Search

Edge-device co-inference, which concerns the cooperation between edge devices and an edge server for completing inference tasks over wireless networks, has been a promising technique for enabling various kinds of intelligent services at the network edge, e.g., auto-driving. In this paradigm, the concerned design objective of the network shifts from the traditional communication throughput to the effective and efficient execution of the inference task underpinned by the network, measured by, e.g., the inference accuracy and latency. In this paper, a task-oriented over-the-air computation scheme is proposed for a multidevice artificial intelligence system. Particularly, a novel tractable inference accuracy metric is proposed for classification tasks, which is called minimum pair-wise discriminant gain. Unlike prior work measuring the average of all class pairs in feature space, it measures the minimum distance of all class pairs. By maximizing the minimum pair-wise discriminant gain instead of its average counterpart, any pair of classes can be better separated in the feature space, and thus leading to a balanced and improved inference accuracy for all classes. Besides, this paper jointly optimizes the minimum discriminant gain of all feature elements instead of separately maximizing that of each element in the existing designs. As a result, the transmit power can be adaptively allocated to the feature elements according to their different contributions to the inference accuracy, opening an extra degree of freedom to improve inference performance. Extensive experiments are conducted using a concrete use case of human motion recognition to verify the superiority of the proposed design over the benchmarking scheme., Comment: This paper was accepted by IEEE Transactions on Vehicular Technology on June 30, 2024

High precision vertex and energy reconstruction is crucial for large liquid scintillator detectors such as JUNO, especially for the determination of the neutrino mass ordering by analyzing the energy spectrum of reactor neutrinos. This paper presents a data-driven method to obtain more realistic and more accurate expected PMT response of positron events in JUNO, and develops a simultaneous vertex and energy reconstruction method that combines the charge and time information of PMTs. For the JUNO detector, the impact of vertex inaccuracy on the energy resolution is about 0.6\%., Comment: 11 pages, 11 figures

In this paper, we address the problem of joint sensing, computation, and communication (SC$^{2}$) resource allocation for federated edge learning (FEEL) via a concrete case study of human motion recognition based on wireless sensing in ambient intelligence. First, by analyzing the wireless sensing process in human motion recognition, we find that there exists a thresholding value for the sensing transmit power, exceeding which yields sensing data samples with approximately the same satisfactory quality. Then, the joint SC$^{2}$ resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time, energy supply, and sensing quality of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determine the joint sensing and communication resource allocation that maximizes the total number of samples that can be sensed during the entire training process; the second one concerns the partition of the attained total number of sensed samples over all the communication rounds to determine the batch size at each round for convergence speed maximization. The first subproblem on joint sensing and communication resource allocation is converted to a single-variable optimization problem by exploiting the derived relation between different control variables (resources), which thus allows an efficient solution via one-dimensional grid search. For the second subproblem, it is found that the number of samples to be sensed (or batch size) at each round is a decreasing function of the loss function value attained at the round. Based on this relationship, the approximate optimal batch size at each communication round is derived in closed-form as a function of the round index. Finally, extensive simulation results are provided to validate the superiority of the proposed joint SC$^{2}$ resource allocation scheme., Comment: 13 pages, submitted to IEEE for possible publication

This letter considers the reconfigurable intelligent surface (RIS)-aided unmanned aerial vehicle (UAV) communication systems in urban areas under the general Rician fading channel. A hybrid offline-online design is proposed to improve the system performance by leveraging both the statistical channel state information (S-CSI) and instantaneous channel state information (I-CSI). For the offline phase, we aim to maximize the expected average achievable rate based on the S-CSI by jointly optimizing the RIS's phase-shift and UAV trajectory. The formulated stochastic optimization problem is difficult to solve due to its non-convexity. To tackle this problem, we propose an efficient algorithm by leveraging the stochastic successive convex approximation (SSCA) techniques. For the online phase, the UAV adaptively adjusts the transmit beamforming and user scheduling according to the effective I-CSI. Numerical results verify that the proposed hybrid design performs better than various bechmark schemes, and also demonstrate a favorable trade-off between system performance and CSI overhead.

Precise vertex reconstruction is essential for large liquid scintillator detectors. A novel method based on machine learning has been successfully developed to reconstruct the event vertex in JUNO previously. In this paper, the performance of machine learning based vertex reconstruction is further improved by optimizing the input images of the neural networks. By separating the information of different types of PMTs as well as adding the information of the second hit of PMTs, the vertex resolution is improved by about 9.4 % at 1 MeV and 9.8 % at 11 MeV, respectively.

The Jiangmen Underground Neutrino Observatory (JUNO) is a multi-purpose neutrino experiment. One of the main goals is to determine the neutrino mass ordering by precisely measuring the energy spectrum of reactor antineutrinos. For reactor antineutrino detection, cosmogenic backgrounds such as $^9$Li/$^8$He and fast neutrons induced by cosmic muons should be rejected carefully by applying muon veto cuts, which requires good muon track reconstruction. With a 20~kton liquid scintillator detector, simulation shows the proportion of muon bundles to be around 8\% in the JUNO, while its reconstruction is rarely discussed in previous experiments. According to the charge response of the PMT array, this paper proposes an efficient algorithm for muon bundle track reconstruction. This is the first reconstruction of muon bundles in a large volume liquid scintillator detector. Additionally, the algorithm shows good performance and potential in reconstruction for both single muon and double muons. The spatial resolution of single muon reconstruction is 20~cm and the angular resolution is $0.5^\circ$. As for double muon reconstruction, the spatial resolution and angular resolution could be 30~cm and $1.0^\circ$, respectively. Moreover, this paper has also discussed muon classification and veto strategy.

This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC). In this system, distributed edge devices first send wireless signals to sense targeted objects/human, and then exchange intermediate computed vectors (instead of raw sensing data) for collaborative recognition while preserving data privacy. To boost the spectrum and hardware utilization efficiency for FEEL, we exploit ISAC for both target sensing and data exchange, by employing dedicated frequency-modulated continuous-wave (FMCW) signals at each edge device. Under this setup, we propose a vertical FEEL framework for realizing the recognition based on the collected multi-view wireless sensing data. In this framework, each edge device owns an individual local L-model to transform its sensing data into an intermediate vector with relatively low dimensions, which is then transmitted to a coordinating edge device for final output via a common downstream S-model. By considering a human motion recognition task, experimental results show that our vertical FEEL based approach achieves recognition accuracy up to 98\% with an improvement up to 8\% compared to the benchmarks, including on-device training and horizontal FEEL., Comment: 5 pages, 7 figures, accepted by IEEE Communications Letters

Training a machine learning model with federated edge learning (FEEL) is typically time-consuming due to the constrained computation power of edge devices and limited wireless resources in edge networks. 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 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. Further, 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 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 optimization algorithm are demonstrated by the experimental results., Comment: 14 pages