:
Basically, the ANN has been generalized to: yi=f(?wikxk+µi) (1) k Where wik are weights attached to the inputs, xk are inputs to the neuron i, ?i is a threshold, f (•) is a transfer function and yi is the output of the neuron. In this a neuron calculates the sum by multiplying input by weight and applies a threshold. In IDS ANN are used to model complex relationships between inputs and outputs or to find patterns in data. The result is transmitted to subsequent neurons. ANN is a mathematical model that consists of an interconnected group of artificial neurons which processes the information.

b) Fuzzy Inference Systems (FIS) in IDS:
Their experiment also showed the importance of variable selection, as the two techniques performed worse when all the variables were used without selection of the variables. Generally, both techniques proved to be good, but with the Fuzzy Inference System having an edge over Artificial Neural Networks with its higher classification accuracies. From the results, it was shown that the Fuzzy Inference System was faster in training, taking few seconds, than the Artificial Neural Networks which took few minutes to converge proposed two machine learning paradigms: Artificial Neural Networks and Fuzzy Inference System, for the design of an Intrusion Detection System. They then tested and validated the models using the 1998.

Application of Artificial Intelligence Techniques in Medical Area
Artificial intelligence techniques have the potential to be applied in almost every field of medical area.

•Artificial Intelligence in Medicine
Fuzzy Expert Systems in Medicine
Fuzzy logic is also used in the diagnosis of acute leukemia and breast and pancreatic cancer and also predict patients? survival with breast cancer. Fuzzy logic is preferred over the multiple logistic regression analysis in diagnosing lung cancer using tumor marker profiles. The techniques of fuzzy logic have been explored in many medical applications. Fuzzy logic is a data handling methodology that permits ambiguity and hence is particularly suited to medical applications. They can also characterize MRI images of brain tumors ultrasound images of the breast, ultrasound. Fuzzy logic controllers have been designed for the administration of vasodilators in the peri-operative period to control blood pressure.

b) Evolutionary Computation in Medicine:
„Genetic Algorithms? based on the natural biological evolution are the most widely used form of evolutionary computation for medical applications. The most widely used form of evolutionary computation for medical applications are „Genetic Algorithms? 8. Evolutionary computation is the general term for several computational techniques based on natural evolution process that imitates the mechanism of natural selection and survival of the fittest in solving real-world problems. The principles of Genetic algorithms have been used to predict outcome in critically ill patients. MRI segmentation of brain tumors to measure the efficacy of treatment strategies is also done through evolutionary computation. They have also been used in computerized analysis of mammographic micro calcification.

Using Artificial Intelligence to Improve Hospital Inpatient Care:
Clinical decision support systems (CDSS) were one of the first successful applications of AI, focusing
Mycin a rule-based expert system for identifying bacteria causing infections and recommending antibiotics to treat these infections was developed in 1970 under the work of CDSS for medical diagnosis. Pathfinder, which used Bayesian networks to help pathologists more accurately diagnose lymph-node diseases. Such approaches help in the diagnosis of various forms of cancer, and congenital heart defects. AI has also been useful for computer-aided detection of tumors in medical images. Primarily on the diagnosis of a patient’s condition given his symptoms and demographic information.

Artificial Intelligence Approaches for Medical Image Classification:
CAD helps radiologist who uses the output from a computerized analysis of medical images as a second opinion in detecting lesions, assessing extent of disease, and improving the accuracy and consistency of radiological diagnosis to reduce the rate of false negative cases. Model-based intelligent analysis and decision-support tools are important in medical imaging for computer-assisted diagnosis and evaluation. Artificial intelligence techniques are used for diagnostic sciences in biomedical image classification.

Artificial Neural Networks Approach on Diagnostic Science:
The following subsections will discuss how ANN is utilized for image classification over generations.
Endoscopic Images:
The concept of fusion of multiple classifiers dedicated to specific feature parameters with an accuracy of 94. In classification of endoscopic images a hybrid implementation by advanced fuzzy inference neural network which combines fuzzy systems and Radial Basis Function (RBF) was proposed. Image classification is an important step in CAD. It extracted both texture and statistical features. 28% but RBF was characterized by a very fast training rate than fuzzy.

MRI Brain Tumor Analysis:
For the MRI brain tumor images a general regression neural network (GRNN) based automatic three-dimensional classification method was proposed. This technique had a higher accuracy of classification over other classifiers as the false negative in LS-SVM was very low compared. Due to automatic defects detection in MR images of brain, extensive research is being performed. Another intelligent classification technique proposed was Least Squares Support Vector Machines (LS-SVM. This method had good time consuming rate and classification accuracy. It identifies normal and abnormal slices of brain MRI data.

