本文選題：腦-機(jī)接口 + 穩(wěn)態(tài)視覺(jué)誘發(fā)電位��； 參考：《天津職業(yè)技術(shù)師范大學(xué)》2014年碩士論文

【摘要】：電極在頭皮表面收集得到的腦電信號(hào)（Electroencephalogram，EEG），可以被理解為是神經(jīng)元電生理活動(dòng)的總體響應(yīng)，人的認(rèn)知、意識(shí)等活動(dòng)形態(tài)和腦電信號(hào)具有很大的關(guān)聯(lián)，存在差別的意識(shí)活動(dòng)能夠通過(guò)對(duì)腦電信號(hào)處理分析出來(lái)，由此可以形成一種獨(dú)立于大腦外周神經(jīng)和肌肉正常輸出通道的通訊控制系統(tǒng)，即腦-機(jī)接口（Brain-Computer Interface，BCI）。視覺(jué)誘發(fā)電位（VEP）是枕葉皮層對(duì)視覺(jué)刺激產(chǎn)生的反應(yīng)，作為一種分析和提取較為方便的腦電信號(hào)，常常作為控制系統(tǒng)的輸入信號(hào)。基于腦-機(jī)接口的智能家電系統(tǒng)，是針對(duì)傳統(tǒng)的智能家居概念提出來(lái)的，在原有的技術(shù)基礎(chǔ)上將腦-機(jī)接口技術(shù)引入其中，可以解決殘疾人的獨(dú)立生活和康復(fù)治療等問(wèn)題�；诒銛y式腦-機(jī)接口的智能家電控制系統(tǒng)主要由腦電采集模塊、數(shù)據(jù)分析模塊、指令轉(zhuǎn)化模塊、指令傳輸網(wǎng)絡(luò)和外部設(shè)備控制等部分組成，其中對(duì)于腦電數(shù)據(jù)的分析精度和速度是研究的重點(diǎn)。 本文利用視覺(jué)誘發(fā)電位設(shè)計(jì)了一套僅使用腦電控制的智能家電系統(tǒng)，不僅可以對(duì)穩(wěn)態(tài)視覺(jué)誘發(fā)電位(Steady-state visual evoked potentials, SSVEP)信號(hào)實(shí)時(shí)的采集分析處理，還能將其轉(zhuǎn)換為對(duì)應(yīng)的控制命令，達(dá)到無(wú)需肢體語(yǔ)言控制智能家電的目的。系統(tǒng)主要分為兩大部分：基于DSP平臺(tái)的腦電信號(hào)實(shí)時(shí)處理器和基于Zigbee無(wú)線網(wǎng)絡(luò)搭建的智能家電裝置。采用TI2000系列DSPTMS320F2812芯片，借助DSP高速、低功耗的特點(diǎn)，實(shí)現(xiàn)對(duì)SSVEP的數(shù)字濾波、特征提取以及分類，最后將特征信號(hào)轉(zhuǎn)化為控制命令從而控制無(wú)線網(wǎng)絡(luò)節(jié)點(diǎn)上的智能家電裝置。在CCS3.3軟件中利用C語(yǔ)言對(duì)TMS320F2812芯片進(jìn)行算法編程，保證系統(tǒng)能夠?qū)SVEP進(jìn)行有效采集處理。Zigbee無(wú)線網(wǎng)絡(luò)控制的智能家電裝置系統(tǒng)的開(kāi)發(fā)主要在IAR810軟件上，實(shí)現(xiàn)對(duì)控制命令的準(zhǔn)確發(fā)送和家電裝置的控制。 通過(guò)對(duì)基于SSVEP的智能家電控制系統(tǒng)進(jìn)行了在線實(shí)驗(yàn)驗(yàn)證，并與搭建在上位機(jī)LabVIEW平臺(tái)上的腦電處理裝置相對(duì)比，在處理速度上DSP腦電處理平臺(tái)處理單個(gè)任務(wù)指令的時(shí)間比傳統(tǒng)的上位機(jī)處理平均提高了約0.98%�；贒SP的處理平臺(tái)具有可移動(dòng)性和便攜性，結(jié)合新的物聯(lián)網(wǎng)智能家居技術(shù)的開(kāi)發(fā)，能夠更好地實(shí)現(xiàn)了腦電控制家電裝置，保證了系統(tǒng)的可靠性和便攜性。
[Abstract]:Electroencephalogram-EEGG, which is collected by electrodes on the scalp surface, can be understood as the overall response of neurons to electrophysiological activities, and the patterns of activities such as human cognition and consciousness have a great relationship with EEG signals. Different conscious activities can be analyzed by processing EEG signals, thus forming a communication control system independent of the normal output channels of the peripheral nerves and muscles of the brain, that is, Brain-Computer Interface (Brain-Computer Interface), Brain-Computer Interface (Brain-Computer Interface), Brain-Computer Interface (Brain-Computer Interface), Brain-Computer Interface (Brain-Computer Interface). Visual evoked potential (VEP) is a response of occipital cortex to visual stimulation. As a kind of convenient EEG signal analysis and extraction, VEP is often used as input signal of control system. The intelligent home appliance system based on brain-computer interface (BCI) is put forward in view of the traditional concept of smart home. The brain-computer interface technology is introduced into the system on the basis of the original technology, which can solve the problems of independent living and rehabilitation treatment of the disabled. The intelligent home appliance control system based on portable brain-computer interface is mainly composed of EEG acquisition module, data analysis module, instruction conversion module, instruction transmission network and external equipment control, etc. The accuracy and speed of EEG data analysis is the focus of the research. In this paper, we design a set of intelligent household electrical appliances which only use EEG control by using visual evoked potential (VEP). Not only can the Steady-state visual evoked potentials, SSVEP signal be collected and analyzed in real time, but also it can be converted into the corresponding control command to achieve the purpose of controlling intelligent appliances without limb language. The system is mainly divided into two parts: a real-time EEG processor based on DSP platform and an intelligent home appliance device based on Zigbee wireless network. By using DSP TMS320F2812 chip of TI2000 series, the digital filtering, feature extraction and classification of SSVEP are realized by the characteristics of DSP high speed and low power consumption. Finally, the feature signal is converted into control command to control the intelligent appliance device on wireless network node. In the CCS3.3 software, we use C language to program the TMS320F2812 chip, so as to ensure that the system can collect and process the SSVEP effectively. Zigbee wireless network control intelligent home appliance system is mainly developed on the IAR810 software. The intelligent home appliance control system based on SSVEP is verified by online experiments and compared with the EEG processing device built on the upper computer LabVIEW platform. The processing time of DSP EEG processing platform is about 0.98 higher than that of traditional PC processing. The processing platform based on DSP has the mobility and portability, combined with the development of the new intelligent home technology of the Internet of things, it can better realize the EEG control appliance device, and ensure the reliability and portability of the system.
【學(xué)位授予單位】：天津職業(yè)技術(shù)師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TU855;TP273

