( 您好!臺灣時間:2024/07/24 17:31
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::


研究生(外文):Wu, Guei-Shian
論文名稱(外文):A Microcontroller with SVM-based seizure detection for Wearable Devices
指導教授(外文):Chiueh, Herming
口試委員(外文):Chiueh, Herming
外文關鍵詞:Epileptic Seizure DetectionWearable DevicesWireless TransmissionSVM
  • 被引用被引用:0
  • 點閱點閱:195
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出應用於癲癇發作偵測的微控制器系統開發,此系統內含有基於支援向量機的硬體加速器。為了支援大多數穿戴式裝置所使用的感測器以及保持系統彈性,此系統內含有一精簡指令集的中央控制器以及常用於嵌入式裝置的序列周邊介面(SPI)與通用非同步收發傳輸器(UART)。此外,本系統當中內整合了藍牙低功耗晶片,使得本系統得以將腦電圖或癲癇偵測等訊息傳至行動裝置。本系統支援高達八通道的類比數位轉換器輸入,並透過非線性邊界之支援向量機硬體加速器,以波士頓麻省兒童醫院臨床數據庫進行驗證,得以提供具有95.5%準確率及0.75%假情報率的腦電圖分類與癲癇偵測。醫生也得以透過此系統進行癲癇事件紀錄(Event Record)等精準治療的行為。
Epilepsy is one of the most common chronic neurological diseases and is characterized by recurrent seizures. There’re approximately 65 million people with epilepsy worldwide. Antiepileptic drug-induced encephalopathy (ADEs) are often used by doctors as a treatment, but about one-third of epilepsy patients still cannot be well controlled. Even patients who have resection surgery to remove the epileptogenic zone will still suffer seizures once in a while
This paper proposed a microcontroller for epileptic seizure detection, which contains a hardware accelerator based on support vector machines (SVM). To support the sensors used by most wearable devices and maintain the flexibility of the system, we include a reduced instruction set computer (RISC), serial peripheral interface (SPI), and universal asynchronous receiver-transmitter (UART) commonly used in embedded systems. Also, A Bluetooth Low Energy (BLE) microcontroller is integrated into this design, which allows us to transmit data such as electroencephalography (EEG) or detection to mobile devices. This system supports up to eight channels of Analog-to-Digital Converter (ADC) inputs and was verified with the CHB-MIT database. SVM hardware accelerator provides 95.5% accuracy and 0.75% false alarm rate (FAR) on EEG classification and epilepsy detection. Doctors can use this system to perform precise treatments by event records.
摘要 I
Abstract II
Acknowledgments III
Contents IV
List of Tables VII
List of Figures VIII
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Previous work 2
1.3 Machine Learning Selection 4
1.4 Goals 6
1.5 System Architecture 6
1.5.1 Seizure Detection Algorithm 8
1.6 Thesis Organization 8
Chapter 2 The Proposed System Design 9
2.1 The Proposed System Architecture 9
2.2 Proposed Solution for Processor Core 10
2.3 Proposed Data Control Unit for ADC & SVM Modules 11
2.4 Support Vector Machine in the Proposed System 13
2.5 Serial Peripheral Interface in the Proposed System 14
2.6 The Proposed Universal Asynchronous Receiver/Transmitter 14
2.7 General Purpose Input/Output in the Proposed System 15
2.8 System Integration 15
Chapter 3 System Implementation 16
3.1 Chip Implementation 16
3.1.1 Design Flow 16
3.1.2 Simulation & Analysis 18
3.1.3 Physical Verification 21
3.1.4 In/Output Descriptions 22
3.1.5 Specification of Chip 24
3.2 Bluetooth Low Energy Microcontroller 25
3.3 PCB design 28
3.4 APP design & Cloud service 30
3.5 System Integration 31
Chapter 4 System Verification 32
4.1 Functional Verification of Bootloader 32
4.2 Functional Verification of Data Control Unit 34
4.3 Functional Verification of SVM 36
4.4 Functional Verification of GPIO 37
4.5 Functional Verification of UART 39
4.6 Functional Verification of SPI 40
4.7 Functional Verification of BLE system 41
4.7.1 1-channel transmission 41
4.7.2 8-channel transmission 43
4.8 Comparison 45
Chapter 5 Conclusion and Future Work 46
Reference 48
[1] S.-A. Huang, K.-C. Chang, H.-H. Liou, and C.-H. Yang, “A 1.9-mW SVM Processor With On-Chip Active Learning for Epileptic Seizure Control,” IEEE J. Solid-State Circuits, vol. 55, no. 2, pp. 452–464, Feb. 2020, doi: 10.1109/JSSC.2019.2954775.
