CN109946538B - Mobile equipment monitoring method and system based on magnetic induction signals - Google Patents
Mobile equipment monitoring method and system based on magnetic induction signals Download PDFInfo
- Publication number
- CN109946538B CN109946538B CN201910193710.3A CN201910193710A CN109946538B CN 109946538 B CN109946538 B CN 109946538B CN 201910193710 A CN201910193710 A CN 201910193710A CN 109946538 B CN109946538 B CN 109946538B
- Authority
- CN
- China
- Prior art keywords
- magnetic induction
- extracted features
- user
- data
- currently running
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006698 induction Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 title claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000007613 environmental effect Effects 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000000513 principal component analysis Methods 0.000 claims description 7
- 230000006403 short-term memory Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims 2
- 230000006399 behavior Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
Landscapes
- Telephone Function (AREA)
- Measuring Magnetic Variables (AREA)
Abstract
Description
技术领域technical field
本发明涉及一种智能移动设备的旁路监控和管理领域，尤其是涉及一种基于磁感应信号的移动设备监控方法及系统。The invention relates to the field of bypass monitoring and management of intelligent mobile devices, in particular to a method and system for monitoring mobile devices based on magnetic induction signals.
背景技术Background technique
移动设备在我们的日常生活中发挥着不可替代的作用。据预测，到2020年底将有超过90亿部手机，平板电脑和笔记本电脑。捕捉用户设备行为，包括知道用户当前使用的设备类型、哪个应用程序正在运行以及哪个用户正在使用设备，这些信息在移动设备监控管理和用户身份认证等领域很有帮助。但是，一个人可能有多个移动设备，例如一个智能手机和一个笔记本电脑。另一方面，一个移动设备可以由多个用户使用，例如，家庭成员公用一台笔记本电脑。常规认证方法不能区分不同的用户。因此，需要跨平台用户认证的方法来理解用户设备行为。一个简单的解决方案是在每个设备中安装一个进程监视器，并在云端进行统计。尽管该解决方案解决了跨平台问题，但用户识别仍然是一个难题。请注意，通过前置摄像头进行识别对于此问题是不切实际的，因为始终打开摄像头会导致电池在短时间内耗尽。指纹识别是识别用户设备行为的有前途的方法。还有许多其他偏信道的研究来实现这一目标，例如使用加速计、功耗和声信号信息。加速度计和功耗信息因太粗糙而无法准确识别用户，而声音信号可能在很大程度上受到环境的干扰。Mobile devices play an irreplaceable role in our daily life. It is predicted that there will be more than 9 billion mobile phones, tablets and laptops by the end of 2020. Capturing user device behavior, including knowing what type of device the user is currently using, which application is running, and which user is using the device, can be useful in areas such as mobile device monitoring management and user authentication. However, a person may have multiple mobile devices, such as a smartphone and a laptop. On the other hand, a mobile device can be used by multiple users, for example, family members share a laptop. Conventional authentication methods cannot differentiate between different users. Therefore, cross-platform user authentication methods are needed to understand user device behavior. A simple solution is to install a process monitor in each device and keep statistics in the cloud. Although this solution solves the cross-platform problem, user identification is still a difficult problem. Note that identification by the front-facing camera is impractical for this issue, as the camera will always drain the battery in a short period of time. Fingerprinting is a promising method to identify user device behavior. There are many other partial channel studies to achieve this, such as using accelerometers, power consumption, and acoustic signal information. The accelerometer and power consumption information is too coarse to accurately identify the user, while the acoustic signal can be largely disturbed by the environment.
使用磁感应信号进行用户认证核心需要解决时间序列分类问题。传统时间序列分类方法人工提取时间特征，然后将其输入到单个分类器或集成分类器中，生成输出。人工特征提取对专家经验依赖严重，且涉及用户认证这种复杂的场景时很难保证特征选取的准确性。此外，传统的方法大多依赖时域上的特征，然而这些特征很容易随时间变化，导致预先训练好的模型不具有很好的泛化性能。The core of user authentication using magnetic induction signals needs to solve the time series classification problem. Traditional time series classification methods manually extract temporal features, which are then fed into a single classifier or an ensemble of classifiers to generate an output. Manual feature extraction relies heavily on expert experience, and it is difficult to ensure the accuracy of feature selection when it comes to complex scenarios such as user authentication. In addition, traditional methods mostly rely on features in the temporal domain, however, these features are easily time-varying, resulting in pre-trained models that do not have good generalization performance.
