Gesture control reconfigurable metasurface system based on wearable device

Abstract

The invention relates to the field of electromagnetic wave regulation and control, and provides a gesture control reconfigurable metasurface system based on wearable equipment, which comprises the wearable equipment, a gesture recognition model, a field programmable gate array and a reconfigurable metasurface, and is characterized in that the wearable equipment is used for collecting and processing surface electromyogram signals in real time and transmitting the surface electromyogram signals to the gesture recognition model; the gesture recognition model efficiently recognizes the electromyographic signals collected by the wearable device in real time, and gesture signals are obtained; the field programmable gate array loads a coding matrix corresponding to a gesture signal recognized by the gesture recognition model to the reconfigurable metasurface, and the reconfigurable metasurface achieves the functions of beam deflection and polarization conversion. According to the invention, the combination of real-time regulation and control of human physiological signals and electromagnetic waves is realized, the method has important potential application in the aspects of intelligent equipment control, virtual reality systems and wireless communication technologies, and a new technical support is provided for progress and innovation of a human-computer interaction technology.

Description

Technical Field

[0001] The present invention relates to the field of electromagnetic wave regulation, and in particular to a gesture-controlled reconfigurable metasurface system based on a wearable device. Background Art

[0002] With the development of information technology and wireless communication technology, the way of human-computer interaction is also constantly evolving. Traditional input devices such as keyboards and mice can no longer meet the growing demand for human-computer interaction. In recent years, gesture recognition has received widespread attention as a natural and intuitive way of human-computer interaction. Through gesture recognition technology, users can control electronic devices through simple gestures, which greatly improves the convenience of interaction and user experience. The gesture recognition methods currently implemented mainly include computer vision methods, radio frequency methods, and wearable devices. Computer vision methods are sensitive to lighting conditions and may affect recognition accuracy in complex backgrounds. Radio frequency methods also face problems such as signal interference and multipath effects. The wearable device method can effectively solve these problems and become an effective method for gesture recognition.

[0003] At the same time, research in the field of electromagnetic wave control has made significant progress, especially the application of reconfigurable metasurface technology. Reconfigurable metasurface is a new type of artificial structure material that can dynamically adjust its reflection, refraction or other electromagnetic properties to achieve flexible control of incident electromagnetic waves. This technology has been applied to many fields such as wireless communications and radar stealth. However, there is still little research on real-time control of electromagnetic waves in combination with human physiological signals. Summary of the invention

[0004] In view of the shortcomings of the above-mentioned technologies, the purpose of the present invention is to provide a gesture-controlled reconfigurable metasurface system based on wearable devices, which can realize the combination of human physiological signals and real-time regulation of electromagnetic waves. It has important potential applications in intelligent device control, virtual reality systems and wireless communication technologies, and provides new technical support for the advancement and innovation of human-computer interaction technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A gesture-controlled reconfigurable metasurface system based on a wearable device includes a wearable device, a gesture recognition model, a field programmable gate array, and a reconfigurable metasurface, wherein: The wearable device can collect and process surface electromyographic signals in real time and transmit them to a gesture recognition model; the gesture recognition model can recognize the electromyographic signals collected by the wearable device in real time and efficiently to obtain gesture signals; the field programmable gate array can load the coding matrix corresponding to the gesture signals recognized by the gesture recognition model into the reconfigurable metasurface, and the reconfigurable metasurface can realize beam deflection and polarization conversion functions.

[0006] Specifically, the wearable device is a wearable armband with multiple electromyography sensor channels, which amplifies, notches and bandpass filters the collected surface electromyography signals, and transmits the data to the gesture recognition model via Bluetooth.

