TW202109552A - Identity recognition system based on compression signal and method thereof - Google Patents
Identity recognition system based on compression signal and method thereof Download PDFInfo
- Publication number
- TW202109552A TW202109552A TW108129847A TW108129847A TW202109552A TW 202109552 A TW202109552 A TW 202109552A TW 108129847 A TW108129847 A TW 108129847A TW 108129847 A TW108129847 A TW 108129847A TW 202109552 A TW202109552 A TW 202109552A
- Authority
- TW
- Taiwan
- Prior art keywords
- signal
- compressed
- recognition
- module
- physiological
- Prior art date
Links
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
本發明涉及一種身分識別系統及其方法,特別是基於壓縮信號的身分識別系統及其方法。The invention relates to an identity recognition system and a method thereof, in particular to an identity recognition system and a method based on compressed signals.
近年來,隨著壓縮感知(Compressive Sensing)的普及與蓬勃發展,其應用範圍日益廣泛,例如:互聯網骨幹和生醫訊號監測系統。In recent years, with the popularization and vigorous development of compressed sensing (Compressive Sensing), its application scope has become more and more extensive, such as Internet backbone and biomedical signal monitoring system.
一般而言,壓縮感知係將高維度的稀疏信號,透過量測矩陣取得低維度的測量值,因此系統只需要以低維度的信號做傳遞,等需要時再利用範數(Norm)極小化等方法將低維度的取樣重建回高維度的信號。然而,壓縮感知除了需考量信號的稀疏特性(信號必須足夠稀疏才有機會將其還原)以外,還需要在後端花費大量的時間與資源將壓縮信號重建還原後,才能進一步使用還原信號,限制了其應用的方便性。Generally speaking, compressed sensing uses high-dimensional sparse signals to obtain low-dimensional measurement values through the measurement matrix. Therefore, the system only needs to transmit low-dimensional signals, and then use the norm (Norm) minimization when needed. The method reconstructs the low-dimensional samples back to the high-dimensional signals. However, in addition to considering the sparse characteristics of the signal (the signal must be sparse enough to have a chance to restore it), compressed sensing also needs to spend a lot of time and resources on the backend to reconstruct the compressed signal before it can be further used to restore the signal. To improve the convenience of its application.
綜上所述,可知先前技術中長期以來一直存在壓縮信號需重建還原後才能進一步使用與應用之問題,因此實有必要提出改進的技術手段,來解決此一問題。In summary, it can be seen that in the prior art, there has been a long-standing problem in the prior art that the compressed signal needs to be reconstructed and restored before further use and application. Therefore, it is necessary to propose improved technical means to solve this problem.
本發明揭露一種基於壓縮信號的身分識別系統及其方法。The invention discloses an identity recognition system and method based on compressed signals.
首先,本發明揭露一種基於壓縮信號的身分識別系統,其包括:感測端與識別端,感測端具有識別模式與學習模式且包括:量測模組、壓縮模組與第一傳輸模組,識別端包括:第一信號分離模組與識別模組。當感測端處於識別模式時,量測模組用以持續量測使用者在至少一第一預定時間長度內的生理識別信號,壓縮模組用以對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,第一傳輸模組用以傳送第一壓縮信號。第一信號分離模組用以接收第一壓縮信號,並根據主要特徵向量取得第一壓縮信號在鑑別子空間中的第一鑑別資訊;識別模組用以接收第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷使用者為多個受測者之一。First of all, the present invention discloses an identity recognition system based on compressed signals, which includes: a sensing terminal and a recognition terminal. The sensing terminal has a recognition mode and a learning mode and includes: a measurement module, a compression module, and a first transmission module , The identification terminal includes: a first signal separation module and an identification module. When the sensing terminal is in the recognition mode, the measurement module is used to continuously measure the physiological recognition signal of the user in at least a first predetermined time length, and the compression module is used to correct the physiological recognition signal of the user in at least a first predetermined time length. The physiological recognition signal undergoes a compression process to generate a first compressed signal, and the first transmission module is used to transmit the first compressed signal. The first signal separation module is used to receive the first compressed signal, and obtain the first discrimination information of the first compressed signal in the discrimination subspace according to the main feature vector; the identification module is used to receive the first discrimination information and learn from The classification model at the end recognizes the first identification information to determine that the user is one of multiple subjects.
此外,本發明揭露一種基於壓縮信號的身分識別方法,其步驟包括:當感測端處於識別模式時,持續量測使用者在至少一第一預定時間長度內的生理識別信號,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,並傳送第一壓縮信號;以及識別端接收第一壓縮信號,並根據主要特徵向量取得第一壓縮信號在鑑別子空間中的第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷使用者為多個受測者之一。In addition, the present invention discloses an identity recognition method based on compressed signals, the steps of which include: when the sensing terminal is in the recognition mode, continuously measuring the user's physiological recognition signal for at least a first predetermined period of time. The physiological recognition signal within the first predetermined length of time undergoes a compression procedure to generate a first compressed signal, and transmits the first compressed signal; and the recognition terminal receives the first compressed signal, and obtains the first compressed signal in the discrimination subspace according to the main feature vector And identify the first identification information according to the classification model from the learning end to determine that the user is one of multiple subjects.
本發明所揭露之系統與方法如上,與先前技術的差異在於本發明是透過當感測端處於識別模式時,持續量測使用者在至少一第一預定時間長度內的生理識別信號,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,傳送第一壓縮信號;識別端接收第一壓縮信號,根據主要特徵向量取得第一壓縮信號在鑑別子空間的第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷該使用者為多個受測者之一。The system and method disclosed in the present invention are as above. The difference from the prior art is that the present invention continuously measures the physiological recognition signal of the user during at least a first predetermined period of time when the sensor is in the recognition mode. At least one physiological identification signal within a first predetermined time length undergoes a compression procedure to generate a first compressed signal, and transmits the first compressed signal; the identification terminal receives the first compressed signal, and obtains the first compressed signal in the discrimination subspace according to the main feature vector The first identification information, and the first identification information is identified according to the classification model from the learning end, to determine that the user is one of a plurality of subjects.
