為了能夠協助新生兒能夠早期發現其聽力異常，本研究透過以嵌入式系統、簡單電子電路與Android APP開發一個能夠量測自動聽性腦幹響應(aABR)與短暫誘發耳聲傳射(TEOAE)的系統，嵌入式系統選擇使用STM32F407G-DISC1開發板，電子電路包含前級放大器、八階帶通Butterworth Sallen-Key Filter、後級放大器、藍芽模組、上拉電路、喇叭接頭與耳機插座，Android APP可以輸入使用者資料、進行藍芽配對與連接、選擇量測項目及結果分析。
在TEOAE量測分析中，使用Derived Nonlinear Response Method以三個正刺激音與一個三倍大振幅的正刺激音量測訊號，接著將訊號通過時間窗及數位濾波器，接著分為兩組計算再現性、訊號強度與雜訊強度，透過訊號在五個頻帶中的SNR來決定是否通過測試。
在aABR量測中，透過比較卡爾曼濾波器、小波卡爾曼濾波器及適應性卡爾曼濾波器在加上指數權重平均後的濾波效果，選擇以表現較佳的適應性卡爾曼濾波器搭配指數權重平均作為系統演算法，接著以擬合參數峰自動捕捉第五波的潛時、大小及寬度，並判斷檢查是否通過。
本研究透過使用電路板及PCB板實現設計之電路，並邀請四位聽力正常的男性及一位高頻聽損的女性作為受試者，量測結果中顯示目前的電路設計無法有效量測，可能是因為訊號能量耗損及冷焊導致。

To help the early detection of hearing impairments in newborns, this study proposes a system capable of measuring automated auditory brainstem response (aABR) and transient evoked otoacoustic emissions (TEOAE) using an embedded system, simple electronic circuits, and an Android application. The embedded system is built on the STM32F407G – DISC1 development board. The electronic circuit includes a preamplifier, an eighth-order band-pass Butterworth Sallen-Key filter, a post-amplifier, a Bluetooth module, a pull-up circuit, a speaker connector, and a headphone jack. The Android application supports user data entry, Bluetooth pairing and connection, selection of test items, and result analysis.
For TEOAE analysis, the Derived Nonlinear Response Method is used, involving three positive polarity stimuli and one positive polarity stimulus with triple amplitude. The recorded signals are processed using time-windowing and digital filtering, then separated into two groups for calculating reproducibility, signal strength, and noise level. The test result is determined by evaluating the signal-to-noise ratio (SNR) across five frequency bands.
In the aABR measurement, three filtering methods—Kalman filter, wavelet Kalman filter, and adaptive Kalman filter—are compared, each combined with exponential weighted averaging. The adaptive Kalman filter with exponential weighting, which showed the best performance, is selected as the system's algorithm. Finally, the system automatically extracts the latency, amplitude, and width of wave V using fitted parametric peak method and evaluates whether the test is passed.
In this study, the designed circuit was implemented using a circuit board and a PCB. Four normal-hearing male and one female with high-frequency hearing loss were invited as subjects. The measurement results indicate that the current circuit design fails to effectively measure the signals. The reason may be attributed to signal energy loss and potential cold solder joints.

Bradley A.P., Wilson W.J. (2005). “Automated Analysis of the Auditory Brainstem Response Using Derivative Estimation Wavelets,” Audiology and Neurotology, vol 10, pp.6-21

Chen, C., Zhan, L. (2021). “Automatic Recognition of Auditory Brainstem Response Characteristic Waveform Based on Bidirectional Long Short-Term Memory,” Frontiers in Medicine, vol. 7

Delgado R.E., Özdamar, Ö. (1994). “Automated Auditory Brainstem Response Interpretation,” IEEE Engineering in Medicine and Biology Magazine, vol. 13, no 2, pp. 227-237

Greg, W., Gary, B. (2006). An Introduction to the Kalman Filter, University of North Carolina at Chapel Hill

Katz, J., Chasin, M., (2015). Handbook of Clinical Audiology, 7th edition, Wolters Kluwer Health

Kemp, D.T, Ryan, P., (1990). “A Guide to the Effective Use of Otoacoustic Emissions,” Ear and Hearing, vol. 11, No. 2

Moore, B. C. J. (2013). An Introduction to the Psychology of Hearing, 6th edition, Brill

Prieve, B.A., Gorga, M.P. (1993). “Analysis of transient-evoked otoacoustic emissions in normal-hearing and hearing-impaired ears,” Journal of the Acoustical Society of America, vol 93

Ravazzani, P., Grandori, F. (1993). “Evoked Otoacoustic Emissions: Nonlinearities and Response Interpretation,” IEEE Transactions on biomedical engineering, vol. 40, No. 5

Stenklev, N.C., Laukli, E. (2003). “Transient evoked otoacoustic emissions in the elderly,” International Journal of Audiology, vol 42

Valderrama, J.T. (2014). “Automatic quality assessment and peak identification of auditory brainstem responses with fitted parametric peaks,” Computer Methods and Programs in Biomedicine, vol 114, p262 - 275

Zhang H. et al., 2022. “A Robust Extraction Approach of Auditory Brainstem Response Using Adaptive Kalman Filtering Method,” IEEE Transactions on Biomedical Engineering, vol. 69, no. 12, pp. 3792-3802
劉致中，「以個人數位助理為平台之短暫誘發耳聲傳射檢測儀」，國立中央大學，碩士論文，民國100年7月
趙柏宇，「以無線自動聽性腦幹響應量測系統發展V波自動判別之方法,」， 國立中央大學，碩士論文，民國106年7月
楊明修，「運用小波卡爾曼濾波及擬合參數峰自動偵測聽性腦幹反應第五波,」，國立中央大學，碩士論文，民國110年6月
世界衛生組織.(2016). 兒童聽力損失. 擷取自https://iris.who.int/bitstream/handle/10665/204507/WHO_NMH_NVI_16.1_chi.pdf?sequence=4&isAllowed=y
世界衛生組織.(2024). Deafness and hearing loss. 擷取自https://www.who.int/news-room/fact-sheets/detail/deafness-and-hearing-loss
國民健康署.(2024). 如何發現嬰幼兒聽力損傷~嬰幼兒聽力篩檢.擷取自https://www.hpa.gov.tw/Pages/Detail.aspx?nodeid=515&pid=522&sid=542
林鴻清.(2009). 新生兒聽力篩檢工具之認識:OAE v.s AABR.擷取自https://hclin59.blogspot.com/2010/05/oae-vs-aabr.html