Learned indexes incorporate machine learning models to predict the locations of keys in the dataset. However, achieving accurate prediction is difficult due to the learning models’ inability to fully capture data distribution. Existing learned indexes used data partition or pre-set error bounds to solve this problem. However, data partition requires constructing a higher index structure, and pre-set error bounds have to train many learning models. In the paper, we propose a new Hierarchical Learned Index with High-Precision query on end nodes (HLIHP), which aims to achieve higher query precision with lower training cost. First, we propose a Precision Correction Model to correct the prediction results, which associates the predicted results with the real positions of the keys. Then, a lightweight learned model is used to construct the superstructure of the index, which can find the end nodes quickly with low training cost and effectively support the query operation. We conduct experiments on four datasets, including covid, genome, osm, and planet, to evaluate the performance of our proposal. The results show that compared to the five hierarchical learned indexes, RMI, PGM-index, XIndex, FINEdex, and ALEX, HLIHP shows on average 2.42×, 1.78×, 5.68×, 6.11×, and 1.48× higher throughput in lookup performance.

The fairness and bias of spectral clustering algorithms have attracted considerable research interest in recent years. Currently fair spectral clustering algorithms are based on the notions of group fairness and individual fairness, which effectively reduce decision bias for similar individuals and sensitive groups. Existing fair spectral clustering algorithms achieve a certain degree of resource redistribution during the clustering process for a particular individual or part of a group, but there is still a situation where the final decision is unfair to the oversized or undersized result clusters. To this end, we present the first principled study of Scale Fairness on Spectral Clustering and propose the SFSC algorithm, which aims to effectively reduce the possibility of the results being oversized or undersized clusters by introducing entropy computation into the spectral clustering process. We measure the scale fairness of clusters by two statistical metrics, and demonstrate on eight classical and real-world datasets that SFSC has better fairness performance compared to spectral clustering while having comparable clustering effect. To the best of our knowledge, this paper is the first study to propose scale fairness for spectral clustering.

This paper studies the integration of over-the-air computation (AirComp) and wireless power transfer (WPT) for achieving sustainable wireless data aggregation (WDA). In such wireless powered AirComp system, a multi-antenna hybrid access point (HAP) employs the transmit energy beamforming to charge multiple single-antenna low-power wireless devices (WDs) in the downlink, and the WDs utilize their harvested energy to simultaneously send messages to the HAP for AirComp in the uplink. Under this setup, our objective is to minimize the computation mean square error (MSE) by jointly optimizing the transmit en-ergy beamforming and the receive AirComp beamforming at the HAP, as well as the transmit power control at the WDs, subject to the wireless energy harvesting constraints at individual WDs. To tackle the non-convex computation MSE minimization problem, we present an efficient algorithm to find a converged high-quality solution by using the alternating optimization technique, in which the transmit energy beamforming (together with WDs' power control) and the receive beamforming are alternately optimized. Simulation results show that the proposed joint WPT-AirComp scheme significantly decreases the system's MSE, as compared to conventional designs without such joint optimization.

In the 6G integrated air-ground network, the process of accomplishing complex tasks through the integrated multimodal communication faces challenges induced by unmanned aerial vehicles (UAVs), such as limited communication, storage and computing capabilities, and the existence of heterogeneous UAV multimodal information and carriers. Inspired by the process of semantic communication, we view successful execution of advanced UAV tasks as semantic recognition and pragmatic execution. Tiny machine learning (TinyML) provides the UAV advanced algorithms and models that can be run on the low-power and resource-constrained platforms. In this article, from the perspective of semantic communication and leveraging the applicability of TinyML for UAVs, we map the heterogeneous multimodal communication and UAV task execution processes aiming to better utilize the capabilities of machine learning and semantic communication to enhance the pragmatic task execution of UAVs. Multimodal virtual semantic communication can provide task-related auxiliary information, enabling the complementary integration of multiple independent modalities in the task domain. The proposed scheme and model achieve a deep integration of communication, sensation, and computation ultimately enhancing the practical task execution capability of UAVs.

To date immunity to disruptions of multi-scale urban road networks (URNs) has not been effectively quantified. This study uses robustness as a meaningful - if partial - representation of immunity. We propose a novel Relative Area Index (RAI) based on traffic assignment theory to quantitatively measure the robustness of URNs under global capacity degradation due to three different types of disruptions, which takes into account many realistic characteristics. We also compare the RAI with weighted betweenness centrality, a traditional topological metric of robustness. We employ six realistic URNs as case studies for this comparison. Our analysis shows that RAI is a more effective measure of the robustness of URNs when multi-scale URNs suffer from global disruptions. This improved effectiveness is achieved because of RAI’s ability to capture the effects of realistic network characteristics such as network topology, flow patterns, link capacity, and travel demand. Also, the results highlight the importance of central management when URNs suffer from disruptions. Our novel method may provide a benchmark tool for comparing robustness of multi-scale URNs, which facilitates the understanding and improvement of network robustness for the planning and management of URNs.

In the multi-view subspace clustering, it is a key challenge to incorporate the complementary information between different views to establish a unified representation (UR). Currently, the problem of establishing a UR tends to be solved in the original data space. However, if there exists the great inconsistency in each view, we cannot obtain a decent UR by above method. To address this issue, by resorting to the latest discovery that the data across all views have a quite similar spectral block structure, we attempt to solve this problem in the spectral embedding domain. Since the spectral block structure among all views has great consistency, the complementary information across all views can be incorporated into a UR with little information loss. Besides, to obtain the high-quality global structure of data on each view, a novel low-rank approximation is proposed by resorting to the tight lower bound on the rank function. In the end, the experimental results demonstrate that, the proposed method is both effective and robust, compared with the cutting-edge methods.

The existing approaches for synthetic aperture radar (SAR) automatic target recognition (ATR) based on deep neural network models have achieved promising performances. However, they cannot give satisfactory detection results when dealing with challenging scenarios, because the performance is influenced by multiple stages. We propose a simple yet powerful method that implements fast and accurate target recognition in SAR image. The system integrates intermediate steps with a single neural network, which can directly predict object of arbitrary orientations in full images. Comparing to the traditional methods, our system can eliminate the influence of previous stage and components in the process. The proposed method is applied to SAR imagery of (moving and stationary target acquisition and recognition) MSTAR dataset and the simulated data. Experimental results used demonstrate the potential of the developed approach in terms of high accuracy and efficiency.

In this paper, we consider a massive MIMO wiretap system where the transmitter, the receiver and the eavesdropper are equipped with a large number of antennas. Being different from the previous works using asymptotic random matrix theory, our analysis relies on the concentration measure of non-asymptotic random matrix theory which allows us to obtain tight bounds for secrecy capacity of massive MIMO system with finite antenna number. The analytical and simulation results reveal the following, in the massive MIMO system employing equal power allocation at each transmit antenna: 1) the secrecy capacity falls within a bounds with a probability growing exponentially with the number of transmit antenna, while the ergodic secrecy capacity falls within a deterministic bounds; 2) the gap between the upper and the lower bound on secrecy rate is proportional to the square root of the SNR at legitimate receiver and the SNR at eavesdropper, respectively; 3) when the entry of legitimate channel matrix and eavesdropping channel matrix satisfies Gaussian distribution, the gap between the upper and the lower bound on secrecy rate is a linear reciprocal function of the number of transmit antennas.