Wireless Channel Conditions Research Articles

Multi-agent Deep Reinforcement Learning-based Key Generation for Graph Layer Security

Recently, the emergence of Internet of Things (IoT) devices has posed a challenge for securing information and avoiding attacks. Most of the cryptography solutions are based on physical layer security (PLS), whose idea is to fully exploit the properties of wireless channel state information (CSI) for generating symmetric keys between two communication nodes. However, accurate channel estimation is vulnerable for attackers and relies on powerful signal processing capability, which is not suitable for low-power IoT devices. In this paper, we expect to apply graph layer security (GLS) to exploit the common features of physical dynamics detected by IoT sensors placed in networked systems to generate keys for data encryption and decryption, which we believe is a new frontier to security for both industry and academic research. We propose a distributed key generation algorithm based on multi-agent deep reinforcement learning (MADRL) approach, which enables communication nodes to cooperatively generate symmetric keys based on their locally detected physical dynamics (e.g., water/gas/oil/electrical pressure/flow/voltage) with low computational complexity and without information exchange. In order to demonstrate the feasibility, we conduct and evaluate our key generation algorithm in both a simulated and real water distribution network. The experimental results show that the proposed algorithm has considerable performance in terms of randomness, bit agreement rate (BAR), etc.

Transmission system with adaptive LDPC-Coded OFDM modulation implemented in GNU Radio

Real-time testing in wireless channel conditions of Forward Error Correction (FEC) coding techniques, Modulation and Coding Scheme (MCS) selection algorithms is a complex and challenging task. GNU Radio and Software Defined Radio (SDR) concept allow a wide range of practical and low-cost solutions to perform the testing operations mentioned above. The paper proposes a duplex transmission system with adaptive LDPC (Low Density Parity Check) coding and OFDM (Orthogonal Frequency Division Multiplexing) modulation implemented in GNU Radio. The frame structure, design principles, system architecture, and mechanisms controlling the transmission process are presented. The system’s modular architecture provides the framework for testing various LDPC coding and MCS selection techniques. The system’s design allows us to maximize the transmission’s efficiency, the encapsulation of various data structures, i.e., frame and transport block, using reduced overheads and the necessity of padding operations is minimized.

Progressive Unsupervised Domain Adaptation for Radio Frequency Signal Attribute Recognition across Communication Scenarios

As the development of low-altitude economies and aerial countermeasures continues, the safety of unmanned aerial vehicles becomes increasingly critical, making emitter identification in remote sensing practices more essential. Effective recognition of radio frequency (RF) signal attributes is a prerequisite for identifying emitters. However, due to diverse wireless communication environments, RF signals often face challenges from complex and time-varying wireless channel conditions. These challenges lead to difficulties in data collection and annotation, as well as disparities in data distribution across different communication scenarios. To address this issue, this paper proposes a progressive maximum similarity-based unsupervised domain adaptation (PMS-UDA) method for RF signal attribute recognition. First, we introduce a noise perturbation consistency optimization method to enhance the robustness of the PMS-UDA method under low signal-to-noise conditions. Subsequently, a progressive label alignment training method is proposed, combining sample-level maximum correlation with distribution-level maximum similarity optimization techniques to enhance the similarity of cross-domain features. Finally, a domain adversarial optimization method is employed to extract domain-independent features, reducing the impact of channel scenarios. The experimental results demonstrate that the PMS-UDA method achieves superior recognition performance in automatic modulation recognition and RF fingerprint identification tasks, as well as across both ground-to-ground and air-to-ground scenarios, compared to baseline methods.

Intelligent non-invasive elderly fall monitoring by designing software defined radio frequency sensing system