透過上述的技術手段,本發明可以使感測端因壓縮技術減少傳送信號的能量,延長其電池的使用壽命;識別端根據主要特徵向量與動態調整的分類模型以第一壓縮信號進行使用者的身分識別,不需重建感測端所傳送的第一壓縮信號再進行使用者的身分識別,簡化運算程序且減少身分識別所需的時間。Through the above-mentioned technical means, the present invention can make the sensor terminal reduce the energy of the transmitted signal due to the compression technology, and extend the service life of its battery; the recognition terminal uses the first compressed signal to perform the user's feedback according to the main feature vector and the dynamically adjusted classification model Identity recognition does not need to rebuild the first compressed signal transmitted by the sensor and then perform the user's identity recognition, which simplifies the calculation procedure and reduces the time required for identity recognition.
在說明本發明所揭露之基於壓縮信號的身分識別系統及其方法之前,先對本發明所自行定義的名詞作說明,本發明所述的感測端、識別端與學習端可以利用各種方式來實現,包含軟體、硬體、韌體或其任意組合。例如,在某些實施方式中,感測端可以利用軟體和/或硬體來實現,本發明的範圍在此方面不受限制。在實施中提出的技術使用軟體或韌體可以被儲存在機器可讀儲存媒體上,例如:唯讀記憶體(ROM)、隨機存取記憶體(RAM)、磁盤儲存媒體、光儲存媒體、快閃記憶體裝置等等,並且可以由一個或多個通用或專用的可程式化微處理器執行。本發明所述的感測端與識別端之間以及感測端與學習端之間可透過無線傳輸技術進行通訊,其中,無線傳輸技術可為但不限於紅外線、藍芽、無線射頻識別技術、Wi-Fi或ZigBee。本發明所述的學習端與識別端之間可利用銅傳輸電纜、光纖傳輸、無線傳輸、路由器、防火牆、交換機、閘道電腦和/或邊緣伺服器進行訊息與資料的傳遞,使得學習端與識別端之間可相互連通,以進行訊息與資料的傳遞。Before describing the identity recognition system and method based on the compressed signal disclosed in the present invention, firstly, the self-defined nouns of the present invention will be explained. The sensing end, recognition end, and learning end of the present invention can be implemented in various ways. , Including software, hardware, firmware or any combination thereof. For example, in some embodiments, the sensing terminal can be implemented by software and/or hardware, and the scope of the present invention is not limited in this respect. The technology used in the implementation of software or firmware can be stored on machine-readable storage media, such as: read-only memory (ROM), random access memory (RAM), disk storage media, optical storage media, fast Flash memory devices, etc., and can be executed by one or more general-purpose or special-purpose programmable microprocessors. The communication between the sensing terminal and the recognition terminal and between the sensing terminal and the learning terminal of the present invention can be carried out through wireless transmission technology. The wireless transmission technology can be, but not limited to, infrared, bluetooth, radio frequency identification technology, Wi-Fi or ZigBee. The learning terminal and the identification terminal of the present invention can use copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers to transmit information and data, so that the learning terminal and The identification terminals can be connected to each other for the transmission of messages and data.
此外,本發明根據多個受測者的鑑別資訊以機器學習法進行訓練的方式設計出一個分類模型,以對使用者的鑑別資訊進行識別,進而判斷使用者為該些受測者之一。由於分類模型會隨著受測者的不同而有所改變,即具有「自我修正更新」的功能,故可保持身分識別之精準度。In addition, the present invention designs a classification model based on the identification information of a plurality of testees by means of machine learning training, so as to identify the user's identification information, and then determine that the user is one of the testees. Since the classification model will change with different subjects, that is, it has the function of "self-correction and update", so the accuracy of identity recognition can be maintained.
在實際實施上可分為兩個階段,在學習階段,感測端用以分別量測每一受測者之預定時間長度的生理識別信號,使用壓縮技術壓縮生理識別信號以生成對應的壓縮信號,使其減少傳輸的信號量,進而減少能量的消耗;學習端接收每一受測者對應的壓縮信號,再透過主要特徵向量取得每一受測者對應的壓縮信號在鑑別子空間中的鑑別資訊,並以機器學習法進行訓練,產生分類模型。接著,在識別階段,感測端壓縮技術壓縮使用者之預定時間長度的生理識別信號以生成對應的壓縮信號,壓縮過的信號會在識別端利用主要特徵向量與分類模型進行使用者的身分識別(即判斷使用者為學習階段的該些受測者之一)。In actual implementation, it can be divided into two stages. In the learning stage, the sensor is used to separately measure the physiological recognition signal of each subject for a predetermined length of time, and compress the physiological recognition signal to generate the corresponding compressed signal. , To reduce the amount of transmitted signals, thereby reducing energy consumption; the learning end receives the compressed signal corresponding to each subject, and then obtains the identification of the compressed signal corresponding to each subject in the discrimination subspace through the main feature vector Information, and trained with machine learning methods to generate classification models. Then, in the recognition stage, the sensor-side compression technology compresses the user’s physiological recognition signal of a predetermined length of time to generate the corresponding compressed signal. The compressed signal will use the main feature vector and classification model to identify the user’s identity on the recognition side. (That is, it is judged that the user is one of the testees in the learning stage).
以下將配合圖式及實施例來詳細說明本發明之實施方式,藉此對本發明如何應用技術手段來解決技術問題並達成技術功效的實現過程能充分理解並據以實施。The following describes the implementation of the present invention in detail with the drawings and embodiments, so as to fully understand and implement the implementation process of how the present invention uses technical means to solve technical problems and achieve technical effects.
請先參閱「第1圖」,「第1圖」為本發明基於壓縮信號的身分識別系統之一實施例系統方塊圖。在本實施例中,基於壓縮信號的身分識別系統100,其包括:感測端110與識別端120。在實際實施上,感測端110係可為但不限於穿戴式裝置,識別端120係可為但不限於電腦。Please refer to "Figure 1" first. "Figure 1" is a system block diagram of an embodiment of the identity recognition system based on compressed signals of the present invention. In this embodiment, the
感測端110具有識別模式與學習模式,可包括:量測模組112、壓縮模組114與第一傳輸模組116。當感測端110處於學習模式時,量測模組112可用以分別持續量測每一受測者在至少一第二預定時間長度內的生理識別信號,壓縮模組114可用以對每一受測者在至少一第二預定時間長度內的生理識別信號進行壓縮程序以生成對應的第二壓縮信號,第一傳輸模組116可用以傳送每一受測者對應的該第二壓縮信號。其中,生理識別信號係為可用以識別每個人身分的信號,即該信號包含可識別每一人的身分特徵,舉例而言,生理識別信號可為但不限於心電圖(electrocardiography,ECG)信號或光電容積圖(photoplethysmography,PPG)信號。The sensing terminal 110 has a recognition mode and a learning mode, and may include a
更詳細地說,在本實施例中,係利用單一感測端110分別配戴於多個受測者身上進行量測,但本實施例並非用以限定本發明,舉例而言,也可讓每一受測者身上皆配戴一個感測端110進行量測。In more detail, in this embodiment, a single sensor terminal 110 is used to separately wear on multiple subjects for measurement. However, this embodiment is not intended to limit the present invention. For example, Each subject wears a sensor terminal 110 for measurement.