[0007] Specifically, the gesture recognition model is a CNN-Transformer hybrid model, which includes an input layer, a CNN module, a Transformer module, and an output layer, wherein: The CNN module includes a convolution layer, a batch normalization layer, a ReLu activation layer and a pooling layer; the Transformer module includes an embedding layer and a Transformer Encoder layer; the output layer includes a fully connected layer and a Softmax layer; During the model training process, the collected surface electromyography signal data is normalized and then imported into the input layer of the CNN-Transformer hybrid model; the convolution layer in the CNN module extracts local features from the input data by applying multiple convolution kernels; the batch normalization layer and the ReLu activation layer speed up the training process and introduce nonlinearity; the pooling layer performs downsampling to reduce the number of features and retain the most relevant features; the embedding layer in the Transformer module embeds the features extracted by CNN into a higher-dimensional space to enhance the expressiveness of the model; the Transformer Encoder layer performs self-attention modeling to capture long-term dependencies; after being processed by the CNN module and the Transformer module, it is finally mapped to a variety of predefined gestures through the output layer.

[0008] Specifically, the input of the field programmable gate array is connected to the gesture recognition model, and the output pin of the field programmable gate array 3 is connected to the reconfigurable metasurface.

[0009] Specifically, the reconfigurable metasurface is composed of a number of metasurface units arranged periodically; the structure of the metasurface unit includes, from top to bottom, a stacked top square patch, a first dielectric substrate, a ground layer, a second dielectric substrate, and a bottom reflective phase shifter; the top square patch, the ground layer, and the bottom reflective phase shifter are three metal layers; The metasurface unit also includes a first metal via, a second metal via, a third metal via, a fourth metal via, and two bottom-layer DC voltage bias line circuits, wherein the two bottom-layer DC voltage bias line circuits are respectively a first bottom-layer DC voltage bias line circuit and a second bottom-layer DC voltage bias line circuit, wherein: the first metal via passes through the first dielectric substrate, the ground layer, and the second dielectric substrate, and is respectively connected to the top-layer square patch and the bottom-layer reflective phase shifter; the second metal via passes through the first dielectric substrate, and is respectively connected to the top-layer square patch and the ground layer; the third metal via passes through the second dielectric substrate, and is respectively connected to the ground layer and the first bottom-layer DC voltage bias line circuit; the fourth metal via passes through the second dielectric substrate, and is respectively connected to the ground layer and the second bottom-layer DC voltage bias line circuit.

[0010] Further, the bottom reflective phase shifter comprises a first microstrip transmission line, a first branch microstrip transmission line, a second branch microstrip transmission line, a second microstrip transmission line, a fan-shaped microstrip stub, a first square patch, a second square patch, and three PIN diodes; the three PIN diodes are respectively a first PIN diode, a second PIN diode, and a third PIN diode; One end of the first branch microstrip transmission line and the second branch microstrip transmission line is vertically connected to the first microstrip transmission line; the other ends of the first branch microstrip transmission line and the second branch microstrip transmission line are connected to the second microstrip transmission line through the first PIN diode and the second PIN diode respectively; the second microstrip transmission line 4-1-5-4 is parallel to the first microstrip transmission line 4-1-5-1, and the two ends of the second microstrip transmission line are respectively connected to the first square patch and the second square patch; the fan-shaped microstrip stub is connected to one end of the first microstrip transmission line through the third PIN diode.

[0011] Furthermore, the first bottom DC voltage bias line circuit is connected to the fan-shaped microstrip stub of the bottom reflective phase shifter, and the second bottom DC voltage bias line circuit is connected to the first square patch of the bottom reflective phase shifter; the closing or opening state of three PIN diodes (first PIN diode, second PIN diode, third PIN diode) is controlled by two bottom DC voltage bias line circuits (first bottom DC voltage bias line circuit and second bottom DC voltage bias line circuit) to achieve different reflection phase responses of the bottom reflective phase shifter.

[0012] Furthermore, the bottom reflective phase shifter has four reflective phase responses, which are 0°, 90°, 180° and 270°. Correspondingly, the four reflective phase responses are encoded into four digital coding states "A", "B", "C" and "D", respectively, where: The digital coding state "A" indicates that the first PIN diode, the second PIN diode, and the third PIN diode are in the off state; the digital coding state "B" indicates that the first PIN diode and the second PIN diode are in the off state, and the third PIN diode is in the on state; the digital coding state "C" indicates that the first PIN diode and the second PIN diode are in the on state, and the third PIN diode is in the off state; the digital coding state "D" indicates that the first PIN diode, the second PIN diode, and the third PIN diode are in the on state.

