Modern vehicles increasingly rely on advanced driver monitoring systems (DMS) to ensure safety and enhance the driving experience. These systems assess driver status to prevent accidents caused by fatigue, inattentiveness, or intoxication. While some DMS applications process video data on vehicle, many rely on edge or cloud-based solutions, raising significant privacy concerns due to the storage of sensor data from vehicles. Existing approaches, such as de-identification and homomorphic encryption, either impose heavy computational overhead on vehicles or insufficiently address privacy. To overcome these limitations, we present the Privacy-preserving Driver Monitoring System (PDMS), a novel framework based on the additive secret sharing theory and privacy-preserving Transformer-based deep learning models. PDMS creates randomized secret shares from driver’s facial video data on vehicle, processes them independently through privacy-preserving Transformer models on edges, and securely aggregates partial results on vehicle, ensuring vehicles’ sensor data and final results remain protected. This approach reduces the computational load on the vehicle, enabling cost-effective and scalable DMS solutions that protect the privacy of the driver both in transit and in processing. Our contributions include the design and optimization of the PDMS system, incorporating privacy-preserving DNN layers that are capable of processing randomized secret shares. Furthermore, we present a practical system that utilizes a vision transformer (ViT)-based gaze estimation model, demonstrating the effectiveness of PDMS through comprehensive experiments.

In this paper, we present a novel benchmark, GSOT3D, that aims at facilitating development of generic 3D single object tracking (SOT) in the wild. Specifically, GSOT3D offers 620 sequences with 123K frames, and covers a wide selection of 54 object categories. Each sequence is offered with multiple modalities, including the point cloud (PC), RGB image, and depth. This allows GSOT3D to support various 3D tracking tasks, such as single-modal 3D SOT on PC and multi-modal 3D SOT on RGB-PC or RGB-D, and thus greatly broadens research directions for 3D object tracking. To provide highquality per-frame 3D annotations, all sequences are labeled manually with multiple rounds of meticulous inspection and refinement. To our best knowledge, GSOT3D is the largest benchmark dedicated to various generic 3D object tracking tasks. To understand how existing 3D trackers perform and to provide comparisons for future research on GSOT3D, we assess eight representative point cloud-based tracking models. Our evaluation results exhibit that these models heavily degrade on GSOT3D, and more efforts are required for robust and generic 3D object tracking. Besides, to encourage future research, we present a simple yet effective generic 3D tracker, named PROT3D, that localizes the target object via a progressive spatial-temporal network and outperforms all current solutions by a large margin. By releasing GSOT3D, we expect to advance further 3D tracking in future research and applications. Our benchmark and model as well as the evaluation results will be publicly released at our webpage https://github.com/ailovejinx/GSOT3D.

High-performance Transformer trackers have exhibited excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently reduce computations without changing the model, an easy solution is to adopt a low-resolution input for efficient Transformer tracking. Albeit faster, this hurts tracking accuracy much due to the information loss in low resolution tracking. In this paper, we aim to mitigate such information loss to boost performance of low-resolution Transformer tracking via dual knowledge distillation from a frozen high-resolution (but not a larger) Transformer tracker. The core lies in two simple yet effective distillation modules, including query-key-value knowledge distillation (QKV-KD) and discrimination knowledge distillation (Disc-KD), across resolutions. The former, from the global view, allows the low-resolution tracker to inherit features and interactions from the high-resolution tracker, while the later, from the target-aware view, enhances the target-background distinguishing capacity via imitating discriminative regions from its high-resolution counterpart. With dual knowledge distillation, our Low-Resolution Transformer Tracker, dubbed LoReTrack, enjoys not only high efficiency owing to reduced computation but also enhanced accuracy by distilling knowledge from the high-resolution tracker. In extensive experiments, LoReTrack with a 2562resolution consistently improves baseline with the same resolution, and shows competitive or better results compared to the 3842high-resolution Transformer tracker, while running 52% faster and saving 56% MACs. Moreover, LoReTrack is resolution-scalable. With a 1282resolution, it runs 25 fps on a CPU with SUC scores of 64.9%/46.4% on LaSOT/LaSOText, surpassing other CPU real-time trackers. Code is released at https://github.com/ShaohuaDong2021/LoReTrack.

Low-Power Wide-Area Networks (LPWANs) have emerged as a promising communication technology for the Internet of Things (IoT). However, frequency overlap among wireless networks using different radio technologies creates significant interference, compromising communication reliability. This challenge is particularly urgent in LoRa networks, which coexist in the 2.4 GHz ISM band with other IoT transmitters capable of transmitting at much higher power levels. In our study, we begin by providing a comprehensive understanding of the LoRa physical layer (PHY), including insights into modulation and demodulation mechanisms. Leveraging this knowledge, we successfully implemented a real-time LoRa PHY on the GNU Radio Software-Defined Radio platform. To address cross-technology interference during peak detection, we introduce a spectrum merging technique that maintains phase coherence between superimposed peaks, minimizing spectral leakage artifacts. Beyond that, our analysis actively enhances the performance of commercial LoRa devices. Furthermore, we systematically explore the interference dynamics between LoRa and IEEE 802.15.4g networks. Our rigorous investigation reveals LoRa’s ability to achieve high packet reception rates, even in the presence of strong IEEE 802.15.4g interference.

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the reference speech, which are irrelevant to speaker identity, can lead to speaker confusion within the speech extraction network. To overcome this challenge, we propose a self-supervised disentangled representation learning method. Our approach tackles this issue through a two-phase process, utilizing a reference speech encoding network and a global information disentanglement network to gradually disentangle the speaker identity information from other irrelevant factors. We exclusively employ the disentangled speaker identity information to guide the speech extraction network. Moreover, we introduce the adaptive modulation Transformer to ensure that the acoustic representation of the mixed signal remains undisturbed by the speaker embeddings. This component incorporates speaker embeddings as conditional information, facilitating natural and efficient guidance for the speech extraction network. Experimental results substantiate the effectiveness of our meticulously crafted approach, showcasing a substantial reduction in the likelihood of speaker confusion.

Vehicle-to-Vehicle (V2V) cooperative perception has become increasingly popular in the field of autonomous driving, effectively overcoming the inherent limitations of single-vehicle perception systems, such as limited range and susceptibility to occlusions. In a V2V system, vehicles in close proximity can share perception data. To fuse this data, which is collected from different viewpoints by each vehicle, accurate pose information (including position and heading direction) is essential to transform the received data to the receiving vehicle's viewpoint. However, pose errors, often caused by measurement noise or sensor failures, can lead to severe misalignment during data fusion, resulting in incorrect object detections and potentially hazardous decisions in autonomous driving systems. To address this challenge, we present BB-Align, a lightweight pose recovery framework that utilizes Lidar Bird's-eye View (BV) images and object bounding Boxes for relative pose estimation. Designed as a plug-and-play solution, the proposed method requires no additional model training, enabling effortless integration into existing V2V systems. Our approach uses Lidar-derived BV images with a Log-Gabor filter-based feature map for effective image matching despite image sparsity. To reduce errors from self-motion distortion, we also integrate object bounding boxes for finer alignment. The proposed method is rigorously evaluated on the V2V 4Real dataset-currently the only real-world V2V dataset. Our approach demonstrates high pose estimation accuracy, outperforming an existing graph-matching method. It achieves translation and rotation errors of less than 1 m and 1°, respectively, in 80 % of cases within a 70 m range between vehicles. Furthermore, by integrating the proposed framework into cooperative object detection models under serious pose error, the result shows up to a 2x increase in Average Precision (AP) compared to those without pose recovery, with more pronounced improvements in the short range.

Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approaches often fully fine-tune a dual-branch encoder-decoder framework with a complicated feature fusion strategy for achieving multimodal semantic segmentation, which is training-costly due to the massive parameter updates in feature extraction and fusion. To address this issue, we propose a surprisingly simple yet effective dual-prompt learning network (dubbed DPLNet) for training-efficient multimodal (e.g., RGBD/T) semantic segmentation. The core of DPLNet is to directly adapt a frozen pre-trained RGB model to multimodal semantic segmentation, reducing parameter updates. For this purpose, we present two prompt learning modules, comprising multimodal prompt generator (MPG) and multimodal feature adapter (MFA). MPG works to fuse the features from different modalities in a compact manner and is inserted from shallow to deep stages to generate the multi-level multimodal prompts that are injected into the frozen backbone, while MFA adapts prompted multimodal features in the frozen backbone for better multimodal semantic segmentation. Since both the MPG and MFA are lightweight, only a few trainable parameters (3.88M, 4.4% of the pre-trained backbone parameters) are introduced for multimodal feature fusion and learning. Using a simple decoder (3.27M parameters), DPLNet achieves new state-of-the-art performance or is on a par with other complex approaches on four RGB-D/T semantic segmentation datasets while satisfying parameter efficiency. Moreover, we show DPLNet is general and applicable to other multimodal segmentation tasks. Without special design, DPLNet outperforms many complicated models. The source code can be found at https://github.com/ShaohuaDong2021/DPLNet.

