Constrained dynamic rule induction learning

Thabtah, Fadi; Qabajeh, Issa; Chiclana, Francisco

doi:10.1016/j.eswa.2016.06.041

Cited by 20 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning software includes pattern and machine learning (ML), which embodies some of the aspects of the human mind that allow us to deal with an extremely complex solution to the problem with the speed overcoming even the fastest computers [48]. Wen et al [49] reported the most commonly used techniques: case-based reasoning (CBR) [50], artificial neural networks (ANN) decision trees (DT) [51], Bayesian networks (BN) [52], support vector regression (SVR) [53], genetic algorithms (GA) [54], genetic programming (GP) [55,56], association rules (AR) [57], rule induction (RI) [58], and fuzzy algorithms [59].…”

Section: Information Systems and Learning Softwarementioning

confidence: 99%

Readiness of Enterprises in Czech Republic to Implement Industry 4.0: Index of Industry 4.0

Vrchota

Pech

2019

Applied Sciences

View full text Add to dashboard Cite

Industry 4.0 includes digital process transformation, information technology (IT) development, mobile devices, learning software, automation, and robotics, as well as intelligent sensors to collect large datasets, store, analyze, and use them in business, including simulation, virtual reality, and digital twins. The aim of the paper is to characterize the readiness of the enterprise to use Industry 4.0. In the research, a questionnaire survey was carried out on a sample of 276 enterprises mainly from the manufacturing industry. Using explorative factor analysis, the index of Industry 4.0 (VPi4) was designed to determine the level of Industry 4.0 implementation in the enterprises. The results were further verified by a statistical analysis, using Mann–Whitney test and correlation coefficients. The results indicate that the VPi4 index was consistent in terms of distribution when comparing the results on the verification sample. Its results correlate with the subjective perception of the enterprises, and different levels of the index reflect the difference in technological intensity of the industry. The VPi4 index enables the enterprises to determine their own level of current state of readiness for Industry 4.0, to better prioritize business development. The proposed solution categorizes Industry 4.0 components into a useful theoretical framework. Further research offers the possibility of applying the index in other sectors, its relation to the size of enterprises, and updating with respect to new trends in information technology.

show abstract

Section: Information Systems and Learning Softwarementioning

confidence: 99%

Readiness of Enterprises in Czech Republic to Implement Industry 4.0: Index of Industry 4.0

Vrchota

Pech

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The learning method pseudocode is shown in Algorithm 1. The algorithm utilizes two thresholds named the Minimum Frequency (Min_Freq) and Rule Strength (R_S) as other Covering approaches such as Dynamic Rule Induction (DRI) 30,48 to find and extract the rules (Definitions 2 and 3, respectively). The Min_Freq threshold is used as a cutoff point for variables and class values in the training data (items).…”

Section: The Learning Covering Algorithmmentioning

confidence: 99%

A new machine learning model based on induction of rules for autism detection

Thabtah

Peebles

2019

Health Informatics J

Self Cite

198

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is a developmental disorder that describes certain challenges associated with communication (verbal and non-verbal), social skills, and repetitive behaviors. Typically, ASD is diagnosed in a clinical environment by licensed specialists using procedures which can be lengthy and cost-ineffective. Therefore, scholars in the medical, psychology and applied behavioral science fields have in recent decades developed screening methods such as the Autism Quotient (AQ) and Modified Checklist for Autism in Toddlers (M-CHAT) for diagnosing autism and other Pervasive Development Disorders (PDDs). The accuracy and efficiency of these screening methods relies primarily on the experience and knowledge of the user, as well as the items designed in the screening method. One promising direction to improve the accuracy and efficiency of ASD detection is to build classification systems using intelligent technologies such as Machine Learning (ML). Machine Learning offers advanced techniques that construct automated classifiers that can be exploited by users and clinicians to significantly improve sensitivity, specificity, accuracy, and efficiency in diagnostic discovery. This paper proposes a new ML method called Rules-Machine Learning (RML) that not only detects autistic traits of cases and controls, but also offers users knowledge bases (rules) that can be utilized by domain experts in understanding the reasons behind the classification. Empirical results on three datasets related to children, adolescents, and adults show that RML offers classifiers with higher predictive accuracy, sensitivity, harmonic mean, and specificity than those of other ML approaches such as Boosting, Bagging, decision trees, and rule induction.

show abstract

“…This methodology suffers a major drawback due to the fact that a lot of time is required to tune the parameters and also a domain expert may be needed to decipher the dataset. Instead of the trial and error, an improved self-structuring NN anti-phishing model was proposed by Thabtah et al [50]. Their algorithm would update several parameters such as the learning rate in a more dynamic way prior to adding a new neuron to the hidden layer.…”

Section: Associative Classification (Ac)mentioning

confidence: 99%

Data Analytics: Intelligent Anti-Phishing Techniques Based on Machine Learning

Baadel

2019

J. Info. Know. Mgmt.

View full text Add to dashboard Cite

According to the international body Anti-Phishing Work Group (APWG), phishing activities have skyrocketed in the last few years and more online users are becoming susceptible to phishing attacks and scams. While many online users are vulnerable and naive to the phishing attacks, playing catch-up to the phishers’ evolving strategies is not an option. Machine Learning techniques play a significant role in developing effective anti-phishing models. This paper looks at phishing as a classification problem and outlines some of the recent intelligent machine learning techniques (associative classifications, dynamic self-structuring neural network, dynamic rule-induction, etc.) in the literature that is used as anti-phishing models. The purpose of this review is to serve researchers, organisations’ managers, computer security experts, lecturers, and students who are interested in understanding phishing and its corresponding intelligent solutions. This will equip individuals with knowledge and skills that may prevent phishing on a wider context within the community.

show abstract

Constrained dynamic rule induction learning

Cited by 20 publications

References 16 publications

Readiness of Enterprises in Czech Republic to Implement Industry 4.0: Index of Industry 4.0

Readiness of Enterprises in Czech Republic to Implement Industry 4.0: Index of Industry 4.0

A new machine learning model based on induction of rules for autism detection

Data Analytics: Intelligent Anti-Phishing Techniques Based on Machine Learning

Contact Info

Product

Resources

About