[0013] Compared with the prior art, the advantages and beneficial effects of the present invention are: The present invention proposes a gesture-controlled reconfigurable metasurface system based on wearable devices for real-time beam deflection and polarization conversion. In terms of surface electromyography signal gesture recognition, the system of the present invention innovatively combines the ability of CNN to extract local spatial features with the advantage of the Transformer model in modeling global temporal dependencies through the self-attention mechanism, significantly improving the model performance and achieving a high classification accuracy of 98.54%. In the metasurface design, a 2-bit reconfigurable metasurface using only three PIN diodes is proposed, and by separating the radiation part from the phase shift part, the design complexity and phase quantization error are balanced, and the integration of diodes is facilitated.

[0014] This invention combines surface electromyography gesture recognition technology and reconfigurable metasurface technology for the first time, and proposes a new type of gesture-controlled metasurface system, which is expected to bring new breakthroughs in the field of human-computer interaction. In addition, the system of the invention represents a pioneering integration of multidisciplinary cutting-edge technologies such as biomedical engineering (surface electromyography signal acquisition and processing), artificial intelligence (gesture recognition model) and electromagnetics (metasurface design and control), achieving interdisciplinary cooperation and innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the gesture-controlled reconfigurable metasurface system described in the present invention; Figure 2 Schematic diagram of signal collection of the wearable device described in the present invention. (a) is the surface electromyography signal collection armband and the gesture selected in the embodiment, and (b) is the surface electromyography signal corresponding to the first gesture; Figure 3 Schematic diagram of the CNN-Transformer hybrid model described in the present invention. (a) is the network structure diagram of the CNN-Transformer hybrid model, and (b) is the recognition accuracy of the trained CNN-Transformer hybrid model; Figure 4Schematic diagram of the structure of the reconfigurable metasurface unit described in the present invention. (a) is a three-dimensional structure diagram, (b) is a top view, and (c) is a bottom view; Figure 5 The experimental results of the beam deflection of the reconfigurable metasurface described in the present invention. Among them, (a) is the unit coding matrix corresponding to the reconfigurable metasurface beam deflection of 10°, (b) is the scattering result diagram of the metasurface beam deflection of 10° after the relevant gesture is recognized and the coding matrix is ​​loaded, (c) is the unit coding matrix corresponding to the reconfigurable metasurface beam deflection of 30°, (d) is the scattering result diagram of the metasurface beam deflection of 30° after the relevant gesture is recognized and the coding matrix is ​​loaded; Figure 6 The experimental results of polarization conversion of the reconfigurable metasurface described in the present invention. Among them, (a) is the unit coding matrix of the reconfigurable metasurface converted from linear polarization to left-hand circular polarization, (b) is the axial ratio result diagram of the metasurface converting linear polarization to left-hand circular polarization after the relevant gesture is recognized and the coding matrix is ​​loaded, (c) is the unit coding matrix of the reconfigurable metasurface converted from linear polarization to right-hand circular polarization, and (d) is the axial ratio result diagram of the metasurface converting linear polarization to right-hand circular polarization after the relevant gesture is recognized and the coding matrix is ​​loaded.

[0016] Reference numerals: Wearable armband 1, CNN-Transformer hybrid model 2, field programmable gate array 3, reconfigurable metasurface 4, metasurface unit 4-1, wearing method diagram 5, first gesture 6, second gesture 7, third gesture 8, fourth gesture 9, fifth gesture 10, sixth gesture 11, seventh gesture 12, eighth gesture 13, top square patch 4-1-1, first dielectric substrate 4-1-2, ground layer 4-1-3, second dielectric substrate 4-1-4, bottom reflective phase shifter 4-1-5, first metal via 4-1-6, second metal via 4-1-7, third metal via 4-1- 8, fourth metal through column 4-1-9, first bottom layer DC voltage bias line circuit 4-1-10, second bottom layer DC voltage bias line circuit 4-1-11, first microstrip transmission line 4-1-5-1, first branch microstrip transmission line 4-1-5-2, second branch microstrip transmission line 4-1-5-3, second microstrip transmission line 4-1-5-4, fan-shaped microstrip stub 4-1-5-5, first square patch 4-1-5-6, second square patch 4-1-5-7, first PIN diode 4-1-5-8, second PIN diode 4-1-5-9, third PIN diode 4-1-5-10. DETAILED DESCRIPTION

[0017] The technical solution provided by the present application will be further described below in conjunction with specific embodiments and accompanying drawings. The advantages and features of the present application will become more apparent with the following description.

