Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor

The use of sensor applications has been steadily increasing, leading to an urgent need for efficient data compression techniques to facilitate the storage, transmission, and processing of digital signals generated by sensors. Unlike other sequential data such as text sequences, sensor signals have m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qianhao Chen, Wenqi Wu, Wei Luo
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	lossless compression sensor signals context-based compressor entropy coding recurrent neural networks Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/ccf26923a48c4f6abf19fbd54252cb62
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ccf26923a48c4f6abf19fbd54252cb62
record_format	dspace
spelling	oai:doaj.org-article:ccf26923a48c4f6abf19fbd54252cb622021-11-11T15:16:58ZLossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor10.3390/app1121102402076-3417https://doaj.org/article/ccf26923a48c4f6abf19fbd54252cb622021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10240https://doaj.org/toc/2076-3417The use of sensor applications has been steadily increasing, leading to an urgent need for efficient data compression techniques to facilitate the storage, transmission, and processing of digital signals generated by sensors. Unlike other sequential data such as text sequences, sensor signals have more complex statistical characteristics. Specifically, in every signal point, each bit, which corresponds to a specific precision scale, follows its own conditional distribution depending on its history and even other bits. Therefore, applying existing general-purpose data compressors usually leads to a relatively low compression ratio, since these compressors do not fully exploit such internal features. What is worse, partitioning a bit stream into groups with a preset size will sometimes break the integrity of each signal point. In this paper, we present a lossless data compressor dedicated to compressing sensor signals which is built upon a novel recurrent neural architecture named multi-channel recurrent unit (MCRU). Each channel in the proposed MCRU models a specific precision range of each signal point without breaking data integrity. During compressing and decompressing, the mirrored network will be trained on observed data; thus, no pre-training is needed. The superiority of our approach over other compressors is demonstrated experimentally on various types of sensor signals.Qianhao ChenWenqi WuWei LuoMDPI AGarticlelossless compressionsensor signalscontext-based compressorentropy codingrecurrent neural networksTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10240, p 10240 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	lossless compression sensor signals context-based compressor entropy coding recurrent neural networks Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	lossless compression sensor signals context-based compressor entropy coding recurrent neural networks Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Qianhao Chen Wenqi Wu Wei Luo Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor
description	The use of sensor applications has been steadily increasing, leading to an urgent need for efficient data compression techniques to facilitate the storage, transmission, and processing of digital signals generated by sensors. Unlike other sequential data such as text sequences, sensor signals have more complex statistical characteristics. Specifically, in every signal point, each bit, which corresponds to a specific precision scale, follows its own conditional distribution depending on its history and even other bits. Therefore, applying existing general-purpose data compressors usually leads to a relatively low compression ratio, since these compressors do not fully exploit such internal features. What is worse, partitioning a bit stream into groups with a preset size will sometimes break the integrity of each signal point. In this paper, we present a lossless data compressor dedicated to compressing sensor signals which is built upon a novel recurrent neural architecture named multi-channel recurrent unit (MCRU). Each channel in the proposed MCRU models a specific precision range of each signal point without breaking data integrity. During compressing and decompressing, the mirrored network will be trained on observed data; thus, no pre-training is needed. The superiority of our approach over other compressors is demonstrated experimentally on various types of sensor signals.
format	article
author	Qianhao Chen Wenqi Wu Wei Luo
author_facet	Qianhao Chen Wenqi Wu Wei Luo
author_sort	Qianhao Chen
title	Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor
title_short	Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor
title_full	Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor
title_fullStr	Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor
title_full_unstemmed	Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor
title_sort	lossless compression of sensor signals using an untrained multi-channel recurrent neural predictor
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/ccf26923a48c4f6abf19fbd54252cb62
work_keys_str_mv	AT qianhaochen losslesscompressionofsensorsignalsusinganuntrainedmultichannelrecurrentneuralpredictor AT wenqiwu losslesscompressionofsensorsignalsusinganuntrainedmultichannelrecurrentneuralpredictor AT weiluo losslesscompressionofsensorsignalsusinganuntrainedmultichannelrecurrentneuralpredictor
_version_	1718435781847023616

Lossless Compression of Sensor Signals Using an Untrained Multi-Channel Recurrent Neural Predictor

Ejemplares similares