Cooperative perception for connected and automated vehicles is traditionally achieved through the fusion of feature maps from two or more vehicles. However, the absence of feature maps shared from other vehicles can lead to a significant decline in 3D object detection performance for cooperative perception models compared to standalone 3D detection models. This drawback impedes the adoption of cooperative perception as vehicle resources are often insufficient to concurrently employ two perception models. To tackle this issue, we present Simultaneous Individual and Cooperative Perception (SiCP), a generic framework that supports a wide range of the state-of-the-art standalone perception backbones and enhances them with a novel Dual-Perception Network (DP-Net) designed to facilitate both individual and cooperative perception. In addition to its lightweight nature with only 0.13M parameters, DP-Net is robust and retains crucial gradient information during feature map fusion. As demonstrated in a comprehensive evaluation on the V2V4Real and OPV2V datasets, thanks to DP-Net, SiCP surpasses state-of-the-art cooperative perception solutions while preserving the performance of standalone perception solutions. The source code can be found at https://github.com/DarrenQu/SiCP.

The allocation of tasks in emergency response services, particularly within the framework of 911 operations, presents a critical challenge especially when ensuring the confidentiality of workers’ whereabouts. This issue arises from the necessity for responders to disclose their whereabouts to a central server for efficient task assignment, raising concerns regarding privacy breaches and potential risks to responders’ safety. In this paper, we address this issue by introducing a novel framework capable of assigning two 911 workers to respond to a patient’s request for help, while effectively safeguarding the workers’ location privacy through a devised location obfuscation strategy. Based on the constrained optimization of the location privacy protection model and task allocation model, we find that it can be approximated as two linear programming problems that can be solved by mature methods. Finally, we conduct a simulation experiments, the results of which illustrate the effectiveness of our approach in task allocation while preserving location privacy.

Cross-technology communication is essential for the Internet of Multimedia Things (IoMT) applications, enabling seamless integration of diverse media formats, optimized data transmission, and improved user experiences across devices and platforms. This integration drives innovative and efficient IoMT solutions in areas like smart homes, smart cities, and healthcare monitoring. However, this integration of diverse wireless standards within cross-technology multimedia communication increases the susceptibility of wireless networks to attacks. Current methods lack robust authentication mechanisms, leaving them vulnerable to spoofing attacks. To mitigate this concern, we introduce DeepSpoof, a spoofing system that utilizes deep learning to analyze historical wireless traffic and anticipate future patterns in the IoMT context. This innovative approach significantly boosts an attacker's impersonation capabilities and offers a higher degree of covertness compared to traditional spoofing methods. Rigorous evaluations, leveraging both simulated and real-world data, confirm that DeepSpoof significantly elevates the average success rate of attacks.

In this paper, we aim to explore the use of uplink semantic communications with the assistance of UAV in order to improve data collection effiicency for metaverse users in remote areas. To reduce the time for uplink data collection while balancing the trade-off between reconstruction quality and computational energy cost, we propose a hybrid action reinforcement learning (RL) framework to make decisions on semantic model scale, channel allocation, transmission power, and UAV trajectory. The variables are classified into discrete type and continuous type, which are optimized by two different RL agents to generate the combined action. Simulation results indicate that the proposed hybrid action reinforcement learning framework can effectively improve the efficiency of uplink semantic data collection under different parameter settings and outperforms the benchmark scenarios.

Noise pollution is a pressing concern in urban areas, exacerbated by the rapid pace of urbanization, industrialization, and high population density. It poses significant risks to human health and disrupts ecosystems. While noise pollution monitoring and E-health technologies have individually made substantial contributions to their respective fields, their integration has been largely overlooked in existing research. This oversight has resulted in missed opportunities for valuable insights and fragmented data analysis. To bridge this gap, we present the development of a collaborative sensing network that simultaneously monitors noise pollution and manages E-health. Our proposed solution, AntiNoise, employs a novel architecture that leverages smart devices and data mules to record noise levels and health statuses, transmitting this information to a cloud platform. To optimize the performance of the system, we design an integrated deep reinforcement learning framework for data mule trajectory planning and employ a deep Q-network algorithm for trajectory control. Through extensive evaluation, we demonstrate the efficiency of our approach, surpassing conventional schemes, particularly in scenarios with strict transmission power budgets.

Genomic scaffold filling problem is an important combinatorial optimization problem belonging to computational genomics. The One-Sided Genomic Scaffold Filling problem based on contig (One-Sided-SF-max) is the focus in this paper. The scaffold in this problem is presented as a sequence of contigs. The missing genes only can be inserted between contigs to ensure the integrity of original contigs. In this paper, an improved algorithm with a factor of$\frac{15}{8}$is proposed using the maximum matching and greedy method. The goal is to maximize the number of common adjacencies between two sequences. The approximate ratio of the algorithm is proved. Compared with the 2-approximation algorithm, the execution efficiency of the algorithm is also improved by running the same simulated data in the experiments of the two algorithms.

With the wider adoption of edge computing services, intelligent edge devices, and high-speed V2X communication, compute-intensive tasks for autonomous vehicles, such as perception using camera, LiDAR, and/or radar data, can be partially offloaded to road-side edge units. However, data privacy becomes a major concern for vehicular edge computing, as sensor data with sensitive information from vehicles can be observed and used by edge servers. We aim to address the privacy problem by protecting both vehicles' sensor data and the detection results. In this paper, we present a privacy preserving perception$(\mathbf{P}^{3})$framework which provides a secure version of every commonly used layers in various perception CNN networks. They server as the building blocks to facilitate the construction of a privacy preserving CNN for any existing or future network.$\mathbf{P}^{3}$leverages the additive secret sharing theory to develop secure functions for perception networks. A vehicle's sensor data is split and encrypted into multiple secret shares, each of which is processed on an edge server by going through the secure layers of a detection network. The detection results can only be obtained by combining the partial results from the participating edge servers. We present two use cases where the secure layers in$\mathbf{P}^{3}$are used to build privacy preserving both single-stage and two-stage object detection CNNs. Experimental results indicate data privacy for vehicles is protected without comprising the detection accuracy and with a reasonable amount of performance degradation. To the best of our knowledge, this is the first work that provides a generic framework to ease the development of vehicle-edge perception networks protecting data privacy.

Planar object tracking is a critical computer vision problem and has drawn increasing interest owing to its key roles in robotics, augmented reality, etc. Despite rapid progress, its further development, especially in the deep learning era, is largely hindered due to the lack of large-scale challenging benchmarks. Addressing this, we introduce PlanarTrack, a large-scale challenging planar tracking benchmark. Specifically, PlanarTrack consists of 1,000 videos with more than 490K images. All these sequences are collected in complex unconstrained scenarios from the wild, which makes PlanarTrack, compared with existing benchmarks, more challenging but realistic for real-world applications. To ensure the high-quality annotation, each frame in PlanarTrack is manually labeled using four corners with multiple-round careful inspection and refinement. To our best knowledge, PlanarTrack, to date, is the largest and the most challenging dataset dedicated to planar object tracking. In order to analyze the proposed PlanarTrack, we evaluate 10 planar trackers and conduct comprehensive comparisons and in-depth analysis. Our results, not surprisingly, demonstrate that current top-performing planar trackers degenerate significantly on the challenging PlanarTrack and more efforts are needed to improve planar tracking in the future. In addition, we further derive a variant named PlanarTrackBBfor generic object tracking from our PlanarTrack. Our evaluation of 10 excellent generic trackers on PlanarTrackBBmanifests that, surprisingly, PlanarTrackBBis even more challenging than several popular generic tracking benchmarks and more attention should be paid to handle such planar objects, though they are rigid. All benchmarks and evaluations are released at https://hengfan2010.github.io/projects/PlanarTrack/.

