Anu Aggarwal ¹, Gitika Sharma ¹, Sumit Sharma ¹

Affiliations
1 CSE Department, Chandigarh University, Gharuan - 140413, Punjab, IN

Abstract

The objectives of paper are to enhance the conceptual based trademark system. Trademarks are essential and important property of a business. A unique trademark allows a company to make status in the market which products or goods it put up for sale. Infringement causes when two trademarks are similar, because of infringement trademarks need security. The conceptual similarity among trademarks arises when more than one trademark evokes the same or similar content. To retrieve this semantic content, there is need of semantic retrieval system of trademarks. Thus, this paper represents an enhancement in semantic retrieval system to find similarity between trademarks using thesaurus of Microsoft word application and feature extraction technique i.e., Principle Component Analysis (PCA) and classification is performed using machine learning algorithms i.e., Artificial Neural Network (ANN), Support Vector Machine (SVM). This system is validated using real 75 infringement cases of trademarks those are conceptual based. The performance is measured using accuracy, precision and recall.

Keywords

Artificial Neural Network, Conceptual Similarity, Feature Extraction Technique, Semantic Retrieval System, Support Vector Machine.

Full Text

   

Gitika Sharma ¹, Sumit Sharma ¹, Anu Aggarwal ¹

Affiliations
1 Department of Computer Science, Chandigarh University. Gharuan - 140413, Mohali, IN

Abstract

The objective of this paper is identification and analysis of the prevention policies of trademark infraction and challenges to find similarity between trademarks. Additionally, this paper proposed an approach to enhance semantic retrieval system of conceptually similar trademarks using algorithms of machine learning like Naive Bayes (NB), Artificial Neural Network (ANN) and Support Vector Machine (SVM). Similarity of trademarks is calculated using Tversky index, Cosine similarity, Jaccard coefficient etc. The performance of classification algorithms are compared on the parameter like accuracy on a same set of trademarks representing real trademark infraction cases. The proposed approach is the first step to automate the process of finding conceptually similar trademarks.

Keywords

Accuracy, Machine Learning, Semantic Retrieval, Similarity, Trademark, Trademark Infraction.

Full Text