Search results
1 – 2 of 2Naga Swetha R, Vimal K. Shrivastava and K. Parvathi
The mortality rate due to skin cancers has been increasing over the past decades. Early detection and treatment of skin cancers can save lives. However, due to visual resemblance…
Abstract
Purpose
The mortality rate due to skin cancers has been increasing over the past decades. Early detection and treatment of skin cancers can save lives. However, due to visual resemblance of normal skin and lesion and blurred lesion borders, skin cancer diagnosis has become a challenging task even for skilled dermatologists. Hence, the purpose of this study is to present an image-based automatic approach for multiclass skin lesion classification and compare the performance of various models.
Design/methodology/approach
In this paper, the authors have presented a multiclass skin lesion classification approach based on transfer learning of deep convolutional neural network. The following pre-trained models have been used: VGG16, VGG19, ResNet50, ResNet101, ResNet152, Xception, MobileNet and compared their performances on skin cancer classification.
Findings
The experiments have been performed on HAM10000 dataset, which contains 10,015 dermoscopic images of seven skin lesion classes. The categorical accuracy of 83.69%, Top2 accuracy of 91.48% and Top3 accuracy of 96.19% has been obtained.
Originality/value
Early detection and treatment of skin cancer can save millions of lives. This work demonstrates that the transfer learning can be an effective way to classify skin cancer images, providing adequate performance with less computational complexity.
Details
Keywords
Ghulam E. Mustafa Abro, Nirbhay Mathur, Saiful Azrin B.M. Zulkifli, Malak Gulbadin Khan Gulbadin Khan Kakar, Naga Swetha Pasupuleti and Vijanth Sagayan Sagayan Asirvadam
The novel coronavirus (COVID-19) has almost affected more than two million people and has taken more than one hundred thousand lives around the globe. At this current state…
Abstract
Purpose
The novel coronavirus (COVID-19) has almost affected more than two million people and has taken more than one hundred thousand lives around the globe. At this current state, researchers are trying their best level to drive the permanent solution for this menace; hence, till now social distancing and hygienic lifestyle are the only solutions. This paper proposes a smart entrance disinfectant gate based on the sanitizer spray station and ultraviolet irradiation mechanisms. This innovative and embedded system design-oriented gate will first capture the image of the entrant, second, measure the temperature, third, spray the sanitizers and, last, provide the ultraviolet irradiation to make sure that the person entering any space may have fewer chances to carry coronavirus. The purpose of this study is to enable the IoT feature that helps the government officials to keep the data record of suspectable, exposed, infected and recovered people which will later help to reduce the reproductive co-efficient Ro of COVID-19 within any state of Malaysia.
Design/methodology/approach
In the current manuscript, design proposes a smart entrance disinfectant gate based on the sanitizer spray station and ultraviolet irradiation mechanisms. This design of the gate is enabled with the feature of the internet of things (IoT) and some efficient sensors along with computer vision facilities.
Findings
This paper bridges an academic research on COVID-19 and addresses IoT and data prediction-based solution to compute the reproductive number for this novel coronavirus.
Originality/value
This paper with the features such as hardware design, IoT and, last but not the least, data prediction and visualization makes this prototype one of its kind and provides approximate results for reproductive number (Ro)
Details