Prediction of quality for different type of winebased on different feature sets using supervised machine learning techniques
Download as DOCX, PDF0 likes34 views
The document discusses predicting wine quality using various supervised machine learning techniques including SVM, Random Forest, and Naïve Bayes, enhanced by feature selection algorithms like Genetic Algorithm (GA) and Simulated Annealing (SA). It details how these methods improve accuracy by refining datasets to focus on relevant attributes, and provides accuracy results of multiple algorithms applied to a wine dataset. Overall, SVM with GA achieved the highest accuracy of 60%, outperforming other tested algorithms.
Prediction of quality for different type of winebased on different feature sets using supervised machine learning techniques
- 1. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] Prediction of Quality for Different Type of Wine based on Different Feature Sets Using Supervised Machine Learning Techniques In this paper author is predicting quality of wine using supervise machine learning algorithmssuch asSVM,Random Forest,NaïveBayes etc. All algorithms prediction accuracy can be better by adding features selection algorithms such as Genetic Algorithm (GA) or Simulated Annealing (SA). Feature selection algorithms can be applied to dataset to remove non relevant attributes or missing values and take only thoseattributes from dataset which are important to makepredictions.Using featureselection algorithmswecan decreasedataset size by removing non relevant data and make prediction accuracy better and faster. Genetic algorithm works in similar way as its work on chromosomes by taking relevant genes to formnew production and remove unhealthy or non-relevant genes. GA algorithm continuously iterate over dataset to look for non-relevant attributes by doing mutation, reproduction and fitness, only those attributes which has high fitness or related to more dataset values can be used for mutation and reproduction and unfitted values will be removed out. Simulated annealing (SA) is a global search/selection method that makes small random changes (i.e. perturbations) to an initial (dataset values) candidate solution. If the performancevalue for the perturbed (new Data) value is better than the previous solution, the new solution (data/attribute) is accepted. If not, an acceptance probability is determined based on the difference between the two performance values and the current iteration of the search. From this, a sub-optimal solution can be accepted on the off-change that it may eventually produce a better solution or best attributes in subsequent iterations. SVMAlgorithm: Machinelearning involvespredicting and classifyingdata and to do so we employ various machinelearning algorithms according to the dataset. SVM or Support Vector Machine is a linear model for classification and regression problems. Itcan solve linear and non-linear problems and work well for many practical problems. The idea of SVM is simple: The algorithm creates a line or a hyperplanewhich separates the data into classes. In machine learning, the radial basis function kernel, or RBF kernel, is a popular kernel function used in various kernelized learning algorithms. In particular, it is commonly used in support vector machine classification. As a simple example, for a classification
- 2. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] taskwith onlytwo features (likethe image above),youcan think of a hyperplane as a line that linearly separates and classifies a set of data. Intuitively, the further from the hyperplane our data points lie, the more confident we are that they have been correctly classified. We therefore want our data points to be as far away from the hyperplane as possible, while still being on the correct side of it. So when new testing data is added, whatever sideof the hyperplaneit lands will decide the class that we assign to it. How do we find the right hyperplane? Or, in other words, how do we best segregate the two classes within the data? The distancebetween the hyperplaneand the nearestdata point fromeither set is known as the margin. The goal is to choose a hyperplane with the greatest possible margin between the hyperplane and any point within the training set, giving a greater chance of new data being classified correctly. Random ForestAlgorithm: it’s an ensemble algorithm which means internally it will use multiple classifier algorithms to build accurate classifier model. Internally this algorithm will use decision tree algorithm to generate it train model for classification. Naive Bayes: Naive Bayes which is one of the most commonly used algorithms for classifying problems is simple probabilistic classifier and is based on Bayes Theorem. It determines the probability of each features occurring in each class and returns the outcome with the highest probability. Dataset Information We downloaded wine dataset from UCI machine learning website and dataset saved inside dataset folder. All machine learning algorithms will take dataset and train a model by splitting dataset into train and test part. Train part will be used to train model and test part will be applied on train model to predict test part class value. Screen shots To run this project double click on ‘run.bat’ file to get below screen
- 3. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] In above screen click on ‘upload White/Red Wine Dataset’ button to upload red or white wine dataset. In above screen I am uploading redwine dataset and after upload will get below screen
- 4. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] Now click on ‘Run SVM with GA’ button to run SVM algorithm with genetic feature selection algorithm. After clicking on this button 5 empty windows will open you just closed all 5 windows and keep the old one running In above screen we got 60% accuracy for SVM with Ga. Now run SVM with SA (Simulated Annealing) Algorithm
- 5. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] In abovescreenfor SVM with SA we got50 % accuracy. Nowrun RandomForest with GA With random forest ga we got 30% accuracy. Now run random forest with SA
- 6. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] In above screenrandom forestSA also got same accuracy and now click on Naïve Bayes with GA In above screennaïve bayes with GA got 40% accuracyand nowrun Naïve Bayes with SA
- 7. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected] Naïve Bayes SA got 40 % accuracy. Now click on ‘Accuracy Graph’ button to get accuracy graph for all algorithms In above graph x-axis represents algorithm name and y-axis represents accuracy of those algorithms and from above graph we can conclude SVM with GA got better accuracy compare to all other algorithms
- 8. Venkat Java Projects Mobile:+91 9966499110 Visit:www.venkatjavaprojects.com Email:[email protected]