The global increase in life expectancy poses challenges related to the safety and well-being of the elderly population, especially in relation to falls. While falls can lead to significant cognitive impairments, timely intervention can mitigate their adverse effects. In this context, the need for non-invasive, efficient monitoring systems becomes paramount. Although wearable sensors have gained traction for monitoring health activities, they may cause discomfort during prolonged use, especially for the elderly. To address this issue, we present an intelligent, non-invasive Software-Defined Radio Frequency (SDRF) sensing system, tailored red for monitoring elderly people's falls during routine activities. Harnessing the power of deep learning and machine learning, our system processes the Wireless Channel State Information (WCSI) generated during regular and fall activities. By employing sophisticated signal processing techniques, the system captures unique patterns that distinguish falls from normal activities. In addition, we use statistical features to streamline data processing, thereby optimizing the computational efficiency of the system. Our experiments, conducted for a typical home environment while using treadmill, demonstrate the robustness of the system. The results show high classification accuracies of 92.5%, 95.1%, and 99.8% for three Artificial Intelligence (AI) algorithms. Notably, the SDRF-based approach offers flexibility, cost-effectiveness, and adaptability through software modifications, circumventing the need for hardware overhaul. This research attempts to bridge the gap in RF-based sensing for elderly fall monitoring, providing a solution that combines the benefits of non-invasiveness with the precision of deep learning and machine learning.

Efficient Handover Mode Synchronization for NR-REDCAP on a Vector DSP

To enable the low-cost design of 5 G IoT Standard reduced capability (NR-REDCAP) devices, hardware-software trade-offs must be made for various signal processing baseband kernels. Dedicated hardware for a kernel provides higher speed and power efficiency but limits the device’s programmability. With the varying range of user equipment (UE) deployment scenarios and dynamic wireless channel conditions, flexible solutions like digital signal processors (DSPs) are favorable for implementing channel estimation, channel equalization, and waveform modulation/demodulation algorithms. Due to stringent requirements on latency for algorithms like decimation, synchronization, and decoding, designers might favor dedicated hardware over DSP-based solutions. Such dedicated hardware increases the device cost as it needs to be added to the modem design solely to implement such specific algorithms. In this work, we study the most critical operation mode of synchronization for the NR-REDCAP standard,i.e., during the Handover between cells. Whereas for the enhanced mobile broadband (eMBB) 5 G NR standard, dedicated hardware might be the best implementation choice for decimation and synchronization; in contrast, for NR-REDCAP, a cost saving can be achieved by implementing and optimizing the kernels onto the vector DSP. We propose an architecture-aware methodology for implementing the most compute-intensive sub-kernels on our vector DSP. Furthermore, we perform structural optimizations to find the most effective sub-kernel variant in performance optimization. After algorithmic and structural optimizations, our results show that the synchronization procedure can be accommodated on a vector DSP with a clock frequency of 500 MHz.

A proposal for fall-risk detection of hospitalized patients from wireless channel state information using Internet of Things devices

Falls of hospitalized patients are a breach of safety and contribute to increasing hospitalization time and worsening recovery conditions, besides impacting other costs. This work explores changes in Channel State Information (CSI), available in local area wireless networks, to detect the risk of falling for hospitalized patients. In practical scenarios, it is impossible to know all fall-risk situations; therefore, one should employ one-class-based detectors since only the risk-free status can be assessed with confidence. Wireless propagation environment changes may indicate the risk of falls and are signaled using the distance from the collected CSI data to the representation learned for the risk-free class. Considering the changes caused by inpatients and nurses’ movement in the infirmary, the learning of the fall-risk-free situation must rely on a limited amount of data and be repeated several times quickly and on the fly. This prevents data-hungry algorithms from being used to learn about risk-free situations. Consequently, we design systems using k-Nearest Neighbors (kNN), Kernel Principal Component Analysis, and Autoencoder. Assuming that the negative class corresponds to falling risk-free, the decision threshold is settled according to a prescribed False Positive Ratio (FPR), and the Matthews Correlation coefficient is used to set the decision threshold. The kNN system accomplishes the highest accuracy value of 87.95%. Thus the performance of the one-class kNN-based fall-risk detector is assessed in two environments that resemble those encountered by hospitalized patients for different FPR values, achieving recall values from 67.47% to 99.40% with an accuracy greater than 79.10%.

Shapley’s Value as a Resource Optimization Strategy for Digital Radio Transmission over IBOC FM

The hybrid in-band on-channel (IBOC) transmission system, which serves as a digital audio radio scheme, facilitates the simultaneous transmission of analog FM and digital audio. In IBOC systems, broadcasters transmit signals within allocated channel bands, posing a challenge in bandwidth allocation for digital audio transmission. To address this, cooperative game theory, supported by the bankruptcy game and Shapley’s value, is proposed as a strategy to optimize bandwidth allocation at each node or station. This approach considers service demand, the number of stations, and radio channel conditions in the FM band. The paper presents a scenario under saturated traffic conditions to evaluate the degree of optimization achievable using the Shapley value under clearly defined traffic and channel conditions. The results indicate that cooperative game theory, with the support of the Shapley value, offers an excellent alternative for optimizing bandwidth in digital broadcasting over IBOC in FM, with potential applicability in other digital radio broadcasting systems.

