Collaborative artificial intelligence (AI) inference has effectively deployed well-trained AI models at the network edge to empower immersive intelligent services such as autonomous driving and smart cities. This paper proposes an integrated sensing-computation-communication (ISCC) scheme for decentralized multi-task collaborative inference systems. The proposed scheme connects multiple devices via device-to-device (D2D) links. Each device first extracts a homogeneous feature vector from the raw sensory data obtained from the same wide view of the source target and then aggregates all local feature vectors using the over-the-air computation (AirComp) technique to complete a specific inference task. To enhance spectrum efficiency, the full-duplex communication technique is adopted, which allows all devices to transmit and receive in the same frequency band. To suppress the self-interference caused by full duplex communications and simultaneously enhance all tasks’ performance, a multi-objective optimization problem is formulated, where discriminant gain is adopted as the inference performance metric. The challenges to solve this problem arise from three aspects: The impact of the self-interference (SI) channel incurred by full-duplex communication, the precoding design of each device, and the coupling among subcarrier allocation, sensing, computation, and communication processes. To tackle this problem, aquadratic transformandweighted bipartite matchingbased alternating maximization approach is proposed. Numerical results based on jointly completing three tasks of human motion classification, human gender recognition, and human age group classification, verify the effectiveness of the proposed method by showing that the proposed method outperforms the state-of-the-art successive convex approximation (SCA) based algorithm.

Gait attracts growing interest from researchers due to its advantages as a non-invasive and non-cooperative biometric feature. Current gait-based attribute recognition methods primarily focus on estimating attributes such as gender, age, and emotions. However, there is insufficient attention to diverse gait attributes in various covariate scenarios. In this paper, we design and collect a Richly Annotated benchmark for 15 gait attributes, named RA-GAR, comprising data from 533 individuals with over 120,000 sequences. To our knowledge, RA-GAR represents the largest and most diverse benchmark of gait attributes currently available. Furthermore, to fully leverage the semantic information and enhance attribute-specific local perception, we propose a two-stage CLIP-based method for Gait Attribute Recognition, named CLIP-GAR. Experiments on the RA-GAR and MA-Gait datasets demonstrate the effectiveness of CLIP-GAR, showing significant improvements in mean accuracy and F1 score.

Spiking neural networks (SNNs) have emerged as an energy-efficient alternative to the traditional artificial neural networks (ANNs) which are compute-intensive. This paper proposes a novel MIMO over-the-air federated learning scheme trained on SNNs using lattice code. Based on the lattice structure, we design a reliable transceiver with lattice quantizer that can combat the noise and interference from the devices. We further derive a convergence analysis of the proposed method considering the nondifferentiable spikes of SNNs. The experimental results verify that the proposed method is effective by showing that the proposed method can achieve comparable accuracy to the ideal benchmarks and outperform the existing approach by employing a small number of antennas at the server and devices. We also show that SNNs are$23.08 \times$more energy-efficient than ANNs.

This paper proposes a novel algorithm, named a quasi-neural network-based decoder (QNN-decoder), for a single-carrier communication system. The algorithm is designed for an inter-symbol-interference (ISI) channel that a trellis diagram can model. According to the trellis diagram, a quasi-neural network (QNN) is built to acquire the likelihoods of the received samples enabling the subsequent decoding. The QNN-decoder differs from artificial neural network (ANN) based algorithms, such as the online learning trellis diagram (OLTD), as it doesn’t rely on data but instead utilizes the physical system model. This means the QNN-decoder can use a much shorter pilot to train its network via backpropagation than OLTD. Meanwhile, the QNN-decoder doesn’t require explicit channel state information (CSI) or statistics of interference and noise. Instead, it can efficiently suppress non-Gaussian interference by learning the CSI and interference and noise statistics. Simulation results verify the QNN-decoder outperforms the state-of-the-art methods and approaches the performance limits provided by the conventional Viterbi with perfect CSI in Gaussian noise only. The QNN-detector outperforms the conventional Viterbi and OLTD with non-Gaussian interference. A few redundant nodes make the QNN-decoder robust to channel length uncertainty, and it may be easily extended to a multi-antenna system for even greater interference suppression.

In the field of gait recognition, regarding gait as a set has emerged as a seminal approach, notably eliminating the dependence on template-based input. Although set-based methods offer notable advantages, such as insensitivity to frame order permutations and robustness to varying frame counts, their performance has consistently lagged behind that of sequence-based methods in subsequent studies. In this work, we advocate for treating gait as an unordered set and argue thatthe lack of set context aggregation in frame-level feature extraction is the primary limitation hindering the full potential of set-based gait recognition. To substantiate this claim, we develop a gait-oriented self-attention module and introduce a Gating Mechanism that facilitates set context awareness for each silhouette whilepreserving the permutation-invariant property. Specifically, the context aggregation operates on diverse bins of feature maps, interleaving fine-grained shape and motion details in an almost parameter-free manner. The Gating Mechanism is employed to ensure that frame-level features are not overwhelmed by the aggregated context. Furthermore, the sampling strategy is carefully enhanced to better support set context modeling. Our research demonstrates that set-based gait recognition can achieve state-of-the-art accuracy on in-the-wild benchmarks (77.6% on Gait3D and 81.1% on GREW) while retaining its inherent advantages.

