Next Article in Journal
Ensemble Classification through Random Projections for Single-Cell RNA-Seq Data
Next Article in Special Issue
Detection of Atrial Fibrillation Using a Machine Learning Approach
Previous Article in Journal
Outage Analysis of Relay-Assisted NOMA in Cooperative Cognitive Radio Networks with SWIPT
Previous Article in Special Issue
Quantitative Cluster Headache Analysis for Neurological Diagnosis Support Using Statistical Classification
Open AccessArticle

Design and Analysis of Binary Scalar Quantizer of Laplacian Source with Applications

1
Faculty of Electronic Engineering, University of Nis, Aleksandra Medvedeva 14, 18000 Nis, Serbia
2
Faculty of Sciences, University of Pristina—Kosovska Mitrovica, Ive Lole Ribara 29, 38220 Kosovska Mitrovica, Serbia
3
Department of Computer Science, University of Luxembourg, Avenue de la Fonte 6, L-4364 Esch-sur-Alzette, Luxembourg
*
Author to whom correspondence should be addressed.
Information 2020, 11(11), 501; https://doi.org/10.3390/info11110501
Received: 15 September 2020 / Revised: 19 October 2020 / Accepted: 20 October 2020 / Published: 27 October 2020
(This article belongs to the Special Issue Signal Processing and Machine Learning)
A compression method based on non-uniform binary scalar quantization, designed for the memoryless Laplacian source with zero-mean and unit variance, is analyzed in this paper. Two quantizer design approaches are presented that investigate the effect of clipping with the aim of reducing the quantization noise, where the minimal mean-squared error distortion is used to determine the optimal clipping factor. A detailed comparison of both models is provided, and the performance evaluation in a wide dynamic range of input data variances is also performed. The observed binary scalar quantization models are applied in standard signal processing tasks, such as speech and image quantization, but also to quantization of neural network parameters. The motivation behind the binary quantization of neural network weights is the model compression by a factor of 32, which is crucial for implementation in mobile or embedded devices with limited memory and processing power. The experimental results follow well the theoretical models, confirming their applicability in real-world applications. View Full-Text
Keywords: quantization; Laplacian distribution; clipping factor; signal to noise ratio; pulse code modulation; delta modulation; neural network quantization; Laplacian distribution; clipping factor; signal to noise ratio; pulse code modulation; delta modulation; neural network
Show Figures

Figure 1

MDPI and ACS Style

Peric, Z.; Denic, B.; Savic, M.; Despotovic, V. Design and Analysis of Binary Scalar Quantizer of Laplacian Source with Applications. Information 2020, 11, 501.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop