Search

Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as ``TP-DDPG'', to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggler-aware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.

In this paper, we propose MM-KWS, a novel approach to user-defined keyword spotting leveraging multi-modal enrollments of text and speech templates. Unlike previous methods that focus solely on either text or speech features, MM-KWS extracts phoneme, text, and speech embeddings from both modalities. These embeddings are then compared with the query speech embedding to detect the target keywords. To ensure the applicability of MM-KWS across diverse languages, we utilize a feature extractor incorporating several multilingual pre-trained models. Subsequently, we validate its effectiveness on Mandarin and English tasks. In addition, we have integrated advanced data augmentation tools for hard case mining to enhance MM-KWS in distinguishing confusable words. Experimental results on the LibriPhrase and WenetPhrase datasets demonstrate that MM-KWS outperforms prior methods significantly., Comment: Accepted at INTERSPEECH 2024

Extended Reality (XR) is an important service in the 5G network and in future 6G networks. In contrast to traditional video on demand services, real-time XR video is transmitted frame-by-frame, requiring low latency and being highly sensitive to network fluctuations. In this paper, we model the quality of experience (QoE) for real-time XR video transmission on a frame-by-frame basis. Based on the proposed QoE model, we formulate an optimization problem that maximizes QoE with constraints on wireless resources and long-term energy consumption. We utilize Lyapunov optimization to transform the original problem into a single-frame optimization problem and then allocate wireless subchannels. We propose an adaptive XR video bitrate algorithm that employs a Long Short Term Memory (LSTM) based Deep Q-Network (DQN) algorithm for video bitrate selection. Through numerical results, we show that our proposed algorithm outperforms the baseline algorithms, with the average QoE improvements of 0.04 to 0.46. Specifically, compared to baseline algorithms, the proposed algorithm reduces average video quality variations by 29% to 50% and improves the frame transmission success rate by 5% to 48%., Comment: 6 pages, 5 figures

Extended reality (XR) is one of the most important applications of beyond 5G and 6G networks. Real-time XR video transmission presents challenges in terms of data rate and delay. In particular, the frame-by-frame transmission mode of XR video makes real-time XR video very sensitive to dynamic network environments. To improve the users' quality of experience (QoE), we design a cross-layer transmission framework for real-time XR video. The proposed framework allows the simple information exchange between the base station (BS) and the XR server, which assists in adaptive bitrate and wireless resource scheduling. We utilize the cross-layer information to formulate the problem of maximizing user QoE by finding the optimal scheduling and bitrate adjustment strategies. To address the issue of mismatched time scales between two strategies, we decouple the original problem and solve them individually using a multi-agent-based approach. Specifically, we propose the multi-step Deep Q-network (MS-DQN) algorithm to obtain a frame-priority-based wireless resource scheduling strategy and then propose the Transformer-based Proximal Policy Optimization (TPPO) algorithm for video bitrate adaptation. The experimental results show that the TPPO+MS-DQN algorithm proposed in this study can improve the QoE by 3.6% to 37.8%. More specifically, the proposed MS-DQN algorithm enhances the transmission quality by 49.9%-80.2%., Comment: 14 pages, 13 figures. arXiv admin note: text overlap with arXiv:2402.01180

Extended reality (XR) is one of the most important applications of 5G. For real-time XR video transmission in 5G networks, a low latency and high data rate are required. In this paper, we propose a resource allocation scheme based on frame-priority scheduling to meet these requirements. The optimization problem is modelled as a frame-priority-based radio resource scheduling problem to improve transmission quality. We propose a scheduling framework based on multi-step Deep Q-network (MS-DQN) and design a neural network model based on convolutional neural network (CNN). Simulation results show that the scheduling framework based on frame-priority and MS-DQN can improve transmission quality by 49.9%-80.2%., Comment: 6 pages, 7 figures

Quantifying the performance bound of an integrated localization and communication (ILAC) system and the trade-off between communication and localization performance is critical. In this letter, we consider an ILAC system that can perform communication and localization via time-domain or frequency-domain resource allocation. We develop an analytical framework to derive the closed-form expression of the capacity loss versus localization Cramer-Rao lower bound (CRB) loss via time-domain and frequency-domain resource allocation. Simulation results validate the analytical model and demonstrate that frequency-domain resource allocation is preferable in scenarios with a smaller number of antennas at the next generation nodeB (gNB) and a larger distance between user equipment (UE) and gNB, while time-domain resource allocation is preferable in scenarios with a larger number of antennas and smaller distance between UE and the gNB., Comment: 5 pages, 3 figures