感測端110更可包括設定模組111,當感測端110處於學習模式時,在持續量測每一受測者在至少一第二預定時間長度內的生理識別信號之前,設定模組111接收基於壓縮信號的身分識別系統100之操作者針對每一受測者所輸入的資料,故可接收每一受測者對應的設定資訊,設定資訊可包括編號與姓名,編號可以透過一維陣列方式呈現,但本實施例並非用以限定本發明。當第一傳輸模組116傳送每一受測者對應的第二壓縮信號予學習端130時也可傳送每一受測者對應設定資訊予學習端130。The sensing terminal 110 may further include a
當感測端110處於學習模式時,量測模組112可透過其具有的感測器分別持續量測每一受測者在至少一第二預定時間長度內的生理識別信號,且量測時間可限定為第二預定時間的長度,實際的量測時間只要大於或等於第二預定時間的長度即可。在本實施例中,第二預定時間可為但不限於1小時,實際第二預定時間的大小可依據實際需求進行調整。When the sensor terminal 110 is in the learning mode, the
壓縮模組114可用以對每一受測者在至少一第二預定時間長度內的生理識別信號進行壓縮程序以生成對應的第二壓縮信號,其中,對在至少一第二預定時間長度內的生理識別信號進行壓縮程序係為利用離散餘弦轉換(Discrete Cosine Transform,DCT)、離散小波轉換(Discrete Wavelet Transformation,DWT)、主成成分分析(Principal Component Analysis,PCA)或壓縮感知(Compressive sensing,CS)技術壓縮每一受測者在至少一第二預定時間長度內的生理識別信號。需注意的是,由於量測模組112係持續將每一受測者之生理識別信號傳送予壓縮模組114,故壓縮模組114可先累積每一受測者在至少一第二預定時間長度內的生理識別信號再進行壓縮以生成對應的第二壓縮信號,也可以依據實際需求將每一受測者在至少一第二預定時間長度內的生理識別信號進行分段壓縮以生成對應的第二壓縮信號,還可以像壓縮感知技術一樣量測與壓縮同時進行。舉例而言,當第二預定時間長度為1小時時,壓縮模組114可累積每一受測者之1小時的生理識別信號後進行一次性壓縮以生成對應的第二壓縮信號,也可以每累積每一受測者之1分鐘的生理識別信號後即進行壓縮,故在進行壓縮程序60次後生成對應的第二壓縮信號。The
在本實施例中, 感測端110更可包括雜訊處理模組118,設置於壓縮模組114與量測模組112之間,可用以在壓縮模組114對每一受測者在至少一第二預定時間長度內的生理識別信號進行壓縮程序之前,對每一受測者在至少一第二預定時間長度內的生理識別信號去除雜訊。其中,雜訊處理模組118包括高通濾波器(High-pass filter)、低通濾波器(Low-pass filter)與基線去除(Baseline Removal)單元。In this embodiment, the sensing end 110 may further include a
第一傳輸模組116可用以傳送每一受測者對應的第二壓縮信號。由於壓縮模組114可先累積每一受測者在至少一第二預定時間長度內的生理識別信號再進行壓縮以生成對應的第二壓縮信號,也可以依據實際需求將每一受測者在至少一第二預定時間長度內的生理識別信號進行分段壓縮以生成對應的第二壓縮信號,還可以像壓縮感知技術一樣量測與壓縮同時進行,故第一傳輸模組116可一次性傳輸每一受測者對應的第二壓縮信號,也可以分段傳送每一受測者對應的第二壓縮信號。The first transmission module 116 can be used to transmit the second compressed signal corresponding to each subject. Since the
基於壓縮信號的身分識別系統100還可包括學習端130,學習端130可包括:第二信號分離模組132、機器學習模組134與第二傳輸模組136,第二信號分離模組132可用以接收每一受測者對應的第二壓縮信號,並根據主要特徵向量ψ取得每一受測者對應的第二壓縮信號在鑑別子空間(discrimination subspace)中的第二鑑別資訊(discrimination information);機器學習模組134可用以根據該些第二鑑別資訊以機器學習法進行訓練,產生分類模型;第二傳輸模組136用以傳送分類模型予識別端120。其中,主要特徵向量ψ可為基於壓縮信號的身分識別系統100的操作者依據其經驗所設定的預設向量(不同種類的生理識別信號對應不同的預設向量),也可為利用多個受測者的生理識別信號經PCA技術所取得的主要特徵向量,主要特徵向量ψ不會因受測者不同而改變。The
更詳細地說,第二信號分離模組132可依據主要特徵向量ψ將每一受測者對應的第二壓縮信號分成在鑑別子空間中的第二鑑別資訊以及在補子空間(complementary subspace)中的第二餘資訊(complementary information),由於第二餘資訊係屬於一般人共同擁有的特徵資訊,故在進行身分辨識時,不考慮第二餘資訊。機器學習模組134可用以根據每一受測者的第二鑑別資訊以機器學習法進行訓練,產生分類模型,其中,機器學習法可為但不限於支持向量機(Support Vector Machine,SVM)演算法或神經網路(Neural Network,NN)。需注意的是,分類模型會因受測者不同而改變,因此,當增加一位受測者時,分類模型會隨之改變,而第二傳輸模組136可將分類模型傳送予識別端120,以供後續身分識別使用。此外,第二傳輸模組136將分類模型傳送予識別端120時,也可將每一受測者對應的設定資訊傳輸予識別端120,以供後續身分識別使用。In more detail, the second signal separation module 132 can divide the second compressed signal corresponding to each subject into the second discrimination information in the discrimination subspace and in the complementary subspace according to the main feature vector ψ. The second complementary information (complementary information), because the second complementary information belongs to the characteristic information commonly owned by ordinary people, so the second complementary information is not considered when performing body discrimination. The
另外,需注意的是,由於受測者於不同的情緒或運動時其生理識別信號可能會有些變化,故為提升身分識別的精準度,受測者可於各種狀態(不同情緒或運動)時進行生理識別信號量測,並提供學習端130執行上述步驟(受測者針對每一狀態進行量測即為新增一位受測者進行量測的概念,但感測端110在量測時所接收的設定資訊為該受測者對應的設定資訊),以調整分類模型。In addition, it should be noted that because the subject’s physiological recognition signal may change in different emotions or sports, in order to improve the accuracy of identity recognition, the subject can be in various states (different emotions or sports). Perform physiological recognition signal measurement, and provide the learning terminal 130 to perform the above steps (the subject to measure for each state is the concept of adding a subject to perform the measurement, but the sensor terminal 110 is in the measurement The received setting information is the setting information corresponding to the subject) to adjust the classification model.
