WO2018223489A1 - Intelligent input method and system based on bone conduction vibration signal propagation - Google Patents
Intelligent input method and system based on bone conduction vibration signal propagation Download PDFInfo
- Publication number
- WO2018223489A1 WO2018223489A1 PCT/CN2017/092769 CN2017092769W WO2018223489A1 WO 2018223489 A1 WO2018223489 A1 WO 2018223489A1 CN 2017092769 W CN2017092769 W CN 2017092769W WO 2018223489 A1 WO2018223489 A1 WO 2018223489A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- signal
- vibration
- vibration signal
- subspace
- processing
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/014—Hand-worn input/output arrangements, e.g. data gloves
-
- G—PHYSICS
- G04—HOROLOGY
- G04G—ELECTRONIC TIME-PIECES
- G04G21/00—Input or output devices integrated in time-pieces
- G04G21/02—Detectors of external physical values, e.g. temperature
- G04G21/025—Detectors of external physical values, e.g. temperature for measuring physiological data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24143—Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
Definitions
- the present invention relates to the field of smart wearable device technologies, and in particular, to an intelligent input method and system based on bone conduction vibration signal propagation.
- Smart watches are popular as a portable device. However, its small size and lightness also face unavoidable technical problems. Since the screen is small, only a few keys can be displayed at a time, and the display of other content is blocked, which is inefficient.
- text input traditional keyboard, text prediction and speech recognition. But the above methods are either not convenient enough or flexible enough. In the case of environmental noise, the speech recognition rate is difficult to achieve the desired effect, and in terms of protecting the user's password and other privacy, it is obviously not suitable to use the voice input in public.
- multi-country research teams have developed finger tracking recognition technology, the user experience of keyboard use has not been able to compare with the fast and comfortable text input of large-screen smartphones.
- the invention provides an intelligent input method based on bone conduction vibration signal propagation, comprising the following steps:
- the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
- the method comprises:
- Step S21 setting two thresholds of high and low for the processed signal
- Step S22 when the energy or zero-crossing rate of the signal exceeds the low threshold, the starting point of the tapping signal is initially determined, and when the energy or zero-crossing rate of the signal exceeds the high threshold, the true starting point of the tapping signal is determined; when the signal energy and the zero-crossing When the rate is lower than the low threshold, the signal end point is determined;
- step S23 the data from the start point to the end point is retained, and a vibration signal segment generated by the back of the taper is obtained.
- the S3. processing step includes:
- Step S31 normalizing the segmented signal, extracting the Mel frequency cepstral coefficient, and obtaining a signal characteristic
- Step S32 classifying the signal features using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position
- the step S32 includes:
- Step S321 collecting the signal features obtained in step S31 as training samples according to different tap positions, and classifying them;
- Step S322 calculating a center point of each type of the training sample by using a nearest center point algorithm
- Step S323 based on the random subspace, the class center points of the test sample and the training sample are compared in the subspace multiple times to obtain a plurality of classification results;
- Step S324 using a simple majority voting principle for the classification result, and setting a certain number of votes, and obtaining a final number of votes while obtaining a majority of the votes, and obtaining a final classification result;
- step S325 the successfully classified samples are classified into new training samples, and the new class center points of the new training samples are recalculated.
- step S321 the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and classified into n types according to the position, and each type is tapped m times. Wherein n and m are greater than or equal to 1;
- the class centers generated in each step S322 are randomly sampled T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training sample sample centers are compared one by one in the subspace.
- the designated part of the human body is the back of the hand;
- the vibration sensor is a piezoelectric ceramic vibration sensor
- the noise reduction processing on the vibration signal includes:
- Step S11 filtering the DC component and the low frequency noise by using a 20 Hz Butterworth high-pass filter
- step S12 high frequency noise is filtered out using 800 Hz low pass filtering.
- the invention also provides an intelligent input system based on bone conduction vibration signal propagation, comprising:
- the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
- the extraction module detects and extracts a vibration signal segment generated by striking a designated part of the human body by using a double threshold end point detection method
- the processing module extracts signal features and classifies signal locations based on the RMN algorithm.
- the extraction module includes:
- a first extraction module configured to set two thresholds of high and low for the processed signal
- the second extraction module is configured to determine the starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the low threshold, and determine the true starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the high threshold; The end of the signal is determined when the energy and zero-crossing rate are simultaneously below the low threshold;
- the third extraction module is configured to retain data from the start point to the end point, and obtain a vibration signal segment generated by the back of the taper.
- the processing module includes:
- a first processing module configured to normalize the segmented signal, extract a Mel frequency cepstral coefficient, and obtain a signal characteristic
- a second processing module configured to classify the signal feature using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position
- the second processing module includes:
- a first processing unit configured to collect the signal features obtained in step S31 as training samples according to different tap positions, and perform classification
- a second processing unit configured to calculate each type of center point of the training sample using a nearest center point algorithm
- a third processing unit configured to compare the class center points of the test sample and the training sample in the subspace multiple times based on the random subspace, to obtain a plurality of classification results
- a fourth processing unit configured to use a simple majority voting principle for the classification result, and set a certain number of votes, and obtain a final classification result if a majority of votes are obtained while a certain number of votes are obtained;
- the fifth processing unit is configured to classify the successfully classified samples into new training samples, and recalculate the new class center points of the new training samples.
- the opponent's back is tapped at different positions, and the signal feature of step S31 is acquired as a training sample, and the position is marked and according to the position.
- the difference is divided into n categories, each type is struck m times, where n and m are greater than or equal to 1;
- the class centers generated in each of the second processing units are randomly sampled by T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training samples are compared one by one in the subspace.
- the Euclidean distance of each class center point find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
- the designated part of the human body is the back of the hand;
- the vibration sensor is a piezoelectric ceramic vibration sensor
- performing noise reduction processing on the vibration signal includes:
- a first receiving module for filtering DC components and low frequency noise using a 20 Hz Butterworth high pass filter
- a second receiving module for filtering high frequency noise using 800 Hz low pass filtering.
- the invention has the beneficial effects that the invention not only solves the problem of the text input mode of the smart watch, but also achieves a high recognition rate, and can input quickly without losing the battery life of the smart watch.
- Figure 1 is a schematic diagram of the user typing on the virtual nine-square grid in the back of the hand;
- FIG. 2 is a schematic diagram of a piezoelectric ceramic vibration sensor
- FIG. 3 is a structural view of a piezoelectric ceramic vibration sensor
- Figure 4 is a waveform diagram of the original signal
- Figure 5 is an adaptive filtering diagram
- Figure 6 is a low pass filter diagram
- Figure 7 is a flow chart of the RNM algorithm.
- the present invention discloses an intelligent input method based on bone conduction vibration signal propagation, which includes the following steps:
- the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
- the designated part of the human body is the back of the hand
- the vibration sensor is a piezoelectric ceramic vibration sensor, and the smart device includes a smart watch, piezoelectric ceramic
- the porcelain vibration sensor is built into the smart watch.
- Figures 2 and 3 show the schematic and structure of the piezoelectric ceramic vibration sensor. Due to the piezoelectric effect, the internal polarity changes, and the voltage change is displayed externally, allowing the operator to strike the back of the hand and collect the vibration signal generated by the tap.
- Figure 4 shows the original signal waveform. It can be seen that the original signal collected has strong anti-interference ability and less noise.
- Figure 5 uses adaptive filtering and Figure 6 waveform diagram after low pass filtering. Low-pass filtering preserves more of the characteristics of the signal and works better for subsequent classification of slightly different vibration signals.
- the noise reduction processing on the vibration signal includes:
- Step S11 filtering the DC component and the low frequency noise by using a 20 Hz Butterworth high-pass filter
- step S12 high frequency noise is filtered out using 800 Hz low pass filtering.
