Accuracy Performance Degradation in Image Classification Models due to Concept Drift
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 5
Abstract
Big data is playing a significant role in the current computing revolution. Industries and organizations are utilizing their insights for Business Intelligence by using Deep Learning Networks (DLN). However, dynamic characteristics of BD introduce many critical issues for DLN; Concept Drift (CD) is one of them. CD issue appears frequently in Online Supervised Learning environments in which data trends change over time. The problem may even worsen in a BD environment due to the veracity and variability factors. The CD issue may render the DLN inapplicable by degrading the accuracy of classification results in DLN which is a very serious issue that needs to be addressed. Therefore, these DLN need to quickly adapt to changes for maintaining the accuracy level of the results. To overcome classification accuracy, we need some dynamical changes in the existing DLN. Therefore, in this paper, we examine some of the existing Shallow Learning and Deep Learning models and their behavior before and after the Concept Drift (in experiment 1) and validate the pre-trained Deep Learning network (ResNet-50). In future work, this experiment will examine the most recent pre-trained DLN (Alex Net, VGG16, VGG19) and identify their suitability to overcome Concept Drift using fine-tuning and transfer learning approaches.
Authors and Affiliations
Manzoor Ahmed Hashmani, Syed Muslim Jameel, Hitham Alhussain, Mobashar Rehman, Arif Budiman
Keywords
Related Articles
- EP ID EP578628
- DOI 10.14569/IJACSA.2019.0100552
- Views 107
- Downloads 0
A Review of Solutions for SDN-Exclusive Security Issues
Software Defined Networking is a paradigm still in its emergent stages in the realm of production-scale networks. Centralisation of network control introduces a new level of flexibility for network administrators and pro...
Hybrid Method and Similarity to Recognize Javanese Keris
This paper describes Hybrid method and Similarity for recoginizing Javanese Keris. Javanese Keris is one of traditional javanese weapon. It is one of the Indonesia Cultural Heritage. Keris is famous for its distinctive w...
A Proposed Framework to Investigate the User Acceptance of Personal Health Records in Malaysia using UTAUT2 and PMT
Personal Health Records (PHRs) can be considered as one of the most important health technologies. PHRs enroll the patients directly to their health decision making through giving them the authority to control and share...
Establishing News Credibility using Sentiment Analysis on Twitter
The widespread use of Internet has resulted in a massive number of websites, blogs and forums. People can easily discuss with each other about different topics and products, and can leave reviews to help out others. This...
The Group Decision Support System to Evaluate the ICT Project Performance Using the Hybrid Method of AHP, TOPSIS and Copeland Score
This paper proposed a concept of the Group Decision Support System (GDSS) to evaluate the performance of Information and Communications Technology (ICT) Projects in Indonesian regional government agencies to overcome any...