电磁信号是进行用户认证和设备管理更合适的解决方案。我们观察到电磁信号是移动设备计算强度的一个反映，例如，重负载应用会提高CPU功耗和其他功耗，从而为应用的识别提供了可能。此外，不同用户在使用同一设备甚至同一应用时会有不同的用户行为习惯，例如：打字的速度、常用的操作等，从而导致电磁信号产生相应的变化。这些也为使用电磁信号进行用户级别的识别提供了可能。近年来，深层神经网络已被用于时间序列分类任务。深度学习模型自动生成特征并达到最先进的性能。长期短期记忆网络则被证明可以很好解决时间序列问题。Electromagnetic signals are a more suitable solution for user authentication and device management. We observe that electromagnetic signals are a reflection of the computational intensity of mobile devices, e.g., heavy-duty applications increase CPU power and other power consumption, thus enabling application identification. In addition, different users will have different user behavior habits when using the same device or even the same application, such as typing speed, common operations, etc., resulting in corresponding changes in electromagnetic signals. These also make it possible to use electromagnetic signals for user-level identification. In recent years, deep neural networks have been used for time series classification tasks. Deep learning models automatically generate features and achieve state-of-the-art performance. Long-term short-term memory networks have been shown to be very good at solving time series problems.
发明内容SUMMARY OF THE INVENTION
本发明的目的就是为了克服上述现有技术存在的缺陷而提供一种基于磁感应信号的移动设备监控方法及系统。The purpose of the present invention is to provide a method and system for monitoring a mobile device based on a magnetic induction signal in order to overcome the above-mentioned defects in the prior art.
本发明的目的可以通过以下技术方案来实现：The object of the present invention can be realized through the following technical solutions:
一种基于磁感应信号的移动设备监控方法，包括：A method for monitoring a mobile device based on a magnetic induction signal, comprising:
收集环境磁感应数据；Collect environmental magnetic induction data;
对所述磁感应数据进行预处理；preprocessing the magnetic induction data;
对预处理后的磁感应数据进行特征提取；Perform feature extraction on the preprocessed magnetic induction data;
将提取的特征输入预训练好的识别模型，输出识别结果，其中，所述识别结果包括使用设备的用户、设备类别和当前运行的应用中的一个或多个。The extracted features are input into the pre-trained recognition model, and a recognition result is output, wherein the recognition result includes one or more of a user using the device, a device category, and a currently running application.
所述对所述磁感应数据进行预处理，包括：The preprocessing of the magnetic induction data includes:
采用高斯滤波算法进行平滑滤波；Smooth filtering using Gaussian filtering algorithm;
采用快速傅里叶变换得到频域信号；Use fast Fourier transform to obtain the frequency domain signal;
采用主成分分析提取其主要成分。The principal components were extracted by principal component analysis.
所述对预处理后的磁感应数据进行特征提取，包括：The feature extraction of the preprocessed magnetic induction data includes:
进行对预处理后的磁感应数据进行时间窗口划分；Perform time window division on the preprocessed magnetic induction data;
使用全连接卷积神经网络模型基于单个时间窗口的时域信号和频域信号进行特征提取。Feature extraction is performed based on the time domain signal and frequency domain signal of a single time window using a fully connected convolutional neural network model.
所述识别结果包括使用设备的用户、设备类别和当前运行的应用；The identification result includes the user using the device, the device category and the currently running application;
所述将提取的特征输入预训练好的识别模型，输出识别结果，具体包括：Inputting the extracted features into a pre-trained recognition model, and outputting a recognition result, specifically includes:
将提取的特征输入预训练好的识别模型；Input the extracted features into the pre-trained recognition model;
根据提取的特征识别得到设备类别；Identify the device category according to the extracted features;
根据提取的特征和得到的设备类别识别得到当前运行的应用；Identify the currently running application according to the extracted features and the obtained device category;
根据提取的特征、得到的设备类别和当前运行的应用识别得到使用设备的用户。Identify the user who uses the device according to the extracted features, the obtained device category and the currently running application.
