Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 43714 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Beigy, Hamid
- Abstract:
- Nowadays, with the increasing size of data,it’s impossible to collect data and fast classification by human, and needs for an automated classification and data analysis, is more interested. Data classification is a process of giving the training data along with their class labels to the learning agent, which learns the relation between the instances and the labels. Then make a prediction to the label of the training data.In this thesis we will observe the classification of the multi-label data. Multi-label data have more than one label. In other words, each instance appears with a vector of labels.In this thesis, a method based on nearest neighbor is proposed to classify the multi-label data.In the proposed method, firstly the algorithm estimates the number of labels for each new instance and then predicts labels for each new arrival instance, considering relation between labels. In this thesis, the nearest neighbor classifier is used as the base classifier, but will not consider the Euclidian distance metric for distance measure.The proposed method evaluates the available data in the field of multi-label data, and compares with well-known methods in this field. It shows that the proposed method comparing other methods, to predict the correct labels for new instances performs better in both time complexity and performance accuracy.
- Keywords:
- Data Classification ; Multilabel Data ; Classification Algorithms
Digital Object List
-
محتواي پايان نامه
- view
Bookmark