摘要(英) |
Based on convolutional neural network(CNN), we introduce a recognition and monitoring system for distinguish fetal electrocardiogram(fECG) signals and maternal electrocardiogram(mECG) signals from pregnant abdominal ECG recording, so that non-invasive electrodes detection can also achieve high detection rate. First, the data pre-processing make the abdominal ECG waveform is partitioned into 250ms as a segment with 10ms overlap area. Marking each segment into four different labels. In order to reduce the noise effect of the ECG signals in time domain, short-time Fourier transform is convert the ECG signals into two-dimensional time-frequency feature map. Then, we removing the baseline wandering. In this thesis, CNN architecture consists of two convolutional layers, two pooling layers, and fully connected layer, the final output result are probability value of 4 classes. The convolutional layer contains the activation function, using sigmoid function. Before the output layer, the data are also converted into the probability through the softmax function. In back propagation, calculating the error of the loss function, and the partial derivative with learning rate to update the parameters. In addition to the fusion, four leads record can generate one final result. We use two set of different ECG signal to test, the detection rates of pregnant a02, and a05 are 98.62% and 98.51%, respectively. Compared with the conventional K-nearest neighbor algorithm and random forest, a higher detection accuracy is achieved. For hardware design, after doing the complexity evaluation and quantization, we decided the FFT architecture with doubling algorithm to reduce the number of multipliers and use 〖radix2〗^2. The CNN architecture is designed by memory based, the schedule of the convolutional layer and local buffer design decreases the number of memory accesses to 7.2%, and 3.3%, respectively. The two hardware of convolutional layers are shared. And make the size of LUT reduced from 2^14 to 2^11 to reduce the area. Finally, the overall hardware design verified by FPGA. |
參考文獻 |
[1] (A.Muthuchudar, Lt.Dr.S.Santosh Baboo, 2013)
[2] L. Goldberger, et al., “PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals”, Circulation, 101(23), pp.215- 220, 13 June 2000.
[3] E. C. Karvounis, M. G. Tsipouras, D. I. Fotiadis and K. K. Naka, ”A Method for Fetal Heart Rate Extraction Based on Time-Frequency Analysis,” 19th IEEE Symposium on Computer-Based Medical Systems (CBMS′06), Salt Lake City, UT, 2006, pp. 347-347.
[4] R. Martín-Clemente, J. L. Camargo-Olivares, S. Hornillo-Mellado, M. Elena and I. Román, ”Fast Technique for Noninvasive Fetal ECG Extraction,” in IEEE Transactions on Biomedical Engineering, vol. 58, no. 2, pp. 227-230, Feb. 2011.
[5] J. A. Delgado, et al., “Haar wavelet transform and principal component anaylsis for fetal QRS classification from abdominal maternal ECG recordings,” Symposium on Signal Processing, Images and Computer Vision, pp. 1-6, 2015.
[6] S. Y. Chun, et al., “ECG based user authentication for wearable devices using short time Fourier transform,” International Conference on Telecommunications and Signal Processing (TSP), pp. 656-659, 2016.
[7] Y. LeCun, C. Cortes, and C. Burges, ”MNIST handwritten digit database, 1998,” URL http://www. research. att. com/~ yann/ocr/mnist,2016.
[8] J. Cardenas-Lattus and H. Kaschel, ”Fetal ECG multi-level analysis using daubechies wavelet transform for non-invasive maternal abdominal ECG recordings,”2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), Pucon, 2017, pp. 1-6.
[9] M. Papadomanolaki, S. Verma, M. Vakalopoulou, S. Gupta and K. Karantzalos, ”Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data,” IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019, pp. 214-217.
[10] J. Zhang, ”Deep Transfer Learning via Restricted Boltzmann Machine for Document Classification,” 2011 10th International Conference on Machine Learning and Applications and Workshops, Honolulu, HI, 2011, pp. 323-326.
[11] P. Sermanet, K. Kavukcuoglu, S. Chintala and Y. Lecun, ”Pedestrian Detection with Unsupervised Multi-stage Feature Learning,” 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, 2013, pp. 3626-3633.
[12] Prasanth K, Baby Paul, Arun Balakrishnan A, ”Fetal ECG Extraction Using Adaptive Filters. International Jrnl of Adv Research in Electrical,” Electronics and Instrumentation Engineering 2, pp. 1483-1487, 2013.
[13] Shousheng He and M. Torkelson, ”A new approach to pipeline FFT processor,” Proceedings of International Conference on Parallel Processing, Honolulu, HI, USA, 1996, pp. 766-770.
[14] J. Wu, F. Li, Z. Chen, Y. Pu and M. Zhan, ”A Neural Network-Based ECG Classification Processor With Exploitation of Heartbeat Similarity,” IEEE Access, vol. 7, pp. 172774-172782, 2019.
[15] H. Sorensen, D. Jones, M. Heideman and C. Burrus, ”Real-valued fast Fourier transform algorithms,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 35, no. 6, pp. 849-863, June 1987.
[16] M. Ayinala and K. K. Parhi, ”FFT Architectures for Real-Valued Signals Based on Radix-$2^{3}$ and Radix-$2^{4}$ Algorithms,” in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 60, no. 9, pp. 2422-2430, Sept. 2013.
|