技术领域technical field
本发明涉及步态检测技术领域，尤其涉及一种基于FMG的步态检测方法及系统。The invention relates to the technical field of gait detection, in particular to an FMG-based gait detection method and system.
背景技术Background technique
随着人们对健康和运动的关注不断提高，步态分析作为一种准确评估人体运动能力的方法，备受关注。步态分析通过测量和分析人体在行走时的步态特征，例如步幅、步频、步态稳定性等，从而能够客观地评估一个人的运动能力和健康状况。这对于疾病预防、治疗和康复具有重要意义，也可以帮助人们更好地了解自己的健康状况和运动状态。因此，步态分析技术的发展可以提高医疗、康复和运动领域的治疗效果和运动表现，并有助于人们更好地管理和维护自己的健康，提升生活质量。As people's health and sports concerns continue to increase, gait analysis has attracted much attention as a method to accurately assess human performance. Gait analysis can objectively evaluate a person's athletic ability and health status by measuring and analyzing the gait characteristics of the human body during walking, such as stride length, stride frequency, gait stability, etc. This has important implications for disease prevention, treatment and rehabilitation, and can also help people better understand their health and exercise status. Therefore, the development of gait analysis technology can improve the treatment effect and sports performance in the medical, rehabilitation and sports fields, and help people to better manage and maintain their health and improve the quality of life.
目前已经使用不同的技术来开发具有步态阶段检测能力的步态监测系统。惯性传感器和带有压力传感器的鞋垫是用于检测步态方法之一，然而，惯性传感器的精度在较低的行走速度下下降，这通常与行走困难有关。惯性传感器的测量结果会随时间的推移而发生漂移，这可能会导致运动状态的不准确性。鞋垫需要定制鞋类，传感器安装不方便，力传感器容易因疲劳应力而发生断裂并且脚下的传感器和线缆可能引起不适。肌电图 (EMG)反映了肌肉的电活动，对皮肤表面的情况很敏感，污渍、汗液都会在采集电信号的过程中带来噪声，从而在根本上影响识别的精确性，长时间使用引起的肌肉疲劳也会使得同一动作的肌电信号发生变化，影响识别精度。Different techniques have been used to develop gait monitoring systems with gait phase detection capabilities. Inertial sensors and insoles with pressure sensors are one of the methods used to detect gait, however, the accuracy of inertial sensors decreases at lower walking speeds, which is often associated with walking difficulties. Measurements from inertial sensors can drift over time, which can lead to inaccuracies in the state of motion. Insoles require custom footwear, sensors are inconvenient to install, force sensors are prone to fracture due to fatigue stress and sensors and cables underfoot can cause discomfort. Electromyography (EMG) reflects the electrical activity of muscles and is very sensitive to the surface of the skin. Stains and sweat will bring noise in the process of collecting electrical signals, which will fundamentally affect the accuracy of recognition. Muscle fatigue will also change the EMG signal of the same action, affecting the recognition accuracy.
FMG根据相应的肌腱的复合体( MC )在默认状态下的刚度变化来反应肢体的位置或运动。目标MC的刚度变化往往通过将力传感器放置在具有预紧力的目标位置来监测以捕捉肌肉收缩时产生的力量信号。通过测量这些信号的幅度和时间特征，可以实现对肌肉收缩状态的监测和分析。The FMG responds to the position or movement of the limb according to the stiffness change of the corresponding tendon complex ( MC ) in the default state. Stiffness changes of the target MC are often monitored by placing a force sensor at the target location with a preload to capture the force signal generated during muscle contraction. By measuring the amplitude and time characteristics of these signals, the monitoring and analysis of the state of muscle contraction can be realized.
FMG在运动监测、康复治疗、健康评估等领域中得到广泛应用，特别是在一些需要连续监测肌肉活动的情况下，FMG技术可以提供更为准确和可靠的测量数据。尽管FMG技术仍处于发展阶段，但它已经得到了一定程度的验证和应用，并且具有很大的潜力成为未来肌肉力量和活动测量的重要方法之一。FMG is widely used in sports monitoring, rehabilitation treatment, health assessment and other fields, especially in some situations that require continuous monitoring of muscle activity, FMG technology can provide more accurate and reliable measurement data. Although FMG technology is still in the development stage, it has been verified and applied to a certain extent, and has great potential to become one of the important methods for measuring muscle strength and activity in the future.