Quantization is an effective technique for reducing the number of computations and improving the performance of deep neural networks (DNNs). Weight quantization is popular because weights can be trained beforehand. However, weight quantization only targets the kernel weights and ignores the sensitivity of input features, which can lead to reduced accuracy. Fine-grained input quantization has gained attention as a way to speed up DNNs while maintaining accuracy. Existing approaches determine computation precision based on input sensitivity but do not effectively reduce computations for insensitive outputs or retain the precision of sensitive outputs. These limitations motivate us to develop an output-directed dynamic quantization method named ODQ in this paper. ODQ is a two-stage DNN quantization scheme designed to improve performance, reduce energy consumption, and maintain and often improve accuracy, compared with existing quantization methods. Specifically, inputs and weights go through sensitivity prediction and result generation. The high-order 2 bits of input and weight are used to predict output sensitivity. Result generation is performed only for predicted sensitive outputs. We designed an FPGA accelerator to optimize ODQ quantization performance for DNNs. We implement a prototype of ODQ and evaluate its performance using several state-of-the-art DNNs. Compared with a state-of-the-art input-directed quantization approach, ODQ achieves a 67.6% performance speedup and a 66.9% energy saving, with minimal accuracy degradation (≤ 0.6%).

In this paper, we present PRECISE, a novel privacy preserving data sharing framework for connected autonomous vehicles (CAVs). PRECISE allows users to define the objects or parts that they wish to protect privacy before sharing data with other vehicles. It leverages secure segmentation and inpainting technologies to protect sensitive data of vehicles. PRECISE explores the edges to offload resource-intensive deep learning workloads. To ensure data privacy in the processing on edge, PRECISE leverages additive secret sharing theory to define secure functions for deep neural networks (DNNs). Two secure DNN models, Secure SegNet and Secure Context Encoder, are introduced, along with detailed explanations of how to develop secure CNN layers and the secure functions used in building these layers. We have implemented a prototype of PRECISE and evaluated its performance. The experimental results demonstrate that PRECISE is lightweight, achieving secure segmentation in 3.47 seconds and secure inpainting in 0.99 seconds. The inference outputs from PRECISE remain the same as those from the original DNNs, while data privacy is protected. To the best of our knowledge, PRECISE is the first of its kind to provide user-defined privacy protection for sensor data sharing among CAVs.

Vehicular cooperative perception aims to provide connected and automated vehicles (CAVs) with a longer and wider sensing range, making perception less susceptible to occlusions. However, this prospect is dimmed by the imperfection of onboard localization sensors such as Global Navigation Satellite Systems (GNSS), which can cause errors in aligning over-the-air perception data (from a remote vehicle) with a Host vehicle’s (HV’s) local observation. To mitigate this challenge, we propose a novel LiDAR-based relative localization framework based on the iterative closest point (ICP) algorithm. The framework seeks to estimate the correct transformation matrix between a pair of CAVs’ coordinate systems, through exchanging and matching a limited yet carefully chosen set of point clouds and usage of a coarse 2D map. From the deployment perspective, this means our framework only consumes conservative bandwidth in data transmission and can run efficiently with limited resources. Extensive evaluations on both synthetic dataset (COMAP) and KITTI-360 show that our proposed framework achieves state-of-the-art (SOTA) performance in cooperative localization. Therefore, it can be integrated with any upper-stream data fusion algorithm and serves as a preprocessor for high-quality cooperative perception.

The emergence of Vertical Federated Learning (VFL) addresses the issue of data isolation and enhances edge intelligence. However, the high computational costs pose a significant challenge when employing Homomorphic Encryption (HE) for privacy protection in VFL. To address this challenge, we present DFedXGB, a secure and reliable framework for Federated XGBoost (FedXGB). DFedXGB incorporates an innovative data desensitization scheme to safeguard raw data and model parameters against privacy disclosure. Furthermore, We also designed a secure aggregation algorithm based on XGBoost to mitigate server collusion. Theoretical analysis confirms the correctness of DFedXGB, and security analysis establishes its provable security. Experimental results on real datasets demonstrate that DFedXGB achieves lossless accuracy comparable to non-privacy-preserving centralized methods. Moreover, DFedXGB reduces computational costs by an average of 85% compared to SecureBoost.

To enable self-driving without a human driver, an autonomous vehicle needs to perceive its surrounding obstacles using onboard sensors, of which the perception accuracy might be limited by their own sensing range. An effective way to improve vehicles’ perception accuracy is to let nearby vehicles exchange their sensor data so that vehicles can detect obstacles beyond their own sensing ranges, called cooperative perception. The shared sensor data, however, might disclose the sensitive information of vehicles’ passengers, raising privacy and safety concerns (e.g. stalking or sensitive location leakage).In this paper, we propose a new data-sharing policy for the cooperative perception of autonomous vehicles, of which the objective is to minimize vehicles’ information disclosure without compromising their perception accuracy. Considering vehicles usually have different desires for data-sharing under different traffic environments, our policy provides vehicles autonomy to determine what types of sensor data to share based on their own needs. Moreover, given the dynamics of vehicles’ data-sharing decisions, the policy can be adjusted to incentivize vehicles’ decisions to converge to the desired decision field, such that a healthy cooperation environment can be maintained in a long term. To achieve such objectives, we analyze the dynamics of vehicles’ data-sharing decisions by resorting to the game theory model, and optimize the data-sharing ratio in the policy based on the analytic results. Finally, we carry out an extensive trace-driven simulation to test the performance of the proposed data-sharing policy. The experimental results demonstrate that our policy can help incentivize vehicles’ data-sharing decisions to the desired decision fields efficiently and effectively.

The ever-increasing number of layers, millions of parameters, and large data volume make deep learning workloads resource-intensive and power-hungry. In this paper, we develop a convolutional neural network (CNN) acceleration framework, named MLCNN, which explores algorithm-hardware co-design to achieve cross-layer cooperative optimization and acceleration. MLCNN dramatically reduces computation and on-off chip communication, improving CNN's performance. To achieve this, MLCNN reorders the position of nonlinear activation layers and pooling layers, which we prove results in a negligible accuracy loss; then the convolutional layer and pooling layer are co-optimized by means of redundant multiplication elimination, local addition reuse, and global addition reuse. To the best of our knowledge, MLCNN is the first of its kind that incorporates cooperative optimization across convolutional, activation, and pooling layers. We further customize the MLCNN accelerator to take full advantage of cross-layer CNN optimization to reduce both computation and on-off chip communication. Our analysis shows that MLCNN can significantly reduce (up to 98%) multiplications and additions. We have implemented a prototype of MLCNN and evaluated its performance on several widely used CNN models using both an accelerator-level cycle and energy model and RTL implementation. Experimental results show that MLCNN achieves 3.2x speedup and 2.9x energy efficiency compared with dense CNNs. MLCNN's optimization methods are orthogonal to other CNN acceleration techniques, such as quantization and pruning. Combined with quantization, our quantized MLCNN gains a 12.8x speedup and 11.3x energy efficiency compared with DCNN.

Cooperative perception provides a novel way to conquer the sensing limitation on a single automated vehicle and potentially improves driving safety. To reduce the transmission data volume, existing solutions use the intermediate data generated by convolutional neural network (CNN) models, namely, feature maps, to achieve cooperative perception. The feature maps are however too large to be transmitted by the current V2X technology. We propose a novel approach, called Slim-FCP, to significantly reduce the transmission data size. It enables a channelwise feature encoder to remove irrelevant features for a better compression ratio. In addition, it adopts an intelligent channel selection strategy through which only representative channels of feature maps are selected for transmission. To evaluate the effectiveness of Slim-FCP, we further define a recall-to-bandwidth (RB) ratio metric to quantitatively measure how the recall of object detection changes with respect to the available network bandwidth. Experiment results show that Slim-FCP reduces the transmission data size by 75%, compared with the best state-of-the-art solution, with a subtle loss on object detection’s recall.