The high computational complexity and energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. However, mobile edge computing (MEC) makes it possible to solve this problem. This paper considers the scene of completing video-based AI inference tasks in the MEC system. We formulate a mixed-integer nonlinear programming problem (MINLP) to reduce inference delays, energy consumption and to improve recognition accuracy. We give a simplified expression of the inference complexity model and accuracy model through derivation and experimentation. The problem is then solved iteratively by using alternating optimization. Specifically, by assuming that the offloading decision is given, the problem is decoupled into two sub-problems, i.e., the resource allocation problem for the devices set that completes the inference tasks locally, and that for the devices set that offloads tasks. For the problem of offloading decision optimization, we propose a Channel-Aware heuristic algorithm. To further reduce the complexity, we propose an alternating direction method of multipliers (ADMM) based distributed algorithm. The ADMM-based algorithm has a low computational complexity that grows linearly with the number of devices. Numerical experiments show the effectiveness of proposed algorithms. The trade-off relationship between delay, energy consumption, and accuracy is also analyzed., Comment: 14 pages, 11 figures. arXiv admin note: text overlap with arXiv:2208.01860

Multi-stream carrier aggregation is a key technology to expand bandwidth and improve the throughput of the fifth-generation wireless communication systems. However, due to the diversified propagation properties of different frequency bands, the traffic migration task is much more challenging, especially in hybrid sub-6 GHz and millimeter wave bands scenario. Existing schemes either neglected to consider the transmission rate difference between multi-stream carrier, or only consider simple low mobility scenario. In this paper, we propose a low-complexity traffic splitting algorithm based on fuzzy proportional integral derivative control mechanism. The proposed algorithm only relies on the local radio link control buffer information of sub-6 GHz and mmWave bands, while frequent feedback from user equipment (UE) side is minimized. As shown in the numerical examples, the proposed traffic splitting mechanism can achieve more than 90% link resource utilization ratio for different UE transmission requirements with different mobilities, which corresponds to 10% improvement if compared with conventional baselines., Comment: 17 pages, 7 figures

Network slicing is a critical driver for guaranteeing the diverse service level agreements (SLA) in 5G and future networks. Inter-slice radio resource allocation (IS-RRA) in the radio access network (RAN) is very important. However, user mobility brings new challenges for optimal IS-RRA. This paper first proposes a soft and hard hybrid slicing framework where a common slice is introduced to realize a trade-off between isolation and spectrum efficiency (SE). To address the challenges posed by user mobility, we propose a two-step deep learning-based algorithm: joint long short-term memory (LSTM)-based network state prediction and deep Q network (DQN)-based slicing strategy. In the proposal, LSTM networks are employed to predict traffic demand and the location of each user in a slicing window level. Moreover, channel gain is mapped by location and a radio map. Then, the predicted channel gain and traffic demand are input to the DQN to output the precise slicing adjustment. Finally, experiment results confirm the effectiveness of our proposed slicing framework: the slices' SLA can be guaranteed well, and the proposed algorithm can achieve near-optimal performance in terms of the SLA satisfaction ratio, isolation degree and SE., Comment: 16 pages, 10 fogures, accepted by China Communications. arXiv admin note: text overlap with arXiv:2204.03502

The high computational complexity and high energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. This paper considers the scene of completing video-based AI inference tasks in the mobile edge computing (MEC) system. We use multiply-and-accumulate operations (MACs) for problem analysis and optimize delay and energy consumption under accuracy constraints. To solve this problem, we first assume that offloading policy is known and decouple the problem into two subproblems. After solving these two subproblems, we propose an iterative-based scheduling algorithm to obtain the optimal offloading policy. We also experimentally discuss the relationship between delay, energy consumption, and inference accuracy., Comment: 6 pages, 7 figures, accepted by Globecom2022

Network slicing is a critical driver for guaranteeing the diverse service level agreements (SLA) in 5G and future networks. Recently, deep reinforcement learning (DRL) has been widely utilized for resource allocation in network slicing. However, existing related works do not consider the performance loss associated with the initial exploration phase of DRL. This paper proposes a new performance-guaranteed slicing strategy with a soft and hard hybrid slicing setting. Mainly, a common slice setting is applied to guarantee slices' SLA when training the neural network. Moreover, the resource of the common slice tends to precisely redistribute to slices with the training of DRL until it converges. Furthermore, experiment results confirm the effectiveness of our proposed slicing framework: the slices' SLA of the training phase can be guaranteed, and the proposed algorithm can achieve the near-optimal performance in terms of the SLA satisfaction ratio, isolation degree and spectrum maximization after convergence., Comment: 5 pages, 5 figures, accepted by VTC2022-Spring

Scene text recognition (STR) is an important bridge between images and text, attracting abundant research attention. While convolutional neural networks (CNNS) have achieved remarkable progress in this task, most of the existing works need an extra module (context modeling module) to help CNN to capture global dependencies to solve the inductive bias and strengthen the relationship between text features. Recently, the transformer has been proposed as a promising network for global context modeling by self-attention mechanism, but one of the main shortcomings, when applied to recognition, is the efficiency. We propose a 1-D split to address the challenges of complexity and replace the CNN with the transformer encoder to reduce the need for a context modeling module. Furthermore, recent methods use a frozen initial embedding to guide the decoder to decode the features to text, leading to a loss of accuracy. We propose to use a learnable initial embedding learned from the transformer encoder to make it adaptive to different input images. Above all, we introduce a novel architecture for text recognition, named TRansformer-based text recognizer with Initial embedding Guidance (TRIG), composed of three stages (transformation, feature extraction, and prediction). Extensive experiments show that our approach can achieve state-of-the-art on text recognition benchmarks.