发明内容Contents of the invention
本发明的目的是提供一种基于FMG的步态检测方法及系统，以解决传统的肌电图（EMG）技术对皮肤表面的情况很敏感，污渍、汗液都会在采集电信号的过程中带来噪声，从而在根本上影响识别的精确性，长时间使用引起的肌肉疲劳也会使得同一动作的肌电信号发生变化，影响识别精度的技术问题。The purpose of the present invention is to provide a gait detection method and system based on FMG to solve the problem that traditional electromyography (EMG) technology is very sensitive to skin surface conditions, and stains and sweat will be brought during the process of collecting electrical signals. Noise, which fundamentally affects the accuracy of recognition, and muscle fatigue caused by long-term use will also change the EMG signal of the same action, which affects the technical problems of recognition accuracy.
本发明是采用以下技术方案实现的：一种基于FMG的步态检测方法，包括如下步骤：The present invention is realized by adopting the following technical scheme: a kind of gait detection method based on FMG comprises the steps:
S1：数据采集，将FMG传感器设置于人体上，实时获取人体行走时的数据；S1: Data acquisition, setting the FMG sensor on the human body to obtain real-time data when the human body is walking;
S2：数据预处理，对获取的数据进行滤波，抑制高频噪声；S2: Data preprocessing, filtering the acquired data to suppress high-frequency noise;
S3：特征提取，从数据中提取多个特征，并进行排序，得到特征矩阵；S3: feature extraction, extract multiple features from the data, and sort them to get the feature matrix;
S4：步态检测，采用支持向量机SVM的监督学习方法生成分类模型，并利用分类模型判断人体当前状态。S4: Gait detection, using the supervised learning method of support vector machine SVM to generate a classification model, and use the classification model to judge the current state of the human body.
进一步的，所述FMG传感器包括多个FSR压力传感器，所述FSR压力传感器均匀嵌入穿戴设备上，人体肌肉体积变化产生的力通过穿戴设备上的薄膜传递至FSR压力传感器，获取人体行走时的数据。Further, the FMG sensor includes a plurality of FSR pressure sensors, and the FSR pressure sensors are evenly embedded in the wearable device, and the force generated by the change of human muscle volume is transmitted to the FSR pressure sensor through the thin film on the wearable device to obtain data when the human body is walking .
进一步的，步骤S1包括如下子步骤：Further, step S1 includes the following sub-steps:
S11：将FMG传感器系于人体大腿上，采集人体行走时力的变化数据，并将数据转化为电阻变化；S11: Tie the FMG sensor to the thigh of the human body, collect the force change data when the human body walks, and convert the data into resistance change;
S12：通过分压器电路将电阻变化转换为电压变化，并传输至控制器；S12: Convert the resistance change into a voltage change through the voltage divider circuit, and transmit it to the controller;
S13：控制器通过无线传输的方式，将数据传输至数据预处理模块。S13: The controller transmits the data to the data preprocessing module through wireless transmission.
进一步的，步骤S2包括如下子步骤：Further, step S2 includes the following sub-steps:
S21：通过滤波器对获取的数据进行滤波，抑制高频噪声；S21: Filter the acquired data through a filter to suppress high-frequency noise;
S22：对每个数据进行归一化处理，消除直流偏移和幅度缩放。S22: Perform normalization processing on each data to eliminate DC offset and amplitude scaling.
进一步的，步骤S22具体为：从数据的平均值中减去信号，并除以标准差来对每个数据进行归一化。Further, step S22 is specifically: subtracting the signal from the mean value of the data, and dividing by the standard deviation to normalize each data.
进一步的，步骤S3具体为：从数据中提取均方根 RMS、平均绝对偏差MAD、绝对误差和SAV、平均绝对值MAV、方差VAR、波长WL、斜率符号变化SSC、过零点数ZC和平均幅度变化AAC，并将得到的特征值向量在列的方向上按加窗时截取的顺序进行排列，形成特征矩阵。Further, step S3 is specifically: extract root mean square RMS, mean absolute deviation MAD, absolute error sum SAV, mean absolute value MAV, variance VAR, wavelength WL, slope sign change SSC, zero-crossing points ZC and average amplitude from the data. Change AAC, and arrange the obtained eigenvalue vectors in the column direction according to the order of interception during windowing to form an eigenmatrix.
进一步的，步骤S4具体为：利用LIBSVM建立四分类步态识别模型，利用四分类步态识别模型判断人体当前状态，并显示检测步态的状态。Further, step S4 specifically includes: using LIBSVM to establish a four-category gait recognition model, using the four-category gait recognition model to judge the current state of the human body, and display the state of the detected gait.
进一步的，所述步态的状态包括一只脚后跟刚触地HS、一只脚竖直站立MS、一只脚后跟即将离地HO和一只脚脚趾即将离地TO。Further, the gait states include one heel just touching the ground HS, one foot standing upright MS, one heel about to leave the ground HO, and one foot toe about to leave the ground TO.
进一步的，采用交叉实验验证的方法提升四分类步态识别模型的准确度。Further, the accuracy of the four-category gait recognition model is improved by cross-experimental verification.
