scholarly journals Cureskin - Skin Disease Prediction using MobileNet Model

2020 ◽  
pp. 32-37
Author(s):  
N. Divya ◽  
Deepthi P Dsouza ◽  
Hariprasad
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Environmental Factors ◽  
Skin Disease ◽  
Skin Diseases ◽  
Disease Prediction ◽  
Android Application ◽  
The People ◽  
The World ◽  
Financial Issues

Skin diseases are getting more common than any other disease in the world. Due to lack of personal care and different environmental factors many of the people are suffering from skin diseases. It may have caused because of infection, allergy, bacteria or viruses, etc. Not every patient has the facility to go to the doctor for primary consultation based on the financial issues. To overcome this problem we developed an android application which helps the patients in diagnosing the disease easily at home. There are several methods or algorithms in machine learning to make this process easier. We proposed an approach to skin disease prediction using MobileNet model which is a part of Convolutional Neural Networks (CNN). In total there are six diseases namely acne, actinic, psoriasis, tinea ringworm, eczema and seborrhoea. Our model is pre-trained by feeding thousands of images also including images which are not diseased and also which do not comes under skin. Our approach is simple, fast and inexpensive and does not require huge equipment for the diagnosis. It is found that MobileNet model gives best accuracy.

scholarly journals Vision-Based Skin Disease Identification Using Deep Learning

2019 ◽  
Vol 8 (6) ◽  
pp. 3784-3788
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Skin Disease ◽  
Medical Image ◽  
Skin Diseases ◽  
Learning Algorithm ◽  
Disease Prediction ◽  
Machine Learning Algorithm ◽  
Disease Identification ◽  
Different Types

Skin disease is the most common health problems worldwide.Human skin is one of the difficult areas topredict. The difficulty is due to rough areas, irregular skin tones, various factors like burns, moles. We have to identify the diseases excluding these factors.In a developing country like India, it is expensive for a large number of people to go to the dermatologist for their skin disease problem.Every year a large number of population in developing countries like India suffer due to different types of skin diseases. So the need for automatic skin disease prediction is increasing for the patients and as well as the dermatologist. In this paper, a method is proposed that uses computer vision-based techniques to detectvariouskinds of dermatological skin diseases. Inception_v3, Mobilenet, Resnetare three deep learning algorithms used for feature extraction in a medical image and machine learning algorithm namely Logistic Regression is used for training and testing the medical images.Using the combined architecture of the three convolutional neural networks considerable efficiency can be achieved.

Development of Dermatological Skin Disease Detection and Classification based on Wavelet and ANN

2018 ◽  
Vol 8 (5) ◽  
pp. 10
Author(s):  
Revati Kadu ◽  
U. A. Belorkar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Skin Disease ◽  
Skin Diseases ◽  
Screening Method ◽  
Phase Detection ◽  
Statistical Measures ◽  
The World ◽  
Artificial Neural ◽  
Wavelet Techniques

One of the most common and augmenting health problems in the world are related to skin. The most  unpredictable and one of the most difficult entities to automatically detect and evaluate is the human skin disease because of complexities of texture, tone, presence of hair and other distinctive features. Many cases of skin diseases in the world have triggered a need to develop an effective automated screening method for detection and diagnosis of the area of disease. Therefore the objective of this work is to develop a new technique for automated detection and analysis of the skin disease images based on color and texture information for skin disease screening. In this paper, system is proposed which detects the skin diseases using Wavelet Techniques and Artificial Neural Network. This paper presents a wavelet-based texture analysis method for classification of five types of skin diseases. The method applies tree-structured wavelet transform on different color channels of red, green and blue dermoscopy images, and employs various statistical measures and ratios on wavelet coefficients. In all 99 unique features are extracted from the image. By using Artificial Neural Network, the system successfully detects different types of dermatological skin diseases. It consists of mainly three phases image processing, training phase, detection  and classification phase.

scholarly journals Ensembling Coalesce of Logistic Regression Classifier for Heart Disease Prediction using Machine Learning

2019 ◽  
Vol 8 (12) ◽  
pp. 127-133
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Heart Disease ◽  
Heart Diseases ◽  
Experimental Results ◽  
Disease Prediction ◽  
Feature Importance ◽  
The World ◽  
Feature Scaling ◽  
Logistic Regression Classifier