Gesture recognition is getting more and more popular due to various application possibilities in human-machine interaction. Existing multi-modal gesture recognition systems take multi-modal data as input to improve accuracy, but such methods require more modality sensors, which will greatly limit their application scenarios. Therefore we propose an end-to-end multi-task learning framework in training 2D convolutional neural networks. The framework can use the depth modality to improve accuracy during training and save costs by using only RGB modality during inference. Our framework is trained to learn a representation for multi-task learning: gesture segmentation and gesture recognition. Depth modality contains the prior information for the location of the gesture. Therefore it can be used as the supervision for gesture segmentation. A plug-and-play module named Multi-Scale-Decoder is designed to realize gesture segmentation, which contains two sub-decoder. It is used in the lower stage and higher stage respectively, and can help the network pay attention to key target areas, ignore irrelevant information, and extract more discriminant features. Additionally, the MSD module and depth modality are only used in the training stage to improve gesture recognition performance. Only RGB modality and network without MSD are required during inference. Experimental results on three public gesture recognition datasets show that our proposed method provides superior performance compared with existing gesture recognition frameworks. Moreover, using the proposed plug-and-play MSD in other 2D CNN-based frameworks also get an excellent accuracy improvement.

Image matting is an important computer vision problem. Many existing matting methods require a hand-made trimap to provide auxiliary information, which is very expensive and limits the real world usage. Recently, some trimap-free methods have been proposed, which completely get rid of any user input. However, their performance lag far behind trimap-based methods due to the lack of guidance information. In this paper, we propose a matting method that use Flexible Guidance Input as user hint, which means our method can use trimap, scribblemap or clickmap as guidance information or even work without any guidance input. To achieve this, we propose Progressive Trimap Deformation(PTD) scheme that gradually shrink the area of the foreground and background of the trimap with the training step increases and finally become a scribblemap. To make our network robust to any user scribble and click, we randomly sample points on foreground and background and perform curve fitting. Moreover, we propose Semantic Fusion Module(SFM) which utilize the Feature Pyramid Enhancement Module(FPEM) and Joint Pyramid Upsampling(JPU) in matting task for the first time. The experiments show that our method can achieve state-of-the-art results comparing with existing trimap-based and trimap-free methods., Comment: Accepted to BMVC2021

Although lots of progress were made in Text Recognition/OCR in recent years, the task of font recognition is remaining challenging. The main challenge lies in the subtle difference between these similar fonts, which is hard to distinguish. This paper proposes a novel font recognizer with a pluggable module solving the font recognition task. The pluggable module hides the most discriminative accessible features and forces the network to consider other complicated features to solve the hard examples of similar fonts, called HE Block. Compared with the available public font recognition systems, our proposed method does not require any interactions at the inference stage. Extensive experiments demonstrate that HENet achieves encouraging performance, including on character-level dataset Explor_all and word-level dataset AdobeVFR, Comment: 8 pages, 2021 3rd International Conference on Advanced Information Science and System (AISS 2021)

With the rising demand for indoor localization, high precision technique-based fingerprints became increasingly important nowadays. The newest advanced localization system makes effort to improve localization accuracy in the time or frequency domain, for example, the UWB localization technique can achieve centimeter-level accuracy but have a high cost. Therefore, we present a spatial domain extension-based scheme with low cost and verify the effectiveness of antennas extension in localization accuracy. In this paper, we achieve sub-meter level localization accuracy using a single AP by extending three radio links of the modified laptops to more antennas. Moreover, the experimental results show that the localization performance is superior as the number of antennas increases with the help of spatial domain extension and angular domain assisted., Comment: To appear at IEEE GLOBECOM 2021

Although recent works based on deep learning have made progress in improving recognition accuracy on scene text recognition, how to handle low-quality text images in end-to-end deep networks remains a research challenge. In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation. IFR contains two branches which focus on scene text recognition and low quality scene text image recovery respectively. We utilize an iterative collaboration between two branches, which can effectively alleviate the impact of low quality input. A feature fusion module is proposed to strengthen the feature representation of the two branches, where the features from the Recognizer are Fused with image Restoration branch, referred to as RRF. Without changing the recognition network structure, extensive quantitative and qualitative experimental results show that the proposed method significantly outperforms the baseline methods in boosting the recognition accuracy of benchmark datasets and low resolution images in TextZoom dataset.