- the method includes:
- Step S21 setting two thresholds of high and low for the processed signal
- Step S22 when the energy or zero-crossing rate of the signal exceeds the low threshold, the starting point of the tapping signal is initially determined, and when the energy or zero-crossing rate of the signal exceeds the high threshold, the true starting point of the tapping signal is determined; when the signal energy and the zero-crossing When the rate is lower than the low threshold, the signal end point is determined;
- step S23 only the data from the start point to the end point is retained, and a vibration signal segment generated by the back of the taper is obtained.
- extracting the signal feature includes: initializing the length of the starting point and the ending point in the training sample as the segmented signal, and normalizing the signal with the same length after the segmentation, using the formula: Where x is the vibration signal and n is the dimension of the signal.
- the normalized signal is extracted, the calculation amount is reduced, and most of the original signal is retained.
- the feature extracts the Mel frequency cepstral coefficient of the signal while retaining the characteristics of the time domain and the frequency domain.
- the S3. processing step includes:
- Step S31 normalizing the segmented signal, extracting the Mel frequency cepstral coefficient, and obtaining a signal characteristic
- Step S32 classifying the signal features using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position
- classifying the signal location based on the RRM algorithm includes: including:
- Step S321 according to different tap positions, the signal feature training obtained in step S31 is collected. Practice the samples and classify them into 9 categories according to the position of Jiugongge;
- Step S322 calculating a center point of each type of the training sample by using a nearest center point algorithm
- Step S323 based on the random subspace, the class center points of the test sample and the training sample are compared in the subspace multiple times to obtain a plurality of classification results;
- Step S324 using a simple majority voting principle for the classification result, and setting a certain number of votes, and obtaining a final number of votes while obtaining a majority of the votes, and obtaining a final classification result;
- step S325 the successfully classified samples are classified into new training samples, and the new class center points of the new training samples are recalculated.
- step S321 the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and divided into n categories according to the position, each type of tapping m times, wherein n and m are greater than or equal to 1;
- the class centers generated in each step S322 are randomly sampled T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training sample sample centers are compared one by one in the subspace.
- the invention also discloses an intelligent input system based on bone conduction vibration signal propagation, comprising:
- the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
- the extraction module detects and extracts a vibration signal segment generated by striking a designated part of the human body by using a double threshold end point detection method
- the processing module extracts signal features and classifies signal locations based on the RMN algorithm.
- the extraction module includes:
- a first extraction module configured to set two thresholds of high and low for the processed signal
- the second extraction module is configured to determine the starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the low threshold, and determine the true starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the high threshold; The end of the signal is determined when the energy and zero-crossing rate are simultaneously below the low threshold;
- the third extraction module is configured to retain only the data from the start point to the end point, and the rest is processed as a segment to obtain a vibration signal segment generated by the back of the taper.
- the processing module includes:
- a first processing module configured to normalize the segmented signal, extract a Mel frequency cepstral coefficient, and obtain a signal characteristic
- a second processing module configured to classify the signal feature using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position
- the second processing module includes:
- a first processing unit configured to collect the signal features obtained in step S31 as training samples according to different tap positions, and perform classification
- a second processing unit configured to calculate each type of center point of the training sample using a nearest center point algorithm
- a third processing unit configured to compare the class center points of the test sample and the training sample in the subspace multiple times based on the random subspace, to obtain a plurality of classification results
- a fourth processing unit configured to use a simple majority voting principle for the classification result, and set a certain number of votes, and obtain a final classification result if a majority of votes are obtained while a certain number of votes are obtained;
- the fifth processing unit is configured to classify the successfully classified samples into new training samples, and recalculate the new class center points of the new training samples.
- the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and divided into n categories according to different positions, each type of tapping m times, where n and m are greater than Or equal to 1;
- the class centers generated in each of the second processing units are randomly sampled by T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training samples are compared one by one in the subspace.
- the Euclidean distance of each class center point find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
- the designated part of the human body is the back of the hand;
- the vibration sensor is a piezoelectric ceramic vibration sensor.
- performing noise reduction processing on the vibration signal includes:
- a first receiving module for filtering DC components and low frequency noise using a 20 Hz Butterworth high pass filter
- a second receiving module for filtering high frequency noise using 800 Hz low pass filtering.
- the invention embeds a tiny thin piezoelectric sensor on a smart watch, which can realize the conversion of mechanical energy to electric energy.
- a nine-square grid keyboard is virtualized.
- the piezoelectric sensor receives mechanical wave signals with different multipath propagations at a time. This mechanical wave signal is spread on the one hand by the voice signal into the air, on the other hand in the interior of the hand, and the so-called bone conduction.
- This part of the mechanical wave signal is not affected by the environmental noise, and can be better accepted by the piezoelectric sensor, and converted into an electrical signal processed by the controller of the smart watch. Because the multipath effects of mechanical waves generated by different grids are different, the letter received by the smart watch The number is different. Using this difference, combined with the classification algorithm of machine learning, you can classify each button of the nine squares. Thereby, a smart watch text input method and system based on the hand back bone conduction technology can be realized.
- the invention adopts a piezoelectric ceramic vibration sensor built in a smart watch, and the vibration of the back of the tapper is used as the text input mode of the smart watch for the first time, and the back of the hand is used as a virtual large screen of the small screen of the smart watch, which facilitates text input; It is the vibration signal after multipath propagation in the human hand behind the percussion, strong anti-interference, and noise reduction, segmentation, normalization, extraction of the Mel frequency cepstral coefficient, etc.
- the RNM algorithm classifies and its recognition rate reaches 92%.
- the algorithm complexity used here is also linear, so fast input of text can be achieved.
- the piezoelectric ceramic vibration sensor consumes a very low amount of electricity and does not significantly reduce the life time of the smart watch.
- the invention not only solves the problem of the text input mode of the smart watch, but also achieves a high recognition rate, and can input quickly without losing the life time of the smart watch.
- the hardware of the invention is low, the system is simple, the use is convenient, and the input of the smart watch based on the bone conduction vibration signal propagation of the back of the hand can be realized simply and quickly.
Abstract
An intelligent input method and system based on bone conduction vibration signal propagation. The intelligent input method comprises: S1. a receiving step, an intelligent device receiving a vibration signal by using a vibration sensor, and performing noise reduction processing on the vibration signal; S2. an extraction step, detecting, by means of a double-threshold endpoint detection method, and extracting a vibration signal segment generated by knocking a specified part of a human body; and S3. a processing step, extracting signal features, and classifying signal positions based on an RNM algorithm. The beneficial effects are that the problem of a text input mode of an intelligent watch can not only be solved, but also a high recognition rate can be achieved, and rapid inputting can be carried out without losing the battery life of the intelligent watch.
Description
本发明涉及智能可穿戴设备技术领域,尤其涉及基于骨传导振动信号传播的智能输入方法及系统。The present invention relates to the field of smart wearable device technologies, and in particular, to an intelligent input method and system based on bone conduction vibration signal propagation.
近几年来,我们见证着智能可穿戴设备的快速发展,智能手环、智能耳机、智能眼镜、智能头盔和智能手表等可穿戴设备在人们日常生活中日益流行,为人们所接受。在智能手机的创新空间不断缩小以及市场增量接近饱和的情况下,智能可穿戴设备作为移动终端产业的下一个热点已被市场广泛认同,被预言为即将取代手机的发明。In recent years, we have witnessed the rapid development of smart wearable devices. Wearable devices such as smart bracelets, smart headphones, smart glasses, smart helmets and smart watches are becoming more and more popular in people's daily lives. As the innovation space of smartphones continues to shrink and the market is approaching saturation, smart wearable devices have been widely recognized as the next hot spot in the mobile terminal industry, and are predicted to be the inventions that will replace mobile phones.