所述识别模型为包含时域和频域特征的长短期记忆全卷积神经网络。The recognition model is a long short-term memory full convolutional neural network including time domain and frequency domain features.
一种基于磁感应信号的移动设备监控系统，包括贴片式磁力传感器，以及与贴片式磁力传感器连接的上位机，所述上位机包括：A mobile device monitoring system based on magnetic induction signals, comprising a patch-type magnetic sensor and a host computer connected to the patch-type magnetic sensor, the host computer comprising:
数据预处理模块，接收贴片式磁力传感器发送的环境磁感应数据，并对所述磁感应数据进行预处理；The data preprocessing module receives the environmental magnetic induction data sent by the chip magnetic sensor, and preprocesses the magnetic induction data;
特征提取模块，对预处理后的磁感应数据进行特征提取；The feature extraction module extracts features from the preprocessed magnetic induction data;
识别分类模块，用于将提取的特征输入预训练好的识别模型，输出识别结果，其中，所述识别结果包括使用设备的用户、设备类别和当前运行的应用中的一个或多个。The recognition and classification module is configured to input the extracted features into the pre-trained recognition model, and output the recognition result, wherein the recognition result includes one or more of the user using the device, the device category and the currently running application.
所述贴片式磁力传感器和上位机通过无线通信方式传输数据。The patch-type magnetic sensor and the upper computer transmit data through wireless communication.
所述对所述磁感应数据进行预处理，包括：The preprocessing of the magnetic induction data includes:
采用高斯滤波算法进行平滑滤波；Smooth filtering using Gaussian filtering algorithm;
采用快速傅里叶变换得到频域信号；The frequency domain signal is obtained by using fast Fourier transform;
采用主成分分析提取其主要成分。The principal components were extracted by principal component analysis.
所述识别结果包括使用设备的用户、设备类别和当前运行的应用；The identification result includes the user using the device, the device category and the currently running application;
所述将提取的特征输入预训练好的识别模型，输出识别结果，具体包括：Inputting the extracted features into a pre-trained recognition model, and outputting a recognition result, specifically includes:
将提取的特征输入预训练好的识别模型；Input the extracted features into the pre-trained recognition model;
根据提取的特征识别得到设备类别；Identify the device category according to the extracted features;
根据提取的特征和得到的设备类别识别得到当前运行的应用；Identify the currently running application according to the extracted features and the obtained device category;
根据提取的特征、得到的设备类别和当前运行的应用识别得到使用设备的用户。Identify the user who uses the device according to the extracted features, the obtained device category and the currently running application.
所述对预处理后的磁感应数据进行特征提取，包括：The feature extraction of the preprocessed magnetic induction data includes:
进行对预处理后的磁感应数据进行时间窗口划分；Perform time window division on the preprocessed magnetic induction data;
使用全连接卷积神经网络模型基于单个时间窗口的时域信号和频域信号进行特征提取。Feature extraction is performed based on the time domain signal and frequency domain signal of a single time window using a fully connected convolutional neural network model.
与现有技术相比，本发明具有以下有益效果：Compared with the prior art, the present invention has the following beneficial effects:
1)在不改变现有电器设备硬件结构的情况下，通过磁场强度传感器，采集智能移动设备工作时自身产生的磁感应信号来完成设备类型的识别、工作状态的识别，以及用户的识别，低成本地实现了移动智能设备的用户认证和设备监控与管理。1) Without changing the hardware structure of the existing electrical equipment, through the magnetic field strength sensor, the magnetic induction signal generated by the smart mobile device itself is collected to complete the identification of the device type, the working status, and the user, and the low cost It realizes user authentication and device monitoring and management of mobile smart devices.
2)在预处理环节，采用了经过快速傅里叶变换的频域信号作为补充，可以弥补时域上的磁感应信号信息很容易受到外界干扰的不足，提高可靠性。2) In the preprocessing link, the frequency domain signal that has undergone fast Fourier transform is used as a supplement, which can make up for the deficiency that the magnetic induction signal information in the time domain is easily affected by external interference and improve reliability.