一种基于FMG的步态检测系统，包括数据采集模块、预处理模块、特征提取模块和步态检测模块，所述数据采集模块用以实时获取人体行走时的数据；所述预处理模块用以对获取的数据进行滤波，抑制高频噪声；所述特征提取模块用以从数据中提取多个特征，并进行排序，得到特征矩阵；所述步态检测模块采用支持向量机SVM的监督学习方法生成分类模型，并利用分类模型判断人体当前状态。A gait detection system based on FMG, comprising a data acquisition module, a preprocessing module, a feature extraction module and a gait detection module, the data acquisition module is used to obtain real-time data when the human body walks; the preprocessing module is used to The obtained data is filtered to suppress high-frequency noise; the feature extraction module is used to extract multiple features from the data, and sort them to obtain a feature matrix; the gait detection module adopts the supervised learning method of support vector machine SVM Generate a classification model, and use the classification model to judge the current state of the human body.
本发明的有益效果在于：The beneficial effects of the present invention are:
1.不受干扰：FMG技术可以测量肌肉产生的力量和运动状态，而不受到外界干扰（如皮肤表面出汗、地面摩擦力、风力、振动等）的影响。1. Undisturbed: FMG technology can measure the force and motion state generated by muscles without being affected by external disturbances (such as sweating on the skin surface, ground friction, wind force, vibration, etc.).
2.能够分辨具体的肌肉活动：FMG技术可以分辨出不同肌肉的活动状态，从而能够更加准确地检测步态。2. Able to distinguish specific muscle activity: FMG technology can distinguish the activity state of different muscles, so as to detect gait more accurately.
3.连续监测：FMG技术可以进行长时间连续监测肌肉活动状态，从而能够更好地了解肌肉的变化情况。3. Continuous monitoring: FMG technology can continuously monitor the state of muscle activity for a long time, so as to better understand the changes of muscles.
4.精度高：FMG技术的精度和准确性较高，可以检测到微小的肌肉活动变化。4. High precision: FMG technology has high precision and accuracy, and can detect tiny changes in muscle activity.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图示出的结构获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to the structures shown in these drawings without creative effort.
图1为本发明流程图；Fig. 1 is a flowchart of the present invention;
图2为FMG传感器结构原理图；Figure 2 is a structural schematic diagram of the FMG sensor;
图3为交叉实验结果图；Fig. 3 is cross experiment result figure;
图中，1-FSR压力传感器，2-魔术贴。In the picture, 1-FSR pressure sensor, 2-Velcro.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本发明实施例的组件可以以各种不同的配置来布置和设计。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations.
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。It should be noted that like numerals and letters denote similar items in the following figures, therefore, once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.
下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。Some embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.
实施例1Example 1
参见图1，一种基于FMG的步态检测方法，包括如下步骤：Referring to Fig. 1, a kind of gait detection method based on FMG comprises the following steps:
S1：数据采集，将FMG传感器设置于人体上，实时获取人体行走时的数据；S1: Data acquisition, setting the FMG sensor on the human body to obtain real-time data when the human body is walking;
S2：数据预处理，对获取的数据进行滤波，抑制高频噪声；S2: Data preprocessing, filtering the acquired data to suppress high-frequency noise;
S3：特征提取，从数据中提取多个特征，并进行排序，得到特征矩阵；S3: feature extraction, extract multiple features from the data, and sort them to get the feature matrix;
S4：步态检测，采用支持向量机SVM的监督学习方法生成分类模型，并利用分类模型判断人体当前状态。S4: Gait detection, using the supervised learning method of support vector machine SVM to generate a classification model, and use the classification model to judge the current state of the human body.