智能手表作为一种便携式设备而流行。但是,它的小巧和轻便也面临不可规避的技术问题。由于屏幕较小,每次只能显示若干个键,并且会挡住其他内容的显示,效率很低。目前智能手表实现文本输入的方式主要有三种:传统键盘、文本预测和语音识别。但以上方式要么不够方便灵活,要么不够安全。在有环境噪声情况下语音识别率很难达到理想效果,并且对于保护用户密码及其他隐私方面,在公共场合使用语音输入是明显不适合的。尽管多国科研团队开发出手指跟踪识别技术,但用户对于键盘使用的体验始终无法与大屏幕智能手机有效快捷舒适的文本输入对比,比如2016年美国华盛顿大学的科研团队实现了毫米级的精准手指跟踪技术,让用户在移动设备上实现基于声波定位的手写输入,但手写输入始终还是太慢,不能满足人们的需求。想要扩大智能手表的市场需求,就必须深度挖掘其应用并解决文本输入问题。Smart watches are popular as a portable device. However, its small size and lightness also face unavoidable technical problems. Since the screen is small, only a few keys can be displayed at a time, and the display of other content is blocked, which is inefficient. At present, there are three main ways for smart watches to implement text input: traditional keyboard, text prediction and speech recognition. But the above methods are either not convenient enough or flexible enough. In the case of environmental noise, the speech recognition rate is difficult to achieve the desired effect, and in terms of protecting the user's password and other privacy, it is obviously not suitable to use the voice input in public. Although multi-country research teams have developed finger tracking recognition technology, the user experience of keyboard use has not been able to compare with the fast and comfortable text input of large-screen smartphones. For example, the research team at the University of Washington in 2016 realized millimeter-level precise finger tracking. Technology allows users to implement handwriting input based on sonic positioning on mobile devices, but handwriting input is still too slow to meet people's needs. In order to expand the market demand for smart watches, it is necessary to dig deep into their applications and solve text input problems.
发明内容Summary of the invention
本发明提供了一种基于骨传导振动信号传播的智能输入方法,包括如下步骤:The invention provides an intelligent input method based on bone conduction vibration signal propagation, comprising the following steps:
S1.接收步骤,智能设备用振动传感器接收振动信号,并对振动信号进行降噪处理;S1. receiving step, the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
S2.提取步骤,利用双门限端点检测法检测并提取由于敲击人体指定部位产生的振动信号片段;S2. an extraction step of detecting and extracting a vibration signal segment generated by striking a designated part of the human body by using a double threshold endpoint detection method;
S3.处理步骤,提取信号特征,基于RNM算法来分类信号位置。S3. Processing steps, extracting signal features, and classifying signal locations based on the RMN algorithm.
作为本发明的进一步改进,在所述S2.提取步骤中包括:
As a further improvement of the present invention, in the S2. extraction step, the method comprises:
步骤S21,对处理的信号设置高、低两个门限;Step S21, setting two thresholds of high and low for the processed signal;
步骤S22,当信号的能量或过零率超越低门限,初步确定敲击信号起点,而当信号的能量或过零率突破高门限,才确定敲击信号真正的起点;当信号能量和过零率同时低于低门限时,确定信号终点;Step S22, when the energy or zero-crossing rate of the signal exceeds the low threshold, the starting point of the tapping signal is initially determined, and when the energy or zero-crossing rate of the signal exceeds the high threshold, the true starting point of the tapping signal is determined; when the signal energy and the zero-crossing When the rate is lower than the low threshold, the signal end point is determined;
步骤S23,保留起点至终点的数据,得到由敲击手背产生的振动信号片段。In step S23, the data from the start point to the end point is retained, and a vibration signal segment generated by the back of the taper is obtained.
作为本发明的进一步改进,所述S3.处理步骤中包括:As a further improvement of the present invention, the S3. processing step includes:
步骤S31,对切段信号进行归一化,提取梅尔频率倒频谱系数,得到信号特征;Step S31, normalizing the segmented signal, extracting the Mel frequency cepstral coefficient, and obtaining a signal characteristic;
步骤S32,对信号特征使用基于随机子空间和最近中心点算法的RNM算法进行分类,进而判断出敲击位置;Step S32, classifying the signal features using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position;
所述步骤S32包括:The step S32 includes:
步骤S321,根据敲击位置的不同,采集步骤S31得到的信号特征作训练样本,并进行分类;Step S321, collecting the signal features obtained in step S31 as training samples according to different tap positions, and classifying them;
步骤S322,使用最近中心点算法计算训练样本的每一类中心点;Step S322, calculating a center point of each type of the training sample by using a nearest center point algorithm;
步骤S323,基于随机子空间,测试样本与训练样本的类中心点多次在子空间对比,得到多个分类结果;Step S323, based on the random subspace, the class center points of the test sample and the training sample are compared in the subspace multiple times to obtain a plurality of classification results;
步骤S324,对分类结果使用简单多数投票原则,并且设置一定票数比例,获得多数票同时达到一定的票数的情况下得到最终分类结果;Step S324, using a simple majority voting principle for the classification result, and setting a certain number of votes, and obtaining a final number of votes while obtaining a majority of the votes, and obtaining a final classification result;
步骤S325,将分类成功的样本归入新的训练样本,重新计算新训练样本的新类中心点。In step S325, the successfully classified samples are classified into new training samples, and the new class center points of the new training samples are recalculated.
作为本发明的进一步改进,在所述步骤S321中,对手背不同位置敲击,采集得到步骤S31的信号特征作为训练样本,标记位置并根据位置的不同分成n类,每类敲击m次,其中n与m大于或等于1;As a further improvement of the present invention, in the step S321, the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and classified into n types according to the position, and each type is tapped m times. Wherein n and m are greater than or equal to 1;
在所述步骤S323中,将步骤S322中每一次产生的类中心分别随机抽样T个属性,重复以上操作Q次,得到Q个子空间,在子空间里逐一对比测试样本与训练样本的各个类中心点的欧式距离,找到最近中心点,即得到Q个子空间分类的结果,其中T、Q大于1。In the step S323, the class centers generated in each step S322 are randomly sampled T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training sample sample centers are compared one by one in the subspace. The Euclidean distance of the point, find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
作为本发明的进一步改进,在所述S2.提取步骤中,人体指定部位为手背;As a further improvement of the present invention, in the S2. extraction step, the designated part of the human body is the back of the hand;
振动传感器为压电陶瓷振动传感器;The vibration sensor is a piezoelectric ceramic vibration sensor;
所述S1.接收步骤中,对振动信号进行降噪处理包括:In the S1. receiving step, the noise reduction processing on the vibration signal includes:
步骤S11,使用20Hz的巴特沃斯高通滤波器滤掉直流分量和低频噪声;
Step S11, filtering the DC component and the low frequency noise by using a 20 Hz Butterworth high-pass filter;
步骤S12,使用800Hz低通滤波滤掉高频噪声。In step S12, high frequency noise is filtered out using 800 Hz low pass filtering.
本发明还提供了一种基于骨传导振动信号传播的智能输入系统,包括:The invention also provides an intelligent input system based on bone conduction vibration signal propagation, comprising:
接收模块,智能设备用振动传感器接收振动信号,并对振动信号进行降噪处理;Receiving module, the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
提取模块,利用双门限端点检测法检测并提取由于敲击人体指定部位产生的振动信号片段;The extraction module detects and extracts a vibration signal segment generated by striking a designated part of the human body by using a double threshold end point detection method;
处理模块,提取信号特征,基于RNM算法来分类信号位置。The processing module extracts signal features and classifies signal locations based on the RMN algorithm.