In recent years, synthetic speech generated by advanced text-to-speech (TTS) and voice conversion (VC) systems has caused great harms to automatic speaker verification (ASV) systems, urging us to design a synthetic speech detection system to protect ASV systems. In this paper, we propose a new speech anti-spoofing model named ResWavegram-Resnet (RW-Resnet). The model contains two parts, Conv1D Resblocks and backbone Resnet34. The Conv1D Resblock is based on the Conv1D block with a residual connection. For the first part, we use the raw waveform as input and feed it to the stacked Conv1D Resblocks to get the ResWavegram. Compared with traditional methods, ResWavegram keeps all the information from the audio signal and has a stronger ability in extracting features. For the second part, the extracted features are fed to the backbone Resnet34 for the spoofed or bonafide decision. The ASVspoof2019 logical access (LA) corpus is used to evaluate our proposed RW-Resnet. Experimental results show that the RW-Resnet achieves better performance than other state-of-the-art anti-spoofing models, which illustrates its effectiveness in detecting synthetic speech attacks., Comment: Accepted for Interspeech2021

Depth completion aims to generate a dense depth map from the sparse depth map and aligned RGB image. However, current depth completion methods use extremely expensive 64-line LiDAR(about $100,000) to obtain sparse depth maps, which will limit their application scenarios. Compared with the 64-line LiDAR, the single-line LiDAR is much less expensive and much more robust. Therefore, we propose a method to tackle the problem of single-line depth completion, in which we aim to generate a dense depth map from the single-line LiDAR info and the aligned RGB image. A single-line depth completion dataset is proposed based on the existing 64-line depth completion dataset(KITTI). A network called Semantic Guided Two-Branch Network(SGTBN) which contains global and local branches to extract and fuse global and local info is proposed for this task. A Semantic guided depth upsampling module is used in our network to make full use of the semantic info in RGB images. Except for the usual MSE loss, we add the virtual normal loss to increase the constraint of high-order 3D geometry in our network. Our network outperforms the state-of-the-art in the single-line depth completion task. Besides, compared with the monocular depth estimation, our method also has significant advantages in precision and model size.

With the rapid development of indoor location-based services (LBSs), the demand for accurate localization keeps growing as well. To meet this demand, we propose an indoor localization algorithm based on graph convolutional network (GCN). We first model access points (APs) and the relationships between them as a graph, and utilize received signal strength indication (RSSI) to make up fingerprints. Then the graph and the fingerprint will be put into GCN for feature extraction, and get classification by multilayer perceptron (MLP).In the end, experiments are performed under a 2D scenario and 3D scenario with floor prediction. In the 2D scenario, the mean distance error of GCN-based method is 11m, which improves by 7m and 13m compare with DNN-based and CNN-based schemes respectively. In the 3D scenario, the accuracy of predicting buildings and floors are up to 99.73% and 93.43% respectively. Moreover, in the case of predicting floors and buildings correctly, the mean distance error is 13m, which outperforms DNN-based and CNN-based schemes, whose mean distance errors are 34m and 26m respectively.

Text detection/localization, as an important task in computer vision, has witnessed substantialadvancements in methodology and performance with convolutional neural networks. However, the vastmajority of popular methods use rectangles or quadrangles to describe text regions. These representationshave inherent drawbacks, especially relating to dense adjacent text and loose regional text boundaries,which usually cause difficulty detecting arbitrarily shaped text. In this paper, we propose a novel text regionrepresentation method, with a robust pipeline, which can precisely detect dense adjacent text instances witharbitrary shapes. We consider a text instance to be composed of an adaptive central text region mask anda corresponding expanding ratio between the central text region and the full text region. More specifically,our pipeline generates adaptive central text regions and corresponding expanding ratios with a proposedtraining strategy, followed by a new proposed post-processing algorithm which expands central text regionsto the complete text instance with the corresponding expanding ratios. We demonstrated that our new textregion representation is effective, and that the pipeline can precisely detect closely adjacent text instances ofarbitrary shapes. Experimental results on common datasets demonstrate superior performance o, Comment: This is an article published in IEEE Access

Recently, video scene text detection has received increasing attention due to its comprehensive applications. However, the lack of annotated scene text video datasets has become one of the most important problems, which hinders the development of video scene text detection. The existing scene text video datasets are not large-scale due to the expensive cost caused by manual labeling. In addition, the text instances in these datasets are too clear to be a challenge. To address the above issues, we propose a tracking based semi-automatic labeling strategy for scene text videos in this paper. We get semi-automatic scene text annotation by labeling manually for the first frame and tracking automatically for the subsequent frames, which avoid the huge cost of manual labeling. Moreover, a paired low-quality scene text video dataset named Text-RBL is proposed, consisting of raw videos, blurry videos, and low-resolution videos, labeled by the proposed convenient semi-automatic labeling strategy. Through an averaging operation and bicubic down-sampling operation over the raw videos, we can efficiently obtain blurry videos and low-resolution videos paired with raw videos separately. To verify the effectiveness of Text-RBL, we propose a baseline model combined with the text detector and tracker for video scene text detection. Moreover, a failure detection scheme is designed to alleviate the baseline model drift issue caused by complex scenes. Extensive experiments demonstrate that Text-RBL with paired low-quality videos labeled by the semi-automatic method can significantly improve the performance of the text detector in low-quality scenes., Comment: Published in: IEEE Access ( Early Access )