當感測端110處於識別模式時,量測模組112可用以持續量測使用者在至少一第一預定時間長度內的生理識別信號,壓縮模組114可用以對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,第一傳輸模組116可用以傳送第一壓縮信號。When the sensing terminal 110 is in the recognition mode, the
更詳細地說,感測端110配戴於使用者身上,當感測端110處於識別模式時,量測模組112可透過其具有的感測器持續量測使用者的生理識別信號,且量測時間可限定為第一預定時間的長度,實際的量測時間只要大於或等於第一預定時間的長度即可,當實際的量測時間越久代表可持續利用本發明進行身分識別(一次身份辨識所需的信號量為第一預定時間長度的生理識別信號,若量測時間大於第一預定時間的長度,可將量測到的生理識別信號切成N個第一預定時間長度的生理識別信號,即可連續進行N次身份辨識,N為正整數),適用於需長期監控人員身分以維護資訊安全的廠房或辦公室。在本實施例中,第一預定時間可為但不限於1分鐘,實際第一預定時間的大小可依據實際需求進行調整。In more detail, the sensor terminal 110 is worn on the user's body. When the sensor terminal 110 is in the recognition mode, the
壓縮模組114連接量測模組112,可用以對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號。需注意的是,由於量測模組112係持續將生理識別信號傳送予壓縮模組114,故壓縮模組114可先累積第一預定時間長度的生理識別信號再進行壓縮以生成第一壓縮信號,也可以依據實際需求將第一預定時間長度的生理識別信號進行分次壓縮,待壓縮第一預定時間長度的生理識別信號後生成第一壓縮信號,還可以像壓縮感知技術一樣量測與壓縮同時進行。舉例而言,當第一預定時間長度為1分鐘時,壓縮模組114可累積1分鐘的生理識別信號後進行一次性壓縮以生成第一壓縮信號,也可以將每1秒鐘的生理識別信號進行壓縮,故在進行壓縮程序60次後生成第一壓縮信號。在本實施例中,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序係為利用DCT、DWT、PCA或CS技術壓縮在至少一第一預定時間長度內的生理識別信號。The
在本實施例中,雜訊處理模組118可用以在壓縮模組114對在至少一第一預定時間長度內的生理識別信號進行壓縮程序之前,對在至少一第一預定時間長度內的生理識別信號去除雜訊。In this embodiment, the
第一傳輸模組116連接壓縮模組114,可用以傳送第一壓縮信號。由於壓縮模組114可先累積第一預定時間長度的生理識別信號再進行壓縮以生成第一壓縮信號,也可以將接收到的每一秒生理識別信號進行壓縮,待壓縮第一預定時間長度的生理識別信號後生成第一壓縮信號,故第一傳輸模組116可一次性傳輸第一壓縮信號,也可以分次傳送第一壓縮信號。The first transmission module 116 is connected to the
在本實施例中,識別端120可包括:第一信號分離模組122與識別模組124,第一信號分離模組122可用以接收第一壓縮信號,並根據主要特徵向量ψ取得第一壓縮信號在鑑別子空間中的第一鑑別資訊。在實際實施中,第一信號分離模組122可依據主要特徵向量ψ將第一壓縮信號分成在鑑別子空間中的第一鑑別資訊以及在補子空間中的第一餘資訊,由於第一餘資訊係屬於一般人共同擁有的特徵資訊,故在進行身分辨識時,不考慮第一餘資訊。In this embodiment, the
識別模組124可用以接收第一鑑別資訊,並根據來自學習端130的分類模型對第一鑑別資訊進行識別,以判斷使用者為感測端110處於學習模式時量測生理識別信號的該些受測者之一。其中,分類模型可為利用多個受測者的生理識別信號經學習端130以機器學習法進行訓練所得到的模型,分類模型會因受測者不同而改變。The
更詳細地說,識別模組124根據來自學習端130的分類模型對第一鑑別資訊進行識別計算後產生對應的一維陣列,識別模組124依據該一維陣列於來自學習端130之每一受測者對應的設定資訊尋找對應的編號(編號透過一維陣列方式呈現),當找到對應的編號時,輸出對應該編號的姓名(即受測者姓名),換句話說,判斷使用者為感測端110處於學習模式時量測生理識別信號的該些受測者之一。In more detail, the
需注意的是,感測端110、識別端120與學習端130可分別包括儲存模組(未繪製),用以儲存生理識別信號、第一壓縮信號、第二壓縮信號、第一鑑別資訊、第二鑑別資訊、主要特徵向量ψ或/與每一受測者對應的設定資訊。It should be noted that the sensing terminal 110, the
另外,在本實施例中,識別端120與學習端130係為兩個不同的裝置,但實際實施上,識別端120與學習端130可為同一裝置,且第一信號分離模組122與第二信號分離模組132可為同一模組,僅為區分在學習階段或識別階段所扮演的角色,故有不同的名稱與符號,此時,第二傳輸模組136可省略。In addition, in this embodiment, the
再者,基於壓縮信號的身分識別系統100也可應用於輔佐判斷使用者是否具有特殊疾病。舉例而言,當感測端110處於學習模式時,在持續量測每一受測者在至少一第二預定時間長度內的心電圖信號之前,設定模組111接收基於壓縮信號的身分識別系統100之操作者針對每一受測者的健康狀態所輸入的資料,故可接收每一受測者對應的設定資訊,設定資訊可包括有心房顫動(Atrial fibrillation,Af)或沒有Af,有無Af可以透過一維陣列方式表示,需注意的是,部分受測者需具有Af,部分受測者不具有Af。量測模組112分別持續量測每一受測者在至少一第二預定時間長度內的心電圖信號,對每一受測者在至少一第二預定時間長度內的心電圖信號進行壓縮程序以生成對應的第二壓縮信號,並傳送每一受測者對應的第二壓縮信號;學習端130接收每一受測者對應的第二壓縮信號,根據主要特徵向量取得每一受測者對應的第二壓縮信號在鑑別子空間中的第二鑑別資訊,並根據該些第二鑑別資訊以機器學習法進行訓練,產生分類模型,並傳送分類模型與每一受測者對應的設定資訊予識別端120。其中,主要特徵向量可為基於壓縮信號的身分識別系統100的操作者依據其經驗所設定的預設向量,也可為利用多個受測者(不論有無Af)的心電圖信號經PCA技術所取得的主要特徵向量,主要特徵向量不會因受測者不同而改變。Furthermore, the
當感測端110處於識別模式時,持續量測使用者在至少一第一預定時間長度內的心電圖信號,對在至少一第一預定時間長度內的心電圖信號進行壓縮程序以生成第一壓縮信號,並傳送第一壓縮信號;以及識別端120接收第一壓縮信號,並根據主要特徵向量取得第一壓縮信號在鑑別子空間中的第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷使用者是否具有Af。更詳細地說,識別模組124根據來自學習端130的分類模型對第一鑑別資訊進行識別計算後產生對應的一維陣列,識別模組124判斷該一維陣列匹配來自學習端130之沒有Af的一維陣列還是有Af的一維陣列,當找到匹配的一維陣列時,輸出對應的結果,換句話說,判斷使用者有無Af。When the sensing terminal 110 is in the recognition mode, it continuously measures the ECG signal of the user in at least a first predetermined time length, and performs a compression procedure on the ECG signal in the at least a first predetermined time length to generate a first compressed signal , And transmit the first compressed signal; and the
