Segmentation of Tissue-Injured Melanoma Convolution Neural Networks

In global dermatological conditions, skin lesions are significant. Curable early in the diagnosis, only skin lesions can be accurately identified by highly trained dermatologists. Around 21 million patients are diagnosed with this disease and more than 10.12 million deaths worldwide. This paper presents basic work for the detection and ensuing purpose of the CNN to dermoscopic images of skin lesions with cancerous inclination. The models proposed are trained and evaluated in the 2018 International Skin Imaging Collaboration challenge, comprising 2100 training samples and 750 test samples, on normal benchmark datasets. Skin-injured images were mainly segment based on person thresholds for channel intensity. The images were added to CNN to extract features. The extracted characteristics were then used to classify the associated ANN classification. In the past, many approaches have been used to diagnose subjects with variable success levels. The methodology described in this paper showed associated accuracy of 97.13% in comparison to the previous best of ninety seven.

Download Full-text

Application of convolutional neural networks for stellar spectral classification

Monthly Notices of the Royal Astronomical Society ◽

10.1093/mnras/stz3100 ◽

2019 ◽

Vol 491 (2) ◽

pp. 2280-2300 ◽

Cited By ~ 6

Author(s):

Kaushal Sharma ◽

Ajit Kembhavi ◽

Aniruddha Kembhavi ◽

T Sivarani ◽

Sheelu Abraham ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Spectral Classification ◽

Stellar Spectra ◽

The Past ◽

Training Samples ◽

Optical Region ◽

Spectral Libraries ◽

Improved Accuracy

ABSTRACT Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, $\rm {\log g}$, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using convolutional neural networks (CNNs). Traditional machine learning (ML) methods with ‘shallow’ architecture (usually up to two hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalization. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like artificial neural networks, Random Forest, and CNN to classify stellar spectra using the Jacoby Atlas, ELODIE, and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coudé Feed Stellar Spectra (CFLIB). We show that using CNNs, we are able to lower the error up to 1.23 spectral subclasses as compared to that of two subclasses achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS data base with SNR > 20.

Download Full-text

Segmentation of Melanocytic Lesion Images Using Gamma Correction with Clustering of Keypoint Descriptors

Diagnostics ◽

10.3390/diagnostics11081366 ◽

2021 ◽

Vol 11 (8) ◽

pp. 1366

Author(s):

Damilola Okuboyejo ◽

Oludayo O. Olugbara

Keyword(s):

Skin Lesions ◽

Diagnostic Process ◽

Melanocytic Lesion ◽

Gamma Correction ◽

Intrinsic Factors ◽

Skin Imaging ◽

Benchmark Datasets ◽

And Performance ◽

Sensitivity Specificity ◽

Performance Results

The early detection of skin cancer, especially through the examination of lesions with malignant characteristics, has been reported to significantly decrease the potential fatalities. Segmentation of the regions that contain the actual lesions is one of the most widely used steps for achieving an automated diagnostic process of skin lesions. However, accurate segmentation of skin lesions has proven to be a challenging task in medical imaging because of the intrinsic factors such as the existence of undesirable artifacts and the complexity surrounding the seamless acquisition of lesion images. In this paper, we have introduced a novel algorithm based on gamma correction with clustering of keypoint descriptors for accurate segmentation of lesion areas in dermoscopy images. The algorithm was tested on dermoscopy images acquired from the publicly available dataset of Pedro Hispano hospital to achieve compelling equidistant sensitivity, specificity, and accuracy scores of 87.29%, 99.54%, and 96.02%, respectively. Moreover, the validation of the algorithm on a subset of heavily noised skin lesion images collected from the public dataset of International Skin Imaging Collaboration has yielded the equidistant sensitivity, specificity, and accuracy scores of 80.59%, 100.00%, and 94.98%, respectively. The performance results are propitious when compared to those obtained with existing modern algorithms using the same standard benchmark datasets and performance evaluation indices.

Download Full-text

Learning with Selective Forgetting

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/137 ◽

2021 ◽

Author(s):

Takashi Shibata ◽

Go Irie ◽

Daiki Ikami ◽

Yu Mitsuzumi

Keyword(s):

Lifelong Learning ◽

Original Data ◽

Ethical Considerations ◽

The Past ◽

Synthetic Signal ◽

Training Samples ◽

Benchmark Datasets ◽

Privacy Issues ◽

New Framework

Lifelong learning aims to train a highly expressive model for a new task while retaining all knowledge for previous tasks. However, many practical scenarios do not always require the system to remember all of the past knowledge. Instead, ethical considerations call for selective and proactive forgetting of undesirable knowledge in order to prevent privacy issues and data leakage. In this paper, we propose a new framework for lifelong learning, called Learning with Selective Forgetting, which is to update a model for the new task with forgetting only the selected classes of the previous tasks while maintaining the rest. The key is to introduce a class-specific synthetic signal called mnemonic code. The codes are "watermarked" on all the training samples of the corresponding classes when the model is updated for a new task. This enables us to forget arbitrary classes later by only using the mnemonic codes without using the original data. Experiments on common benchmark datasets demonstrate the remarkable superiority of the proposed method over several existing methods.

Download Full-text

The machine training in problems of satellite images’s processing

Metrologiya ◽

10.32446/0132-4713.2020-4-15-37 ◽

2020 ◽

pp. 15-37

Author(s):

L. P. Bass ◽

Yu. A. Plastinin ◽

I. Yu. Skryabysheva

Keyword(s):

Remote Sensing ◽

Neural Networks ◽

Computer Vision ◽

Satellite Images ◽

Vision Systems ◽

Earth Remote Sensing ◽

Practical Applications ◽

Convolution Neural Networks ◽

Computer Vision Systems ◽

Trained Neural Network

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

Download Full-text