参见图2，FMG传感器包括8个均匀放置的校准 FSR压力传感器1，所述FSR压力传感器嵌入一个柔性魔术贴2中，将薄膜施加到传感器上以对其进行层压，以便在实验过程中不会出汗。由于肌肉体积变化而产生的力将通过层压薄膜传递到 FSR压力传感器1。使用维可牢尼龙搭扣带系在受试者的大腿上，这些力变化转换为 FSR 压力传感器1中的电阻变化，然后使用简单的分压器电路将其转换为电压变化，并输出连接到STM32微控制器的模拟引脚，该微控制器通过蓝牙模块以 130 Hz 的采样频率将数据无线传输到远程终端，进行预处理。为了观察传输时的数据丢失，将数据与参考信号耦合，八个 FSR 传感器对齐到相应的大腿肌肉：R1-股外侧肌、R2-髂胫束、R3-股二头肌、R4-半腱肌、R5-大收肌、R6-股薄肌和长收肌中点、R7-股内侧肌和R8-直肌股骨肌肉。Referring to Fig. 2, the FMG sensor consists of 8 calibrated FSR pressure sensors 1 placed evenly, which are embedded in a flexible velcro 2, and a thin film is applied to the sensors to laminate them so that they are not exposed during the experiment. will sweat. The force due to the change in muscle volume will be transmitted to the FSR pressure sensor 1 through the laminated film. Attached to the subject's thigh using a Velcro strap, these force changes are converted to resistance changes in the FSR pressure sensor 1, which are then converted to voltage changes using a simple voltage divider circuit, and the output is connected to Analog pin of the STM32 microcontroller that wirelessly transmits data to a remote terminal via the Bluetooth module at a sampling frequency of 130 Hz for preprocessing. In order to observe data loss during transmission, data was coupled with a reference signal, and eight FSR transducers were aligned to the corresponding thigh muscles: R1-vastus lateralis, R2-iliotibial band, R3-biceps femoris, R4-semitendinosus , R5- adductor magnus, R6- midpoint of gracilis and adductor longus, R7- vastus medialis and R8- rectus femoral muscle.
FMG 技术是一种通过测量人体肌肉产生的力量信号来推测肌肉运动的技术，通过肌肉活动来探测肌肉的运动状态，进而推断出人体的动作和姿态等信息，用于人机交互、康复、生物力学等领域。MG技术的信号稳定性和准确性比传统的EMG技术更好，可以有效降低误识别率和误操作率，提高了识别和控制的精度。FMG technology is a technology that infers muscle movement by measuring the force signals generated by human muscles. It detects the state of muscle movement through muscle activity, and then deduces information such as human body movements and postures. It is used for human-computer interaction, rehabilitation, and biology. fields of mechanics. The signal stability and accuracy of MG technology are better than traditional EMG technology, which can effectively reduce the misidentification rate and misoperation rate, and improve the accuracy of identification and control.
远程终端对FMG传感器采集的数据进行预处理：使用截止频率为 20 Hz 的低通巴特沃斯滤波器（四阶）对获取的数据进行过滤，人体移动的频率小于 5 Hz，因此首选 20 Hz的截止频率，信号过滤后，通过一个七点移动平均滤波器，这种两级滤波操作可确保抑制信号中的任何高频噪声。The remote terminal preprocesses the data collected by the FMG sensor: use a low-pass Butterworth filter (fourth order) with a cutoff frequency of 20 Hz to filter the acquired data. The frequency of human body movement is less than 5 Hz, so 20 Hz is preferred The cutoff frequency, after the signal is filtered, is passed through a seven-point moving average filter, this two-stage filtering operation ensures that any high frequency noise in the signal is suppressed.
由于 FMG 传感器穿戴在肢体周围的位置可能不会在每次试验中完全相同，并且个人的步行模式也可能不时发生轻微变化，因此从 FMG 传感器获得的信号可能具有不同的直流偏移或振幅缩放。为了消除信号变化的直流偏移和幅度缩放的影响，从信号的平均值中减去信号然后除以标准差来对每个信号进行归一化，这样的过程通常称为自动缩放，自动缩放步骤在模型生成过程之前平衡每个输入信号的重要性。Since the position where the FMG sensor is worn around the limb may not be exactly the same from trial to trial, and an individual's walking pattern may vary slightly from time to time, the signals obtained from the FMG sensor may have different DC offsets or amplitude scaling. To remove the effects of DC offset and amplitude scaling of signal variations, each signal is normalized by subtracting the signal from its mean value and then dividing by the standard deviation, a process often called autoscaling, the autoscaling step Balance the importance of each input signal before the model generation process.
在本实施例当中，特征提取步骤具体为：在 125 毫秒的滑动窗口帧中检查信号，重叠 93 毫秒，并从数据中提取了总共 9个特征：均方根 (RMS) 、平均绝对偏差(MAD)、绝对误差和(SAV)、平均绝对值(MAV)、方差(VAR)、波长(WL)、斜率符号变化(SSC)、过零点数（ZC）和平均幅度变化 (AAC)，最后，将得到的特征值向量在列方向上按加窗时截取的顺序进行排列，形成一个特征矩阵。In this example, the feature extraction step is as follows: the signal is inspected in sliding window frames of 125 milliseconds, overlapped by 93 milliseconds, and a total of 9 features are extracted from the data: Root Mean Square (RMS), Mean Absolute Deviation (MAD ), Sum of Absolute Error (SAV), Mean Absolute Value (MAV), Variance (VAR), Wavelength (WL), Slope Sign Change (SSC), Number of Zero Crossings (ZC) and Average Amplitude Change (AAC), and finally, the The obtained eigenvalue vectors are arranged in the order of interception during windowing in the column direction to form a feature matrix.