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 堯德中;劉鐵軍;雷旭;楊平;徐鵬;張楊松;;基于腦電的腦-機(jī)接口:關(guān)鍵技術(shù)和應(yīng)用前景[J];電子科技大學(xué)學(xué)報(bào);2009年05期

2 陶國(guó)彬;張秀艷;任玉霞;;FIR濾波器的等波紋最優(yōu)化設(shè)計(jì)[J];大慶石油學(xué)院學(xué)報(bào);2007年06期

3 徐鋒;劉欣;方加寶;;智能家居遠(yuǎn)程控制系統(tǒng)設(shè)計(jì)[J];低壓電器;2009年04期

4 趙麗;孫永;馬彥臻;何洋;;基于SSVEP的腦-機(jī)接口自動(dòng)車系統(tǒng)研究[J];電子測(cè)量技術(shù);2011年12期

5 劉家樂(lè);吳小培;;基于穩(wěn)態(tài)視覺(jué)誘發(fā)電位的腦機(jī)接口系統(tǒng)的設(shè)計(jì)與研究[J];工業(yè)控制計(jì)算機(jī);2011年05期

6 申麗巖;方濱;沈毅;;基于負(fù)熵極大的獨(dú)立分量分析方法[J];中北大學(xué)學(xué)報(bào)(自然科學(xué)版);2005年06期

7 侯俊;吳成東;袁中甲;周蕓;張?jiān)浦?;基于ZigBee的智能家居安全監(jiān)控系統(tǒng)研究[J];機(jī)電工程;2009年01期

8 孫進(jìn);張征;周宏甫;;基于腦機(jī)接口技術(shù)的康復(fù)機(jī)器人綜述[J];機(jī)電工程技術(shù);2010年04期

9 汪成義;田峰;;基于嵌入式Web服務(wù)器的智能家居遠(yuǎn)程控制[J];科技信息;2009年06期

10 王行愚;金晶;張宇;王蓓;;腦控:基于腦-機(jī)接口的人機(jī)融合控制[J];自動(dòng)化學(xué)報(bào);2013年03期

相關(guān)博士學(xué)位論文 前3條

1 施錦河;運(yùn)動(dòng)想象腦電信號(hào)處理與P300刺激范式研究[D];浙江大學(xué);2012年

2 李俊華;腦活動(dòng)狀態(tài)EEG信號(hào)解碼方法及其應(yīng)用[D];上海交通大學(xué);2012年

3 龍錦益;腦信號(hào)分析的算法研究與多模態(tài)腦機(jī)接口[D];華南理工大學(xué);2012年

，

本文編號(hào)：2008019