[0018] like Figure 1 As shown, a gesture-controlled reconfigurable metasurface system based on a wearable device for real-time beam steering and polarization conversion includes: A wearable device, specifically a wearable armband 1, collects multi-channel surface electromyography signals; The gesture recognition model, specifically a CNN-Transformer hybrid model2, runs on a computer to recognize various gesture signals; Field Programmable Gate Array 3; Reconfigurable metasurface 4. The wearable armband 1 is connected to the CNN-Transformer hybrid model 2 in the computer via Bluetooth, the CNN-Transformer hybrid model 2 is connected to the field programmable gate array 3 via USB, and the output pin of the field programmable gate array 3 is connected to the reconfigurable metasurface 4.

[0019] In the embodiment, the wearable armband 1 has 8 electromyographic sensor channels, which can perform 2000 times amplification, 50Hz notch filtering, 15-550Hz bandpass filtering and other processing on the collected surface electromyographic signals, and transmit the data to the CNN-Transformer hybrid model 2 via Bluetooth.

[0020] like Figure 2 As shown in (a), the wearing method of the wearable armband 1 for collecting surface electromyography signals is shown in Figure 5. It is worn on the forearm, and the eight gestures used for identification are respectively recorded as the first gesture 6, the second gesture 7, the third gesture 8, the fourth gesture 9, the fifth gesture 10, the sixth gesture 11, the seventh gesture 12, and the eighth gesture 13. Each gesture has its corresponding electromagnetic wave control function. In the embodiment, the eight gestures correspond to the eight electromagnetic wave control functions of the reconfigurable metasurface. For example, the first gesture 6 corresponds to the conversion of linear polarization to left-hand circular polarization, the eighth gesture 13 corresponds to the conversion of linear polarization to right-hand circular polarization, the second gesture 7 corresponds to a beam deflection of 10°, and the fourth gesture 9 corresponds to a beam deflection of 30°. Figure 2 (b) shows an electromyographic signal collected when performing the first gesture 6 for example.

[0021] like Figure 3 As shown, the CNN-Transformer hybrid model includes an input layer, a CNN module, a Transformer module, and an output layer. The CNN module includes a convolutional layer, a batch normalization layer, a ReLu activation layer, and a pooling layer; the Transformer module includes an embedding layer and a Transformer Encoder layer; and the output layer includes a fully connected layer and a Softmax layer.

[0022] During the model training process, the collected surface electromyography data is normalized and then imported into the input layer of the CNN-Transformer hybrid model. The convolution layer in the CNN module extracts local features from the input data by applying multiple convolution kernels. The batch normalization layer and ReLu activation layer can speed up the training process and introduce nonlinearity. The pooling layer performs downsampling to reduce the number of features and retain the most relevant features. The embedding layer in the Transformer module embeds the features extracted by CNN into a higher-dimensional space to enhance the expressive power of the model; the Transformer Encoder layer performs self-attention modeling to capture long-term dependencies. After being processed by the CNN module and the Transformer module, it is finally mapped to the eight predefined gestures through the output layer.

[0023] The CNN-Transformer hybrid model combines the ability of convolutional neural networks to extract local features with the advantage of the Transformer model in modeling global temporal dependencies through the self-attention mechanism, achieving efficient processing of electromyographic signals. Through multi-level feature extraction and spatiotemporal feature collaborative learning, the model can simultaneously capture local fluctuations and global temporal dependencies of the signal, significantly improving the accuracy of gesture recognition.