在本实施例当中，步态检测具体为：在MATLAB中利用LIBSVM建立四分类步态识别模型，为了验证基于样本的准确性所实施的机器学习算法，使用了交叉试验验证方法：选择每个步行速度的五个试验之一作为测试数据，并将该速度下的其余试验分配给训练数据集。重复此过程，直到所有试验都被视为一次测试数据，然后通过对从所有五次相同速度试验中获得的准确度进行平均来计算准确度，对每个受试者执行上述交叉试验验证（验证结果如图3所示），得到精度较高的四分类步态识别模型。In this embodiment, the gait detection is specifically: use LIBSVM to establish a four-category gait recognition model in MATLAB, in order to verify the machine learning algorithm implemented based on the accuracy of the sample, a cross-test verification method is used: select each walking One of the five trials at that speed was used as test data, and the remaining trials at that speed were assigned to the training dataset. This process is repeated until all trials are considered as one test data, and the accuracy is then calculated by averaging the accuracies obtained from all five trials of the same speed, performing the above cross-trial validation for each subject (validation The results are shown in Figure 3), and a four-category gait recognition model with high accuracy is obtained.
支持向量机（Support Vector Machine，SVM）是一种常见的监督学习方法，可以用于分类和回归任务。其基本思想是找到一个能够将不同类别的数据点分开的最优决策边界（或超平面）。在SVM中，通过寻找具有最大间隔的超平面来进行分类。间隔是指数据点到超平面的距离，而最大间隔则是指所有数据点到超平面距离的最小值。为了找到最大间隔超平面，SVM需要解决一个优化问题，其目标是最小化错误分类点的数量，并使超平面的间隔最大化。这个问题可以转化为一个凸二次规划问题，可以使用现有的数学库进行求解。此外，SVM还可以使用核函数来处理非线性分类问题，通过将原始数据投影到高维空间中进行处理。常用的核函数包括线性核函数、多项式核函数、高斯径向基函数（RBF）核函数等。SVM具有很好的泛化性能，能够处理高维数据和小样本数据，并且在很多实际应用中表现出了很好的性能。其典型的目标函数如下式所示：Support Vector Machine (SVM) is a common supervised learning method that can be used for classification and regression tasks. The basic idea is to find an optimal decision boundary (or hyperplane) that separates data points of different classes. In SVM, classification is done by finding the hyperplane with the largest margin. The interval refers to the distance from the data point to the hyperplane, and the maximum interval refers to the minimum value of the distance from all data points to the hyperplane. To find the maximum margin hyperplane, SVM needs to solve an optimization problem whose goal is to minimize the number of misclassified points and maximize the margin of the hyperplane. This problem can be transformed into a convex quadratic programming problem, which can be solved using existing mathematical libraries. In addition, SVM can also use kernel functions to deal with nonlinear classification problems by projecting the original data into a high-dimensional space for processing. Commonly used kernel functions include linear kernel function, polynomial kernel function, Gaussian radial basis function (RBF) kernel function, etc. SVM has good generalization performance, can handle high-dimensional data and small sample data, and has shown good performance in many practical applications. Its typical objective function is as follows:
。 .
其中，ω为可调权值向量；b为阈值；xi为输入样本值；yi为输出样本值。Among them, ω is the adjustable weight vector; b is the threshold; xi is the input sample value; yi is the output sample value.
。 .
式中，λ 为拉格朗日乘子；λi 为第 i 个拉格朗日乘子。 利用强对偶性转化并对参数 ω 和 b 求偏导数可得到：In the formula, λ is the Lagrangian multiplier; λi is the i-th Lagrange multiplier. Using the strong duality transformation and taking partial derivatives with respect to the parameters ω and b gives:
。 .
用序列最小优化算法(Sequential minimal optimization，SMO)算法可得到最优解 λ*，将其代入下式求得最大分割超平面的系数矩阵：The optimal solution λ* can be obtained by using the Sequential minimal optimization (SMO) algorithm, and it can be substituted into the following formula to obtain the coefficient matrix of the maximum segmentation hyperplane:
。 .
基于上述实施例，本发明至少具有以下技术效果：Based on the foregoing embodiments, the present invention at least has the following technical effects:
1.不受干扰：FMG技术可以测量肌肉产生的力量和运动状态，而不受到外界干扰（如皮肤表面出汗、地面摩擦力、风力、振动等）的影响。1. Undisturbed: FMG technology can measure the force and motion state generated by muscles without being affected by external disturbances (such as sweating on the skin surface, ground friction, wind force, vibration, etc.).
