A Novel Metaheuristic Data Mining Algorithm for the Detection and Classification of Parkinson Disease

Suganya, P.; Sumathi, C. P.

doi:10.17485/ijst/2015/v8i14/72685

Cited by 22 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of the paper [10] have been proposed an ensemble method that includes sparse multinomial logistic regression, rotation forest ensemble with support vector machines and principal components analysis for the prediction of Parkinson disease. The authors of the paper [11] have been studied and adopted a novel metaheuristic data mining algorithm for the detection and classification of Parkinson's disease.The authors of the paper [12] have been proposed a fuzzy neural system (FNS) based method for the classification of Parkinson diseases.The authors of the paper [13] have been proposed a fuzzy k-nearest neighbour based methodfor the classification of Parkinson diseases. The authors of the paper [14] have been studied and proposed support vector machine based method for the prediction of Parkinson disease.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Approaches for Prediction of Parkinson's Disease

Tiwari¹

2016

MLAIJ

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Approaches for Prediction of Parkinson's Disease

Tiwari¹

2016

MLAIJ

View full text Add to dashboard Cite

show abstract

“…The detection methods of the category are sensitive to the number of features and have the large number of parameters. So, optimization algorithms such as hybridization of ACO and ABC (HColonies), modified drafts of ACO (AntMiner) [9] and SPACO [26], DPSO [27], Neuro-rule [28], GA [30,31] and ABO [32] are considered to solve the mentioned disadvantages of the methods. Hcolonies [9] was designed to optimize the decision lists based on consisting of two phases: ACO and ABC phases.…”

Section: Azar Et Almentioning

confidence: 99%

“…Hybrid detections IF2FLS-GA [30] and IT2FLS-FA [29] are beneficial when there are many uncertainties in a system, they are not appropriate without attribute reduction to classification. To optimize feature selection for RF by ABO [32], it calculates the distance between every two spatial coordinates to determine 30 Chemical Reaction Optimization 31 Fast Decision Approach 32 Belief-Based Chaotic Krill Herd Algorithm the new position of each bear that it has increased the computational burden. With the death of 25% of weak polar bears and the production of new bears close to the best solution, the algorithm both traps into local optimal quickly and loses the ability to search for unseen parts of the search space.…”

Section: Azar Et Almentioning

confidence: 99%

A New Fuzzy Bio-Inspired Based Classification to Cancer Detection

Abdolrazzagh-Nezhad,

Izadpanah

2023

Preprint

View full text Add to dashboard Cite

There are several cancer detection methods with their own disadvantages in flexibility, non-linear complexity and sensitive in imbalance data. In this paper, a new fuzzy bio-inspired based classification method is designed to classify the imbalance medical data. The method consists of a new fuzzy draft of Cuckoo Optimization Algorithm (COA) and separating hyper-planes based on assigning binary codes to separated regions that called Hyper-Planes Classifier (HPC). Based on the technical review is done in the paper, the HPC has a better structural superiority than the other classification algorithms. The Fuzzy Cuckoo Optimization Algorithm (FCOA) which fills up its challenge in proper tuning parameters, is proposed to optimize the weights of the separating hyper-planes with linear complexity time. The FCOA is designed based on a fuzzy inference system for the Egg Laying Radius (ELR) parameter setting to increase the efficiency of the generic COA. The proposed fuzzy bio-inspired based classification method is examined with four famous UCI cancer datasets based on one, two, three and four hyper-planes and compared with more than thirty previous researches. The results show that the proposed method is effective compared to the previous methods and also the COA.

show abstract

“…Result showed that k-NN provided best accuracy 90.26% using k ¼ 10 fold validation. Suganya and Sumathi [138] used metaheuristic algorithm for the detection and classification of Parkinson disease. Study reported that ABO algorithm provided best accuracy (97%) as compare SCFW, FCM, ACO and PSO.…”

Section: Classificationmentioning

confidence: 99%

Big data analytics for preventive medicine

Razzak

Imran

2019

Neural Comput & Applic

141

View full text Add to dashboard Cite

Medical data is one of the most rewarding and yet most complicated data to analyze. How can healthcare providers use modern data analytics tools and technologies to analyze and create value from complex data? Data analytics, with its promise to efficiently discover valuable pattern by analyzing large amount of unstructured, heterogeneous, non-standard and incomplete healthcare data. It does not only forecast but also helps in decision making and is increasingly noticed as breakthrough in ongoing advancement with the goal is to improve the quality of patient care and reduces the healthcare cost. The aim of this study is to provide a comprehensive and structured overview of extensive research on the advancement of data analytics methods for disease prevention. This review first introduces disease prevention and its challenges followed by traditional prevention methodologies. We summarize state-of-the-art data analytics algorithms used for classification of disease, clustering (unusually high incidence of a particular disease), anomalies detection (detection of disease) and association as well as their respective advantages, drawbacks and guidelines for selection of specific model followed by discussion on recent development and successful application of disease prevention methods. The article concludes with open research challenges and recommendations.

show abstract

A Novel Metaheuristic Data Mining Algorithm for the Detection and Classification of Parkinson Disease

Cited by 22 publications

References 12 publications

Machine Learning Based Approaches for Prediction of Parkinson's Disease

Machine Learning Based Approaches for Prediction of Parkinson's Disease

A New Fuzzy Bio-Inspired Based Classification to Cancer Detection

Big data analytics for preventive medicine

Contact Info

Product

Resources

About