Analysing Big Data to Build Knowledge Based System for Early Detection of Ovarian Cancer

Yasodha, P.; Ananthanarayanan, N. R.

doi:10.17485/ijst/2015/v8i14/65745

Cited by 21 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the following cycle, AHS is updated with weights with the best possible solution and CS continues its search for the best weights until either the last cycle/epoch of the network is attained or the MSE is accomplished. ( 1 (5) In the Above equation  as a nonlinearity function, w weight matrix, and b is a bias, N is the total number of prediction, j j P and A and are the initial and anticipated data separately. Since each hidden layer has its own weights and activations, they act like selfruling.…”

Section: Stepmentioning

confidence: 99%

“…Thus the hazard level of cancer gets expanded through women's lifetime and it results in few issues, for example, the women with ovarian cancer could never give birth to kids and it makes an issue in the menopause stage amid their lifetime [5]. Thus, the precise ID, solid cancer analyses and the treatment process ought to be enhanced in order to overcome these [6] challenges for the women.…”

Section: Introductionmentioning

confidence: 99%

“…Flowchart for AHSOStep Objective function: Estimate the fitness value of each and every harmony result with the help of equation(5) and then compute the finest result values.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Effective Features to Classify Ovarian Cancer Data in Internet of Medical Things

Elhoseny

Bian

Lakshmanaprabu

et al. 2018

Preprint

View full text Add to dashboard Cite

Ovarian Cancer (OC) is a type of cancer that affects ovaries in women, and is difficult to detect at initial stage due to which it remains as one of the leading causes of cancer death. The ovarian cancer data generated from the Internet of Medical Things (IoMT) was used and a novel approach was proposed for distinguishing the ovarian cancer by utilizing Self Organizing Maps (SOM) and Optimal Recurrent Neural Networks (ORNN). SOM algorithm was utilized for better feature subset selection and was also utilized for separating profitable, understood and intriguing data from huge measures of medical data. In supervised learning techniques, the SOM-based feature selection seems to be a tougher challenge because of the absence of class labels that would guide the search for relevant information to the classifier model. The classification approach can identify ovarian cancer data as benign/malignant. The ovarian cancer detection process can be improved by optimizing the weights of RNN structure using Adaptive Harmony Search Optimization (AHSO). The proposed model in this study can be used to detect cancer at early stages with high accuracy and low Root Mean Square Error (RMSE).

show abstract

Section: Stepmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effective Features to Classify Ovarian Cancer Data in Internet of Medical Things

Elhoseny

Bian

Lakshmanaprabu

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Many classification problems are successfully solved using the SVM algorithm [1][2][3][4][5][6][7][17][18][19][20][24][25][26][27][28][29]. This algorithm implements "supervised learning" and belongs to the group of boundary algorithms and methods.…”

Section: Introductionmentioning

confidence: 99%

Two-Stage Hybrid Data Classifiers Based on SVM and kNN Algorithms

Demidova¹

2021

Symmetry

View full text Add to dashboard Cite

The paper considers a solution to the problem of developing two-stage hybrid SVM-kNN classifiers with the aim to increase the data classification quality by refining the classification decisions near the class boundary defined by the SVM classifier. In the first stage, the SVM classifier with default parameters values is developed. Here, the training dataset is designed on the basis of the initial dataset. When developing the SVM classifier, a binary SVM algorithm or one-class SVM algorithm is used. Based on the results of the training of the SVM classifier, two variants of the training dataset are formed for the development of the kNN classifier: a variant that uses all objects from the original training dataset located inside the strip dividing the classes, and a variant that uses only those objects from the initial training dataset that are located inside the area containing all misclassified objects from the class dividing strip. In the second stage, the kNN classifier is developed using the new training dataset above-mentioned. The values of the parameters of the kNN classifier are determined during training to maximize the data classification quality. The data classification quality using the two-stage hybrid SVM-kNN classifier was assessed using various indicators on the test dataset. In the case of the improvement of the quality of classification near the class boundary defined by the SVM classifier using the kNN classifier, the two-stage hybrid SVM-kNN classifier is recommended for further use. The experimental results approve the feasibility of using two-stage hybrid SVM-kNN classifiers in the data classification problem. The experimental results obtained with the application of various datasets confirm the feasibility of using two-stage hybrid SVM-kNN classifiers in the data classification problem.