Face Anti-spoofing (FAS) is a challenging problem due to complex serving scenarios and diverse face presentation attack patterns. Especially when captured images are low-resolution, blurry, and coming from different domains, the performance of FAS will degrade significantly. The existing multi-modal FAS datasets rarely pay attention to the cross-domain problems under deployment scenarios, which is not conducive to the study of model performance. To solve these problems, we explore the fine-grained differences between multi-modal cameras and construct a cross-domain multi-modal FAS dataset under surveillance scenarios called GREAT-FASD-S. Besides, we propose an Attention based Face Anti-spoofing network with Feature Augment (AFA) to solve the FAS towards low-quality face images. It consists of the depthwise separable attention module (DAM) and the multi-modal based feature augment module (MFAM). Our model can achieve state-of-the-art performance on the CASIA-SURF dataset and our proposed GREAT-FASD-S dataset., Comment: Published in: IEEE Access

Precise indoor localization is one of the key requirements for fifth Generation (5G) and beyond, concerning various wireless communication systems, whose applications span different vertical sectors. Although many highly accurate methods based on signal fingerprints have been lately proposed for localization, their vast majority faces the problem of degrading performance when deployed in indoor systems, where the propagation environment changes rapidly. In order to address this issue, the crowdsourcing approach has been adopted, according to which the fingerprints are frequently updated in the respective database via user reporting. However, the late crowdsourcing techniques require precise indoor floor plans and fail to provide satisfactory accuracy. In this paper, we propose a low-complexity self-calibrating indoor crowdsourcing localization system that combines historical with frequently updated fingerprints for high precision user positioning. We present a multi-kernel transfer learning approach which exploits the inner relationship between the original and updated channel measurements. Our indoor laboratory experimental results with the proposed approach and using Nexus 5 smartphones at 2.4GHz with 20MHz bandwidth have shown the feasibility of about one meter level accuracy with a reasonable fingerprint update overhead., Comment: To appear at ICC 2021

In a wireless network that conveys status updates from sources (i.e., sensors) to destinations, one of the key issues studied by existing literature is how to design an optimal source sampling strategy on account of the communication constraints which are often modeled as queues. In this paper, an alternative perspective is presented -- a novel status-aware communication scheme, namely \emph{parallel communications}, is proposed which allows sensors to be communication-agnostic. Specifically, the proposed scheme can determine, based on an online prediction functionality, whether a status packet is worth transmitting considering both the network condition and status prediction, such that sensors can generate status packets without communication constraints. We evaluate the proposed scheme on a Software-Defined-Radio (SDR) test platform, which is integrated with a collaborative autonomous driving simulator, i.e., Simulation-of-Urban-Mobility (SUMO), to produce realistic vehicle control models and road conditions. The results show that with online status predictions, the channel occupancy is significantly reduced, while guaranteeing low status recovery error. Then the framework is applied to two scenarios: a multi-density platooning scenario, and a flight formation control scenario. Simulation results show that the scheme achieves better performance on the network level, in terms of keeping the minimum safe distance in both vehicle platooning and flight control., Comment: Submitted to IEEE TWC for possible publication. An earlier version was presented at INFOCOM 2020. arXiv admin note: substantial text overlap with arXiv:2002.01255

Spatial Description Resolution, as a language-guided localization task, is proposed for target location in a panoramic street view, given corresponding language descriptions. Explicitly characterizing an object-level relationship while distilling spatial relationships are currently absent but crucial to this task. Mimicking humans, who sequentially traverse spatial relationship words and objects with a first-person view to locate their target, we propose a novel spatial relationship induced (SIRI) network. Specifically, visual features are firstly correlated at an implicit object-level in a projected latent space; then they are distilled by each spatial relationship word, resulting in each differently activated feature representing each spatial relationship. Further, we introduce global position priors to fix the absence of positional information, which may result in global positional reasoning ambiguities. Both the linguistic and visual features are concatenated to finalize the target localization. Experimental results on the Touchdown show that our method is around 24\% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown., Comment: Accepted at NeurIPS 2020; Peiyao Wang and Weixin Luo made equal contribution

Vehicle-to-everything (V2X) is a modern vehicular technology that improves conventional vehicle systems in traffic and communications. V2X communications demand energyefficient and high-reliability networking because of massive vehicular connections and high mobility wireless channels. Nonorthogonal multiple access (NOMA) is a promising solution for 5G V2X services that intend to guarantee high reliability, quality-of-service (QoS) provisioning, and massive connectivity requirements. In V2X, it is vital to inspect imperfect CSI because the high mobility of vehicles leads to more channel estimation uncertainties. Unlike existing literatures, we propose energy-efficient roadside units (RSUs) assisted NOMA multicasting system for 5G cellular V2X communications, and investigate the energy-efficient power allocation problem. The proposed system multicast the information through low complexity optimal power allocation algorithms used under channel outage probability constraint of vehicles with imperfect CSI, QoS constraints of vehicles, and transmit power limits constraint of RSUs. The formulated problem with the channel outage probability constraint is a nonconvex probabilistic optimization problem. This problem is solved efficiently by converting the probabilistic problem through relaxation into a non-probabilistic problem., Comment: TVT