For a web search engine, it is critical to design a mechanism to promote trustworthy websites and eliminate spam ones in the searching results. In this paper, we propose the OpinionRank algorithm to compute the trustworthiness of a website and identify trustworthy ones with high trust values. OpinionRank is essentially a breadth-first-search based algorithm that starts from an existing set of trustworthy websites, also called seeds. Because seeds play a vital role in OpinionRank, we put forward a novel seed selection scheme, named HarMean PageRank algorithm. HarMean combines the results of two seed selection algorithms, i.e. High PageRank and Inverse PageRank, to rank websites based on their trustworthiness. After trustworthy seeds are chosen, OpinionRank iteratively computes the trustworthiness of every website, leveraging trust propagation and trust combination. Using the public dataset WEBSPAM-UK2006, we validate OpinionRank and HarMean PageRank, analyze the impact of seed selection, and evaluate the convergence speed of OpinionRank. Experimental results indicate that OpinionRank can detect more trustworthy websites with fewer seeds, when compared to three state-of-the-art solutions, TrustRank, GoodRank, and Enhanced OpinionWalk algorithms.

The Intelligent Transportation System has become one of the most globally researched topics, with Connected and Autonomous Vehicles(CAV) at its core. The CAV applications can be improved by the study of vehicle platooning immune to real-time traffic and vehicular network losses. In this work, we explore the need to integrate the Network model and Platooning system model for highway environments. The proposed platoon model is designed to be adaptive in length, providing the node vehicles to merge and exit. This overcomes the assumption that all the platoon nodes should have a common source and destination. The challenges of the existing platoon model, such as relay selection, acceleration threshold, are addressed for highly modular platoon design. The presented algorithm for merge and exit events optimizes the trade-off between network parameters such as communication range and vehicle dynamic parameters such as velocity and acceleration threshold. It considers the network bounds like SINR and link stability and vehicle trajectory parameters like the duration of the vehicle in the platoon. This optimizes the traffic throughput while maintaining stability using the PID controller. The work tries to increase the vehicle inclusion time in the platoon while preserving the overall traffic throuahput.

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present Deep Connected Attention Network (DCANet), a novel design that boosts attention modules in a CNN model without any modification of the internal structure. To achieve this, we interconnect adjacent attention blocks, making information flow among attention blocks possible. With DCANet, all attention blocks in a CNN model are trained jointly, which improves the ability of attention learning. Our DCANet is generic. It is not limited to a specific attention module or base network architecture. Experimental results on ImageNet and MS COCO benchmarks show that DCANet consistently outperforms the state-of-the-art attention modules with a minimal additional computational overhead in all test cases. The code is available at: https://github.com/13952522076/DCANet.

In this paper, we present a conceptually simple, yet powerful method for image recognition. The method, called Cooperative Dynamic Convolution (CoConv), introduces a cooperative learning of dynamic convolution from multiple convolutional experts. CoConv can be used as a substitute for the traditional static convolution, and can be seamlessly integrated in various visual models. Moreover, CoConv is easy to train with only a minimal computational overhead introduced in the inference phase. CoConv is trained by using multiple convolutional experts simultaneously, and the convolutional weights are merged by a weighted summation before convolutional operations for efficiency during inference. Results from extensive experiments show that CoConv leads to consistent improvement for image classification on various datasets, independent of the choice of the base convolutional network. Remarkably, CoConv improves the top-1 classification accuracy of ResNet18 by 3.06% on ImageNet. The code is available at: https://github.com/Nyquixt/CoConv.

To reduce the amount of transmitted data, feature map-based fusion is recently proposed as a practical solution to cooperative 3-D object detection by autonomous vehicles (AVs). The precision of object detection, however, may require significant improvement, especially for objects that are far away or occluded. To address this critical issue for the safety of AVs and human beings, we propose a cooperative spatial feature fusion (CoFF) method for AVs to effectively fuse feature maps for achieving a higher 3-D object detection performance. Especially, CoFF differentiates weights among feature maps for a more guided fusion, based on how much new semantic information is provided by the received feature maps. It also enhances the inconspicuous features corresponding to far/occluded objects to improve their detection precision. The experimental results show that CoFF achieves a significant improvement in terms of both detection precision and effective detection range for AVs, compared to previous feature fusion solutions.

Assessing trust in online social networks (OSNs) is critical for many applications such as online marketing and network security. It is a challenging problem, however, due to the difficulties of handling complex social network topologies and conducting accurate assessment in these topologies. To address these challenges, we model trust by proposing the three-valued subjective logic (3VSL) model. 3VSL properly models the uncertainties that exist in trust, thus is able to compute trust in arbitrary graphs. We theoretically prove the capability of 3VSL based on the Dirichlet-Categorical (DC) distribution and its correctness in arbitrary OSN topologies. Based on the 3VSL model, we further design the AssessTrust (AT) algorithm to accurately compute the trust between any two users connected in an OSN. We validate 3VSL against two real-world OSN datasets: Advogato and Pretty Good Privacy (PGP). Experimental results indicate that 3VSL can accurately model the trust between any pair of indirectly connected users in the Advogato and PGP.

Attention mechanisms have shown great success in computer vision. However, the commonly used global average pooling in some implementations aggregates a three-dimensional feature map to a one-dimensional attention map, leading a significant loss of structural information in the attention learning. In this article, we present a novel Spatial Pyramid Attention Network (SPANet), which exploits the structural information and channel relationships for better feature representation. SPANet enhances a base network by adding Spatial Pyramid Attention (SPA) blocks laterally. By rethinking the self-attention mechanism design, we further present three topology structures of attention path connection for our SPANet. They can be flexibly applied to various CNN architectures. SPANet is conceptually simple but practically powerful. It uses both structural regularization and structural information to achieve better learning capability. We have comprehensively evaluated the performance of SPANet on four benchmark datasets for different visual tasks. The experimental results show that SPANet significantly improves the recognition accuracy without adding much computation overhead. Using SPANet, we achieve an improvement of 1.6% top-1 classification accuracy on the ImageNet 2012 benchmark based on ResNet50, and SPANet outperforms SENet and other attention methods. SPANet also significantly improves the object detection performance by a clear margin with negligible additional computation overhead. When applying SPANet to RetinaNet based on the ResNet50 backbone, we improve the performance of the baseline model by 2.3 mAP and the enhanced model outperforms SENet and GCNet by 1.1 mAP and 1.7 mAP respectively. The code of SPANet is made publicly available.11[Online]. Available:https://github.com/13952522076/SPANet_TMM

In this paper, we present a cascaded context dependency module, which is a highly lightweight module that can improve the performance of deep convolutional neural networks for various visual tasks. Inspired by the feature pyramid work in object detection and the context dependency work in image recognition, we consider to cascade the contexts of multiscale feature maps to aggregate the locality and globality in a local region. We further extract the dependency between original input and cascaded contexts for feature recalibration. Without employing learnable layers, our method introduces almost no additional parameters and computations. Furthermore, Our module can be seamlessly plugged into many existing CNN architectures to improve the performance. Experiments on ImageNet and MS COCO benchmarks indicate that our method can achieve results on par with or better than related work. Qualitatively, we achieve an absolute 1.42% (77.3137% vs. 75.8974%) top-1 classification accuracy improvement based on ResNet50 on ImageNet 2012 validation set with negligible computational overhead. Besides, our method yields significant gains on the MS COCO benchmark for the object detection task. All codes and models are made publicly available1.1We submit all the codes, pre-trained models, and training log files to https://github.com/13952522076/ParameterFree.

Attention mechanism has shown great success in computer vision. In this paper, we introduce Spatial Pyramid Attention Network (SPANet) to investigate the role of attention block for image recognition. Our SPANet is conceptually simple but practically powerful. It enhances the base network by adding Spatial Pyramid Attention (SPA) Blocks laterally. In contrast to other attention based networks that leverage global average pooling, our proposed SPANet considers both structural regularization and structural information. Furthermore, we investigate the topology structure of attention path connection and present three SPANet structures. SPA block is flexible to be deployed to various convolutional neural network (CNN) architectures. The experimental results show that our SPANet significantly improves the recognition accuracy without introducing much computation overhead compared with other CNN models. Codes are made publicly available11https://github.com/13952522076/SPANet.

To make Convolutional Neural Networks (CNNs) more efficient and accurate, various lightweight self-attention modules have been proposed. In this paper, we systematically study state-of-the-art attention modules in CNNs and discover that self-attention mechanism can be closely related to normalization. Based on this observation, we propose a novel attention module, named Normalization-Attention module (NA module in short), which is almost parameter-free. The NA module calculates the mean and standard deviation of intermediate feature maps and processes the feature context with normalization, which makes a CNN model easier to be trained and more responsive to informative features. Our proposed Normalization-Attention module can be integrated into various base CNN architectures, and used for many computer vision tasks, including image recognition, object detection, and more. Experimental results on ImageNet and MS COCO benchmarks show that our method outperforms state-of-the-art works using fewer parameters. Codes are made publicly available.