接著,請參閱「第2A圖」,「第2A圖」為「第1圖」之基於壓縮信號的身分識別系統執行基於壓縮信號的身分識別方法之學習階段的一實施例方法流程圖。基於壓縮信號的身分識別方法可包括以下步驟:當感測端處於學習模式時,分別持續量測每一受測者在至少一第二預定時間長度內的生理識別信號,對每一受測者在至少一第二預定時間長度內的生理識別信號進行壓縮程序以生成對應的第二壓縮信號,並傳送每一受測者對應的第二壓縮信號(步驟210);學習端接收每一受測者對應的第二壓縮信號,根據主要特徵向量取得每一受測者對應的第二壓縮信號在鑑別子空間中的第二鑑別資訊,並根據該些第二鑑別資訊以機器學習法進行訓練,產生分類模型,並傳送分類模型予識別端(步驟220)。詳細說明已在上面敘述,在此不再贅述。Next, please refer to "Figure 2A". "Figure 2A" is a flowchart of an embodiment of the learning phase of the compressed signal-based identity recognition system in the "Figure 1" implementation of the compressed signal-based identity recognition method. The identity recognition method based on compressed signals may include the following steps: when the sensor is in the learning mode, continuously measure the physiological recognition signal of each subject for at least a second predetermined time length, and for each subject The physiological recognition signal within at least a second predetermined time length is compressed to generate a corresponding second compressed signal, and the second compressed signal corresponding to each subject is transmitted (step 210); the learning terminal receives each subject According to the second compressed signal corresponding to the subject, obtain the second discrimination information in the discrimination subspace of the second compressed signal corresponding to each subject according to the main feature vector, and perform training according to the second discrimination information by the machine learning method, A classification model is generated, and the classification model is transmitted to the recognition terminal (step 220). The detailed description has been described above and will not be repeated here.
透過上述步驟,可使學習端120根據主要特徵向量ψ取得每一受測者對應的第二鑑別資訊,再以機器學習法進行訓練,產生分類模型,並隨著受測者的不同而調整分類模型,使識別端120可依據調整後之分類模型進行身分辨識,以保持身分識別之精準度。Through the above steps, the learning
請參閱「第2B圖」,「第2B圖」為「第1圖」之基於壓縮信號的身分識別系統執行基於壓縮信號的身分識別方法之識別階段的一實施例方法流程圖。基於壓縮信號的身分識別方法還可包括以下步驟:當感測端處於識別模式時,持續量測使用者在至少一第一預定時間長度內的生理識別信號,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,並傳送第一壓縮信號(步驟230);以及識別端接收第一壓縮信號,並根據主要特徵向量取得第一壓縮信號在鑑別子空間中的第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷使用者為多個受測者之一(步驟240)。其中,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序係為利用DCT、DWT、PCA或CS技術壓縮在至少一第一預定時間長度內的生理識別信號。此外,在對在至少一第一預定時間長度內的生理識別信號進行壓縮程序之前,感測端對至少一第一預定時間長度內的生理識別信號去除雜訊。詳細說明已在上面敘述,在此不再贅述。Please refer to "Figure 2B". "Figure 2B" is a flowchart of an embodiment of the identification phase of the compressed signal-based identity recognition system of the "Figure 1" performing the compressed signal-based identity recognition method. The identity recognition method based on the compressed signal may further include the following steps: when the sensing terminal is in the recognition mode, continuously measuring the physiological recognition signal of the user for at least a first predetermined period of time. The physiological recognition signal in the computer undergoes a compression procedure to generate a first compressed signal, and transmits the first compressed signal (step 230); and the recognition terminal receives the first compressed signal, and obtains the first compressed signal in the discrimination subspace according to the main feature vector And identify the first identification information according to the classification model from the learning terminal to determine that the user is one of the multiple subjects (step 240). Wherein, the compression procedure for the physiological identification signal within at least a first predetermined time length is to compress the physiological identification signal within at least a first predetermined time length by using DCT, DWT, PCA or CS technology. In addition, before performing the compression procedure on the physiological recognition signal within the at least a first predetermined time length, the sensor terminal removes noise from the physiological recognition signal within the at least a first predetermined time length. The detailed description has been described above and will not be repeated here.