作为本发明的进一步改进,在所述提取模块中包括:As a further improvement of the present invention, the extraction module includes:
第一提取模块,用于对处理的信号设置高、低两个门限;a first extraction module, configured to set two thresholds of high and low for the processed signal;
第二提取模块,用于当信号的能量或过零率超越低门限,初步确定敲击信号起点,而当信号的能量或过零率突破高门限,才确定敲击信号真正的起点;当信号能量和过零率同时低于低门限时,确定信号终点;The second extraction module is configured to determine the starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the low threshold, and determine the true starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the high threshold; The end of the signal is determined when the energy and zero-crossing rate are simultaneously below the low threshold;
第三提取模块,用于保留起点至终点的数据,得到由敲击手背产生的振动信号片段。The third extraction module is configured to retain data from the start point to the end point, and obtain a vibration signal segment generated by the back of the taper.
作为本发明的进一步改进,所述处理模块中包括:As a further improvement of the present invention, the processing module includes:
第一处理模块,用于对切段信号进行归一化,提取梅尔频率倒频谱系数,得到信号特征;a first processing module, configured to normalize the segmented signal, extract a Mel frequency cepstral coefficient, and obtain a signal characteristic;
第二处理模块,用于对信号特征使用基于随机子空间和最近中心点算法的RNM算法进行分类,进而判断出敲击位置;a second processing module, configured to classify the signal feature using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position;
所述第二处理模块包括:The second processing module includes:
第一处理单元,用于根据敲击位置的不同,采集步骤S31得到的信号特征作训练样本,并进行分类;a first processing unit, configured to collect the signal features obtained in step S31 as training samples according to different tap positions, and perform classification;
第二处理单元,用于使用最近中心点算法计算训练样本的每一类中心点;a second processing unit, configured to calculate each type of center point of the training sample using a nearest center point algorithm;
第三处理单元,用于基于随机子空间,测试样本与训练样本的类中心点多次在子空间对比,得到多个分类结果;a third processing unit, configured to compare the class center points of the test sample and the training sample in the subspace multiple times based on the random subspace, to obtain a plurality of classification results;
第四处理单元,用于对分类结果使用简单多数投票原则,并且设置一定票数比例,获得多数票同时达到一定的票数的情况下得到最终分类结果;a fourth processing unit, configured to use a simple majority voting principle for the classification result, and set a certain number of votes, and obtain a final classification result if a majority of votes are obtained while a certain number of votes are obtained;
第五处理单元,用于将分类成功的样本归入新的训练样本,重新计算新训练样本的新类中心点。The fifth processing unit is configured to classify the successfully classified samples into new training samples, and recalculate the new class center points of the new training samples.
作为本发明的进一步改进,在所述第一处理单元中,对手背不同位置敲击,采集得到步骤S31的信号特征作为训练样本,标记位置并根据位置
的不同分成n类,每类敲击m次,其中n与m大于或等于1;As a further improvement of the present invention, in the first processing unit, the opponent's back is tapped at different positions, and the signal feature of step S31 is acquired as a training sample, and the position is marked and according to the position.
The difference is divided into n categories, each type is struck m times, where n and m are greater than or equal to 1;
在所述第三处理单元中,将第二处理单元中每一次产生的类中心分别随机抽样T个属性,重复以上操作Q次,得到Q个子空间,在子空间里逐一对比测试样本与训练样本的各个类中心点的欧式距离,找到最近中心点,即得到Q个子空间分类的结果,其中T、Q大于1。In the third processing unit, the class centers generated in each of the second processing units are randomly sampled by T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training samples are compared one by one in the subspace. The Euclidean distance of each class center point, find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
作为本发明的进一步改进,As a further improvement of the present invention,
在所述提取模块中,人体指定部位为手背;In the extraction module, the designated part of the human body is the back of the hand;
振动传感器为压电陶瓷振动传感器;The vibration sensor is a piezoelectric ceramic vibration sensor;
所述接收模块中,对振动信号进行降噪处理包括:In the receiving module, performing noise reduction processing on the vibration signal includes:
第一接收模块,用于使用20Hz的巴特沃斯高通滤波器滤掉直流分量和低频噪声;a first receiving module for filtering DC components and low frequency noise using a 20 Hz Butterworth high pass filter;
第二接收模块,用于使用800Hz低通滤波滤掉高频噪声。A second receiving module for filtering high frequency noise using 800 Hz low pass filtering.
本发明的有益效果是:本发明不仅解决智能手表文本输入方式的问题,还能达到高识别率,并且可以快速进行输入,也不损耗智能手表的续航时间。The invention has the beneficial effects that the invention not only solves the problem of the text input mode of the smart watch, but also achieves a high recognition rate, and can input quickly without losing the battery life of the smart watch.
图1是用户在手背敲击虚拟九宫格打字示意图;Figure 1 is a schematic diagram of the user typing on the virtual nine-square grid in the back of the hand;
图2是压电陶瓷振动传感器的原理图;2 is a schematic diagram of a piezoelectric ceramic vibration sensor;
图3是压电陶瓷振动传感器的结构图;3 is a structural view of a piezoelectric ceramic vibration sensor;
图4是原始信号波形图;Figure 4 is a waveform diagram of the original signal;
图5是自适应滤波图;Figure 5 is an adaptive filtering diagram;
图6是低通滤波图;Figure 6 is a low pass filter diagram;
图7是RNM算法流程图。Figure 7 is a flow chart of the RNM algorithm.
如图1所示,本发明公开了一种基于骨传导振动信号传播的智能输入方法,包括如下步骤:As shown in FIG. 1, the present invention discloses an intelligent input method based on bone conduction vibration signal propagation, which includes the following steps:
S1.接收步骤,智能设备用振动传感器接收振动信号,并对振动信号进行降噪处理;S1. receiving step, the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
S2.提取步骤,利用双门限端点检测法检测并提取由于敲击人体指定部位产生的振动信号片段;S2. an extraction step of detecting and extracting a vibration signal segment generated by striking a designated part of the human body by using a double threshold endpoint detection method;
S3.处理步骤,提取信号特征,基于RNM算法来分类信号位置。S3. Processing steps, extracting signal features, and classifying signal locations based on the RMN algorithm.
在所述S2.提取步骤中,人体指定部位为手背;In the S2. extraction step, the designated part of the human body is the back of the hand;
振动传感器为压电陶瓷振动传感器,智能设备包括智能手表,压电陶
瓷振动传感器内置在智能手表里,图2、3为压电陶瓷振动传感器的原理图和结构图。因压电效应使内部极性产生变化,对外显示出电压的变化,让操作者敲击手背,采集敲击所产生的振动信号。The vibration sensor is a piezoelectric ceramic vibration sensor, and the smart device includes a smart watch, piezoelectric ceramic
The porcelain vibration sensor is built into the smart watch. Figures 2 and 3 show the schematic and structure of the piezoelectric ceramic vibration sensor. Due to the piezoelectric effect, the internal polarity changes, and the voltage change is displayed externally, allowing the operator to strike the back of the hand and collect the vibration signal generated by the tap.
图4为原始信号波形图,可以看出所采集的原始信号对外界抗干扰能力强,噪声较少。图5使用自适应滤波和图6使用低通滤波之后的波形图。低通滤波保留了信号更多的特征,对之后分类微小差别的振动信号的效果更好。Figure 4 shows the original signal waveform. It can be seen that the original signal collected has strong anti-interference ability and less noise. Figure 5 uses adaptive filtering and Figure 6 waveform diagram after low pass filtering. Low-pass filtering preserves more of the characteristics of the signal and works better for subsequent classification of slightly different vibration signals.
