Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite recent advances, non-IID (non-independent and identically distributed) data poses an inevitable challenge that hinders the use of FL. In this work, we address the issue of non-IID histopathological images with feature distribution shifts from an intuitive perspective that has only received limited attention. Specifically, we address this issue from the perspective of data distribution by solely adjusting the data distributions of all clients. Building on the success of diffusion models in fitting data distributions and leveraging stain separation to extract the pivotal features that are closely related to the non-IID properties of histopathological images, we propose a Federated Stain Distribution Alignment (FedSDA) method. FedSDA aligns the stain distribution of each client with a target distribution in an FL framework to mitigate distribution shifts among clients. Furthermore, considering that training diffusion models on raw data in FL has been shown to be susceptible to privacy leakage risks, we circumvent this problem while still effectively achieving alignment. Extensive experimental results show that FedSDA is not only effective in improving baselines that focus on mitigating disparities across clients’ model updates but also outperforms baselines that address the non-IID data issues from the perspective of data distribution. We show that FedSDA provides valuable and practical insights for the computational pathology community.

To facilitate object localization, the existing convolutional neural network (CNN)-based object detection often requires an object proposal method, which, however, may produce inaccurate region proposals and thus impact the performance. To overcome this setback, this paper presents a novel iterative localization refinement method which, undertaken at a mid-layer of a CNN architecture, progressively refines a subset of region proposals in order to match as much ground-truth as possible. In each iteration, the refinement task is cast into a probabilistic framework based on an ingeniously devised probability function. To expedite the computation of the probability function, a divide-and-conquer paradigm is developed by the theorem of total probability. Moreover, an approximate variant based on a refined sampling strategy is also addressed to further reduce the complexity. The proposed ILR method is not only data-driven and free of learning, but it can also be incorporated with many existing CNN-based object detection algorithms, such as Faster R-CNN to enhance the detection accuracy without changing their configurations. Simulations show that the proposed method can improve the main state-of-the-art works on the PASCAL VOC 2007, 2012 and Youtube-Objects data sets.

Accurate region proposals are of importance to facilitate object localization in the existing convolutional neural network (CNN)-based object detection methods. This paper presents a novel iterative localization refinement (ILR) method which, undertaken at a mid-layer of a CNN architecture, iteratively refines region proposals in order to match as much ground-truth as possible. The search for the desired bounding box in each iteration is first formulated as a statistical hypothesis testing problem and then solved by a divide-and-conquer paradigm. The proposed ILR is not only data-driven, free of learning, but also compatible with a variety of CNNs. Furthermore, to reduce complexity, an approximate variant based on a refined sampling strategy using linear interpolation is addressed. Simulations show that the proposed method improves the main state-of-the-art works on the PASCAL VOC 2007 dataset.

Abstract As network technology has rapidly developed over recent years, more research into vehicular ad hoc networks (VANETs) has come to highlight security and privacy issues within these networks. In discussions on security issues, the attempt by VANETs to ensure driver privacy makes non‐repudiation extremely difficult; many studies on security have failed to discuss this important issue. Vehicle drivers' privacy is weighed against sender non‐repudiation; these two factors are generally regarded as being in opposition. Because accident reporting systems will aim to retain complete privacy, they may be unable to guarantee non‐repudiation. This study therefore uses mutual authentication, digital signatures, and authorization certificates to develop an accident reporting system for VANETs which is not only able to retain driver privacy but also to track dangerous behavior on the part of drivers. Copyright © 2016 John Wiley & Sons, Ltd.

This paper presents a hierarchical framework for detecting local and global anomalies via hierarchical feature representation and Gaussian process regression. While local anomaly is typically detected as a 3D pattern matching problem, we are more interested in global anomaly that involves multiple normal events interacting in an unusual manner such as car accident. To simultaneously detect local and global anomalies, we formulate the extraction of normal interactions from training video as the problem of efficiently finding the frequent geometric relations of the nearby sparse spatio-temporal interest points. A codebook of interaction templates is then constructed and modeled using Gaussian process regression. A novel inference method for computing the likelihood of an observed interaction is also proposed. As such, our model is robust to slight topological deformations and can handle the noise and data unbalance problems in the training data. Simulations show that our system outperforms the main state-of-the-art methods on this topic and achieves at least 80% detection rates based on three challenging datasets.

