220 skills found · Page 5 of 8
llmir / The SUSTech SYSU Dataset For Automated Exudate Detection And Diabetic Retinopathy GradingAutomated detection of exudates from fundus images plays an important role in diabetic retinopathy (DR) screening and evaluation, for which supervised or semi-supervised learning methods are typically preferred. However, a potential limitation of supervised and semi-supervised learning based detection algorithms is that they depend substantially on the sample size of training data and the quality of annotations, which is the fundamental motivation of this work. In this study, we construct a dataset containing 1219 fundus images (from DR patients and healthy controls) with annotations of exudate lesions. In addition to exudate annotations, we also provide four additional labels for each image: leftversus- right eye label, DR grade (severity scale) from three different grading protocols, the bounding box of the optic disc (OD), and fovea location. This dataset provides a great opportunity to analyze the accuracy and reliability of different exudate detection, OD detection, fovea localization, and DR classification algorithms. Moreover, it will facilitate the development of such algorithms in the realm of supervised and semi-supervised learning.
abhikkonar05 / Air Quality Prediction Analysis SystemAeroSense Analytics is a machine learning–powered air quality prediction and classification system designed to assess environmental conditions with high accuracy. The project uses advanced data preprocessing, feature engineering, and multiple supervised learning algorithms to predict and classify air quality into “Good” or “Poor” categories.
js-eng / ML Detection Of Phishing WebsiteIn todays era, due to the surge in the usage of internet and other online platforms, security has been a major concern. Many cyber attacks take place each day out of which website phishing is the most common issue. It is an act of imitating a legitimate website and thereby duping the users and stealing their sensitive information. So, with respect to this problem this paper will introduce a possible solution in order to avoid such attacks by checking whether the provided URLs are phishing URL or legitimate URL. It is basically a Machine Learning based system particularly supervised learning where we have provided 2000 phishing and 2000 legitimate URL dataset. We have taken into consideration Random Forest algorithm due to its performance and accuracy. It takes 9 features into consideration and hence detects whether the URL is safe to access or a phishing URL.
dilettagoglia / DataMining🔎Data Understanding, Visualization , Preparation & Cleaning - Clustering algorithms (unsupervised learning) - Classification algorithms (supervised learning) - Sequential Pattern Mining
xtudbxk / Em Adapt Tensorflowthe weakly-supervised semantic segmentation algorithm from "Weakly-and semi-supervised learning of a DCNN for semantic image segmentation"
brendanoconnor913 / SFFSImplementation of sequential forward floating selection algorithm for supervised learning course
LucasKook / CometsAlgorithm-agnostic significance testing in supervised learning with multimodal data
raghavan / Semi Supervised LearningImplementing a semi supervised learning algorithm using SVM as base classifier
andre1araujo / Supervised And Unsupervised Learning ExamplesHere you will find a Notebook with examples of various Machine Learning algorithms (ML), more specifically, Supervised and Unsupervised Learning examples. All of the code is followed by explanations and everything is easy to use and to understand thanks to the documentation.
naranil / Ensemble ComparisonWe present an extensive empirical comparison between twenty prototypical supervised ensemble learning algorithms, including Boosting, Bagging, Random Forests, Rotation Forests, Arc-X4, Class-Switching and their variants, as well as more recent techniques like Random Patches.
mitranos / Exoplanets Discovery Machine LearningDesigned a supervised learning model to discover exoplanets thanks to the Kepler Telescope data. This project involved pre-processing data with Dynamic Time Wrapping and applying different unsupervised learning algorithms to make a prediction about a planet. Discovered 144 planets that were not previously categorized as confirmed.
UrbsLab / HerosThe Heuristic Evolutionary Rule Optimization System (HEROS) is a supervised rule-based machine learning algorithm designed to agnostically model diverse 'structured' data problems and yield compact human interpretable solutions. This implementation is scikit-learn compatible.
roytalman / Deep Contrastive EmbeddingDeep supervised conistrastive learning for small datasets (few shot learning). This repository takes labeled embedding data ,that could be extracted from pre-trained NLP, vision, or any other algorithm that extract embedding, and use deep FFN to learn new embedding that is fine-tuned for the current data. Th algorithm can improve classification per
rarpit1994 / Machine Learning Based Classification Of Cervical Cancer Using K Nearest Neighbor Random Forest AndCervical cancer is the second most common type of cancer that is found in the women worldwide. Generally, cancer caused due to irregular growth of cells in a particular area that or have the potential to spread to the other parts of the body as well. Identification of a cervical cancer test is an examination of the tissue taken from a particular region, which might contain cancerous cells through biopsy, is exceptionally challenging because these types of cells does not offer unusual color or texture variants from the standard cells. To identify the abnormalities in human cell the high-level digital image processing technologies are already present in the market which very costly concerning the money. Therefore, we are proposing the model which going to classify whether a female patient has cervical cancer or not. We are using various attributes from real-life and performing a feature selection algorithm Recursive Feature Elimination (RFE). Afterward, making classification models using three machine-learning algorithms like K-Nearest Neighbor (KNN), Random Forest and Multilayer Perceptron (MLP), MLP is a type of the Artificial Neural Network (ANN) algorithm whereas KNN and Random Forest is a supervised type of algorithm.
sergio94al / Automatic Design Of Quantum Feature Maps Genetic Auto GenerationRegistered Software. Official code of the published article "Automatic design of quantum feature maps". This quantum machine learning technique allows to auto-generate quantum-inspired classifiers by using multiobjetive genetic algorithms for tabular data.
rvssumanth / Capstone Project Credit Card Fraud DetectionThe goal of this project is to find out whether a card holder transaction is fraud or not, using supervised and unsupervised machine learning algorithms.
dblalock / ExtractSupporting website for EXTRACT, the semi-supervised learning algorithm
ThinamXx / MachineLearning With PythonIn this repository, you will gain insights about various Supervised and Unsupervised Machine Learning Algorithms implementation on real data sets along with Visualizations.
fotioudim / GoogleEarthEngine Green Spaces In AthensStudy about Urban Green Spaces in Athens GR, using the Google Earth Engine platform, along with Landsat 8 and 9 imagery and Random Forest supervised machine learning algorithms.
Diwas524 / Weather Prediction Using Machine LearningIn this research paper, we explore the application of ML to weather prediction. Specifically, we focus on the use of supervised learning algorithms, including decision trees, logistic regression, and k-nearest neighbors, to predict weather conditions based on historical data. We use a dataset containing daily weather measurements