所述S1.接收步骤中,对振动信号进行降噪处理包括:In the S1. receiving step, the noise reduction processing on the vibration signal includes:
步骤S11,使用20Hz的巴特沃斯高通滤波器滤掉直流分量和低频噪声;Step S11, filtering the DC component and the low frequency noise by using a 20 Hz Butterworth high-pass filter;
步骤S12,使用800Hz低通滤波滤掉高频噪声。In step S12, high frequency noise is filtered out using 800 Hz low pass filtering.
在所述S2.提取步骤中包括:In the S2. extraction step, the method includes:
步骤S21,对处理的信号设置高、低两个门限;Step S21, setting two thresholds of high and low for the processed signal;
步骤S22,当信号的能量或过零率超越低门限,初步确定敲击信号起点,而当信号的能量或过零率突破高门限,才确定敲击信号真正的起点;当信号能量和过零率同时低于低门限时,确定信号终点;Step S22, when the energy or zero-crossing rate of the signal exceeds the low threshold, the starting point of the tapping signal is initially determined, and when the energy or zero-crossing rate of the signal exceeds the high threshold, the true starting point of the tapping signal is determined; when the signal energy and the zero-crossing When the rate is lower than the low threshold, the signal end point is determined;
步骤S23,只保留起点至终点的数据,得到由敲击手背产生的振动信号片段。In step S23, only the data from the start point to the end point is retained, and a vibration signal segment generated by the back of the taper is obtained.
在S3.处理步骤中,提取信号特征包括:将初始化训练样本中起始点和终点最长的作为切段信号统一的长度,对切段后长度一致的信号进行归一化,使用公式为:其中x是振动信号,n是信号的维度。对归一化后的信号进行特征提取,减少计算量,并保留原信号大部分信息,特征提取的是信号的梅尔频率倒频谱系数,同时保留了时域和频域的特征。In the S3. processing step, extracting the signal feature includes: initializing the length of the starting point and the ending point in the training sample as the segmented signal, and normalizing the signal with the same length after the segmentation, using the formula: Where x is the vibration signal and n is the dimension of the signal. The normalized signal is extracted, the calculation amount is reduced, and most of the original signal is retained. The feature extracts the Mel frequency cepstral coefficient of the signal while retaining the characteristics of the time domain and the frequency domain.
所述S3.处理步骤中包括:The S3. processing step includes:
步骤S31,对切段信号进行归一化,提取梅尔频率倒频谱系数,得到信号特征;Step S31, normalizing the segmented signal, extracting the Mel frequency cepstral coefficient, and obtaining a signal characteristic;
步骤S32,对信号特征使用基于随机子空间和最近中心点算法的RNM算法进行分类,进而判断出敲击位置;Step S32, classifying the signal features using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position;
如图7所示,在所述步骤S32中,基于RNM算法来分类信号位置包括:包括:As shown in FIG. 7, in the step S32, classifying the signal location based on the RRM algorithm includes: including:
步骤S321,根据敲击位置的不同,采集步骤S31得到的信号特征作训
练样本,并进行分类(按照九宫格位置分成9类);Step S321, according to different tap positions, the signal feature training obtained in step S31 is collected.
Practice the samples and classify them into 9 categories according to the position of Jiugongge;
步骤S322,使用最近中心点算法计算训练样本的每一类中心点;Step S322, calculating a center point of each type of the training sample by using a nearest center point algorithm;
步骤S323,基于随机子空间,测试样本与训练样本的类中心点多次在子空间对比,得到多个分类结果;Step S323, based on the random subspace, the class center points of the test sample and the training sample are compared in the subspace multiple times to obtain a plurality of classification results;
步骤S324,对分类结果使用简单多数投票原则,并且设置一定票数比例,获得多数票同时达到一定的票数的情况下得到最终分类结果;Step S324, using a simple majority voting principle for the classification result, and setting a certain number of votes, and obtaining a final number of votes while obtaining a majority of the votes, and obtaining a final classification result;
步骤S325,将分类成功的样本归入新的训练样本,重新计算新训练样本的新类中心点。In step S325, the successfully classified samples are classified into new training samples, and the new class center points of the new training samples are recalculated.
在所述步骤S321中,对手背不同位置敲击,采集得到步骤S31的信号特征作为训练样本,标记位置并根据位置的不同分成n类,每类敲击m次,其中n与m大于或等于1;In the step S321, the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and divided into n categories according to the position, each type of tapping m times, wherein n and m are greater than or equal to 1;
在所述步骤S323中,将步骤S322中每一次产生的类中心分别随机抽样T个属性,重复以上操作Q次,得到Q个子空间,在子空间里逐一对比测试样本与训练样本的各个类中心点的欧式距离,找到最近中心点,即得到Q个子空间分类的结果,其中T、Q大于1。In the step S323, the class centers generated in each step S322 are randomly sampled T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training sample sample centers are compared one by one in the subspace. The Euclidean distance of the point, find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
本发明还公开了一种基于骨传导振动信号传播的智能输入系统,包括:The invention also discloses an intelligent input system based on bone conduction vibration signal propagation, comprising:
接收模块,智能设备用振动传感器接收振动信号,并对振动信号进行降噪处理;Receiving module, the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;
提取模块,利用双门限端点检测法检测并提取由于敲击人体指定部位产生的振动信号片段;The extraction module detects and extracts a vibration signal segment generated by striking a designated part of the human body by using a double threshold end point detection method;
处理模块,提取信号特征,基于RNM算法来分类信号位置。The processing module extracts signal features and classifies signal locations based on the RMN algorithm.
在所述提取模块中包括:The extraction module includes:
第一提取模块,用于对处理的信号设置高、低两个门限;a first extraction module, configured to set two thresholds of high and low for the processed signal;
第二提取模块,用于当信号的能量或过零率超越低门限,初步确定敲击信号起点,而当信号的能量或过零率突破高门限,才确定敲击信号真正的起点;当信号能量和过零率同时低于低门限时,确定信号终点;The second extraction module is configured to determine the starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the low threshold, and determine the true starting point of the tapping signal when the energy or zero-crossing rate of the signal exceeds the high threshold; The end of the signal is determined when the energy and zero-crossing rate are simultaneously below the low threshold;
第三提取模块,用于只保留起点至终点的数据,其余作切段处理,得到由敲击手背产生的振动信号片段。The third extraction module is configured to retain only the data from the start point to the end point, and the rest is processed as a segment to obtain a vibration signal segment generated by the back of the taper.
所述处理模块中包括:The processing module includes:
第一处理模块,用于对切段信号进行归一化,提取梅尔频率倒频谱系数,得到信号特征;a first processing module, configured to normalize the segmented signal, extract a Mel frequency cepstral coefficient, and obtain a signal characteristic;
第二处理模块,用于对信号特征使用基于随机子空间和最近中心点算法的RNM算法进行分类,进而判断出敲击位置;
a second processing module, configured to classify the signal feature using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position;
所述第二处理模块包括:The second processing module includes:
第一处理单元,用于根据敲击位置的不同,采集步骤S31得到的信号特征作训练样本,并进行分类;a first processing unit, configured to collect the signal features obtained in step S31 as training samples according to different tap positions, and perform classification;
第二处理单元,用于使用最近中心点算法计算训练样本的每一类中心点;a second processing unit, configured to calculate each type of center point of the training sample using a nearest center point algorithm;
第三处理单元,用于基于随机子空间,测试样本与训练样本的类中心点多次在子空间对比,得到多个分类结果;a third processing unit, configured to compare the class center points of the test sample and the training sample in the subspace multiple times based on the random subspace, to obtain a plurality of classification results;
第四处理单元,用于对分类结果使用简单多数投票原则,并且设置一定票数比例,获得多数票同时达到一定的票数的情况下得到最终分类结果;a fourth processing unit, configured to use a simple majority voting principle for the classification result, and set a certain number of votes, and obtain a final classification result if a majority of votes are obtained while a certain number of votes are obtained;
第五处理单元,用于将分类成功的样本归入新的训练样本,重新计算新训练样本的新类中心点。The fifth processing unit is configured to classify the successfully classified samples into new training samples, and recalculate the new class center points of the new training samples.
