China
Africa
Explore chapters and articles related to this topic
Psychrophilic Microbiomes
Published in Ajar Nath Yadav, Ali Asghar Rastegari, Neelam Yadav, Microbiomes of Extreme Environments, 2021
Most of the machine learning algorithms are like black boxes as they donot provide us with the explanation of how the classification is being performed, i.e., we do not get to know the mechanism of classification. These types of machine learning algorithms constitute the black box approach. Rule induction algorithms like Jrip (Cohen 1995), C4.5 (Salzberg 1994), Partial Decision Trees (PART) (Frank and Witten 1998), Classification and Regression Trees (CART) (Breiman et al. 1984), etc. constitute the white box approach, as they provide an explanation for their classification mechanism. These rule-induction algorithms provide a set of human interpretable rules which can aid in understanding how the classification is being made. Consequently, these rules constitute the interaction of sequence/structural features which can facilitate in the understanding of low temperature protein adaptation parameters.
Comparative Evaluation of the Discovered Knowledge
Published in Don Potter, Manton Matthews, Moonis Ali, Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, 2020
Inducing IF-THEN rules from data is an interesting aim of machine learning. In many real world applications, the rules discovered are used as a classifier to assign an appropriate class label to a new coming [DK91]. Medical diagnosis, pattern recognition and other applications can be considered as classification tasks, where the input data is shaped by a relational data base containing the classified patterns. The rule induction methods (a branch of machine learning) try to discover a consistent set of rules from this data base. The decision tree methods try to induce a decision tree from the data (a powerless knowledge representation alternative). Whereas decision tree methods are generally faster, precision capabilities measured in real world applications remain a sharp criterion to judge the consistency and the reliability of each method [HCK95, WK91].
Finance and Investments
Published in Jay Liebowitz, The Handbook of Applied Expert Systems, 2019
Barbro Back, Jefferson T. Davis, Alan Sangster
The rule-induction method is based on the learning-from-example approach. The rule induction system is presented with examples of a decision (its inputs and outcomes) and attempts to induce a decision model. A software system called ACLS (Analog Concept Learning System) was used to analyze past examples and formulate decision rules. Rules were generated to predict both an expert market analyst’s prediction of the market and the actual market’s movement. A single expert with 12 years of experience as stock market analyzer was used as the source of expertise. The expert also had experience in giving verbal advice to a large audience — he was writing a newsletter in which he gave biweekly recommendations on the stock market. These recommendations provided the basis for the model. The Dow Jones industrial average (DJI) was used as reference point for the system.
A rule induction framework for the determination of representative learning design in skilled performance
Published in Journal of Sports Sciences, 2019
Sam Robertson, Bart Spencer, Nicole Back, Damian Farrow
To model the constraint interactions for each kick, a rule induction approach was implemented. Rule induction is a branch of machine learning capable of identifying meaningful patterns between variables in large transactional datasets (Agrawal & Srikant, 1994). It has origins in early market-basket analysis, whereby supermarkets were interested in combinations of purchases made by customers; for example, a set of items bought together in a single transaction (i.e. milk, bread and eggs) combined with other identifying information such as date, location and customer profile (Cariñena, 2014). In the context of this research, a transaction refers to the skilled performance (i.e. a kick) occurring at a discrete time point in a given match or practice session. This event may consist of multiple items (constraints) that can be used to describe it; under this framework items are defined as the constraints referred to in Figure 1.
Developing a knowledge-based system for diagnosis and treatment recommendation of neonatal diseases
Published in Cogent Engineering, 2023
Desalegn Wendimu, Kindie Biredagn
Partial Decision Tree (PART): PART is a separate-and-conquer rule learning strategy. The rule induction algorithm produces sets of rules called decision lists which are ordered sets of rules. A new instance is compared to each rule in the decision lists, and the item is assigned to the group of the first matching rule. PART produces a pruned decision tree using the C4.5 statistical classifiers in each iteration. From the best tree, the leaves are translated into rules (Lehr et al., 2011).
Development and Evaluation of a Fuzzy Inference System and a Neuro-Fuzzy Inference System for Grading Apple Quality
Published in Applied Artificial Intelligence, 2018
E.I Papageorgiou, K Aggelopoulou, T.A Gemtos, G.D Nanos
According to Jang and Sun (1995), 1997), the most well-known rule induction method is the ANFIS algorithm, which is used to extract rules from data for decision-making and prediction tasks. To the best of our knowledge, there is not any previous work for grading apple quality in precision agriculture that creates a FIS from experts’ knowledge and compare it with a FIS constructed from available data using this neuro-fuzzy approach.