To improve mobile users' quality-of-experience (QoE) in the mobile cyber-physical system (MCPS), caching layered-coding contents on edge nodes that are close to mobile users has been advocated as a promising solution, which can efficiently lower the content delivery delay and mitigate the overhead of backhaul network. However, due to the complexity of trust management and the limited caching capacities of edge nodes, designing an efficient edge caching scheme for mobile users becomes a challenge. Meanwhile, the content caching in MCPS also faces some security problems, where edge nodes may return incorrect results or viruses to mobile users, and mobile users would deliberately refuse to pay for caching services. To tackle these problems, we propose a novel blockchain-based trustworthy edge caching scheme for mobile users in MCPS. Specifically, we first exploit blockchain to supervise the caching transactions between the edge nodes and mobile users in a distributed manner, whereby the caching service information cannot be modified and denied by any entities. Furthermore, we devise a trust management mechanism for mobile users to search the trustworthy caching services from diversified edge nodes, where the trust degree of the edge node is real-time evaluated and updated by mobile users based on the quality of caching service. To take full advantage of caching resources, we design a max-min-based resource allocation algorithm, with which the trustworthy edge node could fairly allocate its caching resource based on mobile users' optimal demands. The simulation results show that the presented scheme not only improves the utilities of edge nodes but also increases the QoE of mobile users.

The one-sided Exemplar Adjacency Number (EAN) is a known problem for computing the exemplar similarity between a generic linear genome${\mathcal G}$with gene duplications and an exemplar genome$H$(over the same set of$n$gene families). In this problem, we need to compute an exemplar genome$G$, which is a permutation obtained from${\mathcal G}$, such that the number of common adjacencies between$G$and$H$is maximized. Unfortunately, the problem is not only NP-hard but also NP-hard to approximate. In this paper, we approach the problem by relaxing the constraint such that a sub-permutation$G^{+}$obtained from${\mathcal G}$does not have to include all the gene families, but still needs to have a length at least$k$. Hence$G^{+}$is called apseudo-exemplargenome. Then, a slightly more general problem (One-sided EAN+) is defined: compute a pseudo-exemplar genome$G^{+}$from${\mathcal G}$such that the number of common adjacencies between$H$and$G^{+}$is maximized. Certainly One-sided EAN+ contains One-sided EAN as a special case; moreover, it presents some flexibility in designing algorithms. First, we relax and formulate the One-sided EAN+ problem as the maximum independent set (MIS) on a colored interval graph and hence reduce the appearance of each gene to at most two times. We show that this new relaxation is still NP-complete, though a simple factor-2 approximation algorithm can be designed; moreover, we also prove that the problem cannot be approximated within$2-\varepsilon$by a local search technique. We then show that this relaxed version is fixed-parameter tractable (FPT). Second, to ensure that each gene appears in$G^+$at most once, we use integer linear programming (ILP) to solve this problem. Finally, we implement our algorithm and compare it with the up-to-date software GREDU, with simulated signed and unsigned genomes. It turns out that our algorithm is more stable and can process genomes of length up to 12,000 for signed genomes (while GREDU can falter on such a large signed genome and it cannot handle unsigned genomes at all).

Industrial Internet is applicable across a broad industrial spectrum including manufacturing, aviation, road and rail transport, power, oil and gas, healthcare, smart cities and buildings. Some of the major impacts of the Industrial Internet include the development of new and innovative services and products, which in turn also has economic benefits. The purpose of this special issue is to bring together research studies proposing novel techniques, algorithms, models, and solutions to address challenges such as interoperability, security, and privacy associated with Industrial Internet, blockchain and Cyber-physical systems. We accepted seven articles after two review rounds consisting of three reviews from experts in the areas. The special issue contains seven articles organized in the following categories. 1) Secure searching for edge-cloud assisted industrial Internet of Things (IoT) devices. 2) Privacy protection framework for mobile crowdsensing in Industrial Internet of Things (IIoT). 3) Content privacy for autonomous vehicles in cyberphysical system (CPS). 4) Delegated Proof of Stake (DPoS) consensus mechanism in blockchain. 5) Balancing privacy and accountability for industrial mortgage management. 6) Performance and security in wireless blockchain networks. 7) False data injection attacks in networked control systems.

The transmission scheduling is a critical problem in radio frequency (RF) energy harvesting communications. Existing transmission strategies are mainly based on a conventional model, in which the amount of harvested energy is modeled as predetermined random variables and the data transmission is arranged in a fixed feasible energy tunnel. In this paper, we show through the theoretical analysis and experimental results that due to the nonlinear battery charging characteristics, the harvested energy will largely depend on the transmission strategy. The bounds of feasible energy tunnel become dynamic. To describe a practical ambient energy harvesting process more accurately, a new nonlinear recursive model is proposed by adding a feedback loop that reflects the real-time influence of the data transmission on the energy harvesting process. In addition, to improve communication performance, we redesign the optimal transmission scheduling strategy based on the new model. In order to cope with the challenge of the endless loop in the new model, a recursive algorithm is developed. The simulation results reveal that the new transmission scheduling strategy can balance the efficiency of energy harvest and energy utilization regardless of the length of energy packets, thus improving the throughput performance of RF energy harvesting wireless communications.

Nowadays, internet based home automation is made possible with the advent of intelligent device control. These electronic sensing devices transfer an enormous amount of data into the cloud. It is a challenge to discover hidden information from the massive amount of stored data in the cloud. In addition, privacy, security, and stability could also be a concern for users. Due to these issues becoming ever more prevalent in today’s society, the need to have access to readily anomaly detection becomes crucial for the modern smart home user. In this paper, we design, test and evaluate an ensemble model anomaly detection method. Our method targets the data anomalies present in general smart Internet of Things (IoT) devices, allowing for easy detection of anomalous events based on stored data. We make our method robust through ensemble machine learning model training. We aim to simulate different types of anomaly situations on publicly available smart home data sets, thereby exposing our models to likely real world phenomenons and events that may cause anomalies. Experiments are conducted on the processed data and evaluated for accuracy through validation and testing against independent and identically distributed labeled data.

Autonomous vehicles may make wrong decisions due to inaccurate detection and recognition. Therefore, an intelligent vehicle can combine its own data with that of other vehicles to enhance perceptive ability, and thus improve detection accuracy and driving safety. However, multi-vehicle cooperative perception requires the integration of real world scenes and the traffic of raw sensor data exchange far exceeds the bandwidth of existing vehicular networks. To the best our knowledge, we are the first to conduct a study on raw-data level cooperative perception for enhancing the detection ability of self-driving systems. In this work, relying on LiDAR 3D point clouds, we fuse the sensor data collected from different positions and angles of connected vehicles. A point cloud based 3D object detection method is proposed to work on a diversity of aligned point clouds. Experimental results on KITTI and our collected dataset show that the proposed system outperforms perception by extending sensing area, improving detection accuracy and promoting augmented results. Most importantly, we demonstrate it is possible to transmit point clouds data for cooperative perception via existing vehicular network technologies.

Autonomous driving vehicle relies heavily on its perception system to sense surrounding environments and make driving decisions. One important task on autonomous driving vehicles is to correctly recognize different traffic signs. However, the traffic signs in the wild can be in various conditions, e.g., occluded, deteriorated, or vandalized, and not all of them are recognizable. In this work, we propose a novel system that leverages the perception system on autonomous vehicle to identify occluded road signs in real time. Based on transfer learning, we propose the occluded sign classification network (OSCN) that is able to achieve a precision of 96.34% on a real-world dataset.

Assessing the trust between users in a trust social network (TSN) isa critical issue in many applications, e.g., film recommendation,spam detection, and online lending. Despite of various trust assessment methods, a challenge remaining to existing solutions is how to accurately determine the factors that affect trust propagation and trust fusion within a TSN. To address this challenge, we propose the NeuralWalk algorithm to cope with trust factor estimation and trust relation prediction problems simultaneously. NeuralWalk employs a neural network, named WalkNet, to model single-hop trust propagation and fusion in a TSN. By treating original trust relations in a TSN as labeled samples, WalkNet is able to learn the parameters that will be used for trust computation/assessment. Unlike traditional solutions, WalkNet is able to accurately predict unknown trust relations in an inductive manner. Based on WalkNet, NeuralWalk iteratively assesses the unknown multi-hop trust relations among users via the obtained single-hop trust computation rules. Experiments on two real-world TSN datasets indicate that NeuralWalk significantly outperforms the state-of-the-art solutions.