3)使用了主成分分析提取其主要成分，可以避免特征维度过高对系统性能和模型泛化能力造成干扰。3) Using principal component analysis to extract its main components, it can avoid the interference of high feature dimension on system performance and model generalization ability.
4)适用性强，能够应用于各种类型的智能移动设备。4) It has strong applicability and can be applied to various types of smart mobile devices.
5)提出的频域-时域分层深度学习模型，可用于连续可靠地区分应用和用户，即使存在未知的应用程序和用户，这种方法也能很好地执行。5) The proposed frequency-time-domain hierarchical deep learning model can be used to continuously and reliably distinguish applications and users, which performs well even in the presence of unknown applications and users.
附图说明Description of drawings
图1为本发明的整体架构图；Fig. 1 is the overall structure diagram of the present invention;
图2为发明的数据预处理流程图；Fig. 2 is the data preprocessing flow chart of the invention;
图3为多种算法模型分类准确率的比较图；Figure 3 is a comparison chart of the classification accuracy of various algorithm models;
图4为多种算法模型训练时间的比较图。Figure 4 is a comparison diagram of the training time of various algorithm models.
具体实施方式Detailed ways
下面结合附图和具体实施例对本发明进行详细说明。本实施例以本发明技术方案为前提进行实施，给出了详细的实施方式和具体的操作过程，但本发明的保护范围不限于下述的实施例。The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and provides a detailed implementation manner and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.
本申请突破了传统用户认证和设备管理的局限，首创通过跟踪移动设备发出的磁信号来识别用户设备行为。本发明还提出了TF-LSTM-FCN分层分类模型，用于连续可靠地区分应用和用户。即使存在未知的应用程序和用户，这种方法也能很好地执行。本发明能够准确分类用户当前使用的设备类型、正在运行的应用程序以及正在使用这个设备的用户，这些信息在移动设备管理和用户认证等领域很有帮助。This application breaks through the limitations of traditional user authentication and device management, and is the first to identify user device behavior by tracking the magnetic signals emitted by mobile devices. The present invention also proposes a TF-LSTM-FCN hierarchical classification model for continuously and reliably distinguishing applications and users. This approach performs well even in the presence of unknown applications and users. The present invention can accurately classify the device type currently used by the user, the running application program and the user who is using the device, and these information are very helpful in the fields of mobile device management and user authentication.
具体的，本申请的结构需要包括贴片式磁力传感器，以及与贴片式磁力传感器连接的上位机，上位机包括：Specifically, the structure of the present application needs to include a patch-type magnetic sensor and a host computer connected to the patch-type magnetic force sensor, and the host computer includes:
数据预处理模块，接收贴片式磁力传感器发送的环境磁感应数据，并对磁感应数据进行预处理；The data preprocessing module receives the environmental magnetic induction data sent by the SMD magnetic sensor, and preprocesses the magnetic induction data;
特征提取模块，对预处理后的磁感应数据进行特征提取；The feature extraction module extracts features from the preprocessed magnetic induction data;
识别分类模块，用于将提取的特征输入预训练好的识别模型，输出识别结果，其中，识别结果包括使用设备的用户、设备类别和当前运行的应用中的一个或多个。The recognition and classification module is used for inputting the extracted features into the pre-trained recognition model and outputting the recognition result, wherein the recognition result includes one or more of the user using the device, the device category and the currently running application.
贴片式磁力传感器和上位机通过无线通信方式传输数据，优选为WiFi方式，磁力传感器由于功耗较低，可以配置电池为自身供能。The SMD magnetic sensor and the host computer transmit data through wireless communication, preferably WiFi. Due to the low power consumption of the magnetic sensor, a battery can be configured to supply energy for itself.
其中的，对磁感应数据进行预处理，包括：采用高斯滤波算法进行平滑滤波；采用快速傅里叶变换得到频域信号；采用主成分分析提取其主要成分。Among them, the preprocessing of the magnetic induction data includes: using Gaussian filtering algorithm for smooth filtering; using fast Fourier transform to obtain frequency domain signals; using principal component analysis to extract its main components.
