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 88
- Downloads 0
Efficient Model for Distributed Computing based on Smart Embedded Agent
Technological advances of embedded computing exposed humans to an increasing intrusion of computing in their day-to-day life (e.g. smart devices). Cooperation, autonomy, and mobility made the agent a promising mechanism...
Improving K-Means Algorithm by Grid-Density Clustering for Distributed WSN Data Stream
At recent years, Wireless Sensor Networks (WSNs) had a widespread range of applications in many fields related to military surveillance, monitoring health, observing habitat and so on. WSNs contain individual nodes that...
Automatic Conditional Switching (ACS), an Incremental Enhancement to TCP-Reno/RTP to Improve the VoIPv6 Performance
In this research work an Automatic Conditional Switching Protocol (ACSP) is proposed, which is a conditional switching method between Delay based TCP-Reno and RTP (Real-Time Transport Protocol). It is a delay constrained...
Web Anomaly Misuse Intrusion Detection Framework for SQL Injection Detection
Databases at the background of e-commerce applications are vulnerable to SQL injection attack which is considered as one of the most dangerous web attacks. In this paper we propose a framework based on misuse and a...
Online Reputation Model Using Moving Window
Users are increasingly dependent on decision tools to facilitate their transactions on the internet. Reputation models offer a solution to the users in supporting their purchase decisions. The reputation model takes prod...