在所述第一处理单元中,对手背不同位置敲击,采集得到步骤S31的信号特征作为训练样本,标记位置并根据位置的不同分成n类,每类敲击m次,其中n与m大于或等于1;In the first processing unit, the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and divided into n categories according to different positions, each type of tapping m times, where n and m are greater than Or equal to 1;
在所述第三处理单元中,将第二处理单元中每一次产生的类中心分别随机抽样T个属性,重复以上操作Q次,得到Q个子空间,在子空间里逐一对比测试样本与训练样本的各个类中心点的欧式距离,找到最近中心点,即得到Q个子空间分类的结果,其中T、Q大于1。In the third processing unit, the class centers generated in each of the second processing units are randomly sampled by T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training samples are compared one by one in the subspace. The Euclidean distance of each class center point, find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
在所述提取模块中,人体指定部位为手背;振动传感器为压电陶瓷振动传感器。In the extraction module, the designated part of the human body is the back of the hand; the vibration sensor is a piezoelectric ceramic vibration sensor.
所述接收模块中,对振动信号进行降噪处理包括:In the receiving module, performing noise reduction processing on the vibration signal includes:
第一接收模块,用于使用20Hz的巴特沃斯高通滤波器滤掉直流分量和低频噪声;a first receiving module for filtering DC components and low frequency noise using a 20 Hz Butterworth high pass filter;
第二接收模块,用于使用800Hz低通滤波滤掉高频噪声。A second receiving module for filtering high frequency noise using 800 Hz low pass filtering.
本发明在智能手表上嵌入微小细薄的压电传感器,这种压电传感器可以实现机械能到电能的转化。在手背上虚拟一个九宫格键盘,当手指敲击不同位置的格子时,机械波会四面八方地传播出去,碰到物体后反射回来。所以,基于机械波的广播性质,压电传感器一次会接收到带有不同多径传播的机械波信号。这种机械波信号一方面通过语音信号散播到空气中,另一方面在手的内部传播,及所谓的骨传导。这部分机械波信号不受环境噪声的影响,能较好地被压电传感器接受,转化成电信号由智能手表的控制器处理。因为不同格子产生的机械波多径效应不同,智能手表接收到的信
号就有所不同,利用这种差异,结合机器学习的分类算法,可以分类出九宫格的每一个按键。由此,可以实现基于手背骨传导技术的智能手表文本输入方法及系统。The invention embeds a tiny thin piezoelectric sensor on a smart watch, which can realize the conversion of mechanical energy to electric energy. On the back of the hand, a nine-square grid keyboard is virtualized. When the finger taps on the grid at different positions, the mechanical waves will spread out in all directions, and will be reflected back after touching the object. Therefore, based on the broadcast nature of mechanical waves, the piezoelectric sensor receives mechanical wave signals with different multipath propagations at a time. This mechanical wave signal is spread on the one hand by the voice signal into the air, on the other hand in the interior of the hand, and the so-called bone conduction. This part of the mechanical wave signal is not affected by the environmental noise, and can be better accepted by the piezoelectric sensor, and converted into an electrical signal processed by the controller of the smart watch. Because the multipath effects of mechanical waves generated by different grids are different, the letter received by the smart watch
The number is different. Using this difference, combined with the classification algorithm of machine learning, you can classify each button of the nine squares. Thereby, a smart watch text input method and system based on the hand back bone conduction technology can be realized.
本发明在智能手表内置压电陶瓷振动传感器,首次将采集到的敲击手背的振动作为智能手表的文本输入方式,将手背作为智能手表小屏幕的虚拟大屏幕,便于实现文本输入;所采集的是敲击手背后在人手上多径传播后的振动信号,抗干扰性强,并且对信号进行降噪,切段,归一化,提取梅尔频率倒频谱系数等处理后,再使用发明的RNM算法进行分类,其识别率达到92%。此处所使用的算法复杂度也只是线性阶的,所以可以实现文本的快速输入。此外,压电陶瓷振动传感器耗电量极底,不会大幅减少智能手表的续航时间。The invention adopts a piezoelectric ceramic vibration sensor built in a smart watch, and the vibration of the back of the tapper is used as the text input mode of the smart watch for the first time, and the back of the hand is used as a virtual large screen of the small screen of the smart watch, which facilitates text input; It is the vibration signal after multipath propagation in the human hand behind the percussion, strong anti-interference, and noise reduction, segmentation, normalization, extraction of the Mel frequency cepstral coefficient, etc. The RNM algorithm classifies and its recognition rate reaches 92%. The algorithm complexity used here is also linear, so fast input of text can be achieved. In addition, the piezoelectric ceramic vibration sensor consumes a very low amount of electricity and does not significantly reduce the life time of the smart watch.
本发明不仅解决智能手表文本输入方式的问题,还能达到高识别率,并且可以快速进行输入,也不损耗智能手表的续航时间。The invention not only solves the problem of the text input mode of the smart watch, but also achieves a high recognition rate, and can input quickly without losing the life time of the smart watch.
本发明的硬件成低,系统简单,使用方便,能够简单快速的实现基于手背的骨传导振动信号传播的智能手表的输入。The hardware of the invention is low, the system is simple, the use is convenient, and the input of the smart watch based on the bone conduction vibration signal propagation of the back of the hand can be realized simply and quickly.
以上内容是结合具体的优选实施方式对本发明所作的进一步详细说明,不能认定本发明的具体实施只局限于这些说明。对于本发明所属技术领域的普通技术人员来说,在不脱离本发明构思的前提下,还可以做出若干简单推演或替换,都应当视为属于本发明的保护范围。
The above is a further detailed description of the present invention in connection with the specific preferred embodiments, and the specific embodiments of the present invention are not limited to the description. It will be apparent to those skilled in the art that the present invention may be made without departing from the spirit and scope of the invention.
Claims (10)
- 一种基于骨传导振动信号传播的智能输入方法,其特征在于,包括如下步骤:An intelligent input method based on bone conduction vibration signal propagation, characterized in that it comprises the following steps:S1.接收步骤,智能设备用振动传感器接收振动信号,并对振动信号进行降噪处理;S1. receiving step, the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;S2.提取步骤,利用双门限端点检测法检测并提取由于敲击人体指定部位产生的振动信号片段;S2. an extraction step of detecting and extracting a vibration signal segment generated by striking a designated part of the human body by using a double threshold endpoint detection method;S3.处理步骤,提取信号特征,基于RNM算法来分类信号位置。S3. Processing steps, extracting signal features, and classifying signal locations based on the RMN algorithm.
- 根据权利要求1所述的智能输入方法,其特征在于,在所述S2.提取步骤中包括:The intelligent input method according to claim 1, wherein in the S2. extracting step, the method comprises:步骤S21,对处理的信号设置高、低两个门限;Step S21, setting two thresholds of high and low for the processed signal;步骤S22,当信号的能量或过零率超越低门限,初步确定敲击信号起点,而当信号的能量或过零率突破高门限,才确定敲击信号真正的起点;当信号能量和过零率同时低于低门限时,确定信号终点;Step S22, when the energy or zero-crossing rate of the signal exceeds the low threshold, the starting point of the tapping signal is initially determined, and when the energy or zero-crossing rate of the signal exceeds the high threshold, the true starting point of the tapping signal is determined; when the signal energy and the zero-crossing When the rate is lower than the low threshold, the signal end point is determined;步骤S23,保留起点至终点的数据,得到由敲击手背产生的振动信号片段。In step S23, the data from the start point to the end point is retained, and a vibration signal segment generated by the back of the taper is obtained.
