The Performance of Individual and Ensemble Classifiers for an Arabic Sign Language Recognition System
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 5
Abstract
The objective of this paper is to compare different classifiers’ recognition accuracy for the 28 Arabic alphabet letters gestured by participants as Sign Language and captured by two depth sensors. The accuracy results of three individual classifiers: (1) the support vector machine (SVM), (2) random forest (RF), and (3) nearest neighbour (kNN), using the original gestured dataset were compared with the accuracy results using an ensemble of the results of each classifier, as recommended by the literature. SVM produced higher overall accuracy when running as an individual classifier regardless of the number of observations for each letter. However, for letters with fewer than 65 observations each, which created a far smaller dataset, RF had higher accuracy than SVM did when using the ensemble approach. Although RF produced higher accuracy results for classes with limited class observation data, the difference between the accuracy results of RF in phase 2 and SVM in phase 1 was negligible. The researchers conclude that such a difference does not warrant using the ensemble approach for this experiment, which adds more processing complexity without a significant increase in accuracy.
Authors and Affiliations
Miada A. Almasre, Hana Al-Nuaim
Keywords
Related Articles
- EP ID EP258786
- DOI 10.14569/IJACSA.2017.080538
- Views 91
- Downloads 0
Novel Intra-Prediction Framework for H.264 Video Compression using Decision and Prediction Mode
With the increasing usage of multimedia contents and advancement of the communication devices (along with services), there is a heavy demand of an effective multimedia compression protocol. In this regards, H.264 has bee...
Indoor Positioning System using Regression-based Fingerprint Method
Indoor Positioning System has opportunity to be used in different business platform. Based on past research, optimized localization method for Bluetooth Low Energy (BLE) to predict position of person or object with high...
RGBD Human Action Recognition using Multi-Features Combination and K-Nearest Neighbors Classification
In this paper, we present a novel system to analyze human body motions for action recognition task from two sets of features using RGBD videos. The Bag-of-Features approach is used for recognizing human action by extract...
Automatic Cloud Resource Scaling Algorithm based on Long Short-Term Memory Recurrent Neural Network
Scalability is an important characteristic of cloud computing. With scalability, cost is minimized by provisioning and releasing resources according to demand. Most of current Infrastructure as a Service (IaaS) providers...
Ant Colony Optimization (ACO) based Routing Protocols for Wireless Sensor Networks (WSN): A Survey
Wireless Sensor Networks have several issues and challenges with regard to Energy Efficiency, Limited Computational capability, Routing Overhead, Packet Delivery and many more. Designing Energy Efficient Routing Protocol...