[0024] During the model training process of the embodiment, three volunteers repeated eight gestures ten times each, and the collected surface electromyography signal data was normalized and then imported into the input layer of the CNN- Transformer hybrid model. After being processed by the CNN module and the Transformer module, it was finally mapped to the predefined eight gestures through the output layer. Matlab was used for model construction and training, and the model could achieve an accuracy of 98.54% after 100 iterations. The reconfigurable metasurface 4 is composed of a plurality of metasurface units 4-1 arranged periodically. Figure 1 and Figure 4 As shown, the reconfigurable metasurface 4 is composed of 64 metasurface units 4-1 arranged periodically.

[0025] The structure of the metasurface unit 4-1 comprises, from top to bottom, a stacked top square patch 4-1-1, a first dielectric substrate 4-1-2, a grounding layer 4-1-3, a second dielectric substrate 4-1-4, and a bottom reflective phase shifter 4-1-5; the top square patch 4-1-1, the grounding layer 4-1-3, and the bottom reflective phase shifter 4-1-5 are three metal layers; the width of the top square patch 4-1-1 is 23mm; the size of the grounding layer 4-1-3 is 55mm×55mm; the material of the first dielectric substrate 4-1-2 and the second dielectric substrate 4-1-4 are both F4b (dielectric constant 2.47, loss tangent 0.002), the thickness of the first dielectric substrate 4-1-2 is h1=3mm, the thickness of the second dielectric substrate 4-1-4 is h2=1mm, and the size is 55mm×55mm.

[0026] In addition, the metasurface unit 4-1 also includes a first metal via 4-1-6, a second metal via 4-1-7, a third metal via 4-1-8, a fourth metal via 4-1-9, a first bottom layer DC voltage bias line circuit 4-1-10, and a second bottom layer DC voltage bias line circuit 4-1-11. The first metal via 4-1-6 passes through the first dielectric substrate 4-1-2, the grounding layer 4-1-3, and the second dielectric substrate 4-1-4, and is respectively connected to the top square patch 4-1-1 and the bottom reflective phase shifter 4-1-5, and the distance d1 between the first metal via 4-1-6 and the center of the top square patch 4-1-1 is 4 mm; the second metal via 4-1-7 passes through the first dielectric substrate 4-1-2, and is respectively connected to the top square patch 4-1-1 and the grounding layer 4-1-3, and the distance d2 between the second metal via 4-1-7 and the center of the top square patch 4-1-1 is 4 mm; the third metal via 4-1-8 passes through the second dielectric substrate 4-1-4, and is respectively connected to the grounding layer 4-1-3 and the first bottom DC voltage bias line circuit 4-1-10; the fourth metal via 4-1-9 passes through the second dielectric substrate 4-1-4, and is respectively connected to the grounding layer 4-1-3 and the second bottom DC voltage bias line circuit 4-1-11.

[0027] like Figure 4As shown in (c), the bottom reflective phase shifter 4-1-5 includes a first microstrip transmission line 4-1-5-1, a first branch microstrip transmission line 4-1-5-2, a second branch microstrip transmission line 4-1-5-3, a second microstrip transmission line 4-1-5-4, a fan-shaped microstrip stub 4-1-5-5, a first square patch 4-1-5-6, a second square patch 4-1-5-7, and three PIN diodes; the three PIN diodes include a first PIN diode 4-1-5-8, a second PIN diode 4-1-5-9, The third PIN diode 4-1-5-10; the length of the first microstrip transmission line 4-1-5-1 is 14mm, and the width is 2.88mm; the length of the first branch microstrip transmission line 4-1-5-2 and the second branch microstrip transmission line 4-1-5-3 are 6.15mm, and the width is 0.5mm; the length of the second microstrip transmission line 4-1-5-4 is 18mm, and the width is 2mm; the size of the first square patch 4-1-5-6 and the second square patch 4-1-5-7 is 6.5mm×6.5mm.