2.能够分辨具体的肌肉活动：FMG技术可以分辨出不同肌肉的活动状态，从而能够更加准确地检测步态。2. Able to distinguish specific muscle activity: FMG technology can distinguish the activity state of different muscles, so as to detect gait more accurately.
3.连续监测：FMG技术可以进行长时间连续监测肌肉活动状态，从而能够更好地了解肌肉的变化情况。3. Continuous monitoring: FMG technology can continuously monitor the state of muscle activity for a long time, so as to better understand the changes of muscles.
4.精度高：FMG技术的精度和准确性较高，可以检测到微小的肌肉活动变化。4. High precision: FMG technology has high precision and accuracy, and can detect tiny changes in muscle activity.
需要说明的是，对于前述的实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某一些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例属于优选实施例，所涉及的动作并不一定是本申请所必须的。It should be noted that, for the foregoing embodiments, for the sake of simple description, they are expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence, because according to In this application, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by this application.
上述实施例中，描述了本发明的基本原理和主要特征和本发明的优点。本行业的技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下，本领域人员所进行的改动和变化不脱离本发明的精神和范围，则都应在本发明所附权利要求的保护范围内。In the above embodiments, the basic principles and main features of the present invention and the advantages of the present invention are described. It should be understood by those skilled in the art that the present invention is not limited by the above-mentioned embodiments. What is described in the above-mentioned embodiments and description is only to illustrate the principles of the present invention. All modifications and changes without departing from the spirit and scope of the present invention should be within the protection scope of the appended claims of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310558944.XACN116439693B (en) | 2023-05-18 | 2023-05-18 | A gait detection method and system based on FMG |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310558944.XACN116439693B (en) | 2023-05-18 | 2023-05-18 | A gait detection method and system based on FMG |
| Publication Number | Publication Date |
|---|---|
| CN116439693Atrue CN116439693A (en) | 2023-07-18 |
| CN116439693B CN116439693B (en) | 2024-05-28 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310558944.XAActiveCN116439693B (en) | 2023-05-18 | 2023-05-18 | A gait detection method and system based on FMG |
| Country | Link |
|---|---|
| CN (1) | CN116439693B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119405318A (en)* | 2025-01-07 | 2025-02-11 | 北京航空航天大学 | Muscle strength prediction method and device based on FMG and sEMG signals |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130123665A1 (en)* | 2010-07-14 | 2013-05-16 | Ecole Polytechnique Federale De Lausanne (Epfl) | System and method for 3d gait assessment |
| US20130211775A1 (en)* | 2010-08-26 | 2013-08-15 | Nederlandse Organisatie Voor Toegepast-Natuurweten Schappelijk Onderzoek Tno | Method and System for Determining the Walking or Running Speed of a Person |
| CN104107042A (en)* | 2014-07-10 | 2014-10-22 | 杭州电子科技大学 | Electromyographic signal gait recognition method based on particle swarm optimization and support vector machine |
| CN104537382A (en)* | 2015-01-12 | 2015-04-22 | 杭州电子科技大学 | Electromyographic signal gait recognition method for optimizing support vector machine based on genetic algorithm |
| US20150282766A1 (en)* | 2014-03-19 | 2015-10-08 | Tactonic Technologies, Llc | Method and Apparatus to Infer Object and Agent Properties, Activity Capacities, Behaviors, and Intents from Contact and Pressure Images |
| KR20160023981A (en)* | 2014-08-21 | 2016-03-04 | 인하대학교 산학협력단 | A sEMG Signal based Gait Phase Recognition Method selecting Features and Channels Adaptively |
| KR20160101800A (en)* | 2015-02-17 | 2016-08-26 | 인하대학교 산학협력단 | A Human Identification Method based on Gait Cycle Using EMG signal |
| CN106388819A (en)* | 2016-10-28 | 2017-02-15 | 许昌学院 | Human upper limb muscle state monitoring system based on surface electromyogram signals and judging method thereof |
| WO2017156835A1 (en)* | 2016-03-18 | 2017-09-21 | 深圳大学 | Smart method and system for body building posture identification, assessment, warning and intensity estimation |
| CN107440716A (en)* | 2017-07-26 | 2017-12-08 | 电子科技大学 | Human body lower limbs athletic performance classification discrimination method based on single channel electromyographic signal |
| CN109222969A (en)* | 2018-10-31 | 2019-01-18 | 郑州大学 | A kind of wearable human upper limb muscular movement fatigue detecting and training system based on Fusion |
