Computational Intelligence (CI) is a subfield of Artificial Intelligence (AI) that focuses on creating intelligent systems that can learn, reason, and adapt in uncertain and dynamic environments. Data Stream Analysis (DSA) is a subset of Data Mining that deals with the analysis of continuous and rapidly changing data streams. CI techniques can be very effective in analyzing data streams because they can learn from the data in real-time and make decisions quickly. CI techniques can be very useful in DSA because they can learn from the data in real-time and can adapt to changing environments. However, choosing the right CI technique for a particular DSA task can be challenging and requires careful consideration of the problem and the data.
Some common CI techniques used in DSA:
- Artificial Neural Networks (ANNs): ANNs are a biologically inspired computational model that is used for pattern recognition and prediction. ANNs can learn from data in real-time and can adapt to changing environments. ANNs are commonly used in DSA for classification and clustering tasks.
- Fuzzy Logic (FL): FL is a mathematical framework that deals with uncertainty and imprecision. FL is commonly used in DSA for decision-making tasks, where the data is uncertain or ambiguous.
Evolutionary Computation (EC): EC is a computational model that is inspired by the process of natural selection. EC algorithms are used for optimization problems in DSA, such as finding the best set of parameters for a classification or prediction model. - Swarm Intelligence (SI): SI is a computational model that is inspired by the collective behavior of social insects, such as ants and bees. SI algorithms are used for optimization problems in DSA, such as finding the best set of features to use for a classification or prediction model.
- Reinforcement Learning (RL): RL is a machine learning technique that involves an agent learning by interacting with its environment. RL algorithms are commonly used in DSA for decision-making tasks, where the agent needs to learn how to maximize a reward function in a dynamic and uncertain environment
Special Session Chair
- Shengxiang Yang
syang@dmu.ac.uk
De Montfort University, UK