show abstract

“…PSO ile hamming uzaklığı birlikte kullanılarak lenfoma, lösemi ve kolon veri seti üzerinde boyut azaltma işlemi uygulanmış olup, kNN algoritması ile % 93.55 başarı elde edilmiştir [7]. Yumurtalık kanseri mikrodizi veri seti üzerine yapılmış çalışmada, boyut azaltma işlemi için hibrit bir yöntem olarak PSO ve Genetik algoritmaları kullanılmış ve DVM ile yapılan sınıflandırmada % 98 başarı [8], son olarak ta on adet farklı mikro dizi veri setine boyut azaltma işlemi uygulanarak C4.5 algoritmasıyla % 88.15 sınıflandırma başarısı gözlemlenmiştir [9]. Göğüs kanseri üzerine yapılmış TBA algoritması kullanılan çalışmaların ilkinde Apriori algoritması ve YSA uygulayarak % 98.29 başarı oranı [10], diğer çalışmada ise Naive Bayes sınıflandırma algoritması ile % 93.42 başarı oranına ulaşılmıştır [11].…”

unclassified

Parçacık Sürü Optimizasyonu Kullanılarak Boyutu Azaltılmış Mikrodizi Verileri Üzerinde Makine Öğrenmesi Yöntemleri ile Prostat Kanseri Teşhisi

Kılıçarslan¹,

Adem²,

Cömert³

2019

Düzce Üniversitesi Bilim Ve Teknoloji Dergisi

View full text Add to dashboard Cite

ÖZETMikrodizi verilerine dayanan veri madenciliği analizi, hastalık teşhisi ve farmakoloji alanlarında kullanılmaktadır. Analiz aşamasında yaşanan en önemli zorluk, mikrodizilerin yüksek boyutlu olması ve çok sayıda gereksiz öznitelik içermesidir. Bu nedenle çalışmada kullandığımız prostat kanseri mikrodizi veri kümesi üzerinde öznitelik boyut azaltılması amacıyla Temel bileşenler analizi (TBA) ve Parçacık sürü optimizasyonu (PSO) kullanılmıştır. Bu sayede hastalıkları etkileyen genler tespit edilmektedir. Boyutu azaltılmış veri kümeleri Destek Vektör Makinesi ve k-En Yakın Komşuluk sınıflayıcı yöntemlerine giriş olarak verilmiş ve sınıflandırma başarı sonuçları değerlendirilmiştir. Sonuç olarak PSO boyut azaltma yöntemi ile prostat kanserinde etkin genler belirlenmiş ve 50 öznitelik ile %95.77 başarı elde edilmiştir.ABSTRACT Data mining analysis based on microarray data is used in disease diagnosis and pharmacology. The major challenge in the analysis phase is the high dimension of microarrays and the large number of unnecessary features. For this reason, Principle Component Analysis (PCA) and Particle Swarm Optimization (PSO) were used to reduce the feature dimension on the prostate cancer microarray dataset used in the study. In this way, genes that affect diseases are determined. Dimension reduced data sets are given as input to Support Vector Machine and k-Nearest neighbor classification methods and classification success results are evaluated. Finally, active genes in prostate cancer were identified by PSO dimension reduction method and 95.77% success was achieved with 50 attributes.

show abstract

Analysing Big Data to Build Knowledge Based System for Early Detection of Ovarian Cancer

Cited by 21 publications

References 11 publications

Effective Features to Classify Ovarian Cancer Data in Internet of Medical Things

Effective Features to Classify Ovarian Cancer Data in Internet of Medical Things

Two-Stage Hybrid Data Classifiers Based on SVM and kNN Algorithms

Parçacık Sürü Optimizasyonu Kullanılarak Boyutu Azaltılmış Mikrodizi Verileri Üzerinde Makine Öğrenmesi Yöntemleri ile Prostat Kanseri Teşhisi

Contact Info

Product

Resources

About