透過上述步驟,可透過當感測端110處於識別模式時,持續量測使用者在至少一第一預定時間長度內的生理識別信號,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,傳送第一壓縮信號;識別端120接收第一壓縮信號,根據主要特徵向量ψ取得第一壓縮信號在鑑別子空間的第一鑑別資訊,並根據來自學習端130的分類模型對第一鑑別資訊進行識別,以判斷該使用者為多個受測者之一。 因此,感測端110因壓縮技術減少傳送信號的能量,延長其電池的使用壽命;識別端120根據主要特徵向量ψ與動態調整的分類模型以第一壓縮信號進行使用者的身分識別,不需重建感測端110所傳送的第一壓縮信號再進行使用者的身分識別,簡化運算程序且減少身分識別所需的時間。Through the above-mentioned steps, by continuously measuring the physiological recognition signal of the user for at least a first predetermined period of time when the sensor terminal 110 is in the recognition mode, the physiological recognition signal for the period of at least a first predetermined period of time can be measured. The compression program generates the first compressed signal and transmits the first compressed signal; the
其中,基於壓縮信號的身分識別方法還包括以下步驟:當感測端處於學習模式時,感測端接收每一受測者對應的設定資訊,以傳送每一受測者對應的第二壓縮信號與設定資訊予學習端(未繪製)。詳細說明已在上面敘述,在此不再贅述。Wherein, the identity recognition method based on the compressed signal further includes the following steps: when the sensor is in the learning mode, the sensor receives the setting information corresponding to each subject to transmit the second compressed signal corresponding to each subject And setting information to the learning terminal (not drawn). The detailed description has been described above and will not be repeated here.
需注意的是,上述各個步驟如果沒有因果關係,本發明並不限定其執行的先後順序。It should be noted that, if there is no causal relationship among the above steps, the present invention does not limit the order of their execution.
以下配合「第1圖」、「第3A圖」至「第7圖」以實施例的方式進行學習階段的說明。請參閱「第1圖」與「第3A圖」至「第3C圖」,「第3A圖」至「第3C圖」為應用本發明感測端量測三個不同受測者之心電圖信號的示意圖。在本實施例中,利用單一感測端110分別配戴於三個受測者(受測者A、受測者B與受測者C)身上進行量測,當感測端110處於學習模式時,量測模組112可透過其具有的感測器量測每一受測者的心電圖信號。其中,「第3A圖」為受測者A的心電圖信號,「第3B圖」為受測者B的心電圖信號,「第3C圖」為受測者C的心電圖信號。其中,量測時間可限定為1小時,但為避免「第3A圖」至「第3C圖」之圖面過大且複雜,僅以量測1分鐘的心電圖信號為代表。在本實施例中,量測模組112在1分鐘的時間長度可量測到256維度的心電圖信號。The following is the description of the learning phase in the form of examples in conjunction with "Figure 1", "Figure 3A" to "Figure 7". Please refer to "Figure 1" and "Figure 3A" to "Figure 3C". "Figure 3A" to "Figure 3C" are the results of using the sensor terminal of the present invention to measure the ECG signals of three different subjects. Schematic. In this embodiment, a single sensor terminal 110 is used to wear three test subjects (test subject A, test subject B, and test subject C) for measurement. When the sensor terminal 110 is in the learning mode At this time, the
接著,請參照「第1圖」與「第4A圖」至「第4C圖」,「第4A圖」至「第4C圖」為「第3A圖」至「第3C圖」之心電圖信號去除雜訊後的示意圖。在本實施例中,雜訊處理模組118可先對「第3A圖」至「第3C圖」之心電圖信號去除雜訊後,再提供壓縮模組114進行壓縮。Next, please refer to "Figure 1" and "Figure 4A" to "Figure 4C", "Figure 4A" to "Figure 4C" are the ECG signals from "Figure 3A" to "Figure 3C" Schematic diagram after the news. In this embodiment, the
請參照「第1圖」與「第5A圖」至「第5C圖」,「第5A圖」至「第5C圖」為壓縮「第4A圖」至「第4C圖」之去除雜訊的心電圖信號後的第二壓縮信號示意圖。在本實施例中,壓縮模組114可用以對每一受測者之1小時長度的心電圖信號進行壓縮程序以生成對應的第二壓縮信號(「第5A圖」為受測者A的第二壓縮信號示意圖,「第5B圖」為受測者B的第二壓縮信號示意圖,「第5C圖」為受測者C的第二壓縮信號示意圖)。在本實施例中,壓縮模組114可利用CS技術將256維度的心電圖信號壓縮為128維度的第二壓縮信號。Please refer to "
請參照「第1圖」與「第6A圖」至「第6C圖」,「第6A圖」至「第6C圖」為應用本發明學習端取得三個不同受測者對應的第二鑑別資訊示意圖。在本實施例中,第二信號分離模組132可根據主要特徵向量ψ取得每一受測者對應的第二壓縮信號在鑑別子空間中的第二鑑別資訊(「第6A圖」為受測者A的第二鑑別資訊示意圖,「第6B圖」為受測者B的第二鑑別資訊示意圖,「第6C圖」為受測者C的第二鑑別資訊示意圖),為避免「第6A圖」至「第6C圖」之圖面過大且複雜,僅以第二信號分離模組取得「第5A圖」至「第5C圖」之第二壓縮信號在鑑別子空間中的第二鑑別資訊為代表。在本實施例中,主要特徵向量ψ為256×39維度的特徵向量,使得「第6A圖」至「第6C圖」的第二鑑別資訊為39維度的第二鑑別資訊。Please refer to "
其中,主要特徵向量ψ可為基於壓縮信號的身分識別系統100的操作者依據其經驗所設定的預設向量,也可為利用多個受測者的生理識別信號經PCA技術所取得的主要特徵向量,但主要特徵向量ψ的維度大小可依據實際需求進行調整。需注意的是,壓縮模組114所使用的壓縮技術與第二鑑別資訊的維度大小會影響後續身分辨識的精準度,如 「第7圖」所示。「第7圖」為不同壓縮技術之身分識別精準度與第二鑑別資訊的維度大小之關係示意圖,其中,縱軸為身分識別的精準度,數值越大越佳;橫軸為第二鑑別資訊的維度大小,每一數列可代表壓縮模組114所使用的壓縮技術,可分別為DCT技術(以三角形標記的數列)、DWT技術(以叉號標記的數列)、PCA技術(以方形標記的數列)與CS技術(以圓形標記的數列)。從「第7圖」中,可知DCT技術與PCA技術在第二鑑別資訊的維度大小與後續身分辨識的精準度之間的關係幾乎一致,DCT技術、DWT技術、PCA技術與CS技術在第二鑑別資訊的維度越大時身分辨識的精準度越高。Among them, the main feature vector ψ can be a preset vector set by the operator of the
在本實施例中,機器學習模組134可根據該些第二鑑別資訊以機器學習法進行訓練,產生分類模型;第二傳輸模組136可傳送分類模型予識別端120。當每增加一受測者時,機器學習模組134所產生的分類模型隨之改變,第二傳輸模組136可傳送最新的分類模型予識別端120,使識別端120保持身分識別之精準度。In this embodiment, the
綜上所述,可知本發明與先前技術之間的差異在於透過當感測端處於識別模式時,持續量測使用者在至少一第一預定時間長度內的生理識別信號,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,傳送第一壓縮信號;識別端接收第一壓縮信號,根據主要特徵向量取得第一壓縮信號在鑑別子空間的第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷該使用者為多個受測者之一,藉由此一技術手段可以解決先前技術所存在的問題,感測端因壓縮技術減少傳送信號的能量,延長其電池的使用壽命;識別端根據主要特徵向量與動態調整的分類模型以第一壓縮信號進行使用者的身分識別,不需重建感測端所傳送的第一壓縮信號再進行使用者的身分識別,簡化運算程序且減少身分識別所需的時間。To sum up, it can be seen that the difference between the present invention and the prior art is that by continuously measuring the physiological recognition signal of the user for at least a first predetermined period of time when the sensor is in the recognition mode, The physiological recognition signal within a predetermined time length is compressed to generate the first compressed signal, and the first compressed signal is transmitted; the recognition terminal receives the first compressed signal, and obtains the first discrimination of the first compressed signal in the discrimination subspace according to the main feature vector According to the classification model from the learning end, the first identification information is identified to determine that the user is one of multiple subjects. This technical method can solve the problems of the prior art. The sensing end The compression technology reduces the energy of the transmitted signal and prolongs the service life of its battery; the recognition terminal uses the first compressed signal to identify the user according to the main feature vector and the dynamically adjusted classification model, without the need to reconstruct the first transmitted by the sensor terminal. The signal is compressed and then the user's identity is recognized, which simplifies the calculation procedure and reduces the time required for identity recognition.
