本系統以MSP430 為核心發展一套呼吸肌電圖訊號擷取平台，擷取、紀錄訊號去除橫膈膜肌電訊號中的心電雜訊，並從訊號中計算出相關的生理資訊，如呼吸頻率、心率與心率變異等資訊，且透過USB 將資料傳至電腦端並於電腦端作分析進一步之處理、分析（如肌電訊號的過零率及頻譜功率分析）。在肌電訊號的特徵值分析中，自主與非自主呼吸在三個頻段的頻譜功率皆呈現顯著差異(p<0.05)，而過零率上則有明顯的自體差異。在特徵值的應用上，由於其判斷呼吸的閥值選定困難，所以本研究以半自動的方式做評估，而其正確率皆高於83%。在平台演算法的驗證上，本研究以呼吸氣流溫度比對演算法其正確性高達98.9%。

The diaphragm EMG acquisition platform was integrated using a
microprocessor (MSP430) to acquire, save and process the EMG signals. The processes of the EMG signals included the cancellation of ECG interference from diaphragmatic EMG and the calculation for physiology-related information such as the respiratory rate, heart rate and heart rate variability (HRV), and so forth. After all the processes had been
completed on the platform, the data could be conveyed to a computer via USB for further analyses (such as the zero-cross rate and the spectrum of signals) and for other applications. There was significant difference in the power spectrum (p<0.05) between spontaneous and compulsive breathing on the power spectrum. However, this article used the zero-crossing rate specifically for self pattern recognition. Accuracy in differentiating the breathing patterns using the EMG signals was found to be about
83% as a threshold was chosen manually. Furthermore, the accuracy became greater than 98.9%, when a thermistor for sensing the respiratory air flow was devised as the reference of the EMG respiration-detection.