Secure Device-to-Device Communication in IoT: Fuzzy Identity from Wireless Channel State Information for Identity-Based Encryption

With the rapid development of the Internet of Things (IoT), ensuring secure communication between devices has become a crucial challenge. This paper proposes a novel secure communication solution by extracting wireless channel state information (CSI) features from IoT devices to generate a device identity. Due to the instability of the wireless channel, the CSI features are fuzzy and time-varying; thus, we a employ locally sensitive hashing (LSH) algorithm to ensure the stability of the generated identity in a dynamically changing wireless channel environment. Furthermore, zero-knowledge proofs are utilized to guarantee the authenticity and effectiveness of the generated identity. Finally, the identity generated using the aforementioned approach is integrated into an IBE communication scheme, which involves the fuzzy extraction of channel state information from IoT devices, stable identity extraction for fuzzy IoT devices using LSH, and the use of zero-knowledge proofs to ensure the authenticity of the generated identity. This identity is then employed as the identity information in identity-based encryption (IBE), constructing the device’s public key for achieving confidential communication between devices.

Optimizing User-Level Packet Scheduling Performance through Optimal CQI-Based Resource Allocation in LTE

Our research investigates the Dynamic Resource Allocation in the Downlink of OFDMA-based LTE-A networks. It addresses both user-level and system-level packet scheduling performance. At the user-level, a Traffic Differentiator stage segregates packet queues from active users into different service queues based on service types. Users are prioritized within each service queue based on their QoS requirements and wireless channel conditions, utilizing SPSSA. At the system-level, fairness among users is a key consideration. We propose the PITDSA in the TD Scheduler stage, which aims to allocate just enough radio resource to real-time and non-real time services and assign the remaining available resource to background service. In the FD Scheduler stage, we propose an optimal CQI selection algorithm for resource allocation to exploit frequency domain multi-user diversity. We present our simulation results and analyses of all novel algorithms, and the performance of the Optimal CQI selection algorithm is compared with other algorithms. Our proposed scheduling algorithm demonstrates improved QoS for real-time and non-real time services while maintaining a good traded user-level and system-level performance. Future work can focus on optimizing the throughput or the fairness or both, and more advanced and complex techniques can be designed with the same goal.

Toward Effective Aircraft Call Sign Detection Using Fuzzy String-Matching between ASR and ADS-B Data

Recently, artificial intelligence and data science have witnessed dramatic progress and rapid growth, especially Automatic Speech Recognition (ASR) technology based on Hidden Markov Models (HMMs) and Deep Neural Networks (DNNs). Consequently, new end-to-end Recurrent Neural Network (RNN) toolkits were developed with higher speed and accuracy that can often achieve a Word Error Rate (WER) below 10%. These toolkits can nowadays be deployed, for instance, within aircraft cockpits and Air Traffic Control (ATC) systems in order to identify aircraft and display recognized voice messages related to flight data, especially for airports not equipped with radar. Hence, the performance of air traffic controllers and pilots can ultimately be improved by reducing workload and stress and enforcing safety standards. Our experiment conducted at Tangier’s International Airport ATC aimed to build an ASR model that is able to recognize aircraft call signs in a fast and accurate way. The acoustic and linguistic models were trained on the Ibn Battouta Speech Corpus (IBSC), resulting in an unprecedented speech dataset with approved transcription that includes real weather aerodrome observation data and flight information with a call sign captured by an ADS-B receiver. All of these data were synchronized with voice recordings in a structured format. We calculated the WER to evaluate the model’s accuracy and compared different methods of dataset training for model building and adaptation. Despite the high interference in the VHF radio communication channel and fast-speaking conditions that increased the WER level to 20%, our standalone and low-cost ASR system with a trained RNN model, supported by the Deep Speech toolkit, was able to achieve call sign detection rate scores up to 96% in air traffic controller messages and 90% in pilot messages while displaying related flight information from ADS-B data using the Fuzzy string-matching algorithm.