[2] A. Shoeb, “CHB-MIT Scalp EEG Database.” physionet.org, 2010, doi: 10.13026/C2K01R.
[3] A. H. Shoeb, “Application of machine learning to epileptic seizure onset detection and treatment,” Thesis, Massachusetts Institute of Technology, 2009.
[4] “About Epilepsy: The Basics.” Accessed: Oct. 08, 2020. [Online]. Available: https://www.epilepsy.com/learn/about-epilepsy-basics.
[5] “Epilepsy.” World Health Organization, Accessed: Oct. 08, 2020. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/epilepsy.
[6] M. J. Eadie, “Shortcomings in the current treatment of epilepsy,” Expert Rev. Neurother., vol. 12, no. 12, pp. 1419–1427, Dec. 2012, doi: 10.1586/ern.12.129.
[7] D. Schmidt, “Drug treatment of epilepsy: Options and limitations,” Epilepsy Behav., vol. 15, no. 1, pp. 56–65, May 2009, doi: 10.1016/j.yebeh.2009.02.030.
[8] W. H. Theodore, “Brain stimulation for epilepsy,” Nat. Clin. Pract. Neurol., vol. 1, no. 2, Art. no. 2, Dec. 2005, doi: 10.1038/ncpneuro0051.
[9] W. C. Stacey and B. Litt, “Technology Insight: neuroengineering and epilepsy—designing devices for seizure control,” Nat. Clin. Pract. Neurol., vol. 4, no. 4, Art. no. 4, Apr. 2008, doi: 10.1038/ncpneuro0750.
[10] E. Bruno et al., “Wearable technology in epilepsy: The views of patients, caregivers, and healthcare professionals,” Epilepsy Behav., vol. 85, pp. 141–149, Aug. 2018, doi: 10.1016/j.yebeh.2018.05.044.
[11] P. Meritam, P. Ryvlin, and S. Beniczky, “User-based evaluation of applicability and usability of a wearable accelerometer device for detecting bilateral tonic–clonic seizures: A field study,” Epilepsia, vol. 59, no. S1, pp. 48–52, 2018, doi: 10.1111/epi.14051.
[12] R. S. Fisher et al., “Seizure diaries for clinical research and practice: Limitations and future prospects,” Epilepsy Behav., vol. 24, no. 3, pp. 304–310, Jul. 2012, doi: 10.1016/j.yebeh.2012.04.128.
[13] Z. Lasefr, R. R. Reddy, and K. Elleithy, “Smart phone application development for monitoring epilepsy seizure detection based on EEG signal classification,” in 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), Oct. 2017, pp. 83–87, doi: 10.1109/UEMCON.2017.8248992.
[14] A. Marquez, M. Dunn, J. Ciriaco, and F. Farahmand, “iSeiz: A low-cost real-time seizure detection system utilizing cloud computing,” in 2017 IEEE Global Humanitarian Technology Conference (GHTC), Oct. 2017, pp. 1–7, doi: 10.1109/GHTC.2017.8239249.
[15] H. Chen et al., “A wearable sensor system for neonatal seizure monitoring,” in 2017 IEEE 14th International Conference on Wearable and Implantable Body Sensor Networks (BSN), May 2017, pp. 27–30, doi: 10.1109/BSN.2017.7935999.