Internet of Things (IoT), coming with billions of connected devices, could potentially transform our daily life but could also create a serious security headache. It brings greater complications in securely accessing these devices with privacy protection guaranteed, and several research issues need to be investigated in detail, e.g., access control, traceability, anonymity, authentication, security bootstrap, etc. Most of the traditional security protection mechanisms are centralized, which make them difficult to scale up to meet the security demands of the IoT.

Trustworthiness in a vehicular network plays a vital role in facilitating data sharing among vehicles to achieve better driving safety and convenience. Without trustworthiness assessment, a vehicle may not be able to trust other vehicles and, therefore, simply drop the data shared from others to avoid potential driving dangers. This problem was traditionally approached by protecting data security; however, the study of the trustworthiness of data generators (vehicles) is unfortunately omitted. We envision the existences of a vehicular social network on road, wherein vehicles exchanging data between each other are considered socially connected. Leveraging the trust propagation and fusion within a vehicular social network, the trustworthiness of individual vehicles can be accurately assessed. We adopt the three-valued subjective logic model to study trust between vehicles, and propose a holistic solution to trust assessment in vehicular social networks. The proposed solution enables objective and subjective trust assessment of vehicles, in a distributed manner. Simulation results indicate that the proposed solution offers a more accurate trust assessment and a quicker assessing time.

The ever-increasing demand for videos on mobile devices poses a significant challenge to existing cellular network infrastructures. To cope with the challenge, we propose a user-centric video transmission mechanism based on device-to-device communications that allows mobile users to cache and share videos between each other, in a cooperative manner. The proposed solution jointly considers users' similarity in accessing videos, users' sharing willingness, users' location distribution, and users' quality of experience (QoE) requirements, in order to achieve a QoE-guaranteed video streaming service in a cellular network. Specifically, a service set consisting of several service providers and mobile users, is dynamically configured to provide timely service according to the probability of successful service. Numerical results show that when the number of providers and demanded videos is 40 and 2, respectively, the improved users experience rate in the proposed solution is approximately 85%, and the data offload rate on base station(s) is about 78%.

The transmission scheduling is a critical problem in radio frequency (RF) energy harvesting communications. Existing transmission strategies are mainly designed based on a classic model, in which the harvested energy is assumed pre-determined and considered as prior knowledge in offline approaches. In this extended abstract, we challenge this assumption showing that the harvested energy is affected by the transmission scheduling and becomes unknown and not pre-determined. In the new model, we add a feedback line from the data transmission to the harvested energy. It properly indicates the interplay between the energy harvest and the data transmission but challenges the transmission scheduling in the meantime. We formulated the optimal transmission scheduling based on the new model and advocate a recursive solution.

In online social networks (OSNs), e.g. Facebook, the relationship between users is binary, i.e., either friend (trust) or stranger (distrust). However, in real-world life, people always have different trust relationships with others (e.g., best friend, acquaintance, frenemy). For various applications such as social recommendation and semantic web, it is more worthwhile to know the trust strength between users. In this work, via a unique dataset obtained from a Facebook app and a carefully designed user study, we map trust values with users' online interactions, and thus build personalized trust models. For each individual, we learn her trust model via optimization on a ranking-oriented loss function. Experimental results demonstrate the superior of the proposed approach over state-of-the-art method and the good generalization ability of the approach.

Water quality data is incredibly important and valuable, but its acquisition is not always trivial. A promising solution is to distribute a wireless sensor network in water to measure and collect the data; however, a drawback exists in that the batteries of the system must be replaced or recharged after being exhausted. To mitigate this issue, we designed a self-sustained water quality sensing system that is powered by renewable bioenergy generated from microbial fuel cells (MFCs). MFCs collect the energy released from native magnesium oxidizing microorganisms (MOMs) that are abundant in natural waters. The proposed energy-harvesting technology is environmentally friendly and can provide maintenance-free power to sensors for several years. Despite these benefits, an MFC can only provide microwatt-level power that is not sufficient to continuously power a sensor. To address this issue, we designed a power management module to accumulate energy when the input voltage is as low as 0.33V. We also proposed a radio-frequency (RF) activation technique to remotely activate sensors that otherwise are switched off in default. With this innovative technique, a sensor’s energy consumption in sleep mode can be completely avoided. Additionally, this design can enable on-demand data acquisitions from sensors. We implement the proposed system and evaluate its performance in a stream. In 3-month field experiments, we find the system is able to reliably collect water quality data and is robust to environment changes.

Massive trust assessment (MTA) in an Online Social Network (OSN), i.e., computing the trustworthiness of all users in the network, is crucial in various OSN-related applications. Existing solutions are either too slow or inaccurate in addressing the MTA problem. We propose the OpinionWalk algorithm that accurately and efficiently conducts MTA in an OSN. OpinionWalk models trust by the Dirichlet distribution and uses a matrix to represent the direct trust relations among users. From the perspective of a user, other users' trustworthiness are stored in a column vector that is iteratively updated when the algorithm “walks” through the network, in a breadth-first search manner. We identify the overlapping subproblems property in MTA and prove OpinionWalk is a more efficient solution. The accuracy and execution time of OpinionWalk are evaluated and compared to benchmark algorithms including EigenTrust, TrustRank, MoleTrust, TidalTrust and AssessTrust, using two real-world datasets (Advogato and Pretty Good Privacy). Experimental results indicate that OpinionWalk is an efficient and accurate solution to MTA, compared to previous algorithms.

Utilities have traditionally employed or contracted meter readers to collect natural gas usage data, which is expensive and time consuming, and thus necessitates the need of smart natural gas metering. Existing gas metering systems mainly focus on measuring the amount of gas flowing through an microelectro mechanical system (MEMS) thermal gas flow sensor and simply ignore the detailed gas composition. From computational fluid mechanics simulations, however, we discover that gases with different compositions will cause different effects on the reading of an MEMS sensor. Based on a thorough analysis of the working principle of MEMS thermal gas flow sensor, we propose an innovative mechanism to compensate the errors caused by different types of natural gases on the sensor's reading. The proposed solution first measures the physical property of metered gas to derive the composition correction coefficient that will then be used to correct the meter's reading errors, considering the relation between the calorific value and physical property of natural gases. In this way, the proposed solution realizes a real-time multicomposition gas metering via thermal gas flow sensors. We implement and evaluate the proposed gas metering technique in various Internet of Things systems, including industrial flow metering, gas metering in smart home, and gas metering in low-power wide-area networks. Experiment results verify the innovative design and confirm that the proposed solution features high sensitivity, high precision, and high range ratio.

The world has entered into a “smart” era. One area becoming smart is the place where we live-homes. Smart homes are expected to be equipped with numerous sensors to continually monitor, sense, and actuate the space. The data from these sensors can be used to provide various types of services by automating common tasks while causing minimal disruption to daily life. In order to provide these services, a system must have sufficient intelligence to predict future events based on its observations. This paper first examines the requirements for smart home predictions. It then comprehensively reviews prediction algorithms and variations that have been proposed and investigated in smart environments, such as smart homes. It is these prediction algorithms that provide the intelligence required by a smart home. Comparisons are also made upon these prediction algorithms on their features and models.

Multimedia communication in the Internet of Things (IoT) can potentially reach into a vast array of areas and touch people’s lives in profound and different ways. For example, real-time multimedia communication could be applied in the current U.S. 911 system to provide responders with detailed information about the nature and severity of an incident before they arrive on the scene, if the callers can transmit image and/or video of the incident site. City governments can also allow citizens to report traffic and road conditions by uploading real-time multimedia data via a specific smartphone app.

Introduction to a special issue of the journal Security and Communication Networks covering security and privacy in emerging wireless networks.