此外,學習端可根據主要特徵向量取得每一受測者對應的第二鑑別資訊,再以機器學習法進行訓練,產生分類模型,並隨著受測者的不同而調整分類模型,使識別端可依據調整後之分類模型進行身分辨識,以保持身分識別之精準度。In addition, the learning end can obtain the second identification information corresponding to each subject according to the main feature vector, and then use machine learning to train to generate a classification model, and adjust the classification model according to different subjects to make the recognition end The body can be distinguished based on the adjusted classification model to maintain the accuracy of identity recognition.
雖然本發明以前述之實施例揭露如上,然其並非用以限定本發明,任何熟習相像技藝者,在不脫離本發明之精神和範圍內,當可作些許之更動與潤飾,因此本發明之專利保護範圍須視本說明書所附之申請專利範圍所界定者為準。Although the present invention is disclosed in the foregoing embodiments as above, it is not intended to limit the present invention. Anyone familiar with similar art can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of patent protection shall be determined by the scope of the patent application attached to this specification.
100:基於壓縮信號的身分識別系統 110:感測端 111:設定模組 112:量測模組 114:壓縮模組 116:第一傳輸模組 118:雜訊處理模組 120:識別端 122:第一信號分離模組 124:識別模組 130:學習端 132:第二信號分離模組 134:機器學習模組 136:第二傳輸模組 ψ:主要特徵向量 步驟210:感測端處於學習模式時,分別持續量測每一受測者在至少一第二預定時間長度內的生理識別信號,對每一受測者在至少一第二預定時間長度內的生理識別信號進行壓縮程序以生成對應的第二壓縮信號,並傳送每一受測者對應的第二壓縮信號 步驟220:學習端接收每一受測者對應的第二壓縮信號,根據主要特徵向量取得每一受測者對應的第二壓縮信號在鑑別子空間中的第二鑑別資訊,並根據該些第二鑑別資訊以機器學習法進行訓練,產生分類模型,並傳送分類模型予識別端 步驟230:當感測端處於識別模式時,持續量測使用者在至少一第一預定時間長度內的生理識別信號,對在至少一第一預定時間長度內的生理識別信號進行壓縮程序以生成第一壓縮信號,並傳送第一壓縮信號 步驟240:識別端接收第一壓縮信號,並根據主要特徵向量取得第一壓縮信號在鑑別子空間中的第一鑑別資訊,並根據來自學習端的分類模型對第一鑑別資訊進行識別,以判斷使用者為多個受測者之一100: Identity recognition system based on compressed signals 110: sensing end 111: Setting module 112: Measurement module 114: Compression module 116: The first transmission module 118: Noise processing module 120: identification end 122: The first signal separation module 124: Identification Module 130: learning end 132: The second signal separation module 134: Machine Learning Module 136: The second transmission module ψ: main feature vector Step 210: When the sensor terminal is in the learning mode, continuously measure the physiological recognition signal of each subject in at least a second predetermined time length, and measure the physiological recognition signal of each subject in at least a second predetermined time length. The physiological recognition signal is compressed to generate the corresponding second compressed signal, and the second compressed signal corresponding to each subject is transmitted Step 220: The learning terminal receives the second compressed signal corresponding to each subject, obtains the second discrimination information in the discrimination subspace of the second compressed signal corresponding to each subject according to the main feature vector, and according to the first 2. The identification information is trained by machine learning to generate a classification model and send the classification model to the recognition terminal Step 230: When the sensing terminal is in the recognition mode, continuously measure the physiological recognition signal of the user for at least a first predetermined time length, and perform a compression program on the physiological recognition signal for the at least a first predetermined time length to generate The first compressed signal, and the first compressed signal is transmitted Step 240: The recognition terminal receives the first compressed signal, and obtains the first discrimination information of the first compressed signal in the discrimination subspace according to the main feature vector, and recognizes the first discrimination information according to the classification model from the learning terminal to determine the use Is one of multiple subjects
第1圖為本發明基於壓縮信號的身分識別系統之一實施例系統方塊圖。 第2A圖為第1圖之基於壓縮信號的身分識別系統執行基於壓縮信號的身分識別方法之學習階段的一實施例方法流程圖。 第2B圖為第1圖之基於壓縮信號的身分識別系統執行基於壓縮信號的身分識別方法之識別階段的一實施例方法流程圖。 第3A圖至第3C圖為應用本發明感測端量測三個不同受測者之心電圖信號的示意圖。 第4A圖至第4C圖為第3A圖至第3C圖之心電圖信號去除雜訊後的示意圖。 第5A圖至第5C圖為壓縮第4A圖至第4C圖之去除雜訊的心電圖信號後的第二壓縮信號示意圖。 第6A圖至第6C圖為應用本發明學習端取得三個不同受測者對應的第二鑑別資訊示意圖。 第7圖為不同壓縮技術之身分精準度與第二鑑別資訊的維度大小之關係示意圖。Figure 1 is a system block diagram of an embodiment of the identity recognition system based on compressed signals of the present invention. Figure 2A is a flowchart of an embodiment of the learning phase of the compressed signal-based identity recognition system of Figure 1 for executing the compressed signal-based identity recognition method. FIG. 2B is a flowchart of an embodiment of the identification phase of the compressed signal-based identity recognition system in the compressed signal-based identity recognition system of FIG. 1. FIG. 3A to 3C are schematic diagrams of using the sensor terminal of the present invention to measure the electrocardiogram signals of three different subjects. Fig. 4A to Fig. 4C are schematic diagrams of the electrocardiogram signal of Fig. 3A to Fig. 3C after noise is removed. Figs. 5A to 5C are schematic diagrams of the second compressed signal after the electrocardiogram signals of Figs. 4A to 4C are compressed without noise. Figures 6A to 6C are schematic diagrams of applying the learning terminal of the present invention to obtain the second identification information corresponding to three different subjects. Figure 7 is a schematic diagram of the relationship between the identity accuracy of different compression technologies and the dimensionality of the second authentication information.