[16] M. Gheryani, O. Salem, and A. Mehaoua, “An effective approach for epileptic seizures detection from multi-sensors integrated in an Armband,” in 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), Oct. 2017, pp. 1–6, doi: 10.1109/HealthCom.2017.8210777.
[17] J. M. Ramirez-Alaminos, S. Sendra, J. Lloret, and J. Navarro-Ortiz, “Low-cost wearable bluetooth sensor for epileptic episodes detection,” in 2017 IEEE International Conference on Communications (ICC), May 2017, pp. 1–6, doi: 10.1109/ICC.2017.7997413.
[18] G. Regalia, C. Caborni, M. Migliorini, F. Onorati, and R. Picard, “Real-time seizure detection performance with Embrace alert system: One year real-life setting case study,” Jul. 2017, doi: 10.13140/RG.2.2.28448.48648.
[19] S.-K. Lin, Istiqomah, L.-C. Wang, C.-Y. Lin, and H. Chiueh, “An Ultra-Low Power Smart Headband for Real-Time Epileptic Seizure Detection,” IEEE J. Transl. Eng. Health Med., vol. 6, pp. 1–10, 2018, doi: 10.1109/JTEHM.2018.2861882.
[20] “10–20 system (EEG),” Wikipedia. Oct. 21, 2019, Accessed: Oct. 08, 2020. [Online]. Available: https://en.wikipedia.org/w/index.php?title=10%E2%80%9320_system_(EEG)&oldid=922279483.
[21] S. Kalyani and K. Shanti Swarup, “Classification and Assessment of Power System Security Using Multiclass SVM,” IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., vol. 41, no. 5, pp. 753–758, Sep. 2011, doi: 10.1109/TSMCC.2010.2091630.
[22] J. M. Johnson and T. M. Khoshgoftaar, “Survey on deep learning with class imbalance,” J. Big Data, vol. 6, no. 1, p. 27, Mar. 2019, doi: 10.1186/s40537-019-0192-5.
[23] S. Mittal, “A survey of FPGA-based accelerators for convolutional neural networks,” Neural Comput. Appl., vol. 32, no. 4, pp. 1109–1139, Feb. 2020, doi: 10.1007/s00521-018-3761-1.
[24] A. Page, C. Sagedy, E. Smith, N. Attaran, T. Oates, and T. Mohsenin, “A Flexible Multichannel EEG Feature Extractor and Classifier for Seizure Detection,” IEEE Trans. Circuits Syst. II Express Briefs, vol. 62, no. 2, pp. 109–113, Feb. 2015, doi: 10.1109/TCSII.2014.2385211.
[25] V. Sridevi, M. Ramasubba Reddy, K. Srinivasan, K. Radhakrishnan, C. Rathore, and D. S. Nayak, “Improved Patient-Independent System for Detection of Electrical Onset of Seizures,” J. Clin. Neurophysiol., vol. 36, no. 1, pp. 14–24, Jan. 2019, doi: 10.1097/WNP.0000000000000533.
[26] S.-A. Huang, K.-C. Chang, H.-H. Liou, and C.-H. Yang, “A 1.9MW SVM Processor with On-Chip Active Learning for Epileptic Seizure Control,” in 2018 IEEE Symposium on VLSI Circuits, Jun. 2018, pp. 259–260, doi: 10.1109/VLSIC.2018.8502428.
[27] O. AlZoubi, I. Koprinska, and R. A. Calvo, “Classification of brain-computer interface data,” in Proceedings of the 7th Australasian Data Mining Conference - Volume 87, AUS, Nov. 2008, pp. 123–131, Accessed: Oct. 08, 2020. [Online].
[28] S. Siuly and Y. Li, “Designing a robust feature extraction method based on optimum allocation and principal component analysis for epileptic EEG signal classification,” Comput. Methods Programs Biomed., vol. 119, no. 1, pp. 29–42, Apr. 2015, doi: 10.1016/j.cmpb.2015.01.002.
