ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Efficient FPGA Implementation of Multilayer Perceptron for Real-Time Human Activity Classification

Gaikwad, NB and Tiwari, V and Keskar, A and Shivaprakash, NC (2019) Efficient FPGA Implementation of Multilayer Perceptron for Real-Time Human Activity Classification. In: IEEE Access, 7 . pp. 26696-26706.

IEEE_Access_7-8651457_26696-26706_2019.pdf - Published Version

Download (2MB) | Preview
Official URL: https://dx.doi.org/10.1109/ACCESS.2019.2900084


The smartphone-based human activity recognition (HAR) systems are not capable to deliver high-end performance for challenging applications. We propose a dedicated hardware-based HAR system for smart military wearables, which uses a multilayer perceptron (MLP) algorithm to perform activity classification. To achieve the flexible and efficient hardware design, the inherent MLP architecture with parallel computation is implemented on FPGA. The system performance has been evaluated using the UCI human activity dataset with 7767 feature samples of 20 subjects. The three combinations of a dataset are trained, validated, and tested on ten different MLP models with distinct topologies. The MLP design with the 7-6-5 topology is finalized from the classification accuracy and cross entropy performance. The five versions of the final MLP design (7-6-5) with different data precision are implemented on FPGA. The analysis shows that the MLP designed with 16-bit fixed-point data precision is the most efficient MLP implementation in the context of classification accuracy, resource utilization, and power consumption. The proposed MLP design requires only 270 ns for classification and consumes 120 mW of power. The recognition accuracy and hardware results performance achieved are better than many of the recently reported works. © 2013 IEEE.

Item Type: Journal Article
Publication: IEEE Access
Publisher: IEEE
Additional Information: Copyright for this article belongs to IEEE
Keywords: Energy efficiency;Integrated circuit design;Multilayer neural networks;Multilayers;Pattern recognition; Smartphones; Topology; Wearable technology, Activity classifications; Classification accuracy; FPGA implementations; Hardware implementations; Human activity recognition; Multi layer perceptron;Resource utilizations;smart military wearables, Field programmable gate arrays (FPGA)
Department/Centre: Division of Physical & Mathematical Sciences > Instrumentation Appiled Physics
Date Deposited: 09 Apr 2019 06:31
Last Modified: 09 Apr 2019 06:31
URI: http://eprints.iisc.ac.in/id/eprint/62168

Actions (login required)

View Item View Item