Application of Artificial Intelligence in Accounting Databases:
Integrating intelligent systems with accounting databases can assist (either with the decision maker or independent of decision maker) in the investigation of large volumes of data with or without direct participation of the decision maker. The artificial intelligence and expert system builds intelligence into the database to assist users. Thus, the systems can analyze the data and assist the users understanding or interpreting transactions to determine what accounting events are captured by the system 5. The use of artificial intelligence is investigated as the basis to mitigate the problems of accounting databases. There are some artificial intelligence tools or techniques that help in the broader understanding of events captured by the accounting.

Application of Artificial Intelligence Techniques in the Computer Games:
The systems as graphics rendering, playing audio, user input and game artificial intelligence (AI) when put together provide the expected entertainment and make a worthwhile computer game. Artificial intelligence is the most important part of every computer game and playing the game without artificial intelligence would not be any fun. If we remove artificial intelligence from computer games, the games will be so simple that nobody. Playing games is one of the most popular uses for computer technology. In the evolution of computer games, they have grown from modest text based to the three dimensional graphical games with complex and large worlds.

The four artificial intelligence techniques used are Path Finding, Bayesian Networks, Fuzzy Logic, and Genetic Algorithms which help a computer game provide non-playing character path finding and decision making as well as learning. Artificial intelligence solves the three common problems: non playing character (NPC) movement, NPC decision making, and NPC learning.

1) NPC Movement Using Path-Finding:
A* algorithm is the most widely used for path negotiation because of its flexibility and also because it determine the shortest path between two points. h is the heuristic or estimated cost to get from this node to the goal. The A* algorithm also maintains an Open list of the nodes that have not been explored yet and a Closed list of nodes that have been explored. g is the cost to travel from the start node to some node between the goal. Typical A* algorithms have three main attributes, fitness, goal, and heuristic or f, g, and h respectively. AI Search Methods are used to find the path. The following is pseudo code for the A* algorithm.

1. Let P = the starting point.
2. Assign f, g, and h values to P.
3. Add P to the Open list. At this point P is the only node on the Open list.
4. Let B = the best node from the Open list (best node has the lowest f-value). a. If B is the goal node, then quit. A path has been found. b. If the Open list is empty, then quit. A path has been found.

5. Let C = a valid node connected to B.

a. Assign f, g, and h values to C.

b. Check whether C is on the Open and Closed list.

i. If so, check whether the new path is more efficient (lower f-value). 1. If so, update path.

ii. Else, add C to open list. c. Repeat step 5 for all valid children of B.

6. Move B from the Open list to the closed list and repeat from step 4.

2) NPC Decision Making Using Bayesian Networks:
If the player enters causing a noise disturbance, then the monster will sense the player and will start negotiating the shortest path as discussed in the NPC movement using path finding. When the player enters the building from the other side, the monster will be unaware of the presence of the player because of the wall between them. In the previous example of the monster negotiating a path to the player, a different problem must be solved first before negotiating the path. If the game designers give the full information of the game world to the non-playing character then there would be no fun in playing the game. In this the computer calculates the probability of the monster sensing the player if the player has entered the building. The problem is does the monster even know the player is present in the building. In this AI is needed to make the nonplaying character to act in a human like way. This expression can be written as;
P (B|A) = P (B|A) P (A) / P (B) 2
Where P (B|A) is the probability that the monster would sense the player if the player had actually tripped. And P (A) is the probability of the monster sensing the player. And P (B) is the probability of the player tripping.

3) NPC Learning:
Computer games use the Artificial Intelligence Genetic Algorithms to try and implement learning in NPC?s. A genetic algorithm works in the following way.
1. Create a first generation population of random organisms.

2. Test them on the problem that is being solved and rank them according to fitness. If the best organisms have reached our performance goals then stop.
3. Take the best performers and mate them by applying genetic operators such as crossover and mutation. Add a few brand-new random organisms to the population to introduce new variety and help ensure against convergence on a local maximum.
4. Loop to step 2.
Genetic Algorithms try and build the perfect specimen and are very complex. This AI technique has not found itself into many modern computer games because it takes a lot of computer resources and time to evolve a specimen or NPC into something worthwhile.

This paper is based on the concept of artificial intelligence, areas of artificial intelligence and the artificial intelligence techniques used in the field of Power System Stabilizers (PSS) to maintain system stability and damping of oscillation and provide high-quality performance, in the Network Intrusion Detection to protect the network from intruders, in the medical area in the field of medicine, for medical image classification, in the accounting databases, and described how these AI techniques are used in computer games to solve the common problems and to provide features to the games so as to have fun. The field of artificial intelligence gives the ability to the machines to think analytically, using concepts.