[29] “OpenRISC 1200 IP Core Specification.” [Online]. Available: https://opencores.org/websvn/filedetails?repname=openrisc&path=%2Fopenrisc%2Ftrunk%2For1200%2Fdoc%2Fopenrisc1200_spec.pdf&rev=645#:~:text=1.2%20OpenRISC%201200,with%2016%2Dbyte%20line%20size.
[30] T.-J. Chen, S.-C. Lee, C.-H. Yang, C.-F. Chiu, and H. Chiueh, “A 28.6µW mixed-signal processor for epileptic seizure detection,” in 2013 Symposium on VLSI Circuits, Jun. 2013, pp. C52–C53.
[31] L. Yu-Shan, “A Portable Multi-Channel Physiological Signal Acquisition System for Sleep Monitoring,” National Chiao Tung University, 2018.
[32] “CIC Referenced Flow for Cell-based IC Design.” TSRI, Accessed: Oct. 08, 2020. [Online]. Available: https://www.tsri.org.tw/techpaper/pdf/CIC-DSD-RD-08-01.pdf.
[33] “Design Compiler NXT.” synopsys, Accessed: Oct. 08, 2020. [Online]. Available: https://www.synopsys.com/implementation-and-signoff/rtl-synthesis-test/design-compiler-nxt.html.
[34] “Innovus Implementation System.” cadence, Accessed: Oct. 08, 2020. [Online]. Available: https://www.cadence.com/ko_KR/home/tools/digital-design-and-signoff/soc-implementation-and-floorplanning/innovus-implementation-system.html.
[35] “IC Verification and Signoff Using Calibre.” mentor, Accessed: Oct. 08, 2020. [Online]. Available: https://www.mentor.com/products/ic_nanometer_design/verification-signoff/.
[36] Istiqomah, “Development of Real-time Epileptic Seizure Detection Applications,” National Chiao Tung University, 2019.
[37] P. Wagner, N. Strodthoff, R.-D. Bousseljot, W. Samek, and S. Tobias, “PTB-XL, a large publicly available electrocardiography dataset,” PhysioNet. https://www.physionet.org/content/ptb-xl/1.0.1/.
[38] J. Yoo, L. Yan, D. El-Damak, M. A. B. Altaf, A. H. Shoeb, and A. P. Chandrakasan, “An 8-Channel Scalable EEG Acquisition SoC With Patient-Specific Seizure Classification and Recording Processor,” IEEE J. Solid-State Circuits, vol. 48, no. 1, pp. 214–228, Jan. 2013, doi: 10.1109/JSSC.2012.2221220.
[39] G. O’Leary, D. M. Groppe, T. A. Valiante, N. Verma, and R. Genov, “NURIP: Neural Interface Processor for Brain-State Classification and Programmable-Waveform Neurostimulation,” IEEE J. Solid-State Circuits, vol. 53, no. 11, pp. 3150–3162, Nov. 2018, doi: 10.1109/JSSC.2018.2869579.
[40] M. A. Bin Altaf, C. Zhang, and J. Yoo, “A 16-Channel Patient-Specific Seizure Onset and Termination Detection SoC With Impedance-Adaptive Transcranial Electrical Stimulator,” IEEE J. Solid-State Circuits, vol. 50, no. 11, pp. 2728–2740, Nov. 2015, doi: 10.1109/JSSC.2015.2482498.
[41] K. H. Lee and N. Verma, “A Low-Power Processor With Configurable Embedded Machine-Learning Accelerators for High-Order and Adaptive Analysis of Medical-Sensor Signals,” IEEE J. Solid-State Circuits, vol. 48, no. 7, pp. 1625–1637, Jul. 2013, doi: 10.1109/JSSC.2013.2253226.
電子全文 電子全文(網際網路公開日期:20251008)
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
第一頁 上一頁 下一頁 最後一頁 top