This paper presents a hierarchical framework for detecting local and global anomalies via hierarchical feature representation and Gaussian process regression (GPR) which is fully non-parametric and robust to the noisy training data, and supports sparse features. While most research on anomaly detection has focused more on detecting local anomalies, we are more interested in global anomalies that involve multiple normal events interacting in an unusual manner, such as car accidents. To simultaneously detect local and global anomalies, we cast the extraction of normal interactions from the training videos as a problem of finding the frequent geometric relations of the nearby sparse spatio-temporal interest points (STIPs). A codebook of interaction templates is then constructed and modeled using the GPR, based on which a novel inference method for computing the likelihood of an observed interaction is also developed. Thereafter, these local likelihood scores are integrated into globally consistent anomaly masks, from which anomalies can be succinctly identified. To the best of our knowledge, it is the first time GPR is employed to model the relationship of the nearby STIPs for anomaly detection. Simulations based on four widespread datasets show that the new method outperforms the main state-of-the-art methods with lower computational burden.

IEEE 802.16 is defining standards for mobile multihop relay (MMR). The major purpose of MMR is to efficiently extend the coverage of a BS and to enhance the system throughput. Relay station (RS) has been introduced to fulfill this goal. However, packets in MMR would have a large probability of failure transmission because not all links over the multihop path are in good channel condition. Therefore, hybrid automatic repeat request (HARQ) has been designed to increase the reliability in multihop transmission. However, the retransmission mechanism proposed in 802.16j is not efficient. It will result in high packet delay. In this paper, we propose dynamic pre-allocation HARQ (DP-HARQ) which pre-allocates bandwidth for HARQ. Therefore, the packet delay is reduced significantly. The pre-allocated bandwidth is dynamically adjusted so the channel utilization will not be degraded much. We also propose mathematical models to analyze the proposed DP-HARQ. The analysis is validated by extensive simulations. Results show that the proposed DP-HARQ can reduce packet delay and jitter significantly.

Multicast services have received great interests recently. They normally cannot tolerate high packet delay and high loss rate. However, multicast services may be disrupted in mobile and wireless networks. Disruption may be caused by different reasons. In this paper, we consider the disruption resulted from handoffs between base stations. Although many mobile multicast protocols have been proposed, they primarily consider the routing in mobile environment. The protocols usually do not consider how to reduce packet delay and packet loss rate caused by intermittent radio connectivity. In this paper, we propose a mobile multicast protocol which utilizes cooperative communications for intermittent connected networks. Specifically, multicast packets are cached in helpers, which in turn relay the packets to the mobile hosts disconnected from the network. Therefore, multicast services still can be delivered to the disconnected mobile hosts. Hence, packet loss rate can be reduced and throughput can be increased significantly. Most of the studies of cooperative communications focus on MAC and physical layers. We demonstrate how cooperative communications can benefit multicast at network layer. Both mathematical model and simulation are developed to analyze the performance of the proposed protocol.

This paper presents a contention adaptation (CA) mechanism to improve the energy efficiency in IEEE 802.11e EDCA. By suspending some transmissions, the proposed EDCA/CA can reduce the number of collisions. Because unnecessary retransmissions are eliminated, the energy consumption is reduced. Extensive simulations have been performed to demonstrate the performance of the proposed EDCA/CA. The results show that EDCA/CA can reduce the energy consumption significantly. It reduces frame delay as well when traffic load is heavy. When traffic load is light, the proposed EDCA/CA will slightly increase the video delay, which in general is still acceptable. Furthermore, the proposed EDCA/CA is simple and easy to implement. It is fully compatible with the 802.11e EDCA. It is both effective and practical.