Wisconsin Breast Cancer Data Research Articles

Klasifikasi Sel Tumor Payudara Menggunakan Algoritma Support Vector Machine (SVM)

Cancer is a large group of diseases that can begin in almost any organ or tissue of the body when abnormal cells grow uncontrollably, beyond their normal limits to invade adjacent parts of the body and/or spread to other organs. There is a lot of information about breast cancer that can be accessed easily. Information about breast cancer can be processed with machine learning. Machine learning can discover new meaningful correlations, patterns and trends by sifting through large amounts of data stored in repositories, using pattern recognition technology and statistical and mathematical techniques. The purpose of this research is to determine the value of the accuracy of the SVM model on training data and testing data; and to determine the precision value of the SVM model on training data and testing data. Wisconsin Breast Cancer (WBC) data available in the UCI Machine Learning Repository. The data have been processed using the Python programming language with a support vector machine (SVM) modeling algorithm. The results of this research indicate that the value of accuracy in training data was equal to , the value of accuracy in testing data was equal to , and the value of precision in the SVM model algorithm was obtained as large as for training data and as large as for data testing.

Adaptive Neuro Fuzzy Inference System based classifier in diagnosis of breast cancer

Millions of individuals live longer and healthier lives due to modern medical innovations. The advancement of modern medicine to combat numerous ailments has benefited humanity a lot. Breast cancer is one of the most fatal diseases affecting women globally. Early detection is essential for lowering the fatality rate. The objective of the paper is to create a computer-aided diagnostic model that helps in the early detection of breast cancer and hence decreases the death rate. The study introduces a hybrid strategy for effectively diagnosing breast cancer by using a Novel Relief algorithm for feature selection with an Adaptive Neuro-Fuzzy Inference System (ANFIS). The efficiency of this proposed hybrid model and the ANFIS model without using any feature selection technique is estimated using the Wisconsin Breast Cancer Data set (WBCD). The study finds that the new hybrid model has attained the highest accuracy of 99.30% and is ideal for detecting breast cancer.

Comparision of Different Classifiers for Prediction of Breast Cancer

The cell formed in the breast are known as breast cancer. It occurs mainly in women and it may occur rarely in men also. It is considered as the most common ailment that can lead to large number of death in females every year. In spite of the factuality that cancer is treatable and can be relieve if treated at its early stages; many patients are screened for cancer only at a very late stage. Data mining technique such as classifications provides an efficient technique to classify data, where these methods are commonly used for diagnostic decision making. The Machine learning techniques propound various methods such as statistical and probabilistic methods which allow system to learn from past experiences to distinguish and identify patterns from a standard dataset. The research work presents a review of machine learning techniques which can be used in breast cancer disease detection by applying algorithms on breast cancer Wisconsin data set. Algorithms such as Navies Bayes, Random Forest, Support Vector Machine, Adaboost and Decision Trees were used. The result outcome shows that Random Forest performs better than other techniques.

A novel negative selection algorithm with hyper-rectangle detectors based on full coverage of state space for anomaly detection

The traditional negative selection algorithm with a randomly generated hypersphere detector is unable to satisfy the development needs of continuous learning due to the inherent defects of the detector. This paper proposes a novel negative selection algorithm for hyper-rectangle detectors that overcomes the shortcomings of randomly generated hyper-sphere detectors and lays the foundation for a negative selection algorithm with continuous learning capability. It uses self-sample clusters of equal-sized hypercubes instead of self-samples for training. The hyper-rectangle detectors are generated by cutting the nonself-space along the boundary of the self-sample clusters. The state space is covered without overlapping each other by self-sample clusters and detectors. The anomaly detection performance of the proposed method was demonstrated using Iris data, vowel recognition data (Vowel), and Wisconsin Breast Cancer (BCW) data. The experimental results show that the proposed method outperforms other artificial immune algorithms and clustering algorithms under the same parameter conditions.

