Kinect-Based Human Gait Recognition Using Locally Linear Embedded and Support Vector Machine

Journal Title: Jurnal Kejuruteraan - Year 2018, Vol 30, Issue 2

Abstract

Recognition of human gait could be performed effectively provided that significant gait features are well extracted along with effective recognition process. Thus, the gait features should be selected or optimized appropriately for optimal accuracy during recognition. Therefore, in this research, optimization of gait features for both oblique and frontal view are evaluated for recognition purpose using Locally Linear Embedded (LLE) along with multi-class Support Vector Machine (SVM). Firstly, dynamic gait features for one gait cycle are extracted from each subject’s walking gait that is acquired using Kinect sensor. Next, the extracted gait features were then optimized using LLE known as DG-LLE and further classified by multi-class SVM with Error Correcting Output Code (ECOC) algorithm. Further, to validate the effectiveness of LLE as optimization technique, the proposed method is then compared with another two gait features namely the original gait features known as DG and optimization using Principal Component Analysis labeled as DG-PCA. Results showed that the optimization based on DG-LLE outperformed the other two methods namely DG and DG-PCA for both oblique and frontal views. In addition, DG-LLE method contributed as the highest recognition rate for both frontal and oblique views. Results also confirmed that the accuracy rate for frontal view is higher specifically 98.33% as compared to oblique view with 94.67%.

Authors and Affiliations

Rohilah Sahak, Nooritawati Md Tahir, Ahmad Ihsan Mohd Yassin, Fadhlan Hafizhelmi Kamaruzaman

Keywords

Related Articles

Synthesis and Characterization of ZnO-decorated GO Nanocomposite Material with Different ZnO Loading through Sol-gel Method

This work aimed is to synthesis a well dispersed zinc oxide (ZnO) nanoparticles (NPs) decorated on graphene oxide (GO) nanosheet with a practical way by using sol-gel technique. Zinc acetate dehydrate (Zn(CH3COO) 2·2H2O)...

Effect of Aluminium Content on the Tensile Properties of Mg-Al-Zn Alloys

The aim of this study is to investigate the effect of aluminium content on microstructure, tensile properties and work hardenability of Mg-Al-Zn alloys. Two types of magnesium alloys were investigated i.e. AZ31 and AZ61,...

Hubungan di antara Pelaksanaan 5S dan Prestasi Hijau Syarikat Pembuatan PKS di Malaysia: Satu Model Konsep (Relationship between 5S Implementation and Green Performance of Malaysian Manufacturing SMEs: A Conceptual Model)

Because of the global sustainability agenda, environmental factors are increasingly becoming a priority in the implementation of management practices and competitiveness strategies. Management system such as ISO 9001 and...

Sifat Mekanikal Saduran Epoksi Mengandungi Abu Buangan Industri (The Mechanical Properties of Epoxy Coating Containing Industrial Waste Fly Ash)

Saduran organik seperti epoksi menjadi fokus utama dalam kajian saduran kerana ciri-cirinya yang termoset, tinggi daya tahan perekatan terhadap substrat, stabil dari segi struktur, tahan kimia dan menjimatkan. Namun sadu...

Determinants of a Pre-Treatment Model in Achieving Economic and Environmental Sustainability in Membrane Desalination

Feedwater pre-treatment plays a significant role in the production performance of water desalination operations. This study aims to formulate a pre-treatment model to evaluate the determinants in achieving economic and e...

Download PDF file
  • EP ID EP455569
  • DOI 10.17576/jkukm-2018-30(2)-14
  • Views 100
  • Downloads 0

How To Cite

Rohilah Sahak, Nooritawati Md Tahir, Ahmad Ihsan Mohd Yassin, Fadhlan Hafizhelmi Kamaruzaman (2018). Kinect-Based Human Gait Recognition Using Locally Linear Embedded and Support Vector Machine. Jurnal Kejuruteraan, 30(2), 235-247. https://www.europub.co.uk/articles/-A-455569