[0028] One end of the first branch microstrip transmission line 4-1-5-2 and the second branch microstrip transmission line 4-1-5-3 are vertically connected to the first microstrip transmission line 4-1-5-1; the other ends of the first branch microstrip transmission line 4-1-5-2 and the second branch microstrip transmission line 4-1-5-3 are connected to the second microstrip transmission line 4-1-5-4 through the first PIN diode 4-1-5-8 and the second PIN diode 4-1-5-9 respectively; the second microstrip transmission line 4-1-5-4 is parallel to the first microstrip transmission line 4-1-5-1, and the two ends of the second microstrip transmission line 4-1-5-4 are connected to the first square patch 4-1-5-6 and the second square patch 4-1-5-7 respectively; the fan-shaped microstrip stub 4-1-5-5 is connected to one end of the first microstrip transmission line 4-1-5-1 through the third PIN diode 4-1-5-10.

[0029] The first bottom DC voltage bias line circuit 4-1-10 is connected to the fan-shaped microstrip stub 4-1-5-5 of the bottom reflective phase shifter 4-1-5, and the second bottom DC voltage bias line circuit 4-1-11 is connected to the first square patch 4-1-5-6 of the bottom reflective phase shifter 4-1-5. The closed or open state of three PIN diodes (first PIN diode 4-1-5-8, second PIN diode 4-1-5-9, third PIN diode 4-1-5-10) is controlled by two bottom DC voltage bias line circuits (first bottom DC voltage bias line circuit 4-1-10 and second bottom DC voltage bias line circuit 4-1-11) to achieve different reflection phase responses of the bottom reflective phase shifter.

[0030] The bottom reflective phase shifter has four reflection phase responses, namely 0°, 90°, 180° and 270°. Correspondingly, the four reflection phase responses are respectively encoded into four digital coding states "A", "B", "C" and "D", wherein: the digital coding state "A" indicates that the first PIN diode, the second PIN diode and the third PIN diode are in the off state; the digital coding state "B" indicates that the first PIN diode and the second PIN diode are in the off state, and the third PIN diode is in the on state; the digital coding state "C" indicates that the first PIN diode and the second PIN diode are in the on state, and the third PIN diode is in the off state; the digital coding state "D" indicates that the first PIN diode, the second PIN diode and the third PIN diode are in the on state.

[0031] The control method of the gesture-controlled reconfigurable metasurface system based on wearable devices is as follows: when the user wears the wearable armband 1 and makes a gesture, the wearable armband 1 will collect surface electromyographic signals of 8 channels, and then send the signals to the computer via Bluetooth; the computer uses the pre-trained CNN-Transformer hybrid model 2 to identify the received electromyographic signals, and further controls the output of the field programmable gate array 3 according to the encoding matrix corresponding to the identified gesture, and controls the opening or closing state of the three PIN diodes by driving the two bottom DC voltage bias line circuits of the reconfigurable metasurface 4, thereby realizing different electromagnetic wave manipulation functions. When the reconfigurable metasurface performs the beam deflection function, it will reflect the incident electromagnetic wave at different deflection angles; and when the polarization conversion function of the reconfigurable metasurface is activated, the linearly polarized incident wave will be converted into a left-handed circularly polarized wave or a right-handed circularly polarized wave.

[0032] like Figure 5 As shown, when the reconfigurable metasurface 4 realizes the beam deflection function, the required encoding matrix takes deflection of 10° and 30° as examples, respectively. Figure 5 As shown in (a) and (c) in the gesture-controlled reconfigurable metasurface system based on wearable devices of the present invention, when the wearable armband 1 collects the executed second gesture 7 and fourth gesture 9, the surface electromyography signal data is sent to the trained CNN-Transformer hybrid model 2 via Bluetooth for recognition, and then the metasurface unit coding matrix corresponding to the recognized gesture is loaded into the DC voltage bias line circuit of the reconfigurable metasurface 4 via the field programmable gate array 3, so that the reconfigurable metasurface 4 realizes the metasurface beam deflection function corresponding to the coding matrix. Figure 5 (b) is the scattering result diagram of the metasurface beam deflected by 10° after the second gesture 7 is recognized and the encoding matrix is ​​loaded. Figure 5 (d) is the scattering result diagram of the metasurface beam deflected by 30° after the fourth gesture 9 is recognized and the encoding matrix is ​​loaded. Figure 5The result diagrams (b) and (d) show that the gesture-controlled reconfigurable metasurface system based on wearable devices of the present invention can effectively realize the beam deflection function of gesture-controlled electromagnetic waves.

[0033] like Figure 6 As shown, when the reconfigurable metasurface 4 realizes the polarization conversion function, the required encoding matrices are as follows: Figure 6 When the wearable device-based gesture-controlled reconfigurable metasurface system of the present invention performs the linear polarization conversion to left-hand circular polarization function corresponding to the first gesture 6, the axial ratio measured in the frequency range of 3.82-3.85 GHz is less than 3 dB, as shown in (a) and (c). Figure 6 As shown in (b); when the linear polarization corresponding to the eighth gesture 13 is converted to right-hand circular polarization, the axial ratio measured in the frequency range of 3.68-3.82GHz is less than 3dB, as shown in Figure 6 As shown in (d); Figure 6 The results in (b) and (d) illustrate that the gesture-controlled reconfigurable metasurface system based on wearable devices of the present invention can effectively realize the polarization conversion function of gesture-controlled electromagnetic waves.

[0034] The above description is only a description of the preferred embodiments of the present application, and is not intended to limit the scope of the present application. Any changes or modifications made by any person skilled in the art based on the above disclosed technical contents shall be deemed as equivalent effective embodiments and shall fall within the scope of protection of the technical solution of the present application.

Claims

1. A gesture-controlled reconfigurable metasurface system based on wearable devices, characterized in that: The invention comprises a wearable device, a gesture recognition model, a field programmable gate array (3), and a reconfigurable metasurface (4), wherein: The wearable device collects and processes surface electromyographic signals in real time and transmits them to a gesture recognition model; the gesture recognition model recognizes the electromyographic signals collected by the wearable device in real time and efficiently, and obtains gesture signals; the field programmable gate array (3) loads the coding matrix corresponding to the gesture signals recognized by the gesture recognition model into a reconfigurable metasurface (4), and the reconfigurable metasurface (4) realizes beam deflection and polarization conversion functions.

2. A gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 1, characterized in that: The wearable device is a wearable armband (1) having a plurality of electromyographic sensor channels, which amplifies, performs notch filtering and bandpass filtering on the collected surface electromyographic signals, and transmits the data to a gesture recognition model via Bluetooth.

3. The gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 1, characterized in that: The gesture recognition model is a CNN-Transformer hybrid model (2), which includes an input layer, a CNN module, a Transformer module, and an output layer, wherein: The CNN module includes a convolution layer, a batch normalization layer, a ReLu activation layer and a pooling layer; The Transformer module includes an embedding layer and a Transformer Encoder layer; The output layer includes a fully connected layer and a Softmax layer; During the model training process, the collected surface electromyography signal data is normalized and then imported into the input layer of the CNN-Transformer hybrid model; the convolution layer in the CNN module extracts local features from the input data by applying multiple convolution kernels, the batch normalization layer and the ReLu activation layer speed up the training process and introduce nonlinearity, and the pooling layer performs downsampling to reduce the number of features and retain the most relevant features; the embedding layer in the Transformer module embeds the features extracted by CNN into a higher-dimensional space to enhance the expressiveness of the model; the Transformer Encoder layer performs self-attention modeling to capture long-term dependencies; after being processed by the CNN module and the Transformer module, it is finally mapped to a variety of predefined gestures through the output layer.

4. The gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 1, characterized in that: The input of the field programmable gate array (3) is connected to the gesture recognition model, and the output pin of the field programmable gate array 3 is connected to the reconfigurable metasurface (4).

5. The gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 1, characterized in that: The reconfigurable metasurface (4) is composed of a plurality of metasurface units (4-1) arranged periodically; The structure of the metasurface unit (4-1) comprises, from top to bottom, a stacked top square patch (4-1-1), a first dielectric substrate (4-1-2), a grounding layer (4-1-3), a second dielectric substrate (4-1-4), and a bottom reflective phase shifter (4-1-5), wherein the top square patch (4-1-1), the grounding layer (4-1-3), and the bottom reflective phase shifter (4-1-5) are three metal layers; The metasurface unit (4-1) further comprises a first metal through column (4-1-6), a second metal through column (4-1-7), a third metal through column (4-1-8), a fourth metal through column (4-1-9), and two bottom-layer DC voltage bias line circuits, wherein the two bottom-layer DC voltage bias line circuits are respectively a first bottom-layer DC voltage bias line circuit (4-1-10) and a second bottom-layer DC voltage bias line circuit (4-1-11), wherein: A first metal through column (4-1-6) passes through the first dielectric substrate (4-1-2), the grounding layer (4-1-3), and the second dielectric substrate (4-1-4), and is respectively connected to the top square patch (4-1-1) and the bottom reflective phase shifter (4-1-5); The second metal through column (4-1-7) passes through the first dielectric substrate (4-1-2) and is respectively connected to the top square patch (4-1-1) and the ground layer (4-1-3); The third metal through column (4-1-8) passes through the second dielectric substrate (4-1-4) and is respectively connected to the ground layer (4-1-3) and the first bottom layer DC voltage bias line circuit (4-1-10); The fourth metal through column (4-1-9) passes through the second dielectric substrate (4-1-4) and is respectively connected to the ground layer (4-1-3) and the second bottom layer DC voltage bias line circuit (4-1-11).

6. The gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 5, characterized in that: The bottom reflective phase shifter (4-1-5) comprises a first microstrip transmission line (4-1-5-1), a first branch microstrip transmission line (4-1-5-2), a second branch microstrip transmission line (4-1-5-3), a second microstrip transmission line (4-1-5-4), a fan-shaped microstrip stub (4-1-5-5), a first square patch (4-1-5-6), a second square patch (4-1-5-7), and three PIN diodes, wherein the three PIN diodes are respectively a first PIN diode (4-1-5-8), a second PIN diode (4-1-5-9), and a third PIN diode (4-1-5-10); One end of the first branch microstrip transmission line (4-1-5-2) and the second branch microstrip transmission line (4-1-5-3) is vertically connected to the first microstrip transmission line (4-1-5-1); the other ends of the first branch microstrip transmission line (4-1-5-2) and the second branch microstrip transmission line (4-1-5-3) are connected to the second microstrip transmission line (4-1-5-4) through a first PIN diode (4-1-5-8) and a second PIN diode (4-1-5-9) respectively; the second microstrip transmission line (4-1-5-4) is parallel to the first microstrip transmission line (4-1-5-1), and two ends of the second microstrip transmission line (4-1-5-4) are connected to a first square patch (4-1-5-6) and a second square patch (4-1-5-7) respectively; the fan-shaped microstrip stub (4-1-5-5) is connected to one end of the first microstrip transmission line (4-1-5-1) through a third PIN diode (4-1-5-10).

7. The gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 6, characterized in that: The first bottom DC voltage bias line circuit (4-1-10) is connected to the fan-shaped microstrip stub (4-1-5-5) of the bottom reflective phase shifter (4-1-5), and the second bottom DC voltage bias line circuit (4-1-11) is connected to the first square patch (4-1-5-6) of the bottom reflective phase shifter (4-1-5); The first bottom layer DC voltage bias line circuit (4-1-10) and the second bottom layer DC voltage bias line circuit (4-1-11) are used to control the closing or opening state of the first PIN diode (4-1-5-8), the second PIN diode (4-1-5-9), and the third PIN diode (4-1-5-10) to achieve different reflection phase responses of the bottom layer reflective phase shifter.

8. The gesture-controlled reconfigurable metasurface system based on a wearable device as claimed in claim 6, characterized in that: The bottom reflective phase shifter has four reflective phase responses, namely 0°, 90°, 180° and 270°. Correspondingly, the four reflective phase responses are respectively encoded into four digital coding states "A", "B", "C", and "D", where: The digital code state "A" indicates that the first PIN diode, the second PIN diode, and the third PIN diode are in the off state; The digital code state "B" indicates that the first PIN diode and the second PIN diode are in the closed state, and the third PIN diode is in the open state; The digital code state "C" indicates that the first PIN diode and the second PIN diode are in the open state, and the third PIN diode is in the closed state; The digital code state "D" indicates that the first PIN diode, the second PIN diode, and the third PIN diode are in the open state.

Images