Edge inference refers to the use of artificial intelligent (AI) models at the network edge to provide mobile devices inference services and thereby enable intelligent services such as auto-driving and Metaverse towards 6G. However, departing from the classic paradigm of data-centric designs, the 6G networks for supporting edge AI features task-oriented techniques that focus on effective and efficient execution of AI task. Targeting end-to-end system performance, such techniques are sophisticated as they aim to seamlessly integrate sensing (data acquisition), communication (data transmission), and computation (data processing). Aligned with the paradigm shift, a task-oriented over-the-air computation (AirComp) scheme is proposed in this paper for multi-device split-inference system. In the considered system, local feature vectors, which are extracted from the real-time noisy sensory data on devices, are aggregated over-the-air by exploiting the waveform superposition in a multiuser channel. Then the aggregated features as received at a server are fed into an inference model with the result used for decision making or control of actuators. To design inference-oriented AirComp, the transmit precoders at edge devices and receive beamforming at edge server are jointly optimized to rein in the aggregation error and maximize the inference accuracy. The problem is made tractable by measuring the inference accuracy using a surrogate metric called discriminant gain, which measures the discernibility of two object classes in the application of object/event classification. It is discovered that the conventional AirComp beamforming design for minimizing the mean square error in generic AirComp with respect to the noiseless case may not lead to the optimal classification accuracy. The reason is due to the overlooking of the fact that feature dimensions have different sensitivity towards aggregation errors and are thus of different importance levels for classification. This issue is addressed in this work via a new task-oriented AirComp scheme designed by directly maximizing the derived discriminant gain. However, the resultant problem of joint transmit precoding and receive beamforming is nonconvex and difficult to solve due to the complicated form of discriminant gain and the coupling between the control variables. We overcome the difficulty using the successive convex approximation. The performance gain of the proposed task-oriented scheme over the conventional schemes is verified by extensive experiments targeting the application of human motion recognition.

This paper studies a new multi-device edge artificial-intelligent (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) to enable low-latency intelligent services at the network edge. In this system, multiple ISAC devices perform radar sensing to obtain multi-view data, and then offload the quantized version of extracted features to a centralized edge server, which conducts model inference based on the cascaded feature vectors. Under this setup and by considering classification tasks, we measure the inference accuracy by adopting an approximate but tractable metric, namely discriminant gain, which is defined as the distance of two classes in the Euclidean feature space under normalized covariance. To maximize the discriminant gain, we first quantify the influence of the sensing, computation, and communication processes on it with a derived closed-form expression. Then, an end-to-end task-oriented resource management approach is developed by integrating the three processes into a joint design. This integrated sensing, computation, and communication (ISCC) design approach, however, leads to a challenging non-convex optimization problem, due to the complicated form of discriminant gain and the device heterogeneity in terms of channel gain, quantization level, and generated feature subsets. Remarkably, the considered non-convex problem can be optimally solved based on the sum-of-ratios method. This gives the optimal ISCC scheme, that jointly determines the transmit power and time allocation at multiple devices for sensing and communication, as well as their quantization bits allocation for computation distortion control. By using human motions recognition as a concrete AI inference task, extensive experiments are conducted to verify the performance of our derived optimal ISCC scheme.

Sensing, computation, and communication (SC2) are highly coupled processes in federated edge learning (FEEL) and need to be jointly designed in a task-oriented manner for pursuing the best FEEL performance under the stringent resource constraints at edge devices. However, this remains an open problem as there is a lack of theoretical understanding on how the SC2resources jointly affect the FEEL performance. In this paper, we address the problem of joint SC2resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing. Specifically, the joint SC2resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time and energy supply of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determining a joint sensing and communication resource allocation that maximizes the total number of samples sensed during the entire training process; the second one concerns the partition of the total number of sensed samples over communication rounds to determine the batch size at each round for convergence speed maximization. Finally, extensive simulation results are provided to validate the superiority of the proposed scheme over several baseline schemes.

This paper studies a new multi-device edge artificial-intelligent (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) to enable low-latency intelligent services at the network edge. In this system, multiple ISAC devices perform radar sensing to obtain multi-view data, and then offload the quantized version of extracted features to a centralized edge server, which conducts model inference based on the cascaded feature vectors. Under this setup and by considering classification tasks, we measure the inference accuracy by adopting an approximate but tractable metric, namely discriminant gain, which is defined as the distance of two classes in the Euclidean feature space under normalized covariance. To maximize the discriminant gain, we first quantify the influence of the sensing, computation, and communication processes on it with a derived closed-form expression. Then, an end-to-end task-oriented resource management approach is developed by designing an optimal integrated sensing, computation, and communication (ISCC) scheme. By using human motions recognition as a concrete AI inference task, extensive experiments are conducted to verify the performance of the proposed scheme.

A task-oriented over-the-air computation (AirComp) scheme is proposed in this paper for multi-device edge split inference system. In the considered system, local noise-corrupted feature vectors are aggregated at the server via AirComp to generate a denoised one for the subsequent inference task. By considering classification tasks, the transmit precoders at edge devices and receive beamforming at edge server are jointly designed in an effort to rein in the aggregation error and maximize the inference accuracy, which is approximately measured by a surrogate but more tractable metric called discriminant gain. It is found that the conventional AirComp beamforming design for minimizing the mean square error between the aggregated feature vector by AirComp and the ideally aggregated one may not lead to the optimal classification accuracy, as it fails to respect the fact that some feature dimensions are more sensitive to the aggregation error than the others in terms of the classification accuracy. To tackle this issue, a new task-oriented AirComp scheme is proposed for directly maximizing the derived discriminant gain. The superiority of the proposed scheme over the heuristic benchmarks is verified by extensive experimental results based on a concrete inference task of human motion recognition.

In this paper, the training time minimization problem is investigated in a quantized FEEL system, where the heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels. In particular, a stochastic quantization scheme is adopted for compression of uploaded gradients, which can reduce the burden of per-round communication but may come at the cost of increasing number of communication rounds. The intrinsic trade-off between the number of communication rounds and per-round latency is characterized. Specifically, we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap. Constrained by total bandwidth, the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem. To this end, an algorithm based on alternating optimization is proposed, which alternatively solves the subproblem of quantization optimization via successive convex approximation and the subproblem of bandwidth allocation via bisection search. With different learning tasks and models, the validation of our analysis and the near-optimal performance of the proposed algorithm are demonstrated by the experimental results.

Training a machine learning model with federated edge learning (FEEL) is typically time consuming due to the constrained computation power of edge devices and the limited wireless resources in edge networks. In this study, the training time minimization problem is investigated in a quantized FEEL system, where heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels. In particular, a stochastic quantization scheme is adopted for compression of uploaded gradients, which can reduce the burden of per-round communication but may come at the cost of increasing the number of communication rounds. The training time is modeled by taking into account the communication time, computation time, and the number of communication rounds. Based on the proposed training time model, the intrinsic trade-off between the number of communication rounds and per-round latency is characterized. Specifically, we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap. Furthermore, a joint data-and-model-driven fitting method is proposed to obtain the exact optimality gap, based on which the closed-form expressions for the number of communication rounds and the total training time are obtained. Constrained by the total bandwidth, the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem. To this end, an algorithm based on alternating optimization is proposed, which alternatively solves the subproblem of quantization optimization through successive convex approximation and the subproblem of bandwidth allocation by bisection search. With different learning tasks and models, the validation of our analysis and the near-optimal performance of the proposed optimization algorithm are demonstrated by the simulation results.

We investigate the reconfigurable intelligent surface (RIS) assisted downlink secure transmission where only the statistical channel of eavesdropper is available. To handle the stochastic ergodic secrecy rate (ESR) maximization problem, a deterministic lower bound of ESR (LESR) is derived. We aim to maximize the LESR by jointly designing the transmit beamforming at the access point (AP) and reflect beamforming by the phase shifts at the RIS. To solve the non-convex LESR maximization problem, we develop a novel penalty dual convex approximation (PDCA) algorithm based on the penalty dual decomposition (PDD) optimization framework, where the exacting constraints are penalized and dualized into the objective function as augmented Lagrangian components. The proposed PDCA algorithm performs double-loop iterations, i.e., the inner loop resorts to the block successive convex approximation (BSCA) to update the optimization variables; while the outer loop adjusts the Lagrange multipliers and penalty parameter of the augmented Lagrangian cost function. The convergence to a Karush-Kuhn-Tucker (KKT) solution is theoretically guaranteed with low computational complexity. Simulation results show that the proposed PDCA scheme is better than the commonly adopted alternating optimization (AO) scheme with the knowledge of statistical channel of eavesdropper.

This paper investigates a X-duplex decode-and-forward relay system in the presence of direct link from the source to destination. X-duplex relays can adaptively switch between half-duplex mode and full-duplex mode according to the instantaneous channel conditions. Unlike previous work on X-duplex relay, we treat the direct link as an additional information path and propose a new transmission scheme based on dirty paper coding (DPC). By using DPC as the precoding scheme at the source, the messages can be divided into two parts which are sent from the source to destination through the relay link and direct link, respectively. In addition, the destination performs successive interference cancellation as the decoding strategy. The optimal transmit powers at the source and relay by maximizing the end-to-end achievable rate are obtained. The numerical results show that the new transmission scheme achieves a better performance over the reference scheme.

Three-dimensional visible light positioning (3D-VLP) is capable of achieving superior locating accuracy in comparison with other existing positioning techniques, such as global positioning system (GPS) and Wi-Fi-based method, which draws much attention from the researchers. In this paper, a novel 3D-VLP scheme using regression neural network is proposed to provide accurate and real-time positioning service. In the proposed method, the angle of arrival (AOA) vectors corresponding to the light-emitting diodes (LEDs) are obtained by the image sensor of the receiver and then fed into a regression neural network, which directly outputs the positioning results. Simulations are carried out to validate the superiority of the proposed method. It’s observed that, in spite of the inevitable quantization error in the positioning process, the mean positioning error is still as accurate as 1.1 cm. In addition, the proposed positioning method is more robust to camera’s height, and takes only 0.27ms to calculate the position, which could be used for real-time locating.

A 3D positioning method based on visible light communication is proposed. Compared to the previous methods, we only need three light emitting diodes (LEDs) with known coordinates to obtain the object position without the priori knowledge of the receiver's height and tile angle. The gradient descent method and vector method are used to obtain the coordinate and inclination of the object (i.e., camera). To validate the effectiveness of our methods, the relation of mean positioning error caused by the discrete camera sensor pixel and the system parameters (i.e., focal length of the camera, pixel density and height of the receiver) is analyzed. Simulation results show the quantization error is about 5 cm.