In today’s modern world, the world population is affected with some kind of heart diseases. With the vast knowledge and advancement in applications, the analysis and the identification of the heart disease still remain as a challenging issue. Due to the lack of awareness in the availability of patient symptoms, the prediction of heart disease is a questionable task. The World Health Organization has released that 33% of population were died due to the attack of heart diseases. With this background, we have used Heart Disease Prediction dataset extracted from UCI Machine Learning Repository for analyzing and the prediction of heart disease by integrating the ensembling methods. The prediction of heart disease classes are achieved in four ways. Firstly, The important features are extracted for the various ensembling methods like Extra Trees Regressor, Ada boost regressor, Gradient booster regress, Random forest regressor and Ada boost classifier. Secondly, the highly importance features of each of the ensembling methods is filtered from the dataset and it is fitted to logistic regression classifier to analyze the performance. Thirdly, the same extracted important features of each of the ensembling methods are subjected to feature scaling and then fitted with logistic regression to analyze the performance. Fourth, the Performance analysis is done with the performance metric such as Mean Squared error (MSE), Mean Absolute error (MAE), R2 Score, Explained Variance Score (EVS) and Mean Squared Log Error (MSLE). The implementation is done using python language under Spyder platform with Anaconda Navigator. Experimental results shows that before applying feature scaling, the feature importance extracted from the Ada boost classifier is found to be effective with the MSE of 0.04, MAE of 0.07, R2 Score of 92%, EVS of 0.86 and MSLE of 0.16 as compared to other ensembling methods. Experimental results shows that after applying feature scaling, the feature importance extracted from the Ada boost classifier is found to be effective with the MSE of 0.09, MAE of 0.13, R2 Score of 91%, EVS of 0.93 and MSLE of 0.18 as compared to other ensembling methods.

Prediction of Skin Diseases Using Machine Learning

2022 ◽  
pp. 154-178
Author(s):  
Siddhartha Kumar Arjaria ◽  
Vikas Raj ◽  
Sunil Kumar ◽  
Priyanshu Shrivastava ◽  
Monu Kumar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Skin Disease ◽  
Skin Diseases ◽  
Information Gain ◽  
Machine Learning Algorithms ◽  
Ensemble Method ◽  
Chi Square ◽  
Data Mining Techniques ◽  
Disease Rates

Skin disease rates have been increasing over the past few decades. It has led to both fatal and non-fatal disabilities all around the world, especially in those areas where medical resources are not good enough. Early diagnosis of skin diseases increases the chances of cure significantly. Therefore, this work is comparing six machine learning algorithms, namely KNN, random forest, neural network, naïve bayes, logistic regression, and SVM, for the prediction of the skin diseases. The information gain, gain ratio, gini decrease, chi-square, and relieff are used to rank the features. This work comprises the introduction, literature review, and proposed methodology parts. In this research paper, a new method of analyzing skin disease has been proposed in which six different data mining techniques are used to develop an ensemble method that integrates all the six data mining techniques as a single one. The ensemble method used on the dermatology dataset gives improved result with 94% accuracy in comparison to other classifier algorithms and hence is more effective in this area.

Educational Software Based on Matlab GUIs for Neural Networks Courses

2016 ◽  
pp. 333-358 ◽  
Author(s):  
Pablo Díaz-Moreno ◽  
Juan José Carrasco ◽  
Emilio Soria-Olivas ◽  
José M. Martínez-Martínez ◽  
Pablo Escandell-Montero ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Educational Software ◽  
Machine Learning Techniques ◽  
Teaching Tool ◽  
Neural Models ◽  
Learning Techniques ◽  
The World ◽  
Programming Skills

Neural Networks (NN) are one of the most used machine learning techniques in different areas of knowledge. This has led to the emergence of a large number of courses of Neural Networks around the world and in areas where the users of this technique do not have a lot of programming skills. Current software that implements these elements, such as Matlab®, has a number of important limitations in teaching field. In some cases, the implementation of a MLP requires a thorough knowledge of the software and of the instructions that train and validate these systems. In other cases, the architecture of the model is fixed and they do not allow an automatic sweep of the parameters that determine the architecture of the network. This chapter presents a teaching tool for the its use in courses about neural models that solves some of the above-mentioned limitations. This tool is based on Matlab® software.

Skin Disease Prediction

2020 ◽  
Vol 17 (8) ◽  
pp. 3458-3462
Author(s):  
S. L. Jany Shabu ◽  
Maram Sai Nithin ◽  
Medepalli Santhosh ◽  
M. S. Roobini ◽  
K. Mohana Prasad ◽  
...  
Keyword(s):  
Skin Disease ◽  
Skin Diseases ◽  
Skin Inflammation ◽  
Disease Prediction ◽  
Clinical Parameters

As of late, skin diseases are expanded in people. Skin illnesses are brought about by microscopic organisms or because of contaminations. A portion of the skin illnesses resemble ring worm, yeast disease, sensitivities and so on are increments and spread over skin step by step. So this sort of maladies ought to be distinguished in its previous stage to abstain from spreading. It tends to be distinguished utilizing a few variables like clinical parameters which are considered for recognizing the infection. The conceivable skin sicknesses in various ages are dermatitis in age 0–5 years, moles influences in 6–11 years age, and skin inflammation vulgaris in 12–16 years age. Dermatomyositis is a sort of skin illness that influences youngsters at age of 5–15 and grown-up at 40–60 age. Right now, objective is to give a device to help experts and buyers in finding and picking sickness. To accomplish this objective, we build up a methodology that permits a client to inquiry for disease that fulfil a lot of conditions dependent on sickness properties, for example, infection signs.