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatiotemporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor., Comment: 5 figures; AAAI 2020

The existing localization systems for indoor applications basically rely on wireless signal. With the massive deployment of low-cost cameras, the visual image based localization become attractive as well. However, in the existing literature, the hybrid visual and wireless approaches simply combine the above schemes in a straight forward manner, and fail to explore the interactions between them. In this paper, we propose a joint visual and wireless signal feature based approach for high-precision indoor localization system. In this joint scheme, WiFi signals are utilized to compute the coarse area with likelihood probability and visual images are used to fine-tune the localization result. Based on the numerical results, we show that the proposed scheme can achieve 0.62m localization accuracy with near real-time running time., Comment: To appear in Globecom 2020

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization. In this paper, we propose Coarse-to-Fine Action Detector (CFAD),an original end-to-end trainable framework for efficient spatio-temporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatio-temporal action tubes from video streams, and then refines the tubes' location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our framework. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, theproposed CFAD achieves competitive results on action detection benchmarks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3x faster than the nearest competitors., Comment: 7 figures, 3 tables; ECCV2020

Conventional schemes often require extra reference signals or more complicated algorithms to improve the time-of-arrival (TOA) estimation accuracy. However, in this letter, we propose to generate fine-grained features from the full band and resource block (RB) based reference signals, and calculate the cross-correlations accordingly to improve the observation resolution as well as the TOA estimation results. Using the spectrogram-like cross-correlation feature map, we apply the machine learning technology with decoupled feature extraction and fitting to understand the variations in the time and frequency domains and project the features directly into TOA results. Through numerical examples, we show that the proposed high accurate TOA estimation with fine-grained feature generation can achieve at least 51% root mean square error (RMSE) improvement in the static propagation environments and 38 ns median TOA estimation errors for multipath fading environments, which is equivalently 36% and 25% improvement if compared with the existing MUSIC and ESPRIT algorithms, respectively.

The emerging edge caching provides an effective way to reduce service delay for mobile users. However, due to high deployment cost of edge hosts, a practical problem is how to achieve minimum delay under a proper edge deployment strategy. In this letter, we provide an analytical framework for delay optimal mobile edge deployment in a partially connected wireless network, where the request files can be cached at the edge hosts and cooperatively transmitted through multiple base stations. In order to deal with the heterogeneous transmission requirements, we separate the entire transmission into backhaul and wireless phases, and propose average user normalized delivery time (AUNDT) as the performance metric. On top of that, we characterize the trade-off relations between the proposed AUNDT and other network deployment parameters. Using the proposed analytical framework, we are able to provide the optimal mobile edge deployment strategy in terms of AUNDT, which provides a useful guideline for future mobile edge deployment.

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The classification performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. However, ESC often suffers from the semantically irrelevant frames and silent frames. In order to deal with this, we employ a frame-level attention model to focus on the semantically relevant frames and salient frames. Specifically, we first propose a convolutional recurrent neural network to learn spectro-temporal features and temporal correlations. Then, we extend our convolutional RNN model with a frame-level attention mechanism to learn discriminative feature representations for ESC. We investigated the classification performance when using different attention scaling function and applying different layers. Experiments were conducted on ESC-50 and ESC-10 datasets. Experimental results demonstrated the effectiveness of the proposed method and our method achieved the state-of-the-art or competitive classification accuracy with lower computational complexity. We also visualized our attention results and observed that the proposed attention mechanism was able to lead the network tofocus on the semantically relevant parts of environmental sounds., Comment: arXiv admin note: substantial text overlap with arXiv:1907.02230

Driven by explosive computation demands of Internet of Things (IoT), mobile edge computing (MEC) provides a promising technique to enhance the computation capability for mobile users. In this paper, we propose a joint resource allocation and load management mechanism in an MEC system with wireless power transfer (WPT), by jointly optimizing the transmit power for WPT, the local/edge computing load, the offloading time, and the frequencies of the central processing units (CPUs) at the access point (AP) and the users. To achieve an energy-efficient and sustainable WPT-MEC system, we minimize the total energy consumption of the AP, while meeting computation latency requirements. Cooling energy which is non-negligible, is taken into account in minimizing the energy consumption of the MEC system. By rigorously orchestrating the state-of-the-art optimization techniques, we design an iterative algorithm and obtain the optimal solution in a semi-closed form. Based on the solution, interesting properties and insights are summarized. Extensive numerical tests show that the proposed algorithm can save up to 90.4% the energy of existing benchmarks., Comment: submitted for review

The commercial deployment of 5G communication networks makes the industry and academia to seriously consider the possible solutions for the next generation. Although the conventional approach indicates that 6G vision and requirements can be figured out by simply multiplying a certain amount of magnitude on top of the previous generations, we argue in this article that 1000 times price reduction from the customer's view point is the key to success. Guided by this vision, we categorize the current candidate technologies in a well organized manner and select AI-assisted intelligent communications as an example to elaborate the drive-force behind. Although it is impossible to identify every detail of 6G during the current time frame, we believe this article will help to eliminate the technical uncertainties and aggregate the efforts towards key breakthrough innovations for 6G., Comment: Accepted by IEEE Open Journal of Vehicular Technology (OJVT)

Real-time status update in future vehicular networks is vital to enable control-level cooperative autonomous driving. Cellular Vehicle-to-Everything (C-V2X), as one of the most promising vehicular wireless technologies, adopts a Semi-Persistent Scheduling (SPS) based Medium-Access-Control (MAC) layer protocol for its sidelink communications. Despite the recent and ongoing efforts to optimize SPS, very few work has considered the status update performance of SPS. In this paper, Age of Information (AoI) is first leveraged to evaluate the MAC layer performance of C-V2X sidelink. Critical issues of SPS, i.e., persistent packet collisions and Half-Duplex (HD) effects, are identified to hinder its AoI performance. Therefore, a piggyback-based collaboration method is proposed accordingly, whereby vehicles collaborate to inform each other of potential collisions and collectively afford HD errors, while entailing only a small signaling overhead. Closed-form AoI performance is derived for the proposed scheme, optimal configurations for key parameters are hence calculated, and the convergence property is proved for decentralized implementation. Simulation results show that compared with the standardized SPS and its state-of-the-art enhancement schemes, the proposed scheme shows significantly better performance, not only in terms of AoI, but also of conventional metrics such as transmission reliability., Comment: Submitted to IEEE TWC for possible publication

Ultra-Reliable and Low-Latency Communications (URLLC) services in vehicular networks on millimeter-wave bands present a significant challenge, considering the necessity of constantly adjusting the beam directions. Conventional methods are mostly based on classical control theory, e.g., Kalman filter and its variations, which mainly deal with stationary scenarios. Therefore, severe application limitations exist, especially with complicated, dynamic Vehicle-to-Everything (V2X) channels. This paper gives a thorough study of this subject, by first modifying the classical approaches, e.g., Extended Kalman Filter (EKF) and Particle Filter (PF), for non-stationary scenarios, and then proposing a Reinforcement Learning (RL)-based approach that can achieve the URLLC requirements in a typical intersection scenario. Simulation results based on a commercial ray-tracing simulator show that enhanced EKF and PF methods achieve packet delay more than $10$ ms, whereas the proposed deep RL-based method can reduce the latency to about $6$ ms, by extracting context information from the training data., Comment: 7 pages, 8 figures, to appear in ICC 2020

Wireless communications for status update are becoming increasingly important, especially for machine-type control applications. Existing work has been mainly focused on Age of Information (AoI) optimizations. In this paper, a status-aware predictive wireless interface design, networking and implementation are presented which aim to minimize the status recovery error of a wireless networked system by leveraging online status model predictions. Two critical issues of predictive status update are addressed: practicality and usefulness. Link-level experiments on a Software-Defined-Radio (SDR) testbed are conducted and test results show that the proposed design can significantly reduce the number of wireless transmissions while maintaining a low status recovery error. A Status-aware Multi-Agent Reinforcement learning neTworking solution (SMART) is proposed to dynamically and autonomously control the transmit decisions of devices in an ad hoc network based on their individual statuses. System-level simulations of a multi dense platooning scenario are carried out on a road traffic simulator. Results show that the proposed schemes can greatly improve the platooning control performance in terms of the minimum safe distance between successive vehicles, in comparison with the AoI-optimized status-unaware and communication latency-optimized schemes---this demonstrates the usefulness of our proposed status update schemes in a real-world application., Comment: To appear in IEEE INFOCOM 2020

The 5G Phase-2 and beyond wireless systems will focus more on vertical applications such as autonomous driving and industrial Internet-of-things, many of which are categorized as ultra-Reliable Low-Latency Communications (uRLLC). In this article, an alternative view on uRLLC is presented, that information latency, which measures the distortion of information resulted from time lag of its acquisition process, is more relevant than conventional communication latency of uRLLC in wireless networked control systems. An AI-assisted Situationally-aware Multi-Agent Reinforcement learning framework for wireless neTworks (SMART) is presented to address the information latency optimization challenge. Case studies of typical applications in Autonomous Driving (AD) are demonstrated, i.e., dense platooning and intersection management, which show that SMART can effectively optimize information latency, and more importantly, information latency-optimized systems outperform conventional uRLLC-oriented systems significantly in terms of AD performance such as traffic efficiency, thus pointing out a new research and system design paradigm., Comment: To appear in IEEE Wireless Communications