Breast Cancer Classification Using Outlier Detection and Variance Inflation Factor

In terms of malignant tumors, breast cancer is one of the most prevalent. Breast cancer is a form of cancer that develops in the breast tissue when the surrounding, healthy breast tissue is overtaken by the uncontrollably growing cells in the breast tissue. Several features or patient conditions can be used in a machine learning approach to predict breast cancer. Machine learning will be utilized in these situations to determine if the cancer is malignant or benign. The Wisconsin Breast Cancer (Diagnostic) Data Set, which contains 32 characteristics and 569 collected data, was the dataset used in this research.. Feature selection in this study is done by eliminating outliers using the upper and lower quartile of each feature then feature selection is also carried out on features that have features that have a high variance inflation factor. The machine learning methods used in this research are Logistic Regression, Random Forest, KNN, SVC, XG Boost, Gradient Boosting, and Ridge Classifier. The selection of this method is based on the target that will be predicted by 2 labels, namely benign cancer, and malignant cancer. The result obtained is that the selection of features using the variance inflation factor increases the accuracy of the previous Logistic Regression and Random Forest methods from 98.25% to 99.12%. The method that has the highest level of accuracy is the Logistic Regression and Random Forest methods which have a value of 99.12%. The next research will be developed by trying other optimization techniques for hyperparameter tuning.

Effective kernel‐principal component analysis based approach for wisconsin breast cancer diagnosis

This work aims to identify cancerous (malignant) and non-malignant (non-cancerous) cells in a breast cancer database. Wisconsin breast cancer data (WBC) was utilized and obtained from the University of California, Irvine's machine learning repository. The proposed approach involves the Naive bayes algorithm with Gaussian distribution of the function in combination with Chi-squared-based attributes selection approach. This experimentation has been done after reducing the dimensional space of the used data with extended Kernel Principal Component Analysis (K-PCA). Five different kernels in K-PCA have been tested after the implementation of necessary pre-processing techniques. The performance assessment of the proposed system has been evaluated based on confusion matrix-based accuracy, precision, sensitivity, and specificity. Our proposed methodology with six selected feature and sigmoid K-PCA attained the best accuracy of 99.28%. This result outer performs many state-of-the-art studies recently published on the identical dataset.

Comparison of Decision Tree, Random Forest and Linear Discriminant Analysis Models in Breast Cancer Prediction

Breast cancer is one of the illnesses that has become a leading cause of female death worldwide, and early diagnosis of these diseases is a difficult and important undertaking. The intention of this paper is to design prediction models based on Decision Tree, Random Forest and Linear Discriminant Analysis respectively to forecast the breast cancer occurrence at an early stage. The design is focused on analyzing the minimum set of attributes from the clinical data set that have been chosen by experts, and then compare the performances of the models to find their advantages in each model. Breast Cancer Wisconsin Data Set is used in this paper to construct the expected prediction models. Classification accuracy which is determined by comparing real values with predicted values, and generalization ability which is reflected by Receiver Operating Characteristic curve, are used to gauge the performance of the models. The results confirm that the Random Forest model can achieve the highest accuracy to 99.4% and the best generalization ability. However, the Linear Discriminant Analysis model can keep better stability in prediction accuracy and has the fastest running speed.

Breast Cancer Identification Using Machine Learning

Breast cancer is a cancer disease that seriously threatens women’s health and occupies the first place in female cancer mortality. At present, the incidence rate of breast cancer in China is the first in the world and is on the rise. In view of the serious harm of breast cancer to life and health, researchers and institutions are making unremitting efforts to find a perfect diagnosis and treatment plan. With the improvement of computer performance and machine learning levels, intelligent algorithms have been able to replace human behavior and judgment in some fields. The traditional breast cancer diagnosis process requires medical experts to observe patient data repeatedly. In this case, the algorithm technology is used to quickly feedback a high probability reference result to doctors, which is particularly important to increase the diagnosis efficiency and reduce the burden of doctors. In order to improve the accuracy of existing breast cancer recognition methods, this paper proposes and implements a scheme based on a whale optimization algorithm to iteratively adjust the key parameters of the support vector machine to improve the accuracy of breast cancer recognition. In order to verify the performance of the WOA-SVM algorithm, this paper uses the Wisconsin breast cancer data in the UCI database for performance verification experiments. Experiments show that the WOA-SVM model has higher recognition accuracy than the traditional breast cancer recognition model.

Minimum relevant features to obtain AI explainable system for predicting breast cancer in WDBC

The potential to explain why a machine learning model produces a certain prediction in incomprehensible terms is becoming increasingly crucial, as it provides accountability and confidence in the algorithm's decision-making process. The interpretation of complex models is difficult. Various approaches to dealing with this issue are being offered. These problems are typically handled in tree ensemble methods by assigning priority levels to input features globally or for a specific prediction. We show that current feature attribution approaches are inconclusive, and develop solutions using SHAP (SHapley Additive Explanation) values, LIME (Local Interpretable Model-Agnostic Explanations), and the Skope Rules package. We employ feature selection methods from SHAP and LIME in this work, which uses the Breast cancer Wisconsin data sets. In the suggested method, features are chosen at the first level of feature selection using Decision tree entropy values. Based on the SHAP and LIME reports, level 2 features are chosen from fewer options. The features are tested on a Decision Tree (DT) model and a DT and Support Vector Machine (SVM) ensemble. Experiments suggest that the ensemble works better as compared to DT. We have also used the Skope Rules package to generate global rules for generalization.

Breast Cancer Detection Using Machine Learning Techniques

Abstract: Cancer is one of the most prominent cause of fatalities around the world, accounting over 1 crore deaths in past year out of which 22.6% deaths were due to Breast cancer (BC). BC is the most common type of cancer among women, it accounts for 14.7 % of cancer cases in India. Multiple pieces of research have been conducted over the early detection of BC that can help begin treatment on time thus decreasing the mortality rate. Out of the total diagnosed, only about 86% are diagnosed correctly. Biopsy images of cells have a risk of false detection which may endanger the life of a person. There is a dire need of discovering new alternative methods that have an easy implementation with different data sets, are cost-effective, reliable, and safer, that can give an accurate prediction. This paper proposes a model combined with several Machine Learning algorithms(ML) that are Decision Trees, Artificial Neural Network, K-Nearest Neighbour, Support Vector Machine for an effective and accurate breast cancer diagnosis. Index Terms - Breast Cancer; Breast Cancer Detection; Machine Learning Key Words: Breast Cancer (BC); Artificial neural networks (ANN); Wisconsin breast cancer data set.

In-Memory Principal Component Analysis by Crosspoint Array of Resistive Switching Memory: A new hardware approach for energy-efficient data analysis in edge computing

In-Memory Computing (IMC) is one of the most promising candidates for data-intensive computing accelerators of machine learning (ML). A key ML algorithm for dimensionality reduction and classification is principal component analysis (PCA), which heavily relies on matrix-vector multiplications (MVM) for which classic von Neumann architectures are not optimized. Here, we provide the experimental demonstration of a new IMC-based PCA algorithm based on power iteration and deflation executed in a 4-kbit array of resistive switching random-access memory (RRAM). The classification accuracy of the Wisconsin Breast Cancer data set reaches 95.43%, close to floating-point implementation. Our simulations indicate a 250× improvement in energy efficiency compared to commercial GPUs, thus supporting IMC for energy-efficient ML in modern data-intensive computing.

Convergence of Blockchain, k-medoids and homomorphic encryption for privacy preserving biomedical data classification

Data privacy on the Internet of Medical Things (IoMT) remains a critical concern when handling biomedical data. While extant studies focus on cryptography and differential privacy, few of them capture the utility and authenticity of data. As a result, data privacy remains the primary concern when training a machine learning (ML) model with IoMT data from various data sources/owners such as k − medoids. To overcome the above-mentioned issues, this study proposes secure ​k − medoids ​that are implemented together with Blockchain and partial homomorphic cryptosystem (Paillier) to ensure authenticity and protect all entities (i.e., data owner and data analyst) data privacy. The homomorphic property of Paillier is utilized to develop secure building blocks (i.e., secure polynomial operations, secure comparison, and secure biasing operations) to ensure data privacy and eliminate dependency on any third parties. We utilized three different biomedical datasets, and these are (I) Heart Disease Data (HDD), (II) Diabetes Data (DD), and (III) Breast Cancer Wisconsin Data (BCWD). Rigorous security analysis demonstrates that secure ​k − medoids ​protect against sensitive data breaches. It also showed superior performance in both BCWD (Accuracy 97.80%, Precision 96.83%, and Recall 99.80%) and HDD (Accuracy 82.50%, Precision 81.28%, and Recall 80.50%) datasets, respectively. However, similar performance was not reflected in the case of the DD dataset. Furthermore, the study explains why such performance results are observed. In addition, the proposed system has been proven to take less execution time compared to the extant studies.

Considerations on the region of interest in the ROC space.

Receiver Operating Characteristic curves have been widely used to represent the performance of diagnostic tests. The corresponding area under the curve, widely used to evaluate their performance quantitatively, has been criticized in several respects. Several proposals have been introduced to improve area under the curve by taking into account only specific regions of the Receiver Operating Characteristic space, that is, the plane to which Receiver Operating Characteristic curves belong. For instance, a region of interest can be delimited by setting specific thresholds for the true positive rate or the false positive rate. Different ways of setting the borders of the region of interest may result in completely different, even opposing, evaluations. In this paper, we present a method to define a region of interest in a rigorous and objective way, and compute a partial area under the curve that can be used to evaluate the performance of diagnostic tests. The method was originally conceived in the Software Engineering domain to evaluate the performance of methods that estimate the defectiveness of software modules. We compare this method with previous proposals. Our method allows the definition of regions of interest by setting acceptability thresholds on any kind of performance metric, and not just false positive rate and true positive rate: for instance, the region of interest can be determined by imposing that (also known as the Matthews Correlation Coefficient) is above a given threshold. We also show how to delimit the region of interest corresponding to acceptable costs, whenever the individual cost of false positives and false negatives is known. Finally, we demonstrate the effectiveness of the method by applying it to the Wisconsin Breast Cancer Data. We provide Python and R packages supporting the presented method.

Breast Cancer Detection with Revamped Dataset Using Machine Learning Techniques

Machine learning is a current topic of interest in research and industry, with the implementation of novel strategies all the time. The main purpose of this research activity is to determine the efficiency of machine learning techniques in the detection research of breast cancer. The incidence and mortality of breast cancer in women are increasing day by day. Worldwide, researchers have worked hard to help clinicians provide the best model for detecting diagnosis and breast cancer. In this work, learning UCI machine Wisconsin breast cancer data from a set of databases, model, and analyze the performance of existing work use, compared to the same data set. The dataset is analyzed, and the revamped dataset is constructed by eliminating redundant features and appending new features essential for prediction. Logistic regression, K nearest neighbors (KNN), support vector machine (SVM), decision trees, random forest, XGBoost, using a machine learning algorithm, such as re-organized data set of artificial neural network AdaBoost, 8 one of prediction build the model application (ANN). Standard to analyze the accuracy rate. In the experiment, these classifications have been shown to work for breast cancer with >97% accuracy. Logistic regression, XGBoost and Adaboost, stand on top with 99.28 percent accuracy. The experiment also, the balanced data set of removal outliers and balance, shows that have a significant impact on the model’s prediction performance.

Breast Cancer Risk Analysis using Machine Learning

When cells in and around breast are affected and damaged due to cancer, we call it Breast Cancer. It is commonlyfound among women and a very few men. Breast Cancer poses major health hazard and best way to handle itis to identify the symptoms as early as possible. Recently, Machine Learning techniques have been aggressivelyused by many researchers for different types of analysis and predictions in medical domain. In literature, BreastCancer classification and prediction through Machine Learning techniques, based on Breast Cancer WisconsinData Set, has come into picture many times. Typical attributes like radius, perimeter, tumour size (often fetchthrough X-Rays) apart from others, provides comprehensive inputs for the prediction process, often at a laterstage. However, till date, work on evaluation of the Risk of Breast Cancer is quite limited. We have worked onthe problem of risk prediction of breast cancer on the basis of self-assessed parameters, to find if the patient islikely to get the disease, at a very early stage. Risk evaluation / prediction tries to identify if a person is at riskof getting infected with disease. Risk analysis can not only save money but also enable the patient to undertakecourse correction in terms of food intake and medication, before it is too late. In this paper we present our analysisbased on well-defined parameters, discuss our results and then compare those results with one other similar work.

RDOF: An outlier detection algorithm based on relative density

AbstractAn outlier has a significant impact on data quality and the efficiency of data mining. The outlier identification algorithm observes only data points that do not follow clearly defined meanings of projected behaviour in a data set. Several techniques for identifying outliers have been presented in recent years, but if outliers are located in areas where neighbourhood density varies substantially, it can result in an imprecise estimate. To address this problem, we provide a ‘Relative Density‐based Outlier Factor (RDOF)’ algorithm based on the concept of mutual proximity between a data point and its neighbours. The proposed approach is divided into two stages: an influential space is created at a test point in the first stage. In the later stage, a test point is assigned an outlier‐ness score. We have conducted experiments on three real‐world data sets, namely the Johns Hopkins University Ionosphere, the Iris Plant, and Wisconsin Breast Cancer data sets. We have investigated three performance metrics for comparison: precision, recall, and rank power. In addition, we have compared our proposed method against a set of relevant baseline methods. The experimental results reveal that our proposed method detected all (i.e., 100%) outlier class objects with higher rank power than baseline approaches over these experimental data sets.

Breast Cancer Classification Using Discrete Wavelet Transformation and Deep Learning

Background: One of the most prevalent diseases these days is breast cancer which is common amongst women. This sickness has been increasing to an alarming rate due to the lack of accurate diagnoses. Early and accurate detection is one of the safest ways to cure a breast cancer patient. Objectives: The objective of this study was to provide a more effective way to accurately classify a cancer sample; whether is benign or malignant. Methods: The classification model is based on the data collected from the UCI machine learning repository acquired from the Wisconsin hospital called Wisconsin Breast Cancer Data (WBCD). In this study, we preprocessed the dataset using Discrete Wavelet Transform (DWT) and then tested the efficiency of Deep Learning (DL) for breast cancer classification. The model was developed using a feed-forward neural network and the result was compared with the observed values. Results: The result of the experiment proved the effectiveness of the proposed classification technique. The new technique accomplished 98.90% accuracy for classifying breast cancer. Conclusions: The result from the experiment shows the importance of data preprocessing and the efficiency of the neural network over other classification algorithms.

An improved Kohonen self-organizing map clustering algorithm for high-dimensional data sets

<p>Manipulating high-dimensional data is a major research challenge in the field of computer science in recent years. To classify this data, a lot of clustering algorithms have already been proposed. Kohonen self-organizing map (KSOM) is one of them. However, this algorithm has some drawbacks like overlapping clusters and non-linear separability problems. Therefore, in this paper, we propose an improved KSOM (I-KSOM) to reduce the problems that measures distances among objects using EISEN Cosine correlation formula. So far as we know, no previous work has used EISEN Cosine correlation distance measurements to classify high-dimensional data sets. To the robustness of the proposed KSOM, we carry out the experiments on several popular datasets like Iris, Seeds, Glass, Vertebral column, and Wisconsin breast cancer data sets. Our proposed algorithm shows better result compared to the existing original KSOM and another modified KSOM in terms of predictive performance with topographic and quantization error.</p>

Regularized matrix-variate logistic regression with response subject to misclassification

Matrix-variate logistic regression is useful in facilitating the relationship between the binary response and complex-featured matrix-variates arising commonly from medical imaging research. However, standard inference procedures based on such a model are impaired by the presence of the response misclassification as well as inactive covariates. It is imperative to account for the misclassification effects and select active covariates when employing matrix-variate logistic regression to analyze such data. In this paper, we develop penalized unbiased estimating functions using the smoothly clipped absolute deviation (SCAD) penalty to address the sparsity of matrix-variate data as well as the response misclassification effects. The proposed methods are justified both theoretically and numerically. We analyze the Breast Cancer Wisconsin data with the proposed methods.

Application of noise-reduction techniques to machine learning algorithms for breast cancer tumor identification

The application of machine learning (ML) techniques to digitized images of biopsied cells for breast cancer diagnosis is an active area of research. We hypothesized that reducing noise in the data would lead to an increase in classification accuracies. To test this hypothesis, we first compared several classification techniques in their ability to discriminate between malignant and benign breast cancer tumors using the Wisconsin Breast Cancer Data Set and subsequently evaluated the effect of noise reduction techniques on model accuracies. We applied two noise-reduction techniques based on Principal Component Analysis – dimensionality reduction and outlier removal – to a comprehensive list of ML algorithms with different learning paradigms including Decision Trees (fine, medium, coarse), dimensionality reduction techniques (Linear Discriminant Analysis, Quadratic Discriminant Analysis, Partial Least Squares-Discriminant Analysis), logistic Regression, Bayesian techniques (Gaussian Naive, Kernel Naive), Support Vector Machines (Linear, Quadratic, Cubic, Gaussian), instance-based techniques (fine, medium, coarse, cosine, cubic, and weighted K-Nearest Neighbors), and Artificial Neural Networks. Results showed that noise removal through dimensionality reduction is most effective when using a cross-validated number of principal components, and accuracies surpassing 99% across all ML models are obtained when both noise-reduction techniques are applied sequentially. Even though such a high accuracy has been demonstrated in few instances for specific algorithms, the methodology proposed herein is the first published report demonstrating the applicability of a technique to a wide range of ML models to achieve high accuracies. We show that dimensionality reduction and outlier analysis can be used as effective approaches to improve discrimination accuracies. Also, dimensionality reduction through a cross-validated number of principal components can provide an effective framework for reducing noise in the data prior to applying a ML algorithm.