具体的，由于贴片式磁力传感器收集的磁感应数据存在很多噪声，噪声主要分为人工操作、线性噪声能量、电极噪声、外界噪声和内部噪声。这些噪声可以通过调整贴片电路板的位置、周边探测环境，还有一些滤波噪声的算法来减小噪声信号对有用传感器信号的干扰。所以在进行特征提取之前需要进行数据预处理，先对窗口中的数据进行归一化，在采用高斯滤波算法进行平滑滤波。此外，实验发现时域上的磁感应信号信息很容易受到外界干扰，因此本发明同时采用了经过快速傅里叶变换的频域信号作为补充；为了避免特征维度过高对系统性能和模型泛化能力造成干扰，频域信息同时使用了主成分分析提取其主要成分。Specifically, since there is a lot of noise in the magnetic induction data collected by the chip magnetic sensor, the noise is mainly divided into manual operation, linear noise energy, electrode noise, external noise and internal noise. These noises can be adjusted by adjusting the position of the SMD circuit board, the surrounding detection environment, and some algorithms to filter the noise to reduce the interference of the noise signal to the useful sensor signal. Therefore, it is necessary to perform data preprocessing before feature extraction. First, the data in the window is normalized, and then the Gaussian filtering algorithm is used for smooth filtering. In addition, it is found that the magnetic induction signal information in the time domain is easily disturbed by the outside world, so the present invention also uses the frequency domain signal that has undergone fast Fourier transform as a supplement; in order to avoid excessive feature dimensions, system performance and model generalization ability To cause interference, the frequency domain information is also used to extract its principal components using principal component analysis.
传统的手工提取特征的方法通常耗时，需要额外的领域知识。因此，我们转向深度学习算法自动提取特征。已有的研究表明，全卷积网络在从时间序列数据中提取特征的质量和效率方面表现良好。因此，在时域和频域上，应用全卷积神经网络提取特征。如图2所示，将时域和频域数据一起加入模型进行特征提取和分类。在我们使用模型直接分类时间序列数据之后，由于分类的三个级别(设备、应用程序和用户级别)并不相互独立。例如，当对设备的类型进行分类时，结果不受设备上运行的应用程序和这个设备的用户的影响；而分类应用程序的结果又与设备的类型有很强的联系。因此，我们使用层次分类，以提高每个分类模型的准确性。Traditional methods of manually extracting features are usually time-consuming and require additional domain knowledge. Therefore, we turn to deep learning algorithms to automatically extract features. Existing studies have shown that fully convolutional networks perform well in terms of the quality and efficiency of feature extraction from time series data. Therefore, in both time and frequency domains, fully convolutional neural networks are applied to extract features. As shown in Figure 2, time domain and frequency domain data are added to the model together for feature extraction and classification. After we use the model to directly classify time series data, since the three levels of classification (device, application and user level) are not independent of each other. For example, when classifying the type of device, the results are not affected by the applications running on the device and the user of this device; and the results of classifying applications are strongly related to the type of device. Therefore, we use hierarchical classification to improve the accuracy of each classification model.
识别模型需要进行预先训练，如图1所示，对于识别模型而言需要训练模型和实时预测。在训练模型中，系统首先收集历史电磁信号，并标记移动设备模型、用户和应用类型等信息，然后将标记后的信号馈送到所提出的分层深层学习算法中，用于监督训练。在实时预测步骤中，将实时磁感应信号输入到训练好的模型，模型返回预测结果，例如，用户A在设备B上使用软件C，实现了移动智能设备的用户认证和设备管理；The recognition model needs to be pre-trained, as shown in Figure 1, for the recognition model, the training model and real-time prediction are required. In training the model, the system first collects historical electromagnetic signals and labels information such as mobile device model, user, and application type, and then feeds the labelled signals into the proposed hierarchical deep learning algorithm for supervised training. In the real-time prediction step, the real-time magnetic induction signal is input into the trained model, and the model returns the prediction result. For example, user A uses software C on device B to realize user authentication and device management of mobile smart devices;
本申请采用的分类器算法为频域-时域长短期记忆全卷积神经网络(Time-Frequency Long Short Term Memory Fully ConvolutionalNetwork,TF-LSTM-FCN)。LSTM是一个常用来处理时间序列问题的时间递归神经网络，由于独特的设计结构，LSTM适合于处理和预测时间序列中间隔和延迟非常长的重要事件，通常用在模式识别、自然语言处理等领域。使用时域和频域信息增强，并使用全卷积神经网络自动化特征提取的TF-LSTM-FCN模型能够充分利用原始电磁感应数据提供的信息，实现了移动智能设备的用户认证和设备管理的完全智能化。The classifier algorithm adopted in this application is a frequency domain-time domain long short term memory fully convolutional neural network (Time-Frequency Long Short Term Memory Fully Convolutional Network, TF-LSTM-FCN). LSTM is a time recurrent neural network commonly used to deal with time series problems. Due to its unique design structure, LSTM is suitable for processing and predicting important events with very long intervals and delays in time series. It is usually used in pattern recognition, natural language processing and other fields. . The TF-LSTM-FCN model, augmented with time domain and frequency domain information and automated feature extraction using fully convolutional neural networks, can make full use of the information provided by the raw electromagnetic induction data, and realize complete user authentication and device management of mobile smart devices. Intelligent.