Joint Task Offloading and Resource Allocation for Intelligent Reflecting Surface-Aided Integrated Sensing and Communication Systems Using Deep Reinforcement Learning Algorithm.

This paper investigates an intelligent reflecting surface (IRS)-aided integrated sensing and communication (ISAC) framework to cope with the problem of spectrum scarcity and poor wireless environment. The main goal of the proposed framework in this work is to optimize the overall performance of the system, including sensing, communication, and computational offloading. We aim to achieve the trade-off between system performance and overhead by optimizing spectrum and computing resource allocation. On the one hand, the joint design of transmit beamforming and phase shift matrices can enhance the radar sensing quality and increase the communication data rate. On the other hand, task offloading and computation resource allocation optimize energy consumption and delay. Due to the coupled and high dimension optimization variables, the optimization problem is non-convex and NP-hard. Meanwhile, given the dynamic wireless channel condition, we formulate the optimization design as a Markov decision process. To tackle this complex optimization problem, we proposed two innovative deep reinforcement learning (DRL)-based schemes. Specifically, a deep deterministic policy gradient (DDPG) method is proposed to address the continuous high-dimensional action space, and the prioritized experience replay is adopted to speed up the convergence process. Then, a twin delayed DDPG algorithm is designed based on this DRL framework. Numerical results confirm the effectiveness of proposed schemes compared with the benchmark methods.

SlimFL: Federated Learning With Superposition Coding Over Slimmable Neural Networks

Federated learning (FL) is a key enabler for efficient communication and computing, leveraging devices’ distributed computing capabilities. However, applying FL in practice is challenging due to the local devices’ heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions. To cope with these issues, this paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNN). Integrating FL with SNNs is challenging due to time-varying channel conditions and data distributions. In addition, existing multi-width SNN training algorithms are sensitive to the data distributions across devices, which makes SNN ill-suited for FL. Motivated by this, we propose a communication and energy-efficient SNN-based FL (named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SlimFL</i> ) that jointly utilizes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">superposition coding (SC)</i> for global model aggregation and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">superposition training (ST)</i> for updating local models. By applying SC, SlimFL exchanges the superposition of multiple-width configurations decoded as many times as possible for a given communication throughput. Leveraging ST, SlimFL aligns the forward propagation of different width configurations while avoiding inter-width interference during backpropagation. We formally prove the convergence of SlimFL. The result reveals that SlimFL is not only communication-efficient but also deals with non-IID data distributions and poor channel conditions, which is also corroborated by data-intensive simulations.

Longer Term Time Dynamics of Bit Error Rates

n this paper an analysis is conducted to study the properties of indoor and outdoor wireless channel conditions over long time scales (several minutes). It shows that long term time dynamics exist in many different situations even when transmitters and receivers are stationary and the distance between them is only a few meters. We use software-defined radio (SDR) that implements radio communication functionalities in software. Transmissions have been achieved using the Universal Software Radio Peripheral (USRP), with the signal processing and time synchronization occurring in the GNU Radio environment on the LINUX (Ubuntu 14.04 LTS) platform. The work has been implemented in a typical school environment i.e., indoor conditions including a lab environment along with a hallway and outdoor conditions comprising a quadrangle environment. We used the benchmarking tool in the GNU Radio that defines and modifies modulation schemes, transmitter and receiver gains, operating frequencies, and other channel properties. Per-packet bit error rate is computed, visualized, and compared across multiple scenarios. We find a series of interesting time dynamics of the BER over several minutes that are not commonly studied in the literature.

FedSSC: Joint client selection and resource management for communication-efficient federated vehicular networks

As a promising distributed technology, federated learning (FL) has been widely used in vehicular networks involving large amounts of IoT-enabled sensor data, which derives federated vehicular networks (FVNs). However, the efficiency of FVN is generally limited by vehicle selection policy and communication conditions, which leads to high communication costs and latency. The original FVN transmits model parameters from a random subset of vehicles to the roadside unit (RSU) and ignores the diversity of learning quality among vehicles. In addition, a few vehicles with poor wireless channel conditions may prolong communication latency. To address these two issues, we propose a communication-efficient federated learning approach, composed of Vehicle Selection, Student–Project Allocation (SPA) matching model, and Convex Optimization, called FedSSC, to improve the communication efficiency in FVN. The parameter variations for the same vehicle in two consecutive rounds are used to quantify the quality of the learning results by cosine distance and Affinity Propagation (AP) clustering. Moreover, a subchannel allocation algorithm based on the SPA matching model, as well as a convex optimal power allocation solution are integrated to minimize the communication latency of each training round. According to extensive experiments, the proposed FedSSC reduces the communication overhead by 26.32% on average compared with the benchmarks, whereas the communication latency decreases by 21.84%.

