Existing integrated sensing and communication (ISAC) systems face two critical challenges: a trade-off between resource allocation and interference management, and a lack of a unified performance metric that can be simultaneously applied to both sensing and communication functions. To address two aforementioned issues, a non-orthogonal multiple access-assisted ISAC (NOMA-ISAC) scheme is first proposed in this paper, which can simultaneously perform the sensing and communication tasks on shared radio resource, significantly improving spectral efficiency while mitigating mutual interference. Furthermore, in order to provide a unified metric to simplify the performance analysis in ISAC systems, we extend the definition of the outage probability from a mean square error (MSE) perspective. Then based on the built framework, the tractable expressions of the outage probability are derived for both communication and sensing tasks to evaluate the performance of our proposed NOMA-ISAC scheme and the conventional orthogonal radio resource-based ISAC (OR-ISAC) scheme. Next, the asymptotic outage probability comparisons are carried out to show that the NOMA-ISAC scheme can achieve better performance than the OR-ISAC scheme. Finally, simulation results are provided to verify the analytical derivations, and also demonstrate the robustness and performance gains of our proposed NOMA-ISAC scheme over OR-ISAC scheme.

Federated learning is a new artificial intelligence technology with which an edge server can orchestrate with multiple end users to train a global model collaboratively. Under this setting, users only upload the locally trained parameters instead of their local data, substantially reducing communication costs and boosting data privacy. Nonetheless, federated learning mainly relies on users’ local training, overlooking the abundant computing resources owned by the edge server. To exploit the edge server’s processing power, we propose a hybrid learning paradigm that consists of centralized and federated learning components. This scheme uploads a portion of users’ data for centralized learning when the local model is trained under federated learning. We derive a theoretical upper bound for the model accuracy, which can be used to assess the performance of the proposed new learning paradigm. To balance the computation and communication resources for a good model accuracy performance, we establish a joint optimization problem of model accuracy, latency, and energy consumption. We also devise the corresponding joint optimization algorithm to solve the problem. Experiment results show that compared with centralized and federated learning, the proposed hybrid learning algorithm can effectively improve the model accuracy and significantly reduce computation and communication resources.

Long Short-Term Memory (LSTM) networks have been widely used to solve sequence modeling problems. For researchers, using LSTM networks as the core and combining it with pre-processing and post-processing to build complete algorithms is a general solution for solving sequence problems. As an ideal hardware platform for LSTM network inference, Field Programmable Gate Array (FPGA) with low power consumption and low latency characteristics can accelerate the execution of algorithms. However, implementing LSTM networks on FPGA requires specialized hardware and software knowledge and optimization skills, which is a challenge for researchers. To reduce the difficulty of deploying LSTM networks on FPGAs, we propose F-LSTM, an FPGA-based framework for heterogeneous computing. With the help of F-LSTM, researchers can quickly deploy LSTM-based algorithms to heterogeneous computing platforms. FPGA in the platform will automatically take up the computation of the LSTM network in the algorithm. At the same time, the CPU will perform the pre-processing and post-processing in the algorithm. To better design the algorithm, compress the model, and deploy the algorithm, we also propose a framework based on F-LSTM. The framework also integrates Pytorch to increase usability. Experimental results on sentiment analysis tasks show that deploying algorithms to the F-LSTM hardware platform can achieve a 1.8× performance improvement and a 5.4× energy efficiency improvement compared to GPU. Experimental results also validate the need to build heterogeneous computing systems. In conclusion, our work reduces the difficulty of deploying LSTM on FPGAs while guaranteeing algorithm performance compared to traditional work.

In this paper, we investigate the outage performance of full-duplex (FD) and half-duplex (HD) vehicular networks deployed with roadside unit (RSU). We consider two vehicular communication scenarios, i.e., RSU-to-vehicle-to-vehicle (RVV) and vehicle-to-RSU-to-vehicle (VRV) scenarios. In particular, we analyze the performance of vehicular networks with the amplifyand- forward (AF) and decode-and-forward (DF) protocols under the effect of residual loop-back-interference (LBI) and channel estimation errors. For RVV scenario, we derive the upper bound for the outage probability for AF relaying protocol over double Rayleigh fading channel. Moreover, we derive the approximate closed form expression of the outage probability for DF relaying protocol; For VRV scenario, we derive the exact closed-form expressions of the outage probability for AF and DF relaying protocols. Furthermore, we derive the approximate closed-form expression of the outage probability for hybrid FD/HD mode on AF and DF relaying protocols. The numerical and simulation results corroborate our theoretical ones and quantify the impact of the data rates, channel estimation errors and the residual LBI on the systems performance.

Recently, Internet of Things (IoT) is becoming an important enabler to achieve smart health care for patients, where electrocardiograph (ECG) analyzing has been widely studied. In order to realize long-term detection of ECG under the limited hardware and network resources especially in the power/computing constrained IoT scenarios, compressive sensing (CS) has attracted tremendous research efforts thanks to its high efficiency in sample collection and information retrieval. Most existing researches focus on reconstructing the original ECG signal from the received compressive samples, which however not only leads to high energy consumption but also suffers from unnecessarily huge computational complexity for full-dimensional recovery. To solve such problems, this paper aims at a task-cognizant sparse signal processing technique for retrieving the necessary information only. Specifically, a correlation-assist compression with adaptive length (CCAL) algorithm is developed, where ECG signal is compressed individually within each pseudo-period to retain the information of each separate heartbeat. In doing so, the compression length is dynamically varying, which is determined by calculating the correlation coefficients between adjacent fragments. In addition, a preprocessing filter is adopted to offset the performance loss resulted from compression. With the compressed heartbeat acquired through CCAL, we extract autoregressive (AR) coefficients directly in the compressed domain. Afterwards, an SVM classifier is used to identify the conditions of the ECG signal. Finally, real data from MIT-BIH arrhythmia database is used for validating the proposed techniques that work efficiently in moderate compression ratios, while achieving desired classification accuracy as the non-compression benchmark at much reduced computational complexity.

Intelligent applications have greatly promoted the development of fog computing. The protocols have emerged diversely, causing the problems in the interworking between terminal devices, which has seriously hindered the development of fog computing. Based on the Open Connectivity Foundation (OCF) protocol, this paper proposes an interworking solution for intelligent devices, and designs an OCF-based multi-protocol gateway to access non-OCF services. The main functions are divided into three categories: manager, adapter and device agent. In part, the manager provides centralized management services, the adapter provides communication services between the client and the server device, and the device agent provides access services for the server device. The semantic conversion scheme of OCF protocol with other protocols is proposed in the device agent, which solves the problem of interoperability between OCF client device and non-OCF server devices. Finally, the OCF multi-protocol interworking gateway was built, and the semantic conversion between the OCF protocol, AllJoyn protocol, and the ZigBee protocol was implemented. The interoperability between the OCF client, AllJoyn device, and ZigBee device was verified.