本申请将训练好的实时传感器数据分类器模型运用到实际应用中，并验证模型的分类效果。在实验室环境下，选取了10个用户在10种智能移动设备使用30种不同应用程序的数据。设备类型分别：苹果，惠普，联想，三星，戴尔，弘基，华硕等笔记本电脑，应用类型包括微软Word,Excel,PPT,微信，QQ，Minecraft等。如图3和图4所示，实验表明本系统能够对94.31％的用户、91.64％的应用和98.6％的移动设备进行正确分类。This application applies the trained real-time sensor data classifier model to practical applications, and verifies the classification effect of the model. In the laboratory environment, the data of 10 users using 30 different applications on 10 smart mobile devices were selected. The device types are: Apple, HP, Lenovo, Samsung, Dell, Hongji, ASUS and other laptops, and the application types include Microsoft Word, Excel, PPT, WeChat, QQ, Minecraft, etc. As shown in Figures 3 and 4, experiments show that the system can correctly classify 94.31% of users, 91.64% of applications and 98.6% of mobile devices.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910193710.3A CN109946538B (en) | 2019-03-14 | 2019-03-14 | Mobile equipment monitoring method and system based on magnetic induction signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910193710.3A CN109946538B (en) | 2019-03-14 | 2019-03-14 | Mobile equipment monitoring method and system based on magnetic induction signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109946538A CN109946538A (en) | 2019-06-28 |
| CN109946538B true CN109946538B (en) | 2020-06-19 |
Family
ID=67008846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910193710.3A Active CN109946538B (en) | 2019-03-14 | 2019-03-14 | Mobile equipment monitoring method and system based on magnetic induction signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109946538B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113569930B (en) * | 2021-07-15 | 2024-10-22 | 南京逸智网络空间技术创新研究院有限公司 | Intelligent equipment application identification method based on magnetic field data side channel analysis |
| CN116611585A (en) * | 2023-07-18 | 2023-08-18 | 北京辰尧科技有限公司 | Mobile device management method and system and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320966A (en) * | 2015-10-30 | 2016-02-10 | 东软集团股份有限公司 | Vehicle driving state recognition method and apparatus |
| CN109039643A (en) * | 2018-06-28 | 2018-12-18 | 中南民族大学 | A kind of sustainable method for authenticating user identity and system based on electromagnetic radiation |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096798B (en) * | 2011-01-25 | 2013-08-21 | 上海交通大学 | Signal processing method for electromagnetic induction state recognition |
| CN103425999A (en) * | 2013-08-27 | 2013-12-04 | 西安电子科技大学 | Brain cognitive state judgment method based on non-negative tensor projection operator decomposition algorithm |
| WO2017185068A1 (en) * | 2016-04-21 | 2017-10-26 | Carnegie Mellon University | A system for enabling rich contextual applications for interface-poor smart devices |
| CN107292359B (en) * | 2017-05-04 | 2019-12-17 | 浙江大学 | A cross-device item marking method and device based on electromagnetic signal feature recognition |
| CN107273795B (en) * | 2017-05-04 | 2019-12-17 | 浙江大学 | A method and device for constructing a cross-device electromagnetic fingerprint database based on machine learning |
| CN107220506A (en) * | 2017-06-05 | 2017-09-29 | 东华大学 | Breast cancer risk assessment analysis system based on deep convolutional neural network |
| CN107423756A (en) * | 2017-07-05 | 2017-12-01 | 武汉科恩斯医疗科技有限公司 | Nuclear magnetic resonance image sequence sorting technique based on depth convolutional neural networks combination shot and long term memory models |
| US9964607B1 (en) * | 2017-08-28 | 2018-05-08 | Seagate Technology Llc | Recognizing and identifying defect patterns on magnetic media |
| CN108196998A (en) * | 2018-01-02 | 2018-06-22 | 联想(北京)有限公司 | A kind of state identification method, mobile equipment and server |