While medical image segmentation has achieved impressive progress, it usually being constrained by labor-intensive and costly pixel-wise annotations. The existing semi-supervised learning methods ignore the inherent imbalance and high similarity of different categories in medical images. To address the above issues, we present a Progressive Mixed Contrastive Learning (ContrMix) framework, which contains a Cycle-mix module and a mix-based Contrastive Learning module. In Cycle-mix, a progressive mixing strategy with a cycle loss is designed to enforce the consistency between the mixed segmentation and corresponding generated mixing samples, effectively enhancing the ability to learn geometric features of the imbalanced medical data. We also introduce a mix-based Contrastive Learning module that learns the inter-instance similarities between the mixed patches and the original ones, which encourages the model to learn background-invariant representations from samples under different distortions and improves the semantic discrimination of high similarity categories. We conduct extensive experiments on the ACDC dataset and LA dataset and our method outperforms other state-of-the-art semi-supervised approaches.

In this work, we present AerialGait, a comprehensive dataset for aerial-ground gait recognition. This dataset comprises 82,454 sequences totaling over 10 million frames from 533 subjects, captured from both aerial and ground perspectives. To align with real-life scenarios of aerial and ground surveillance, we utilize a drone and a ground surveillance camera for data acquisition. The drone is operated at various speeds, directions, and altitudes. Meanwhile, we conduct data collection across five diverse surveillance sites to ensure a comprehensive simulation of real-world settings. AerialGait has several unique features: 1) The gait sequences exhibit significant variations in views, resolutions, and illumination across five distinct scenes. 2) It incorporates challenges of motion blur and frame discontinuity due to drone mobility. 3) The dataset reflects the domain gap caused by the view disparity between aerial and ground views, presenting a realistic challenge for drone-based gait recognition. Moreover, we perform a comprehensive analysis of existing gait recognition methods on AerialGait dataset and propose the Aerial-Ground Gait Network (AGG-Net). AGG-Net effectively learns discriminative features from aerial views by uncertainty learning and clusters features across aerial and ground views through prototype learning. Our model achieves state-of-the-art performance on both AerialGait and DroneGait datasets.

This paper proposes a Quasi-neural network-based detection algorithm, namely QNN-detector, for a single-carrier communication system in an inter-symbol interference (ISI) channel, which can be modeled by a trellis diagram. According to the trellis diagram, a quasi-neural network (QNN) is built to acquire the normalized likelihoods to enable the subsequent detection or decoding. The QNN can accommodate non-Gaussian interferences through ingeniously designing its hidden layers. Unlike the artificial neural network (ANN) based algorithms, which are data-driven, the QNN-detector relies on the physical system model and only needs a short pilot sequence for training. Moreover, it requires neither explicit channel state information (CSI) nor statistics of interference and noise. Simulation results illustrate that in a channel under white Gaussian noise, the QNN-detector significantly outperforms the ANN-based algorithms in that its network training requires a far shorter pilot sequence, and can approach the performance limits provided by the Viterbi detector with perfect CSI. The simulations also show that in the presence of non-Gaussian interferences, the QNN-detector can learn the distribution of the interferences and therefore suppress them effectively, while the conventional Viterbi detector fails to.

In this article, we investigate a resource allocation problem for a multiunmanned aerial vehicle (UAV) assisted integrated sensing and communication (ISAC) system, where a group of dual-functional UAVs perform simultaneous radar sensing of a target and data communication with multiple ground users (GUs). In particular, the trajectory of UAVs, user association, and beamforming design are jointly considered to maximize the sum weighted bit rate of all GUs while ensuring the sensing beampattern gain of the target. To cope with the above mixed-integer nonconvex optimization problem, we propose an efficient strategy by decomposing the original problem into two subproblems under the alternating optimization framework. For the user association and beamforming design, we propose a novel algorithm to circumvent the coupling relationship among GUs and UAVs by leveraging matching theory and fractional programming theory. For the nonconvex UAV trajectory subproblem, we apply the sequential quadratic programming to obtain a suboptimal solution by solving a sequence of quadratic programming problems. The above two subproblems are iteratively solved and a stable solution is obtained upon convergence. Simulation results show that the proposed strategy outperforms various benchmark schemes that are based on the deferred acceptance algorithm, K-means algorithm, and a heuristic algorithm. It is demonstrated that the proposed strategy efficiently improve the sensing beampattern gain and communication rate.

Cancer development is driven by an accumulation of a small number of driver genetic mutations that confer the selective growth advantage to the cell, while most passenger mutations do not contribute to tumor progression. The identification of these driver genes responsible for tumorigenesis is a crucial step in designing effective cancer treatments. Although many computational methods have been developed with this purpose, the majority of existing methods solely provided a single driver gene list for the entire cohort of patients, ignoring the high heterogeneity of driver events across patients. It remains challenging to identify the personalized driver genes. Here, we propose a novel method (PDRWH), which aims to prioritize the mutated genes of a single patient based on their impact on the abnormal expression of downstream genes across a group of patients who share the co-mutation genes and similar gene expression profiles. The wide experimental results on 16 cancer datasets from TCGA showed that PDRWH excels in identifying known general driver genes and tumor-specific drivers. In the comparative testing across five cancer types, PDRWH outperformed existing individual-level methods as well as cohort-level methods. Our results also demonstrated that PDRWH could identify both common and rare drivers. The personalized driver profiles could improve tumor stratification, providing new insights into understanding tumor heterogeneity and taking a further step toward personalized treatment. We also validated one of our predicted novel personalized driver genes on tumor cell proliferation by vitro cell-based assays, the promoting effect of the high expression of Low-density lipoprotein receptor-related protein 1 (LRP1) on tumor cell proliferation.

Human Identification at a Distance (HID) is an important research area due to its importance (especially in biometrics) and inherent challenges within this domain. To mitigate some of the constraints, we have introduced the HID challenge. This paper presents an overview of the 4th International Competition on Human Identification at a Distance (HID 2023), which serves as a benchmark for evaluating various methods in the field of human identification at a distance. We have introduced a new dataset, SUSTech-Competition, engulfing a cross-domain challenge. This dataset has 859 subjects, having various variations of clothing, carrying conditions, occlusions, and view angles. With a substantial participation of 254 registered teams, HID 2023 has attracted considerable attention and yielded highly encouraging results. Notably, the top-performing teams achieved significantly good accuracies. In this paper, we provide an introduction to the competition, encompassing the dataset, experimental settings, and competition organization, as well as an analysis of the results obtained by the top teams. Additionally, we delve into the methodologies employed by these leading teams. The progress demonstrated in this competition offers an optimistic outlook on the advancements in gait recognition, highlighting its potential for robust real applications.

BACKGROUND: Recent advances in next-generation sequencing technologies have helped investigators generate massive amounts of cancer genomic data. A critical challenge in cancer genomics is identification of a few cancer driver genes whose mutations cause tumor growth. However, the majority of existing computational approaches underuse the co-occurrence mutation information of the individuals, which are deemed to be important in tumorigenesis and tumor progression, resulting in high rate of false positive. RESULTS: To make full use of co-mutation information, we present a random walk algorithm referred to as DriverRWH on a weighted gene mutation hypergraph model, using somatic mutation data and molecular interaction network data to prioritize candidate driver genes. Applied to tumor samples of different cancer types from The Cancer Genome Atlas, DriverRWH shows significantly better performance than state-of-art prioritization methods in terms of the area under the curve scores and the cumulative number of known driver genes recovered in top-ranked candidate genes. Besides, DriverRWH discovers several potential drivers, which are enriched in cancer-related pathways. DriverRWH recovers approximately 50% known driver genes in the top 30 ranked candidate genes for more than half of the cancer types. In addition, DriverRWH is also highly robust to perturbations in the mutation data and gene functional network data. CONCLUSION: DriverRWH is effective among various cancer types in prioritizes cancer driver genes and provides considerable improvement over other tools with a better balance of precision and sensitivity. It can be a useful tool for detecting potential driver genes and facilitate targeted cancer therapies.

Compressive sensing (CS) theory is able to acquire measurements of a scene at sub-Nyquist rate and recover the scene image from these under-sampled measurements. Recent years, CS has been improved greatly for the application of deep learning technology. In conventional methods, block-based mechanism is used to recover images from measurements, which usually causes block effect in reconstructed images. In this paper, we propose a novel CNN-based network for CS to solve this problem. In the measurement part, the input is measured block by block to acquire the measurements. While in the recovery part, all the measurements from one image are used simultaneously to reconstruct the full image. Different from previous methods recovering images block by block, the proposed framework rebuilds the structure information destroyed in the measurement part. Block effect is removed accordingly. Experiments show that there is no block effect at all in the reconstructed images. On a standard dataset our method has significant improvements in reconstruction results compared with existing state-of-the-art methods.

We propose a novel compressive sensing framework for color images. Recently, compressive sensing (CS) has gain its popularity with the development of deep learning. To our best knowledge, existing methods all deal with RGB images channel by channel. This brings redundancy of measurements. In this paper, we do a breakthrough work. Instead of recovering RGB images channel by channel uniformly, we adopt non-uniform sampling in different channels in YCbCr color space. The luminance component takes up more measurements while the other channels take up less in the proposed framework. It greatly enhances the performance on CS for color images. Moreover, perceptual loss gives a powerful ability to better capture the structure information. We give the measurement rate at 2% as an example in the experiments, and the results show the proposed method outperforms all the existing methods with better structure of images.