| CN109446972A (en)* | 2018-10-24 | 2019-03-08 | 电子科技大学中山学院 | Gait recognition model establishing method, recognition method and device based on electromyographic signals |
| CN110141239A (en)* | 2019-05-30 | 2019-08-20 | 东北大学 | A motion intention recognition and device method for lower extremity exoskeleton |
| US20190365287A1 (en)* | 2018-05-30 | 2019-12-05 | Industry-Academic Cooperation Foundation, Dankook University | Apparatus and method for gait type classification using pressure sensor of smart insole |
| KR20190136324A (en)* | 2018-05-30 | 2019-12-10 | 단국대학교 산학협력단 | Apparatus and Method for Gait Type Classificating Using Pressure Sensor of Smart Insole |
| CN111700623A (en)* | 2020-07-17 | 2020-09-25 | 华南理工大学 | A system and method for human gait detection based on plantar pressure |
| CN112244819A (en)* | 2020-11-10 | 2021-01-22 | 浙大宁波理工学院 | A system and method for identifying abnormal gait in children based on plantar pressure array detection |
| CN112370049A (en)* | 2020-11-16 | 2021-02-19 | 天津市环湖医院(天津市神经外科研究所、天津市脑系科中心医院) | Freezing gait acquisition and analysis system and method based on multi-mode signal synchronization |
| KR20210022375A (en)* | 2019-08-20 | 2021-03-03 | 단국대학교 산학협력단 | Apparatus and method for identifying individuals by performing discriminant analysis for various detection information |
| CN112754468A (en)* | 2021-01-07 | 2021-05-07 | 华南理工大学 | Human body lower limb movement detection and identification method based on multi-source signals |
| CN113273999A (en)* | 2021-05-25 | 2021-08-20 | 南开大学 | Wearable multi-dimensional gait analysis system and method |
| CN113627500A (en)* | 2021-07-28 | 2021-11-09 | 中国长江三峡集团有限公司 | Gait information acquisition system based on multi-sensor fusion and recognition algorithm |
| US20210345960A1 (en)* | 2018-10-17 | 2021-11-11 | Nec Corporation | Body weight estimation device, body weight estimation method, and program recording medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130123665A1 (en)* | 2010-07-14 | 2013-05-16 | Ecole Polytechnique Federale De Lausanne (Epfl) | System and method for 3d gait assessment |
| US20130211775A1 (en)* | 2010-08-26 | 2013-08-15 | Nederlandse Organisatie Voor Toegepast-Natuurweten Schappelijk Onderzoek Tno | Method and System for Determining the Walking or Running Speed of a Person |
| US20150282766A1 (en)* | 2014-03-19 | 2015-10-08 | Tactonic Technologies, Llc | Method and Apparatus to Infer Object and Agent Properties, Activity Capacities, Behaviors, and Intents from Contact and Pressure Images |
| CN104107042A (en)* | 2014-07-10 | 2014-10-22 | 杭州电子科技大学 | Electromyographic signal gait recognition method based on particle swarm optimization and support vector machine |
| KR20160023981A (en)* | 2014-08-21 | 2016-03-04 | 인하대학교 산학협력단 | A sEMG Signal based Gait Phase Recognition Method selecting Features and Channels Adaptively |
| CN104537382A (en)* | 2015-01-12 | 2015-04-22 | 杭州电子科技大学 | Electromyographic signal gait recognition method for optimizing support vector machine based on genetic algorithm |
| KR20160101800A (en)* | 2015-02-17 | 2016-08-26 | 인하대학교 산학협력단 | A Human Identification Method based on Gait Cycle Using EMG signal |
| WO2017156835A1 (en)* | 2016-03-18 | 2017-09-21 | 深圳大学 | Smart method and system for body building posture identification, assessment, warning and intensity estimation |
| CN106388819A (en)* | 2016-10-28 | 2017-02-15 | 许昌学院 | Human upper limb muscle state monitoring system based on surface electromyogram signals and judging method thereof |
| CN107440716A (en)* | 2017-07-26 | 2017-12-08 | 电子科技大学 | Human body lower limbs athletic performance classification discrimination method based on single channel electromyographic signal |
| KR20190136324A (en)* | 2018-05-30 | 2019-12-10 | 단국대학교 산학협력단 | Apparatus and Method for Gait Type Classificating Using Pressure Sensor of Smart Insole |
| US20190365287A1 (en)* | 2018-05-30 | 2019-12-05 | Industry-Academic Cooperation Foundation, Dankook University | Apparatus and method for gait type classification using pressure sensor of smart insole |
| US20210345960A1 (en)* | 2018-10-17 | 2021-11-11 | Nec Corporation | Body weight estimation device, body weight estimation method, and program recording medium |
| CN109446972A (en)* | 2018-10-24 | 2019-03-08 | 电子科技大学中山学院 | Gait recognition model establishing method, recognition method and device based on electromyographic signals |
| CN109222969A (en)* | 2018-10-31 | 2019-01-18 | 郑州大学 | A kind of wearable human upper limb muscular movement fatigue detecting and training system based on Fusion |
| CN110141239A (en)* | 2019-05-30 | 2019-08-20 | 东北大学 | A motion intention recognition and device method for lower extremity exoskeleton |
