A novel hybrid artificial neural network technique for the early skin cancer diagnosis using color space conversions of original images

Tajjour, Salwan; Garg, Sonia; Chandel, S.S.; Sharma, Diksha

doi:10.1002/ima.22784

Cited by 26 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various strategies have been created and extensively researched for automated melanoma detection. Decision trees, artificial neural networks, and basic thresholding techniques for segmentation are some examples of the more well-known ones [42,43]. There was, however, scant information at the time.…”

Section: IImentioning

confidence: 99%

A Review on Skin Disease Classification and Detection Using Deep Learning Techniques

Kavitha,

Prasanna

2023

IJRITCC

View full text Add to dashboard Cite

Skin cancer ranks among the most dangerous cancers. Skin cancers are commonly referred to as Melanoma. Melanoma is brought on by genetic faults or mutations on the skin, which are caused by Unrepaired Deoxyribonucleic Acid (DNA) in skin cells. It is essential to detect skin cancer in its infancy phase since it is more curable in its initial phases. Skin cancer typically progresses to other regions of the body. Owing to the disease's increased frequency, high mortality rate, and prohibitively high cost of medical treatments, early diagnosis of skin cancer signs is crucial. Due to the fact that how hazardous these disorders are, scholars have developed a number of early-detection techniques for melanoma. Lesion characteristics such as symmetry, colour, size, shape, and others are often utilised to detect skin cancer and distinguish benign skin cancer from melanoma. An in-depth investigation of deep learning techniques for melanoma's early detection is provided in this study. This study discusses the traditional feature extraction-based machine learning approaches for the segmentation and classification of skin lesions. Comparison-oriented research has been conducted to demonstrate the significance of various deep learning-based segmentation and classification approaches.

show abstract

Section: IImentioning

confidence: 99%

A Review on Skin Disease Classification and Detection Using Deep Learning Techniques

Kavitha,

Prasanna

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…These methods can automatically evaluate complex criteria from the input images and easily diagnosis the infected part even though there is a changes in size and shape due to the occurrence of blur, noise, intensity, presence of light, color changes (Tighe et al, 2023). The problems such as high computational cost and over fitting faced by the existing method is rectified by this deep learning dependent techniques (Tajjour et al, 2023). Dermatologists must possess a high degree of skill and incur significant costs while analyzing dermoscopy images to accurately diagnose the condition (Osman & Yap, 2020; Sathish et al, 2020; Skin Lesion Images for Melanoma Classification, 2019).…”

Section: Introductionmentioning

confidence: 99%

Optimized self‐attention based cycle‐consistent generative adversarial network adopted melanoma classification from dermoscopic images

Harini,

Madhavi,

Latha

et al. 2024

Microscopy Res & Technique

View full text Add to dashboard Cite

Skin is the exposed part of the human body that constantly protected from UV rays, heat, light, dust, and other hazardous radiation. One of the most dangerous illnesses that affect people is skin cancer. A type of skin cancer called melanoma starts in the melanocytes, which regulate the colour in human skin. Reducing the fatality rate from skin cancer requires early detection and diagnosis of conditions like melanoma. In this article, a Self‐attention based cycle‐consistent generative adversarial network optimized with Archerfish Hunting Optimization Algorithm adopted Melanoma Classification (SACCGAN‐AHOA‐MC‐DI) from dermoscopic images is proposed. Primarily, the input Skin dermoscopic images are gathered via the dataset of ISIC 2019. Then, the input Skin dermoscopic images is pre‐processed using adjusted quick shift phase preserving dynamic range compression (AQSP‐DRC) for removing noise and increase the quality of Skin dermoscopic images. These pre‐processed images are fed to the piecewise fuzzy C‐means clustering (PF‐CMC) for ROI region segmentation. The segmented ROI region is supplied to the Hexadecimal Local Adaptive Binary Pattern (HLABP) to extract the Radiomic features, like Grayscale statistic features (standard deviation, mean, kurtosis, and skewness) together with Haralick Texture features (contrast, energy, entropy, homogeneity, and inverse different moments). The extracted features are fed to self‐attention based cycle‐consistent generative adversarial network (SACCGAN) which classifies the skin cancers as Melanocytic nevus, Basal cell carcinoma, Actinic Keratosis, Benign keratosis, Dermatofibroma, Vascular lesion, Squamous cell carcinoma and melanoma. In general, SACCGAN not adapt any optimization modes to define the ideal parameters to assure accurate classification of skin cancer. Hence, Archerfish Hunting Optimization Algorithm (AHOA) is considered to maximize the SACCGAN classifier, which categorizes the skin cancer accurately. The proposed method attains 23.01%, 14.96%, and 45.31% higher accuracy and 32.16%, 11.32%, and 24.56% lesser computational time evaluated to the existing methods, like melanoma prediction method for unbalanced data utilizing optimized Squeeze Net through bald eagle search optimization (CNN‐BES‐MC‐DI), hyper‐parameter optimized CNN depending on Grey wolf optimization algorithm (CNN‐GWOA‐MC‐DI), DEANN incited skin cancer finding depending on fuzzy c‐means clustering (DEANN‐MC‐DI).Research Highlights This manuscript, self‐attention based cycle‐consistent. SACCGAN‐AHOA‐MC‐DI method is implemented in Python. (SACCGAN‐AHOA‐MC‐DI) from dermoscopic images is proposed. Adjusted quick shift phase preserving dynamic range compression (AQSP‐DRC). Removing noise and increase the quality of Skin dermoscopic images.

show abstract

“…Machine learning is used in artificial intelligence, with the development of today's computer technology, artificial intelligence has entered many different application areas from health [1][2][3], and logistics [4,5] to chemistry, finance [6], [7] to education [8] to computer game [9,10] and industry [11][12][13]. The main cause is that machine learning methods can evaluate and interpret data faster and more accurately today and make the most appropriate and correct decisions.…”

Section: Introduction *mentioning

confidence: 99%

Controlling a Single Tank Liquid Level System with Classical Control Methods and Reinforcement Learning Methods

Çimen,

Garip

2024

Kocaeli Journal of Science and Engineering

View full text Add to dashboard Cite

In this study, the control of the single tank liquid level system used in control systems have been carried out. The control of the single tank liquid level system has been performed with the classic PI, modified PI, state feedback with integrator action, and Q learning algorithm and SARSA algorithms, one of the artificial intelligence methods. The tank system to be modelled was carried out using classical physics, namely Newton's laws. Then, the mathematical model obtained of the system that are continuous model in time is acquired. The originality of the study; the non-linear liquid tank system is controlled by classical controllers and reinforcement methods. For this purpose, the system was firstly designed to model the system, then the system have been linearized at a specific point in order to design classic PI, modified PI, and state feedback with integral. After that, agents of Q Learning algorithm and SARSA algorithms were trained for the system. Then the agents have controlled the single -level tank system. The results of the classic controllers and supervised system are contrasted with regard to performance criteria such as rising time, settling time, overshoot and integral square error. Consequently, Q learning algorithm has produced and exhibited more thriving and successful results than other methods.

show abstract

A novel hybrid artificial neural network technique for the early skin cancer diagnosis using color space conversions of original images

Cited by 26 publications

References 59 publications

A Review on Skin Disease Classification and Detection Using Deep Learning Techniques

A Review on Skin Disease Classification and Detection Using Deep Learning Techniques

Optimized self‐attention based cycle‐consistent generative adversarial network adopted melanoma classification from dermoscopic images

Controlling a Single Tank Liquid Level System with Classical Control Methods and Reinforcement Learning Methods

Contact Info

Product

Resources

About