MIoT Based Skin Cancer Detection Using Bregman Recurrent Deep Learning

Mobile clouds are the most common medium for aggregating,storing,and analyzing data from the medical Internet of Things(MIoT).It is employed to monitor a patient’s essential health signs for earlier disease diagnosis and prediction.Among the various disease,skin cancer was the wide variety of cancer,as well as enhances the endurance rate.In recent years,many skin cancer classification systems using machine and deep learning models have been developed for classifying skin tumors,including malignant melanoma(MM)and other skin cancers.However,accurate cancer detection was not performed with minimum time consumption.In order to address these existing problems,a novel Multidimensional Bregman Divergencive Feature Scaling Based Cophenetic Piecewise Regression Recurrent Deep Learning Classification(MBDFS-CPRRDLC)technique is introduced for detecting cancer at an earlier stage.The MBDFS-CPRRDLC performs skin cancer detection using different layers such as input,hidden,and output for feature selection and classification.The patient information is composed of IoT.The patient information was stored in mobile clouds server for performing predictive analytics.The collected data are sent to the recurrent deep learning classifier.In the first hidden layer,the feature selection process is carried out using the Multidimensional Bregman Divergencive Feature Scaling technique to find the significant features for disease identification resulting in decreases time consumption.Followed by,the disease classification is carried out in the second hidden layer using cophenetic correlative piecewise regression for analyzing the testing and training data.This process is repeatedly performed until the error gets minimized.In this way,disease classification is accurately performed with higher accuracy.Experimental evaluation is carried out for factors namely Accuracy,precision,recall,F-measure,as well as cancer detection time,by the amount of patient data.The observed result confirms that the proposed MBDFS-CPRRDLC technique increases accuracy as well as lesser cancer detection time compared to the conventional approaches.

Acral melanoma detection using dermoscopic images and convolutional neural networks

Acral melanoma(AM)is a rare and lethal type of skin cancer.It can be diagnosed by expert dermatologists,using dermoscopic imaging.It is challenging for dermatologists to diagnose melanoma because of the very minor differences between melanoma and non-melanoma cancers.Most of the research on skin cancer diagnosis is related to the binary classification of lesions into melanoma and non-melanoma.However,to date,limited research has been conducted on the classification of melanoma subtypes.The current study investigated the effectiveness of dermoscopy and deep learning in classifying melanoma subtypes,such as,AM.In this study,we present a novel deep learning model,developed to classify skin cancer.We utilized a dermoscopic image dataset from the Yonsei University Health System South Korea for the classification of skin lesions.Various image processing and data augmentation techniques have been applied to develop a robust automated system for AM detection.Our custombuilt model is a seven-layered deep convolutional network that was trained from scratch.Additionally,transfer learning was utilized to compare the performance of our model,where AlexNet and ResNet-18 were modified,fine-tuned,and trained on the same dataset.We achieved improved results from our proposed model with an accuracy of more than 90%for AM and benign nevus,respectively.Additionally,using the transfer learning approach,we achieved an average accuracy of nearly 97%,which is comparable to that of state-of-the-art methods.From our analysis and results,we found that our model performed well and was able to effectively classify skin cancer.Our results show that the proposed system can be used by dermatologists in the clinical decision-making process for the early diagnosis of AM.

Weighted-averaging-based classification of laser-induced breakdown spectroscopy measurements using most informative spectral lines

In this study,efficient spectral line selection and wcightcd-avcraging-bascd processing schemes are proposed for the classification of laser-induced breakdown spectroscopy(UBS)measurements.For fast on-line classification,a set of representative spectral lines arc selected ami processed relying on the information metric,instead of the time consuming full spectrum based analysis.I he most informative spectral line sets arc investigated by the joint mutual information estimation(MIR)evaluated with the Gaussian kernel density,where dominant intensity peaks associated with the concentrated components arc not necessarily most valuable for classification.In order to further distinguish the characteristic patterns of die LIBS measured spectrum,two-dimensional spectral images are synthesized through column-wise concatenation of the peaks along with their neighbors.For fast classification while preserv ing die effect of distinctive peak patterns,column-wise Gaussian weighted averaging is applied to die synthesized images,yielding a favorable trade off between classification performance and computational complexity.To explore the applicability of the proposed schemes,two applications of alloy classification and skin cancer detection arc investigated with the multi-class and binary support vector machines classifiers,respectively.Ihc MIE measures associated with selected spectral lines in bodi applications show a strong correlation to the actual classification or detection accuracy,which enables to find out meaningful combinations of spectral lines.In addition,the peak patterns of the selected lines and their Gaussian weighted averaging with nciehbors of the selected peaks efficiently distineuish different classes of LIBS measured spectrum.