Application of Artificial Neural Networks for Heart Disease Prediction

2020 ◽  
Vol 17 (9) ◽  
pp. 4190-4196
Author(s):  
Kumar Suyash ◽  
K. R. Shobha
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Intelligent Systems ◽  
Heart Diseases ◽  
Medical Science ◽  
Back Propagation ◽  
Diagnostic System ◽  
Science Field ◽  
The World ◽  
Significant Life

Heart related diseases are on a rise throughout the world. While the WHO estimates 31% of all deaths worldwide are caused by heart related diseases, some estimates even attribute 18 million deaths throughout the world due to such diseases. Although, the monumental strides in the field of machine learning, especially neural networks have enabled us to solve complex recognition problems, we still at large have been unable to utilize their power to the maximum in the data rich medical science field. These networks can in fact be used to construct intelligent systems which can help predict the presence of heart diseases in their early stages. Such intelligent systems shall result in significant life savings due to the readily available timely medical care and the following treatments. Encompassing the techniques of classification, a supervised learning approach of machine learning, in these intelligent systems can be aimed at pinpointing the accurate diagnosis. This paper thus, proposes a diagnostic system for predicting the presence of heart diseases using neural networks with back propagation.

scholarly journals A Review of Skin Disease Classification Techniques based on Machine Learning

2021 ◽  
Vol 9 (8) ◽  
pp. 1097-1101
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Skin Cancer ◽  
Basal Cell Carcinoma ◽  
Actinic Keratosis ◽  
Skin Disease ◽  
Skin Diseases ◽  
Skin Condition ◽  
Disease Classification ◽  
Vascular Lesions

Dermatology is one of the most unpredictable and difficult field to diagnose. In this field, more tests are needed to be carried out so as to decide the skin condition the patient may be facing. The time to diagnose may vary according to the different dermatologist. Machine learning and image processing can be used to efficiently detect the skin diseases. There are seven different categories of skin cancer- melanocytic nevi, melanoma, benign keratosis, Basal cell carcinoma, actinic keratosis, vascular lesions and dermatofibroma. The purpose of this review is to outline types, diagnosis, methodology and treatment of skin cancer.

scholarly journals Assessment of Classifiers with Machine Learning based Thyroid Disease Prediction System

2020 ◽  
Vol 8 (5) ◽  
pp. 4718-4721
Keyword(s):  
Machine Learning ◽  
Thyroid Disease ◽  
System Model ◽  
Disease Prediction ◽  
Prediction System ◽  
The People ◽  
Different Types ◽  
Antithyroid Treatment ◽  
Roc Area ◽  
F Measure

Most of the people in different nations are suffering from Thyroid related diseases and these are lifelong. Many people are unaware of having Thyroid related diseases. Main cause for this is due to improper functioning of Thyroid gland secreting Thyroid hormone which regulates body metabolism. In this paper we have made survey on classifiers like Decision Tree C4.5(J48), Multilayer Perceptron, Naïve Bayes by measuring TP Rate, FP Rate, Precision, Recall, F-Measure, MCC, ROC Area, PRC Area and developed a prediction system for Thyroid diseases. For training and testing the classifiers we have used Thyroid dataset from UCI repository. Dataset consists of 9172 records containing 29 attribute values and 1 diagnosis class value. The diagnosis class value consists of different types Thyroid disease conditions like hyperthyroid conditions, hypothyroid conditions, binding protein, general health, replacement therapy, antithyroid treatment and miscellaneous. The proposed prediction system model capable of predicting type of Thyroid disease whether a person is suffering or not.

scholarly journals Rainfall Prediction using Machine Learning and Neural Network

2020 ◽  
Vol 9 (1) ◽  
pp. 1954-1961
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Weather Forecasting ◽  
Research Work ◽  
Primary Source ◽  
Coastal Areas ◽  
Complex Data ◽  
Linear Pattern ◽  
Rainfall Prediction ◽  
The People

Rainfall prediction model mainly based on artificial neural networks have been proposed in India until now. This research work does a comparative study of two rainfall prediction approaches and finds the more accurate one. The present technique to predict rainfall doesn’t work well with the complex data present. The approaches which are being used now-a-days are statistical methods and numerical methods, which don’t work accurately when there is any non-linear pattern. Existing system fails whenever the complexity of the datasets which contains past rainfall increases. Henceforth, to find the best way to predict rainfall, study of both machine learning and neural networks is performed and the algorithm which gives more accuracy is further used in prediction. Recently, rainfall is considered the primary source of most of the economy of our country. Agriculture is considered the main economy driven source. To do a proper investment on agriculture, a proper estimation of rainfall is needed. Along with agriculture, rainfall prediction is needed for the people in coastal areas. People in coastal areas are in high risk of heavy rainfall and floods, so they should be aware of the rainfall much earlier so that they can plan their stay accordingly. For areas which have less rainfall and faces water scarcity should have rainwater harvesters, which can collect the rainwater. To establish a proper rainwater harvester, rainfall estimation is required. Weather forecasting is the easiest and fastest way to get a greater outreach. This research work can be used by all the weather forecasting channels, so that the prediction news can be more accurate and can spread to all parts of the country

Sign in / Sign up

Export Citation Format

Share Document