- 根据权利要求1所述的智能输入方法,其特征在于,所述S3.处理步骤中包括:The intelligent input method according to claim 1, wherein the S3. processing step comprises:步骤S31,对切段信号进行归一化,提取梅尔频率倒频谱系数,得到信号特征;Step S31, normalizing the segmented signal, extracting the Mel frequency cepstral coefficient, and obtaining a signal characteristic;步骤S32,对信号特征使用基于随机子空间和最近中心点算法的RNM算法进行分类,进而判断出敲击位置;Step S32, classifying the signal features using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position;所述步骤S32包括:The step S32 includes:步骤S321,根据敲击位置的不同,采集步骤S31得到的信号特征作训练样本,并进行分类;Step S321, collecting the signal features obtained in step S31 as training samples according to different tap positions, and classifying them;步骤S322,使用最近中心点算法计算训练样本的每一类中心点;Step S322, calculating a center point of each type of the training sample by using a nearest center point algorithm;步骤S323,基于随机子空间,测试样本与训练样本的类中心点多次在子空间对比,得到多个分类结果;Step S323, based on the random subspace, the class center points of the test sample and the training sample are compared in the subspace multiple times to obtain a plurality of classification results;步骤S324,对分类结果使用简单多数投票原则,并且设置一定票数比例, 获得多数票同时达到一定的票数的情况下得到最终分类结果;Step S324, using a simple majority voting principle for the classification result, and setting a certain number of votes, The final classification result is obtained when a majority of votes are obtained and a certain number of votes are reached;步骤S325,将分类成功的样本归入新的训练样本,重新计算新训练样本的新类中心点。In step S325, the successfully classified samples are classified into new training samples, and the new class center points of the new training samples are recalculated.
- 根据权利要求3所述的智能输入方法,其特征在于:The intelligent input method according to claim 3, wherein:在所述步骤S321中,对手背不同位置敲击,采集得到步骤S31的信号特征作为训练样本,标记位置并根据位置的不同分成n类,每类敲击m次,其中n与m大于或等于1;In the step S321, the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and divided into n categories according to the position, each type of tapping m times, wherein n and m are greater than or equal to 1;在所述步骤S323中,将步骤S322中每一次产生的类中心分别随机抽样T个属性,重复以上操作Q次,得到Q个子空间,在子空间里逐一对比测试样本与训练样本的各个类中心点的欧式距离,找到最近中心点,即得到Q个子空间分类的结果,其中T、Q大于1。In the step S323, the class centers generated in each step S322 are randomly sampled T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training sample sample centers are compared one by one in the subspace. The Euclidean distance of the point, find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
- 根据权利要求1所述的智能输入方法,其特征在于:The intelligent input method according to claim 1, wherein:在所述S2.提取步骤中,人体指定部位为手背;In the S2. extraction step, the designated part of the human body is the back of the hand;振动传感器为压电陶瓷振动传感器;The vibration sensor is a piezoelectric ceramic vibration sensor;所述S1.接收步骤中,对振动信号进行降噪处理包括:In the S1. receiving step, the noise reduction processing on the vibration signal includes:步骤S11,使用20Hz的巴特沃斯高通滤波器滤掉直流分量和低频噪声;Step S11, filtering the DC component and the low frequency noise by using a 20 Hz Butterworth high-pass filter;步骤S12,使用800Hz低通滤波滤掉高频噪声。In step S12, high frequency noise is filtered out using 800 Hz low pass filtering.
- 一种基于骨传导振动信号传播的智能输入系统,其特征在于,包括:An intelligent input system based on bone conduction vibration signal propagation, characterized in that it comprises:接收模块,智能设备用振动传感器接收振动信号,并对振动信号进行降噪处理;Receiving module, the smart device receives the vibration signal by using the vibration sensor, and performs noise reduction processing on the vibration signal;提取模块,利用双门限端点检测法检测并提取由于敲击人体指定部位产生的振动信号片段;The extraction module detects and extracts a vibration signal segment generated by striking a designated part of the human body by using a double threshold end point detection method;处理模块,提取信号特征,基于RNM算法来分类信号位置。The processing module extracts signal features and classifies signal locations based on the RMN algorithm.
- 根据权利要求6所述的智能输入系统,其特征在于,在所述提取模块中包括:The intelligent input system according to claim 6, wherein the extraction module comprises:第一提取模块,用于对处理的信号设置高、低两个门限;a first extraction module, configured to set two thresholds of high and low for the processed signal;第二提取模块,用于当信号的能量或过零率超越低门限,初步确定敲击信 号起点,而当信号的能量或过零率突破高门限,才确定敲击信号真正的起点;当信号能量和过零率同时低于低门限时,确定信号终点;a second extraction module, configured to initially determine a tapping signal when the energy or zero-crossing rate of the signal exceeds a low threshold Number starting point, and when the energy or zero-crossing rate of the signal breaks through the high threshold, the true starting point of the tapping signal is determined; when the signal energy and the zero-crossing rate are simultaneously lower than the low threshold, the signal end point is determined;第三提取模块,用于保留起点至终点的数据,得到由敲击手背产生的振动信号片段。The third extraction module is configured to retain data from the start point to the end point, and obtain a vibration signal segment generated by the back of the taper.
- 根据权利要求6所述的智能输入系统,其特征在于,所述处理模块中包括:The intelligent input system according to claim 6, wherein the processing module comprises:第一处理模块,用于对切段信号进行归一化,提取梅尔频率倒频谱系数,得到信号特征;a first processing module, configured to normalize the segmented signal, extract a Mel frequency cepstral coefficient, and obtain a signal characteristic;第二处理模块,用于对信号特征使用基于随机子空间和最近中心点算法的RNM算法进行分类,进而判断出敲击位置;a second processing module, configured to classify the signal feature using an RMN algorithm based on a random subspace and a nearest center point algorithm, thereby determining a tap position;所述第二处理模块包括:The second processing module includes:第一处理单元,用于根据敲击位置的不同,采集步骤S31得到的信号特征作训练样本,并进行分类;a first processing unit, configured to collect the signal features obtained in step S31 as training samples according to different tap positions, and perform classification;第二处理单元,用于使用最近中心点算法计算训练样本的每一类中心点;a second processing unit, configured to calculate each type of center point of the training sample using a nearest center point algorithm;第三处理单元,用于基于随机子空间,测试样本与训练样本的类中心点多次在子空间对比,得到多个分类结果;a third processing unit, configured to compare the class center points of the test sample and the training sample in the subspace multiple times based on the random subspace, to obtain a plurality of classification results;第四处理单元,用于对分类结果使用简单多数投票原则,并且设置一定票数比例,获得多数票同时达到一定的票数的情况下得到最终分类结果;a fourth processing unit, configured to use a simple majority voting principle for the classification result, and set a certain number of votes, and obtain a final classification result if a majority of votes are obtained while a certain number of votes are obtained;第五处理单元,用于将分类成功的样本归入新的训练样本,重新计算新训练样本的新类中心点。The fifth processing unit is configured to classify the successfully classified samples into new training samples, and recalculate the new class center points of the new training samples.
- 根据权利要求8所述的智能输入系统,其特征在于:The intelligent input system of claim 8 wherein:在所述第一处理单元中,对手背不同位置敲击,采集得到步骤S31的信号特征作为训练样本,标记位置并根据位置的不同分成n类,每类敲击m次,其中n与m大于或等于1;In the first processing unit, the opponent's back is tapped at different positions, and the signal feature of step S31 is collected as a training sample, and the position is marked and divided into n categories according to different positions, each type of tapping m times, where n and m are greater than Or equal to 1;在所述第三处理单元中,将第二处理单元中每一次产生的类中心分别随机抽样T个属性,重复以上操作Q次,得到Q个子空间,在子空间里逐一对比测试样本与训练样本的各个类中心点的欧式距离,找到最近中心点,即得到Q个子空间分类的结果,其中T、Q大于1。 In the third processing unit, the class centers generated in each of the second processing units are randomly sampled by T attributes, and the above operations are repeated Q times to obtain Q subspaces, and the test samples and the training samples are compared one by one in the subspace. The Euclidean distance of each class center point, find the nearest center point, that is, the result of Q subspace classification, where T and Q are greater than 1.