Precise indoor localization is an increasingly demanding requirement for various emerging applications, like Virtual/Augmented reality and personalized advertising. Current indoor environments are equipped with pluralities of WiFi access points (APs), whose deployment is expected to be massive in the future enabling highly precise localization approaches. Though the conventional model-based localization schemes have achieved sub-meter level accuracy by fusing multiple channel state information (CSI) observations, the corresponding computational overhead is usually significant, especially in the current multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. In order to address this issue, model-free localization techniques using deep learning frameworks have been lately proposed, where mainly classification methods were applied. In this paper, instead of classification based mechanism, we propose a logistic regression based scheme with the deep learning framework, combined with Cram\'er-Rao lower bound (CRLB) assisted robust training, which achieves more robust sub-meter level accuracy (0.97m median distance error) in the standard laboratory environment and maintains reasonable online prediction overhead under the single WiFi AP settings., Comment: IEEE Access (Volume: 7). arXiv admin note: text overlap with arXiv:1902.06226

Green radios jointly consider the spectrum efficiency and the energy efficiency in wireless networks in order to provide sustainable development. In the past two decades, various green radio solutions for different types of terminals and radio access networks have been developed, some of which have been used in the designs of wireless products. In this paper, we provide a historical view on some fundamental works and practical issues. In addition to providing a comprehensive overview on theoretical achievements, we also discuss several important power saving solutions with notable engineering impacts, such as Doherty power amplifier and separated baseband unit - remote radio unit architecture, which might be overlooked in previous publications. Moreover, with the huge growth of wireless traffic in the near future, green radio design for future wireless networks shall involve an end-to-end energy efficiency investigation of mobile terminals, radio access and core networks, and different applications. By introducing green radio schemes for advanced terminals and future wireless networks, this article will not only be beneficial for readers with only preliminary background in communications and signal processing but also have reference and historical values for researchers and practical engineers in the area.

Environmental Sound Classification (ESC) is an important and challenging problem, and feature representation is a critical and even decisive factor in ESC. Feature representation ability directly affects the accuracy of sound classification. Therefore, the ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. In this paper, we propose a subspectrogram segmentation based ESC classification framework. In addition, we adopt the proposed Convolutional Recurrent Neural Network (CRNN) and score level fusion to jointly improve the classification accuracy. Extensive truncation schemes are evaluated to find the optimal number and the corresponding band ranges of sub-spectrograms. Based on the numerical experiments, the proposed framework can achieve 81.9% ESC classification accuracy on the public dataset ESC-50, which provides 9.1% accuracy improvement over traditional baseline schemes., Comment: accepted in the 2019 IEEE International Workshop on Signal Processing Systems (SiPS2019)

Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization. The embeddings learned by softmax are not discriminative enough for open-set verification tasks. Angular based embedding learning target can achieve such discriminativeness by optimizing angular distance and adding margin penalty. We apply several different popular angular margin embedding learning strategies in this work and explicitly compare their performance on Voxceleb speaker recognition dataset. Observing the fact that encouraging inter-class separability is important when applying angular based embedding learning, we propose an exclusive inter-class regularization as a complement for angular based loss. We verify the effectiveness of these methods for learning a discriminative embedding space on ASV task with several experiments. These methods together, we manage to achieve an impressive result with 16.5% improvement on equal error rate (EER) and 18.2% improvement on minimum detection cost function comparing with baseline softmax systems., Comment: 5 pages

Speaker embeddings become growing popular in the text-independent speaker verification task. In this paper, we propose two improvements during the training stage. The improvements are both based on triplet cause the training stage and the evaluation stage of the baseline x-vector system focus on different aims. Firstly, we introduce triplet loss for optimizing the Euclidean distances between embeddings while minimizing the multi-class cross entropy loss. Secondly, we design an embedding similarity measurement network for controlling the similarity between the two selected embeddings. We further jointly train the two new methods with the original network and achieve state-of-the-art. The multi-task training synergies are shown with a 9% reduction equal error rate (EER) and detected cost function (DCF) on the 2016 NIST Speaker Recognition Evaluation (SRE) Test Set., Comment: 5 pages, Accepted to The Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2019 (APSIPA ASC 2019)

In this paper, we present a two-stage language identification (LID) system based on a shallow ResNet14 followed by a simple 2-layer recurrent neural network (RNN) architecture, which was used for Xunfei (iFlyTek) Chinese Dialect Recognition Challenge and won the first place among 110 teams. The system trains an acoustic model (AM) firstly with connectionist temporal classification (CTC) to recognize the given phonetic sequence annotation and then train another RNN to classify dialect category by utilizing the intermediate features as inputs from the AM. Compared with a three-stage system we further explore, our results show that the two-stage system can achieve high accuracy for Chinese dialects recognition under both short utterance and long utterance conditions with less training time., Comment: Accepted to Interspeech 2019

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. However, ESC often suffers from the semantically irrelevant frames and silent frames. In order to deal with this, we employ a frame-level attention model to focus on the semantically relevant frames and salient frames. Specifically, we first propose an convolutional recurrent neural network to learn spectro-temporal features and temporal correlations. Then, we extend our convolutional RNN model with a frame-level attention mechanism to learn discriminative feature representations for ESC. Experiments were conducted on ESC-50 and ESC-10 datasets. Experimental results demonstrated the effectiveness of the proposed method and achieved the state-of-the-art performance in terms of classification accuracy., Comment: Accepted to Chinese Conference on Pattern Recognition and Computer Vision (PRCV) 2019