Channel state information-based wireless localization by signal reconstruction

Wireless localization technology has been widely used in indoor and outdoor fields. Channel estimation based on channel state information is a hot research topic in recent years. However, due to the interference of acquisition bandwidth, noise and Doppler effect, high-resolution channel estimation is a difficult problem. In this paper, the least squares estimate the amplitude of the signal subspace projection and estimate the time delay, using wireless channel state information to delay obey exponential distribution and magnitude obey normal distribution features, and reconstruction after the signal space and sampling to the Euclidean distance between the signal space, common as gradient optimization parameters, estimate the arrival time delay of high precision. The algorithm proposed in this paper filters out the noise interference in wireless communication and improves the accuracy of channel estimation through the method of least square and gradient optimization, which provides a feasible scheme for indoor wireless localization.

Sequential Offloading for Distributed DNN Computation in Multiuser MEC Systems

This paper studies a sequential task offloading problem for a multiuser mobile edge computing (MEC) system. While most of the existing works consider static one-shot offloading optimization with fixed wireless channel conditions and fixed computational tasks, we consider a dynamic optimization approach, which embraces wireless channel fluctuations and random deep neural network (DNN) task arrivals over an infinite horizon. Specifically, we introduce a local CPU workload queue (WD-QSI) and an MEC server workload queue (MEC-QSI) to model the dynamic workload of DNN tasks at each WD and the MEC server, respectively. The transmit power and the partitioning of the local DNN task at each WD are dynamically determined based on the instantaneous channel conditions (to capture the transmission opportunities) and the instantaneous WD-QSI and MEC-QSI (to capture the dynamic urgency of the tasks) to minimize the average latency of the DNN tasks. The joint optimization can be formulated as an ergodic Markov decision process (MDP), in which the optimality condition is characterized by a centralized Bellman equation. However, the brute force solution of the MDP is not viable due to the curse of dimensionality as well as the requirement for knowledge of the global state information. To overcome these issues, we first decompose the MDP into multiple lower dimensional sub-MDPs, each of which can be associated with a WD or the MEC server. Next, we further develop a parametric online Q-learning algorithm, so that each sub-MDP is solved locally at its associated WD or the MEC server. The proposed solution is completely decentralized in the sense that the transmit power for sequential offloading and the DNN task partitioning can be determined based on the local channel state information (CSI) and the local WD-QSI at the WD only. Additionally, no prior knowledge of the distribution of the DNN task arrivals or the channel statistics will be needed for the MEC server. The proposed solution can achieve the superb performance over various state-of-the-art baselines.

Hand-Breathe: Noncontact Monitoring of Breathing Abnormalities From Hand Palm

In post-covid19 world, radio frequency (RF)-based non-contact methods, e.g., software-defined radios (SDR)-based methods have emerged as promising candidates for intelligent remote sensing of human vitals, and could help in containment of contagious viruses like covid19. To this end, this work utilizes the universal software radio peripherals (USRP)-based SDRs along with classical machine learning (ML) methods to design a non-contact method to monitor different breathing abnormalities. Under our proposed method, a subject rests his/her hand on a table in between the transmit and receive antennas, while an orthogonal frequency division multiplexing (OFDM) signal passes through the hand. Subsequently, the receiver extracts the channel frequency response (basically, fine-grained wireless channel state information), and feeds it to various ML algorithms which eventually classify between different breathing abnormalities. Among all classifiers, linear SVM classifier resulted in a maximum accuracy of 88.1%. To train the ML classifiers in a supervised manner, data was collected by doing real-time experiments on 4 subjects in a lab environment. For label generation purpose, the breathing of the subjects was classified into three classes: normal, fast, and slow breathing. Furthermore, in addition to our proposed method (where only a hand is exposed to RF signals), we also implemented and tested the state-of-the-art method (where full chest is exposed to RF radiation). The performance comparison of the two methods reveals a trade-off, i.e., the accuracy of our proposed method is slightly inferior but our method results in minimal body exposure to RF radiation, compared to the benchmark method.

Stable Communications in Green Unmanned Aerial Relaying Systems

Green unmanned aerial relaying (UAR) systems, featuring solar-powered unmanned aerial vehicles (UAVs) to provide agile and flexible communication services, have recently gained significant attention for their wide applications. Nonetheless, due to the essential dynamics of wireless channel conditions and solar energy supply, maintaining system stability is a critical concern in practical green UAR systems, as fluctuation in these two factors can significantly affect communication performance. To address this issue, this paper proposes a scheme design for stable communications in a UAR system with dynamic solar energy supply and wireless channel conditions. Specifically, we first formulate an optimization problem, called OFL, to control the power allocation and flow data rate assignment to minimize long-term time-averaged energy consumption while ensuring the demanded data rate and system stability. Considering that solving OFL needs complete prior information about the solar power supply and wireless channel conditions, which is hardly acquired, we then explore the Lyapunov theory to transform OFL as an online optimization problem, called ONL. To find the solution to ONL, we subsequently design a distributed algorithm that enables each UAV to make its own decision locally, thus reducing the computational overhead of each UAV. Particularly, we prove that stability can be guaranteed by employing the designed algorithm. Extensive simulations are conducted to show the performance achieved by the proposed scheme.

Software defined radio frequency sensing framework for intelligent monitoring of sleep apnea syndrome.

Healthy sleep is vital to all functions in the body. It improves physical and mental health, strengthens resistance against diseases, and develops strong immunity against metabolism and chronic diseases. However, a sleep disorder can cause the inability to sleep well. Sleep apnea syndrome is a critical breathing disorder that occurs during sleeping when breathing stops suddenly and starts when awake, causing sleep disturbance. If it is not treated timely, it can produce loud snoring and drowsiness or causes more acute health problems such as high blood pressure or heart attack. The accepted standard for diagnosing sleep apnea syndrome is full-night polysomnography. However, its limitations include a high cost and inconvenience. This article aims to develop an intelligent monitoring framework for detecting breathing events based on Software Defined Radio Frequency (SDRF) sensing and verify its feasibility for diagnosing sleep apnea syndrome. We extract the wireless channel state information (WCSI) for breathing motion using channel frequency response (CFR) recorded in time at every instant at the receiver. The proposed approach simplifies the receiver structure with the added functionality of communication and sensing together. Initially, simulations are conducted to test the feasibility of the SDRF sensing design for the simulated wireless channel. Then, a real-time experimental setup is developed in a lab environment to address the challenges of the wireless channel. We conducted 100 experiments to collect the dataset of 25 subjects for four breathing patterns. SDRF sensing system accurately detected breathing events during sleep without subject contact. The developed intelligent framework uses machine learning classifiers to classify sleep apnea syndrome and other breathing patterns with an acceptable accuracy of 95.9%. The developed framework aims to build a non-invasive sensing system to diagnose patients conveniently suffering from sleep apnea syndrome. Furthermore, this framework can easily be further extended for E-health applications.

Physical Layer Key Generation Scheme for MIMO System Based on Feature Fusion Autoencoder

Recently, the use of wireless channel state information (CSI) to generate encryption keys in the physical layer has gained significant attention from researchers. Unlike classical cryptography, this approach relies on the variability of the wireless channel, channel reciprocity, and spatial decorrelation to ensure security, making it more lightweight and providing strong randomness. This paper proposes a physical layer key generation scheme for wireless LAN MIMO systems based on feature fusion autoencoder (FFAEncoder) to address the issue of a high key disagreement rate (KDR). Our approach involves extracting amplitude and phase features separately, fusing them through multiplication operator in a neural network, and using an autoencoder to extract common features. The proposed scheme was evaluated on multiple datasets in different real-world scenarios, and it was found that the transmitter and receiver codeword’s mean squared error (MSE) and mean absolute error (MAE) were smaller than those of the current models, indicating better key generation performance. Additionally, the proposed scheme’s KDR was smaller, with a decay rate faster than that of the other two models in the same environment, and the primary key bits were 1/2 and 1/3 that of the other models, respectively, as the signal-to-noise ratio (SNR) increased.