| CN108596150A (en) * | 2018-05-10 | 2018-09-28 | 南京大学 | A kind of Activity recognition system and its working method excluding abnormal operation |
| CN109344809A (en) * | 2018-11-21 | 2019-02-15 | 上海交通大学 | An intelligent management system for household electrical appliances based on magnetic induction signals |
-
2019
- 2019-03-14 CN CN201910193710.3A patent/CN109946538B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320966A (en) * | 2015-10-30 | 2016-02-10 | 东软集团股份有限公司 | Vehicle driving state recognition method and apparatus |
| CN109039643A (en) * | 2018-06-28 | 2018-12-18 | 中南民族大学 | A kind of sustainable method for authenticating user identity and system based on electromagnetic radiation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109946538A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109309630B (en) | Network traffic classification method and system and electronic equipment | |
| KR101939683B1 (en) | Apparatus and method for recognizing user activity | |
| Rossi et al. | AmbientSense: A real-time ambient sound recognition system for smartphones | |
| CN110390357A (en) | A DTU Security Monitoring Method Based on Side Channels | |
| CN113435546A (en) | Migratable image recognition method and system based on differentiation confidence level | |
| CN108806718B (en) | Audio identification method based on analysis of ENF phase spectrum and instantaneous frequency spectrum | |
| US20190043489A1 (en) | Acoustic event detector with reduced resource consumption | |
| CN109946538B (en) | Mobile equipment monitoring method and system based on magnetic induction signals | |
| CN113793620A (en) | Speech noise reduction method, device, device and storage medium based on scene classification | |
| CN118646823B (en) | Call quality intelligent detection method, device and storage medium | |
| Pan et al. | Cognitive acoustic analytics service for Internet of Things | |
| CN111339511A (en) | Identity validity verification method and device and terminal equipment | |
| CN116304915B (en) | WiFi-based contactless action recognition method, system and laboratory device | |
| CN103778916A (en) | Method and system for monitoring environmental sound | |
| Ji et al. | No seeing is also believing: electromagnetic-emission-based application guessing attacks via smartphones | |
| CN116907029A (en) | Methods and control devices for detecting abnormality of fans in outdoor units and air-conditioning outdoor units | |
| CN117079005A (en) | Optical cable fault monitoring method, system, device and readable storage medium | |
| CN110751942A (en) | Method and device for identifying characteristic sound | |
| Yang et al. | Magprint: Deep learning based user fingerprinting using electromagnetic signals | |
| CN115080972A (en) | A method and device for detecting abnormal access to an interface of a power mobile terminal | |
| CN106874852A (en) | A kind of device-fingerprint based on acceleration transducer is extracted and recognition methods | |
| CN118262746B (en) | Intelligent noise identification method | |
| Liu et al. | WiFi sensing for drastic activity recognition with CNN-BiLSTM architecture | |
| CN112863548A (en) | Method for training audio detection model, audio detection method and device thereof | |
| Vecchio et al. | Gait-based authentication: Evaluation of energy consumption on commercial devices |
Legal Events
| 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 | ||
| CB02 | Change of applicant information |
Address after: 200030 Dongchuan Road, Minhang District, Minhang District, Shanghai Applicant after: Shanghai Jiaotong University Address before: 200030 Huashan Road, Shanghai, No. 1954, No. Applicant before: Shanghai Jiaotong University |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |