CanDiag: Fog Empowered Transfer Deep Learning Based Approach for Cancer Diagnosis

Pati, Abhilash; Parhi, Manoranjan; Pattanayak, Binod Kumar; Sahu, Bibhuprasad; Khasim, Syed

doi:10.3390/designs7030057

Cited by 12 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rana et al [7] have applied the classification techniques SVM, KNN, NB, and LR on the WBCD dataset using the MATLAB tool, and the results show that KNN implemented with Euclidean distance achieved the highest accuracy of 95.68 percent, which outperforms other implemented classification algorithms.…”

Section: Shah and Jivanimentioning

confidence: 99%

“…A comparison of this proposed work with some existing works considered in this paper on breast cancer classification specifically is shown in Table 4 and Figure 8. [4] 97.38 X X X BC -NB [5] 95.99 X X X KNN -Euclidean [7] 95.68 X X X J48 DT [15] 95.38 97.3 95.4 X SVM [16] 97.13 98.0 97.0 97.5 RFA [17] 92.2 X X X SVM -PCA [18] 92.78 X X X Proposed FOHC Model 98.94 99.0 98.0 98.5 The effectiveness of a classification model is shown using a receiver operating characteristic (ROC) curve, which takes into account all possible levels of categorization. The link between the TPR and the FPR is shown by this curve.…”

Section: Empirical Analysismentioning

confidence: 99%

See 1 more Smart Citation

FOHC: Firefly Optimizer Enabled Hybrid approach for Cancer Classification

Pati,

Panigrahi,

Sahu

et al. 2023

IJRITCC

View full text Add to dashboard Cite

Early detection and prediction of cancer, a group of chronic diseases responsible for a large number of deaths each year and a serious public health hazard, can lead to more effective treatment at an earlier stage in the disease's progression. In the current era, machine learning (ML) has widely been used to develop predictive models for incurable diseases such as cancer, heart disease, and diabetes, among others, taking into account both existing datasets and personally collected datasets, more research is still being conducted in this area. Using recursive feature elimination (RFE), principal component analysis (PCA), the Firefly Algorithm (FA), and a support vector machine (SVM) classifier, this study proposed a Firefly Optimizer-enabled Hybrid approach for Cancer classification (FOHC). This study considers feature selection and dimensionality reduction techniques RFE and PCA, and FA is used as the optimization algorithm. In the last stage, the SVM is applied to the pre-processed dataset as the classifier. To evaluate the proposed model, empirical analysis has been carried out on three different kinds of cancer disease datasets including Brain, Breast, and Lung cancer obtained from the UCI-ML warehouse. Based on the various performance parameters like accuracy, error rate, precision, recall, f-measure, etc., some experiments are carried out on the Jupyter platform using Python codes. This proposed model, FOHC, surpasses previous methods and other considered state-of-the-art works, with 98.94% accuracy for Breast cancer, 95.58% accuracy for Lung cancer, and 96.34% accuracy for Brain cancer. The outcomes of these experiments represent the effectiveness of the proposed work.

show abstract

Section: Shah and Jivanimentioning

confidence: 99%

Section: Empirical Analysismentioning

confidence: 99%

FOHC: Firefly Optimizer Enabled Hybrid approach for Cancer Classification

Pati,

Panigrahi,

Sahu

et al. 2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…In contrast, microarray data may be quickly analysed using ML for better diagnostics. Microarray data presents challenges because to its high dimensional nature, which must be surmounted before the data can be used for categorization [7]. Because microarray data includes a large quantity of genetic information but a limited number of samples, applying machine learning algorithms to it presents a unique challenge known as the small sample size problem.…”

Section: International Journal On Recent and Innovation Trends In Com...mentioning

confidence: 99%

En-PaFlower: An Ensemble Approach using PSO and Flower Pollination Algorithm for Cancer Diagnosis

Senapati,

Shrivastava,

Mahapatra

2023

IJRITCC

View full text Add to dashboard Cite

Machine learning now is used across many sectors and provides consistently precise predictions. The machine learning system is able to learn effectively because the training dataset contains examples of previously completed tasks. After learning how to process the necessary data, researchers have proven that machine learning algorithms can carry out the whole work autonomously. In recent years, cancer has become a major cause of the worldwide increase in mortality. Therefore, early detection of cancer improves the chance of a complete recovery, and Machine Learning (ML) plays a significant role in this perspective. Cancer diagnostic and prognosis microarray dataset is available with the biopsy dataset. Because of its importance in making diagnoses and classifying cancer diseases, the microarray data represents a massive amount. It may be challenging to do an analysis on a large number of datasets, though. As a result, feature selection is crucial, and machine learning provides classification techniques. These algorithms choose the relevant features that help build a more precise categorization model. Accurately classifying diseases is facilitated as a result, which aids in disease prevention. This work aims to synthesize existing knowledge on cancer diagnosis using machine learning techniques into a compact report. Current research work aims to propose an ensemble-based machine learning model En-PaFlower using Particle Swarm Optimization (PSO) as the feature selection algorithm, Flower Pollination algorithm (FPA) as the optimization algorithm with the majority voting algorithm. Finally, the performance of the proposed algorithm is evaluated over three different types of cancer disease datasets with accuracy, precision, recall, specificity, and F-1 Score etc as the evaluation parameters. The empirical analysis shows that the proposed methodology shows highest accuracy as 95.65%.

show abstract

“…The World Health Organization (WHO) ranks breast tumors as the most common worldwide reason for death in women. Early identification of breast tumors in women is the greatest approach to saving lives and reducing healthcare expenditures [6]. In general, cancers are classified as either benign or malignant.…”

Section: Introductionmentioning

confidence: 99%

Detection of Breast Cancer in Mammogram Images Using Multi Attention Feature Extraction with Hybrid RSA Based AlexNet

Bommagani,

Challageri,

Naik

et al. 2024

IJCMEM

View full text Add to dashboard Cite

Breast tumors have become one of the most frequent illnesses among women, with 287,850 new cases projected to be discovered in 2022. Of those, 43,250 women passed away from this malignancy. The mortality rate for cancer might be decreased through early detection. Despite this, employing mammography photographs to manually identify this kind of cancer is a challenging process that always demands an expert. In the literature, a number of AI-based (Artificial Intelligence) strategies have been proposed. However, they still deal with issues including irrelevant feature extraction, inadequate training models, and similarities between cancerous and non-cancerous areas. In order to identify breast cancer, this research suggested an SMO-MAFNet-Hybrid Alexnet model. The images in this study were first preprocessed to get rid of noise. After that, the multi-attention fusion network (MAFNet) is used to extract features. The Spider Monkey Optimization (SMO) method is utilized in this work to optimize the learning rate in MAFNet. Following feature extraction, classification is done using the AlexNet model. In this work, hybrid optimization, namely Ant Colony Optimization-Reptile Search Algorithm (ACO-RSA), is applied to fine-tune the hyperparameters in AlexNet classification. The suggested method was tested using the CBIS-DDSM (Curated breast imaging subset of Digital Database for Screening Mammography) dataset and demonstrated an accuracy of 98%, outperforming previous models.

show abstract

CanDiag: Fog Empowered Transfer Deep Learning Based Approach for Cancer Diagnosis

Cited by 12 publications

References 34 publications

FOHC: Firefly Optimizer Enabled Hybrid approach for Cancer Classification

FOHC: Firefly Optimizer Enabled Hybrid approach for Cancer Classification

En-PaFlower: An Ensemble Approach using PSO and Flower Pollination Algorithm for Cancer Diagnosis

Detection of Breast Cancer in Mammogram Images Using Multi Attention Feature Extraction with Hybrid RSA Based AlexNet

Contact Info

Product

Resources

About