- 根据权利要求6所述的智能输入系统,其特征在于:The intelligent input system of claim 6 wherein:在所述提取模块中,人体指定部位为手背;In the extraction module, the designated part of the human body is the back of the hand;振动传感器为压电陶瓷振动传感器;The vibration sensor is a piezoelectric ceramic vibration sensor;所述接收模块中,对振动信号进行降噪处理包括:In the receiving module, performing noise reduction processing on the vibration signal includes:第一接收模块,用于使用20Hz的巴特沃斯高通滤波器滤掉直流分量和低频噪声;a first receiving module for filtering DC components and low frequency noise using a 20 Hz Butterworth high pass filter;第二接收模块,用于使用800Hz低通滤波滤掉高频噪声。 A second receiving module for filtering high frequency noise using 800 Hz low pass filtering.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710433231.5 | 2017-06-09 | ||
CN201710433231.5A CN107300971B (en) | 2017-06-09 | 2017-06-09 | The intelligent input method and system propagated based on osteoacusis vibration signal |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018223489A1 true WO2018223489A1 (en) | 2018-12-13 |
Family
ID=60134750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2017/092769 WO2018223489A1 (en) | 2017-06-09 | 2017-07-13 | Intelligent input method and system based on bone conduction vibration signal propagation |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107300971B (en) |
WO (1) | WO2018223489A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112272019A (en) * | 2020-10-22 | 2021-01-26 | 广东美的制冷设备有限公司 | Control method and device for sound-control knocking switch, household appliance and storage medium |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108681709B (en) * | 2018-05-16 | 2020-01-17 | 深圳大学 | Intelligent input method and system based on bone conduction vibration and machine learning |
JP2021528643A (en) * | 2018-06-22 | 2021-10-21 | イーエヌデータクト ゲーエムベーハーiNDTact GmbH | Sensor placement structure, use of sensor placement structure, and how to detect solid-borne sound |
CN109840480B (en) * | 2019-01-04 | 2021-08-13 | 深圳大学 | Interaction method and interaction system of smart watch |
CN109933202B (en) * | 2019-03-20 | 2021-11-30 | 深圳大学 | Intelligent input method and system based on bone conduction |
CN110058689A (en) * | 2019-04-08 | 2019-07-26 | 深圳大学 | A kind of smart machine input method based on face's vibration |
CN110414196B (en) * | 2019-07-29 | 2021-09-17 | 深圳大学 | Smart watch identity verification method based on vibration signal |
CN110931031A (en) * | 2019-10-09 | 2020-03-27 | 大象声科(深圳)科技有限公司 | Deep learning voice extraction and noise reduction method fusing bone vibration sensor and microphone signals |
CN111752388A (en) * | 2020-06-19 | 2020-10-09 | 深圳振科智能科技有限公司 | Application control method, device, equipment and storage medium |
CN111741419B (en) * | 2020-08-21 | 2020-12-04 | 瑶芯微电子科技(上海)有限公司 | Bone conduction sound processing system, bone conduction microphone and signal processing method thereof |
CN113342159A (en) * | 2021-05-07 | 2021-09-03 | 哈尔滨工业大学 | Wrist wearable system identified through wrist vibration |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102436345A (en) * | 2011-10-31 | 2012-05-02 | 广州市动景计算机科技有限公司 | Method for interface operation and control of mobile device and implement device |
CN102770829A (en) * | 2010-03-15 | 2012-11-07 | 日本电气株式会社 | Input device, input method and program |
US9199098B2 (en) * | 2012-09-05 | 2015-12-01 | Olympus Corporation | Ultrasonic treatment device |
CN106128452A (en) * | 2016-07-05 | 2016-11-16 | 深圳大学 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8798292B2 (en) * | 2012-06-06 | 2014-08-05 | Google Inc. | External vibration reduction in bone-conduction speaker |
CN104461004B (en) * | 2014-12-12 | 2018-04-10 | 北京奇宝科技有限公司 | A kind of wearable smart machine |
CN106339104B (en) * | 2016-08-24 | 2019-02-15 | 广州市香港科大霍英东研究院 | The text entry method and device of smartwatch |
-
2017
- 2017-06-09 CN CN201710433231.5A patent/CN107300971B/en active Active
- 2017-07-13 WO PCT/CN2017/092769 patent/WO2018223489A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102770829A (en) * | 2010-03-15 | 2012-11-07 | 日本电气株式会社 | Input device, input method and program |
CN102436345A (en) * | 2011-10-31 | 2012-05-02 | 广州市动景计算机科技有限公司 | Method for interface operation and control of mobile device and implement device |
US9199098B2 (en) * | 2012-09-05 | 2015-12-01 | Olympus Corporation | Ultrasonic treatment device |
CN106128452A (en) * | 2016-07-05 | 2016-11-16 | 深圳大学 | Acoustical signal detection keyboard is utilized to tap the system and method for content |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112272019A (en) * | 2020-10-22 | 2021-01-26 | 广东美的制冷设备有限公司 | Control method and device for sound-control knocking switch, household appliance and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107300971A (en) | 2017-10-27 |
CN107300971B (en) | 2019-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018223489A1 (en) | Intelligent input method and system based on bone conduction vibration signal propagation | |
Du et al. | Wordrecorder: Accurate acoustic-based handwriting recognition using deep learning | |
Qifan et al. | Dolphin: Ultrasonic-based gesture recognition on smartphone platform | |
CN105938399B (en) | The text input recognition methods of smart machine based on acoustics | |
WO2019218725A1 (en) | Intelligent input method and system based on bone-conduction vibration and machine learning | |
US20210109598A1 (en) | Systems, methods and devices for gesture recognition | |
CN109508728B (en) | Novel identity authentication method for wearable equipment | |
CN111210021A (en) | Audio signal processing method, model training method and related device | |
CN108182418B (en) | Keystroke identification method based on multi-dimensional sound wave characteristics | |
CN106128452A (en) | Acoustical signal detection keyboard is utilized to tap the system and method for content | |
TW201214227A (en) | Method for determining a touch event and touch sensitive device | |
CN110069199A (en) | A kind of skin-type finger gesture recognition methods based on smartwatch | |
Zou et al. | AcouDigits: Enabling users to input digits in the air | |
WO2019128639A1 (en) | Method for detecting audio signal beat points of bass drum, and terminal | |
Yin et al. | Ubiquitous writer: Robust text input for small mobile devices via acoustic sensing | |
CN107491254A (en) | A kind of gesture operation method, device and mobile terminal | |
CN110946554A (en) | Cough type identification method, device and system | |
CN109933202B (en) | Intelligent input method and system based on bone conduction | |
Chen et al. | WritePad: Consecutive number writing on your hand with smart acoustic sensing | |
CN107340864A (en) | A kind of virtual input method based on sound wave | |
WO2022001791A1 (en) | Intelligent device interaction method based on ppg information | |
CN102760312A (en) | Intelligent door control system with speech recognition | |
Yu et al. | Mobile devices based eavesdropping of handwriting | |
CN110547806A (en) | gesture action online recognition method and system based on surface electromyographic signals | |
Suresh et al. | Computer-aided interpreter for hearing and speech impaired |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17912456 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09.03.2020) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17912456 Country of ref document: EP Kind code of ref document: A1 |