100:基於壓縮信號的身分識別系統 100: Identity recognition system based on compressed signals
110:感測端 110: sensing end
111:設定模組 111: Setting module
112:量測模組 112: Measurement module
114:壓縮模組 114: Compression module
116:第一傳輸模組 116: The first transmission module
118:雜訊處理模組 118: Noise processing module
120:識別端 120: identification end
122:第一信號分離模組 122: The first signal separation module
124:識別模組 124: Identification Module
130:學習端 130: learning end
132:第二信號分離模組 132: The second signal separation module
134:機器學習模組 134: Machine Learning Module
136:第二傳輸模組 136: The second transmission module
ψ:主要特徵向量 ψ: main feature vector
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW108129847A TWI709148B (en) | 2019-08-21 | 2019-08-21 | Identity recognition system based on compression signal and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW108129847A TWI709148B (en) | 2019-08-21 | 2019-08-21 | Identity recognition system based on compression signal and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI709148B TWI709148B (en) | 2020-11-01 |
TW202109552A true TW202109552A (en) | 2021-03-01 |
Family
ID=74202275
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW108129847A TWI709148B (en) | 2019-08-21 | 2019-08-21 | Identity recognition system based on compression signal and method thereof |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI709148B (en) |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8850293B2 (en) * | 2011-12-06 | 2014-09-30 | Welch Allyn, Inc. | Wireless transmission reliability |
JP6873914B2 (en) * | 2015-07-03 | 2021-05-19 | インテル・コーポレーション | Devices and methods for data compression in wearable devices |
CN105827250B (en) * | 2016-03-16 | 2019-10-01 | 江苏大学 | A kind of power quality data compression reconfiguration method based on self-adapting dictionary study |
TWI610267B (en) * | 2016-08-03 | 2018-01-01 | 國立臺灣大學 | Compressive sensing system based on personalized basis and method thereof |
US10205466B2 (en) * | 2016-12-22 | 2019-02-12 | Mediatek Inc. | Electronic device with flexible processing of compressive sensing samples |
TWI657352B (en) * | 2017-07-21 | 2019-04-21 | 中華電信股份有限公司 | Three-dimensional capacitive wear human-computer interaction device and method thereof |
-
2019
- 2019-08-21 TW TW108129847A patent/TWI709148B/en active
Also Published As
Publication number | Publication date |
---|---|
TWI709148B (en) | 2020-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10467548B2 (en) | Method, apparatus and system for biometric identification | |
US9946942B2 (en) | Method, apparatus and system for biometric identification | |
US10398319B2 (en) | Adverse physiological events detection | |
EP3037036B1 (en) | Biometric authentication method and apparatus | |
Mullen et al. | Real-time neuroimaging and cognitive monitoring using wearable dry EEG | |
US9787676B2 (en) | Multi-modal biometric identification | |
WO2019109738A1 (en) | Login method and apparatus, and electronic device | |
EP2730216B1 (en) | Biosignal transmitter, biosignal receiver, and biosignal transmitting method | |
Deshpande et al. | Iot based real time ecg monitoring system using cypress wiced | |
US20190073605A1 (en) | Systems and methods for real-time neural command classification and task execution | |
CN108334766A (en) | Electronic device, unlocking method and related product | |
CN110226928A (en) | Atrial fibrillation is early with room and atrial fibrillation is with the poor recognition methods passed and device | |
CN110200626A (en) | A kind of vision induction motion sickness detection method based on ballot classifier | |
KR102342825B1 (en) | Electronic apparatus, signal processing method of thereof, vital signal measuring system, and non-transitory computer readable recording medium | |
WO2015129411A1 (en) | Individual identification device and individual identification method | |
US11481675B2 (en) | Identity recognition system based on compressed signals and method thereof | |
TWI709148B (en) | Identity recognition system based on compression signal and method thereof | |
US20230172467A1 (en) | System and method for monitoring a plurality of bio-signals, and a gateway device operable therein | |
Granados et al. | Towards workload-balanced, live deep learning analytics for confidentiality-aware IoT medical platforms | |
Laudato et al. | Combining rhythmic and morphological ECG features for automatic detection of atrial fibrillation: local and global prediction models | |
Gupta et al. | ECG signal analysis using emerging tools in current scenario of health informatics | |
Sathiya Rani et al. | A remote healthcare monitoring system for faster identification of cardiac abnormalities from compressed ECG using advanced data mining approach | |
KR101615480B1 (en) | Method and Apparatus for Automatic Threshold Control of Unsupervised Form for Real Time Detection of Spike in Time Series Data | |
Pusarla et al. | Automatic EEG Based Emotion Recognition Using Extreme Learning Machine | |
CN115105079B (en) | Electroencephalogram emotion recognition method based on self-attention mechanism and application thereof |