Study on ECG Data Lossless Compression Algorithm Based on K-means Cluster

Zhou, Qunyi

doi:10.1109/fcc.2009.54

Cited by 10 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the K-means cluster of Zhou's method [11] needs to square each point when matching templates, and the Huffman codebook in Zhou's method contains 2048 items the compress the ECG signal of the ARRDB (which has 11-bit resolution), more than the variable number of the proposed S system; the Takagi-Sugeno Fuzzy Neural Network in [12] contains many multiply-accumulate operations when predicting each point; and both [13] and [14] need integer division operations. So the computational complexity of [11]- [14] are higher than that of the proposed method. [3], [5]- [9] used simple prediction and entropy encoding algorithms, but the proposed S system achieves significantly higher CR than these methods so that this method can save more transmission power or storage space.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…Actually, since only integer operations can be performed in low-power devices, we set t to 4 times the predicted value to improve the precision. Second, k is calculated by (11) to encode M [n]. For low power ASICs or embedded systems, log 2 can be calculated by searching the most significant bit of t. When k = 0, the code length increases significantly with the increase of M [n], thus causing a great penalty when t 4 is lower than M [n].…”

Section: B Context-based Error Modelingmentioning

confidence: 99%

“…Among which, Miaou and Chao [10] applied the combination of distortionconstrained codebook replenishment (DCCR), set partitioning in hierarchical tree (SPIHT), and bit-plane coding (BPC) algorithms, but this method contains recursive operation and requires many variables. Zhou [11] applied k-means cluster predictor + Huffman encoding, and Tseng et al [12] applied Takagi-Sugeno fuzzy neural network + arithmetic encoding, but they require multiply-accumulate operation many times when predicting each point. Tsai and Tsai [13] applied adaptive linear predictor + Golomb-Rice encoding, and Rzepka [14] applied selective and multichannel linear predictor + asymmetric numeral systems encoding, but they all require integer division operation hence increasing the computational complexity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Lossless Electrocardiogram Compression System Based on Dual-Mode Prediction and Error Modeling

Jia

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Long-term electrocardiogram (ECG) monitoring requires high-ratio lossless compression techniques to reduce data transmission energy and data storage capacity. In this paper, we have proposed a high-ratio ECG compression system with low computational complexity. Firstly, as the morphologies of the ECG change over time, we divide the signal of each heartbeat cycle into two regions. To achieve high prediction accuracy, a 1 st order linear predictor and a combination of the template predictor and 3 rd order linear predictor are applied in the two regions respectively. Secondly, we introduce a context-based error modeling module to the system, which cancels the statistical bias of the prediction algorithm and further improves the prediction accuracy. Thirdly, we modify the Golomb-Rice encoding algorithm to adaptively encode the prediction errors, while preserving a code space for packaging the information that is necessary for prediction. We evaluate the proposed system by using the MIT-BIH Arrhythmia Database (ARRDB). The experimental results show that with memory requirements as low as 444 to 14556 total variables this system achieves a compression ratio (CR) from 2.975 to 3.040, suggesting that it is highly applicable to both the low-power design and the cloud.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: B Context-based Error Modelingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Lossless Electrocardiogram Compression System Based on Dual-Mode Prediction and Error Modeling

Jia

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…CS theory is a mathematical framework in acquiring and recovering sparse signals with the help of an incoherent 978-1-4244-7929-0/14/$26.00 ©2014 IEEE projecting basis that provides insight into how a high resolution dataset can be inferred from a relatively small and random number of measurements using simple random linear process [16,17]. Thus, rather than measuring each sample and then computing a compressed representation, CS suggests that we can measure a compressed representation directly [18].…”

Section: Advanced K-means Algorithmmentioning

confidence: 99%

Fast clustering algorithm for large ECG data sets based on CS theory in combination with PCA and K-NN methods

Balouchestani

Krishnan

2014

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Long-term recording of Electrocardiogram (ECG) signals plays an important role in health care systems for diagnostic and treatment purposes of heart diseases. Clustering and classification of collecting data are essential parts for detecting concealed information of P-QRS-T waves in the long-term ECG recording. Currently used algorithms do have their share of drawbacks: 1) clustering and classification cannot be done in real time; 2) they suffer from huge energy consumption and load of sampling. These drawbacks motivated us in developing novel optimized clustering algorithm which could easily scan large ECG datasets for establishing low power long-term ECG recording. In this paper, we present an advanced K-means clustering algorithm based on Compressed Sensing (CS) theory as a random sampling procedure. Then, two dimensionality reduction methods: Principal Component Analysis (PCA) and Linear Correlation Coefficient (LCC) followed by sorting the data using the K-Nearest Neighbours (K-NN) and Probabilistic Neural Network (PNN) classifiers are applied to the proposed algorithm. We show our algorithm based on PCA features in combination with K-NN classifier shows better performance than other methods. The proposed algorithm outperforms existing algorithms by increasing 11% classification accuracy. In addition, the proposed algorithm illustrates classification accuracy for K-NN and PNN classifiers, and a Receiver Operating Characteristics (ROC) area of 99.98%, 99.83%, and 99.75% respectively.

show abstract

“…Schematic diagram of run-length coding is shown in Figure 8. The characteristics of run-length coding algorithm is: run-length coding algorithm is very precise, one of the symbols has an error, which affects the entire encoding sequence so that the run-length encoding cannot be restored to the original data (Huang et al, 2005;Zhou, 2009). The compression rate obtained by the run-length coding depends largely on the characteristics of the data itself.…”

Section: Run-length Coding Algorithmmentioning

confidence: 99%

Research on battery data compression method for electric vehicles

Mei

et al. 2018

IJEHV

View full text Add to dashboard Cite

The transmission and storage of electric vehicle battery management system (BMS) data are time consuming and infeasible, which reduces the efficiency of data transmission and storage. For this problem, this paper presents a method of battery data compression, the pre-compression is to reduce the amount of data and improve the data redundancy and repeatability, and a strategy was formulated that two universal compression methods, Huffman coding and run-length coding, were applied to different battery data. Experimental results show the method of battery data compression can obtain a good compressibility. The battery data compressibility of this paper was about 21%.

show abstract

Study on ECG Data Lossless Compression Algorithm Based on K-means Cluster

Cited by 10 publications

References 3 publications

A Lossless Electrocardiogram Compression System Based on Dual-Mode Prediction and Error Modeling

A Lossless Electrocardiogram Compression System Based on Dual-Mode Prediction and Error Modeling

Fast clustering algorithm for large ECG data sets based on CS theory in combination with PCA and K-NN methods

Research on battery data compression method for electric vehicles

Contact Info

Product

Resources

About