To improve the performance of mobile video delivery, caching layered videos at a site near to mobile end users (e.g., at the edge of mobile service provider's backbone) was advocated because cached videos can be delivered to mobile users with a high quality of experience, e.g., a short latency. How to optimally cache layered videos based on caching price, the available capacity of cache nodes, and the social features of mobile users, however, is still a challenging issue. In this paper, we propose a novel edge caching scheme to cache layered videos. First, a framework to cache layered videos is presented in which a cache node stores layered videos for multiple social groups, formed by mobile users based on their requests. Due to the limited capacity of the cache node, these social groups compete with each other for the number of layers they request to cache, aiming at maximizing their utilities while all mobile users in each group share the cost involved in the cache of video contents. Second, a Stackelberg game model is developed to study the interaction among multiple social groups and the cache node, and a noncooperative game model is introduced to analyze the competition among mobile users in different social groups. Third, leveraging the backward induction method, the optimal strategy of each player in the game model is proposed. Finally, simulation results show that the proposed method outperforms the exiting counterparts with a higher hit ratio and lower delay of delivering video contents.

Non-destructive concurrent transmissions recently attract widespread attention in wireless sensor networks research community, and many studies demonstrate that non-destructive interference in concurrent transmissions enables routing-free packet transmission with low latency and increased reliability. In this paper, we present a new MAC protocol, called Non-Destructive Interference MAC (NDI-MAC), that integrates non-destructive simultaneous transmissions into receiver-initiated protocols, achieving energy efficient and low latency data transmission under a variety of traffic loads. The capture effect is exploited in NDI-MAC to finish rendezvous between multiple senders and receivers. NDI-MAC also relies on triggercast, a distributed middleware to trigger synchronous packet transmissions with constructive interference. So as to ensure single-hop reliability, backcast primitive is used under unicast traffic. Evaluation results show that NDI-MAC achieves high performance in terms of energy consumption and data delivery latency under data dissemination and collection traffic.

Naive Bayes classifiers are widely used to filter spam emails, however, the strong independence assumptions between features limit their performance in accurately identifying spams. To address this issue, we proposed a support machine vector based naive Bayes - SVM-NB - filtering system. The SVM-NB first constructs an optimal separating hyperplane that divides samples in the training set into two categories. For samples located nearby the hyperplane, if they are in different categories, one of them will be eliminated from the training set. In this way, the dependence between samples is reduced and the entire training sample space is simplified. With the trimmed training set, the naive Bayes algorithm is applied to classify emails in the test set. The SVM-NB system is evaluated with the dataset obtained from DATAMALL. Experiment results demonstrate that SVM-NB can achieve a higher spam-detection accuracy and a faster classification speed.

Abstract Location privacy protection in vehicular ad hoc networks considers preserving two types of information: the locations and identifications of users. However, existing solutions, which either replace identifications by pseudonyms or hide locations in areas, cannot be directly applied to geographic routing protocols because they degrade network performance. To address this issue, we proposed a location‐preserved contention (LPC) based routing protocol, in which greedy forwarding is achieved using dummy distance to the destination information instead of users’ true locations. Unlike the contention‐based forwarding protocol, the number of duplicated responses in LPC can be reduced by adjusting the parameterα, which is a timer scaling factor. To quantify the efficiency of location privacy protection, an entropy‐based analytical method is proposed. LPC is compared with existing routing and location privacy protection protocols in simulations. Results show that LPC provides 11.7% better network performance and a higher level of location privacy protection than the second best protocol. Copyright © 2014 John Wiley & Sons, Ltd.

Multi-channel media access control (MAC) is important in wireless sensor networks because it allows parallel data transmissions and resists external wireless interference. Existing multi-channel MAC protocols, however, do not efficiently support delay-sensitive applications that require reliable and timely data transmissions. In addition, multi-channel operation is inherently deficient for supporting multi-hop broadcasting, due to independent waking-up schedules on sensors. To address these issues, we present a routing-enhanced multi-channel MAC (RM-MAC) which allows nodes to coordinately select their channel polling times based on cross-layer routing information. RMMAC also supports a ripple broadcast mechanism which achieves efficient multi-hop broadcast among sensors. Simulation results show that RM-MAC provides significant improvement over the MuCHMAC [1], in terms of end-to-end delay, under a wide range of traffic loads including both unicast and broadcast traffic.

Software Defined Network (SDN) may significantly enhance network and service management by enabling separated control and data planes. The centralized OpenFlow controller with a global vision of network states offers a promising approach to realizing flow-based admission control for supporting Quality of Service (QoS) provisioning in SDN. However, per-flow process brings in challenges to scalability of OpenFlow-based SDN. Flow aggregation has been explored as an effective method to address this issue. In this paper, we investigate admission control with flow aggregation for QoS provisioning in SDN. Specifically we propose a model for admission control with flow aggregation and develop the analysis techniques for determining the required amounts of bandwidth and buffer space at OpenFlow-enabled switches for meeting performance requirements in delay and packet loss. Network calculus is applied in our modeling and analysis; which makes our method applicable to general OpenFlow-based SDNs with various implementations. Numerical experiment results are also provided to evaluate effectiveness of the developed modeling and analysis techniques.

Hadoop is the de facto engine that drives current cloud computing practice. Current Hadoop architecture suffers from single point of failure problems: its job management lacks of fault tolerance. If a job management fails, even if its tasks remains still active on cloud nodes, this job loses all state information and has to restart from scratch. In this work, we propose a distributed MapReduce engine for Hadoop with the Distributed Hash Table (DHT) algorithm that drives the scalable peer-to-peer networks today. The distributed Hadoop engine provides the fault-tolerance capability necessary to support efficient job computation required in the cloud computing with numerous jobs running at a moment. We have implemented the proposed distributed solution into Hadoop and evaluated its performance in job failures under various network deployments.

Efficient and accurate target localization is one of the most fundamental problems in Wireless Sensor Networks (WSN), and has been studied for several years. Due to its simplicity and low energy consumption, binary sensing model is widely used in the literature to achieve fast target localization but with low accuracy. To improve localization accuracy, we propose a novel multi-bit sensing model where multi-bit information is sent by sensors to report the relative distances between a target and the sensors. Based on this sensing model, a new target localization algorithm is proposed, which can improve localization precision by estimating a targets position within a reduced area. Furthermore, the proposed algorithm works well with irregular sensing boundary caused by noise, channel fading, and obstacles. Simulation results show that the multi-bit sensing based target localization (MSTL) algorithm could improve localization accuracy by 50%.

Assessing multi-hop interpersonal trust in online social networks (OSNs) is critical for many social network applications such as online marketing but challenging due to the difficulties of handling complex OSN topology, in existing models such as subjective logic, and the lack of effective validation methods. To address these challenges, we for the first time properly define trust propagation and combination in arbitrary OSN topologies by proposing 3VSL (Three-Valued Subjective Logic). The 3VSL distinguishes the posteriori and priori uncertainties existing in trust, and the difference between distorting and original opinions, thus be able to compute multi-hop trusts in arbitrary graphs. We theoretically proved the capability based on the Dirichlet distribution. Furthermore, an online survey system is implemented to collect interpersonal trust data and validate the correctness and accuracy of 3VSL in real world. Both experimental and numerical results show that 3VSL is accurate in computing interpersonal trust in OSNs.

Wireless communication is indispensable to Internet of Things (IoT). Carrier sensing multiple access/collision avoidance (CSMA/CA) is a well-proven wireless random access protocol and allows each node of equal probability in accessing wireless channel, which incurs equal throughput in long term regardless of the channel conditions. To exploit node diversity that refers to the difference of channel condition among nodes, this paper proposes two opportunistic random access mechanisms: overlapped contention and segmented contention, to favor the node of the best channel condition. In the overlapped contention, the contention windows of all nodes share the same ground of zero, but have different upper bounds upon channel condition. In the segmented contention, the contention window upper bound of a better channel condition is smaller than the lower bound of a worse channel condition; namely, their contention windows are segmented without any overlapping. These algorithms are also polished to provide temporal fairness and avoid starving the nodes of poor channel conditions. The proposed mechanisms are analyzed, implemented, and evaluated on a Linux-based testbed and in the NS3 simulator. Extensive comparative experiments show that both opportunistic solutions can significantly improve the network performance in throughput, delay, and jitter over the current CSMA/CA protocol. In particular, the overlapped contention scheme can offer 73.3% and 37.5% throughput improvements in the infrastructure-based and ad hoc networks, respectively.

Though collisions in wireless networks can be caused either by known stations within the transmission range or by unknown hidden stations, rate adaptation algorithms that are designed to adapt to varying channel quality deal with both cases in the same manner so that they do not effectively respond to the different channel conditions. In this paper, after examining the core issues regarding rate adaptation, we propose a novel rate adaptation algorithm, called RACD (Rate Adaptation with Collision Differentiation), with the ability to differentiate the sources of collision by utilizing a new feature of IEEE 802.11, CTS-to-self frame, and adjusting the size of the contention window accordingly. Our simulation results show that RACD outperforms previous rate adaptation schemes, in terms of data throughput, by effectively distinguishing the cause for adverse channel conditions.

Round trip time (RTT) is widely used in ranging algorithms to compute the time of arrival (TOA) of a packet sent from a mobile station (STA) to an access point (AP). We propose a mechanism for measuring RTT in IEEE 802.11g using data and acknowledgement (ACK) messages at the driver layer. The scheme is implemented in the ATH9K driver in which timestamps (in nano-second) are collected when data are sent and ACK messages are received. The time differences between those two events (or interrupts) are considered the RTT for delivering these packets. However, due to noise caused by hardware, interrupt handling, and packet processing, directly using the measured RTT data to compute range of a mobile device can generate a high error of about 100ft. In fact, we discover from experiments that the standard deviation of RTT samples is 79µs. We prove that 1.7 million samples are required to achieve a ranging accuracy of 30ft. To reduce the size of samples, we use Euclidean distance (ED) to measure the difference of two sets of RTT data. With the help of ED, we only need 40k samples and achieve ranging accuracies of 10 ft and 50 ft for indoor and outdoor scenarios, respectively. Because the entire ranging system is implemented in the ATH9K driver, it can be easily installed in current STAs without modifying the existing APs.

An increasing number of commodity clusters are connected to each other by public networks, which have become a potential threat to security sensitive parallel applications running on the clusters. To address this security issue, we developed a Message Passing Interface (MPI) implementation to preserve confidentiality of messages communicated among nodes of clusters in an unsecured network. We focus on M PI rather than other protocols, because M PI is one of the most popular communication protocols for parallel computing on clusters. Our MPI implementation-called ES-MPICH2-was built based on MPICH2 developed by the Argonne National Laboratory. Like MPICH2, ES-MPICH2 aims at supporting a large variety of computation and communication platforms like commodity clusters and high-speed networks. We integrated encryption and decryption algorithms into the MPICH2 library with the standard MPI interface and; thus, data confidentiality of MPI applications can be readily preserved without a need to change the source codes of the MPI applications. MPI-application programmers can fully configure any confidentiality services in MPICHI2, because a secured configuration file in ES-MPICH2 offers the programmers flexibility in choosing any cryptographic schemes and keys seamlessly incorporated in ES-MPICH2. We used the Sandia Micro Benchmark and Intel MPI Benchmark suites to evaluate and compare the performance of ES-MPICH2 with the original MPICH2 version. Our experiments show that overhead incurred by the confidentiality services in ES-MPICH2 is marginal for small messages. The security overhead in ES-MPICH2 becomes more pronounced with larger messages. Our results also show that security overhead can be significantly reduced in ES-MPICH2 by high-performance clusters. The executable binaries and source code of the ES-MPICH2 implementation are freely available at http:// www.eng.auburn.edu/~xqin/software/es-mpich2/.

Compared to traditional wireless network routing protocols, geographic routing provides superior scalability and thus is widely used in vehicular ad hoc networks (VANETs). However, it requires every vehicle to broadcast its location information to its neighboring nodes, and this process will compromise user's location privacy. Existing solutions to this problem can be categorized into two groups: 1) hiding user's location or 2) preserving user's identification information in routing protocols, which drastically reduce network performances. To address this issue, we proposed a dummy-based location privacy protection (DBLPP) routing protocol, in which routing decision is made based upon the dummy distance to the destination (DOD), instead of users' true locations. In this scheme, users' true locations and identification information are preserved, so the user's location privacy is protected. Compared to existing solutions, simulation results show that while DBLPP provides similar network performances as other routing protocols, it achieves a higher level of location privacy protection on vehicles in networks.

In largely distributed clusters, computing nodes are geographically deployed in various computing sites. Information processed in a distributed cluster is shared among a group of distributed processes or users by virtue of messages passing protocols (e.g. message passing interface - MPI) running on the Internet. Because of the open accessible nature of the Internet, data encryption for these large-scale distributed clusters becomes a non-trivial and challenging problem. To address this issue, we enhanced the security of the MPI (Message Passing Interface) protocol by encrypting and decrypting messages sent and received among computing nodes. In this study we focused on MPI rather than other protocols because MPI is one of the most popular communication protocols for cluster computing environments. From among a variety of MPI implementations, we picked MPICH2 developed by the Argonne National Laboratory. The design goal of MPICH2 - a widely used MPI implementation - is to combine portability with high performance. We integrated encryption algorithms into the MPICH2 library so that data confidentiality of MPI applications could be readily preserved without a need to change the source codes of the MPI applications. since we provide a security enhanced MPI-library with the standard MPI interfact, data communications of a conventional MPI program can be secured without converting the program into the corresponding secure version. We used Sandia Micro Benchmark and Intel MPI Benchmarks to evaluate and compared the performance of original MPICH2 and Enhanced Security MPICH2. According to the performance evaluation, ES-MPICH2 provides secured Message Passing Interface by sacrificing reasonable system performance.

Developing routing protocol for vehicular ad hoc networks (VANET) is a challenging task due to potentially large network sizes, rapidly changing topology and frequent network disconnections, which can cause failure or inefficiency in traditional ad hoc routing protocols. We propose an adaptive connectivity aware routing (ACAR) protocol that addresses these problems by adaptively selecting an optimal route with the best network transmission quality based on the statistical and realtime density data that are gathered through an on-the-fly density collection process. The protocol consists of two parts: (1) select an optimal route, consisting of road segments, with the best estimated transmission quality (2) in each road segment in the selected route, select the most efficient multi-hop path that will improve delivery ratio and throughput. The optimal route can be selected using our new connectivity model that takes into account vehicles densities and traffic light periods to estimate transmission quality at road segments, which considers the probability of connectivity and data delivery ratio for transmitting packets. In each road segment along the optimal path, each hop is selected to minimize the packet error rate of the entire path. Our simulation results show that the proposed ACAR protocol outperforms existing VANET routing protocols in terms of data delivery ratio, throughput and data packet delay. In addition, ACAR works very well even if accurate statistical data is not available.

The original CPA (closest point of approach) algorithm can localize and track moving targets within a wireless sensor network that has a specific node configuration with respect to the target trajectory. As a target moves through a large network of randomly deployed sensors, the configuration of the nodes triggered along the target trajectory may not meet this requirement and will not localize and track the target correctly. To address this problem, we propose the enhanced CPA (ECPA) algorithm that can correctly compute the bearing of the target trajectory, the relative position between the sensors and the trajectory, and the velocity of the target. To validate ECPA, we designed and implemented the algorithm over a data-centric sensor network. This ECPA software also communicates over a collaborative mixed wireless sensor network with control software for controlling video sensor nodes that capture real-time images or video of the target at its predicted location. Our experimental results show that we can achieve our goals of detecting the target and predicting its location, velocity and direction of travel with reasonable accuracy. In addition, results from the target detection algorithm can be used to predict the future target location so that a camera can capture video of the moving target for identification purposes.

Multi-hop car to car communications are useful for supporting many vehicular applications that provide drivers with safety and convenience ranging from office on the wheel to real traffic query, vehicle safety, parking space searching and on-road advertisement. Developing multi-hop communication in vehicular ad hoc networks (VANET) is a challenging problem due to the rapidly changing topology and frequent network disconnections, which cause failure or inefficiency in traditional ad hoc routing protocols. The problem of frequent network disconnections can be partially addressed using a carry-and- forward mechanism which may incur higher delay. However, our connectivity aware routing (CAR) protocol addresses this problem by selecting an optimal route with the least probability of network disconnection and avoids carry-and-forward delay. This can be achieved using our new probabilistic model of network connectivity which takes into account a more realistic clustering phenomenon of vehicle traffic in city scenarios that is caused by traffic lights. Our simulation results show that the proposed CAR protocol outperforms existing VANET routing protocols in terms of data delivery ratio, data packet delay and network throughput. In addition, CAR improves performance for both sparse and dense networks.