| KR20210022375A (en)* | 2019-08-20 | 2021-03-03 | 단국대학교 산학협력단 | Apparatus and method for identifying individuals by performing discriminant analysis for various detection information |
| CN111700623A (en)* | 2020-07-17 | 2020-09-25 | 华南理工大学 | A system and method for human gait detection based on plantar pressure |
| CN112244819A (en)* | 2020-11-10 | 2021-01-22 | 浙大宁波理工学院 | A system and method for identifying abnormal gait in children based on plantar pressure array detection |
| CN112370049A (en)* | 2020-11-16 | 2021-02-19 | 天津市环湖医院(天津市神经外科研究所、天津市脑系科中心医院) | Freezing gait acquisition and analysis system and method based on multi-mode signal synchronization |
| CN112754468A (en)* | 2021-01-07 | 2021-05-07 | 华南理工大学 | Human body lower limb movement detection and identification method based on multi-source signals |
| CN113273999A (en)* | 2021-05-25 | 2021-08-20 | 南开大学 | Wearable multi-dimensional gait analysis system and method |
| CN113627500A (en)* | 2021-07-28 | 2021-11-09 | 中国长江三峡集团有限公司 | Gait information acquisition system based on multi-sensor fusion and recognition algorithm |
| Title |
|---|
| PEIKAI ZOU, YAXIN WANG, HUAXUAN CAI, TAO PENG , TINGRUI PAN: "Wearable Iontronic FMG for Classification of Muscular Locomotion", IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, vol. 26, no. 7, pages 2854 - 2863, XP011913039, DOI: 10.1109/JBHI.2022.3173968* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119405318A (en)* | 2025-01-07 | 2025-02-11 | 北京航空航天大学 | Muscle strength prediction method and device based on FMG and sEMG signals |
| Publication number | Publication date |
|---|---|
| CN116439693B (en) | 2024-05-28 |
| Publication | Publication Date | Title |
|---|---|---|
| US10986465B2 (en) | Automated detection and configuration of wearable devices based on on-body status, location, and/or orientation | |
| CN112754468B (en) | Human body lower limb movement detection and identification method based on multi-source signals | |
| Luo et al. | A low-cost end-to-end sEMG-based gait sub-phase recognition system | |
| CN109480858B (en) | A wearable intelligent system and method for quantitatively detecting symptoms of bradykinesia in Parkinson's patients | |
| Jain et al. | Stride segmentation of inertial sensor data using statistical methods for different walking activities | |
| CN109480857B (en) | Device and method for detecting frozen gait of Parkinson disease patient | |
| Yuwono et al. | Unsupervised nonparametric method for gait analysis using a waist-worn inertial sensor | |
| Chen et al. | Kinematic analysis of human gait based on wearable sensor system for gait rehabilitation | |
| Lu et al. | Effective recognition of human lower limb jump locomotion phases based on multi-sensor information fusion and machine learning | |
| Fallahzadeh et al. | SmartSock: A wearable platform for context-aware assessment of ankle edema | |
| Pendharkar et al. | Using blind source separation on accelerometry data to analyze and distinguish the toe walking gait from normal gait in ITW children | |
| Jalloul et al. | Activity recognition using complex network analysis | |
| Potluri et al. | Machine learning based human gait segmentation with wearable sensor platform | |
| CN113017616B (en) | A wireless wearable gait signal monitoring system with analysis function | |
| Jiang et al. | Exploration of gait parameters affecting the accuracy of force myography-based gait phase detection | |
| Ye et al. | An adaptive method for gait event detection of gait rehabilitation robots | |
| Pan et al. | Evaluation of hemiplegic gait based on plantar pressure and inertial sensors | |
| CN112115923A (en) | Multichannel time sequence gait analysis algorithm based on direct feature extraction | |
| Fallahzadeh et al. | Smart-cuff: A wearable bio-sensing platform with activity-sensitive information quality assessment for monitoring ankle edema | |
| CN116439693B (en) | A gait detection method and system based on FMG | |
| CN112107290B (en) | System, method and software application for predicting KAM for multiple gait cycles of a subject | |
| CN119896473A (en) | A gait detection and abnormality recognition system based on multi-sensor fusion | |
| Miyake et al. | Heel-contact gait phase detection based on specific poses with muscle deformation | |
| Yang et al. | Rehabilitation Training Evaluation and Correction System Based on BlazePose | |
| Djamaa et al. | BoostSole: Design and realization of a smart insole for automatic human gait classification |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |