Deep Learning-based Wireless Signal Classification in the IoT Environment

With the development of the Internet of Things(IoT),diverse wireless devices are increasing rapidly.Those devices have different wireless interfaces that generate incompatible wireless signals.Each signal has its own physical characteristics with signal modulation and demodulation scheme.When there exist different wireless devices,they can suffer from severe Cross-Technology Interferences(CTI).To reduce the communication overhead due to the CTI in the real IoT environment,a central coordinator can be able to detect and identify wireless signals existing in the same communication areas.This paper investigates how to classify various radio signals using Convolutional Neural Networks(CNN),Long Short-TermMemory(LSTM)and attention mechanism.CNN can reduce the amount of computation by reducing weights by using convolution,and LSTM belonging to RNNmodels can alleviate the long-term dependence problem.Furthermore,attention mechanism can reduce the short-term memory problem of RNNs by reexamining the data output from the decoder and the entire data entered into the encoder at every point in time.To accurately classify radio signals according to their weights,we design a model based on CNN,LSTM,and attention mechanism.As a result,we propose a model CLARINet that can classify original data by minimizing the loss and detects changes in sequences.In a case of the real IoT environment with Wi-Fi,Bluetooth and ZigBee devices,we can normally obtain wireless signals from 10 to 20 dB.The accuracy of CLARINet’s radio signal classification with CNN-LSTM and attention mechanism can be seen that signal-to-noise ratio(SNR)exhibits high accuracy at 16 dB to about 92.03%.

Design and application of wireless signal strength measurement system on the near-ground

The wireless communication system's performance is greatly constrained by the wireless channel characteristics,especially in some specific environment.Therefore,signal transmission will be greatly impacted even if not in a complicated topography.Testing results show that it is hardly to characterize the radio propagation properties for the antenna installed on the ground.In order to ensure a successful communication,the radio frequency(RF)wireless signal intensity monitor system was designed.We can get the wireless link transmission loss through measuring signal strength from received node.The test shows that the near-ground wireless signal propagation characteristics still can be characterized by the log distance propagation loss model.These results will conduce to studying the transmission characteristic of Near-Earth wireless signals and will predict the coverage of the earth's surface wireless sensor network.

Multi Multi-Task Learning with Dynamic Splitting for Open Open-Set Wireless Signal Recognition

Open-set recognition(OSR)is a realistic problem in wireless signal recogni-tion,which means that during the inference phase there may appear unknown classes not seen in the training phase.The method of intra-class splitting(ICS)that splits samples of known classes to imitate unknown classes has achieved great performance.However,this approach relies too much on the predefined splitting ratio and may face huge performance degradation in new environment.In this paper,we train a multi-task learning(MTL)net-work based on the characteristics of wireless signals to improve the performance in new scenes.Besides,we provide a dynamic method to decide the splitting ratio per class to get more precise outer samples.To be specific,we make perturbations to the sample from the center of one class toward its adversarial direction and the change point of confidence scores during this process is used as the splitting threshold.We conduct several experi-ments on one wireless signal dataset collected at 2.4 GHz ISM band by LimeSDR and one open modulation recognition dataset,and the analytical results demonstrate the effective-ness of the proposed method.

Human Activity Recognition Based on Frequency-Modulated Continuous Wave and DenseNet

With the development of wireless technology, Frequency-Modulated Continuous Wave (FMCW) radar has increased sensing capability and can be used to recognize human activity. These applications have gained wide-spread attention and become a hot research area. FMCW signals reflected by target activity can be collected, and human activity can be recognized based on the measurements. This paper focused on human activity recognition based on FMCW and DenseNet. We collected point clouds from FMCW and analyzed them to recognize human activity because different activities could lead to unique point cloud features. We built and trained the neural network to implement human activities using a FMCW signal. Firstly, this paper presented recent reviews about human activity recognition using wireless signals. Then, it introduced the basic concepts of FMCW radar and described the fundamental principles of the system using FMCW radar. We also provided the system framework, experiment scenario, and DenseNet neural network structure. Finally, we presented the experimental results and analyzed the accuracy of different neural network models. The system achieved recognition accuracy of 100 percent for five activities using the DenseNet. We concluded the paper by discussing the current issues and future research directions.

Signal Path Reckoning Localization Method in Multipath Environment

In the wireless localization application, multipath propagation seriously affects the localization accuracy. This paper presents two algorithms to solve the multipath problem. Firstly, we improve the Line of Possible Mobile Device(LPMD) algorithm by optimizing the utilization of the direct paths for single-bound scattering scenario. Secondly, the signal path reckoning method with the assistance of geographic information system is proposed to solve the problem of localization with multi-bound scattering paths. With the building model's idealization, the proposed method refers to the idea of ray tracing and dead reckoning. According to the rule of wireless signal reflection, the signal propagation path is reckoned using the measurements of emission angle and propagation distance, and then the estimated location can be obtained. Simulation shows that the proposed method obtains better results than the existing geometric localization methods in multipath environment when the angle error is controlled.

Research on the Early Warning System of Cold Chain Cargo Based on OCR Technology

This paper designs a set of semi-automatic intelligent cold chain cargo proximity warning system with wireless data transmission, lightweight Optical Character Recognition identification algorithm framework and electronic label automatic warning as the core technology for cold chain dairy Fast Moving Consumer Goods contractors. In terms of hardware, Pulse Frequency Modulation modulation and demodulation are used as the main technology to realize wireless transmission and reception of equipment, and digital electronic tags are added to warn the same batch of upcoming goods. In terms of software, based on Chinese-ocr algorithm, image preprocessing and recognition methods are studied, and an early warning system is designed. So as to realize semi-automatic early warning of cold chain logistics goods.

Experimental demonstration for 40-km fiber and 2-m wireless transmission of 4-Gb/s OOK signals at 100-GHz carrier

We experimentally demonstrate a 4-Gb/s radio-over-fiber （RoF） system with 40-kin fiber and 2-m wireless distance downstream at 100-GHz carrier. To the best of our knowledge, this is for the first time in China to realize optical wireless link at 100 GHz. In this letter, simple intensity modulator with direct detector （IM-DD） modulation is employed and optical power penalty afZer 40-kin single mode fiber （SMF）-28 and 2-m air link is 3.2 dB with bit-error-rate （BER） at 1 × 10- 9.

Indoor Human Fall Detection Algorithm Based on Wireless Sensing

As the main health threat to the elderly living alone and performing indoor activities,falls have attracted great attention from institutions and society.Currently,fall detection systems are mainly based on wear sensors,environmental sensors,and computer vision,which need to be worn or require complex equipment construction.However,they have limitations and will interfere with the daily life of the elderly.On the basis of the indoor propagation theory of wireless signals,this paper proposes a conceptual verification module using Wi-Fi signals to identify human fall behavior.The module can detect falls without invading privacy and affecting human comfort and has the advantages of noninvasive,robustness,universality,and low price.The module combines digital signal processing technology and machine learning technology.This paper analyzes and processes the channel state information(CSI)data of wireless signals,and the local outlier factor algorithm is used to find the abnormal CSI sequence.The support vector machine and extreme gradient boosting algorithms are used for classification,recognition,and comparative research.Experimental results show that the average accuracy of fall detection based on wireless sensing is more than 90%.This work has important social significance in ensuring the safety of the elderly.

A Reducing Iteration Orthogonal Matching Pursuit Algorithm for Compressive Sensing

In recent years, Compressed Sensing（CS） has been a hot research topic. It has a wide range of applications, such as image processing and speech signal processing owing to its characteristic of removing redundant information by reducing the sampling rate. The disadvantage of CS is that the number of iterations in a greedy algorithm such as Orthogonal Matching Pursuit（OMP） is fixed, thus limiting reconstruction precision.Therefore, in this study, we present a novel Reducing Iteration Orthogonal Matching Pursuit（RIOMP） algorithm that calculates the correlation of the residual value and measurement matrix to reduce the number of iterations.The conditions for successful signal reconstruction are derived on the basis of detailed mathematical analyses.When compared with the OMP algorithm, the RIOMP algorithm has a smaller reconstruction error. Moreover, the proposed algorithm can accurately reconstruct signals in a shorter running time.