According to the World Health Organization (WHO), pneumonia kills about 2 million children under the age of 5 every year. Traditional machine learning methods can be used to diagnose chest X-rays of pneumonia in children, but there is a privacy and security issue in centralizing the data for training. Federated learning prevents data privacy leakage by sharing only the model and not the data, and it has a wide range of application in the medical field. We use federated learning method for classification, which effectively protects data security. And for the data heterogeneity phenomenon existing in the actual scenario, which will seriously affect the classification effect, we propose a method based on two-end control variables. Specifically, based on the classical federated learning FedAvg algorithm, we modify the loss function on the client side by adding a regular term or a penalty term, and add momentum after the average aggregation on the server side. The federated learning approach prevents the data privacy leakage problem compared to the traditional machine learning approach. In order to solve the problem of low classification accuracy due to data heterogeneity, our proposed method based on two-end control variables achieves an average improvement of 2% and an accuracy of 98% on average, and 99% individually, compared to the previous federated learning algorithms and the latest diffusion model-based method. The classification results and methodology of this study can be utilized by clinicians worldwide to improve the overall detection of pediatric pneumonia.
As a part of intelligent transportation, vehicle ad hoc networks (VANETs) have attracted the attention of industry and academia and have brought great convenience to drivers. As an open communication environment, any user can broadcast messages in the system. However, some of these users are malicious users and malicious users can broadcast false messages to interfere with the normal operation of the system. Therefore, we needed to authenticate the identity of the message sender. Currently, there are two main authentication methods in VANETs, one using public key infrastructure (PKI) to verify message integrity and sender identity, and the other using anonymous authentication schemes. Due to the high computational and transport overhead involved in validation, the certification efficiency of most existing schemes is not satisfactory. Therefore, these schemes are generally not applicable to real-world scenarios. In order to improve the efficiency of certification and satisfy the security requirements, in this paper, we proposed a hybrid proxy based authentication scheme (HPBS). In HPBS, by introducing the concept of agent vehicles and integrating identity-based and PKI-based hybrid authentication, we solved three problems in the VANETs environment: (1) improving the effectiveness of roadside units (RSUs) in terms of authenticating messages; (2) reducing the computational burden of RSUs; (3) protecting the privacy of users. The simulation results illustrate that the scheme not only ensures network security, but also greatly improves the efficiency of information verification.
18 April 2023 in IEEE Transactions on Neural Networks and Learning Systems
Convolutional neural networks (CNNs) have been successfully applied to various fields. However, CNNs’ overparameterization requires more memory and training time, making it unsuitable for some resource-constrained devices. To address this issue, filter pruning as one of the most efficient ways was proposed. In this article, we propose a feature-discrimination-based filter importance criterion, uniform response criterion (URC), as a key component of filter pruning. It converts the maximum activation responses into probabilities and then measures the importance of the filter through the distribution of these probabilities over classes. However, applying URC directly to global threshold pruning may cause some problems. The first problem is that some layers will be completely pruned under global pruning settings. The second problem is that global threshold pruning neglects that filters in different layers have different importance. To address these issues, we propose hierarchical threshold pruning (HTP) with URC. It performs a pruning step limited in a relatively redundant layer rather than comparing the filters’ importance across all layers, which can avoid some important filters being pruned. The effectiveness of our method benefits from three techniques: 1) measuring filter importance by URC; 2) normalizing filter scores; and 3) conducting prune in relatively redundant layers. Extensive experiments on CIFAR-10/100 and ImageNet show that our method achieves the state-of-the-art performance on multiple benchmarks.
Mobile edge storage is an emerging computing paradigm which enables users to enjoy high quality of experience when they access cloud services. However, extremely fast increasing multimedia data traffic from cloud to mobile users comes with the challenges of low-latency and high-bandwidth over cloud computing model. How to design cache strategies by exploiting terminal nodes' utility is still a challenging issue. In this paper, by exploiting 5G technology and cooperative edge computing, we propose a cooperative edge caching framework to tackle three issues simultaneously in the application scenarios of massive short video services: (1) reducing data transportation latency to improve mobile uses' quality of experience; (2) mitigating data traffic pressure on backbone network; (3) decreasing the workload on cloud servers. Firstly, we define a cooperative edge caching network model, in which many edge nodes equipped with capacities of storage, user admittance and Internet access form an ad hoc network and each node serves multiple mobile users. Secondly, we design a non-cooperative game model to investigate the cooperation behavior among the edge nodes, we allow each edge node server as a player and make decision of cache (storage) initialization and replacement strategies. Thirdly, we find there is a Nash Equilibrium in the proposed game. Finally, we design a distributed algorithm to achieve the equilibrium according to our theoretical analysis. Experiment results show that the proposed game-based edge caching strategy can improve mobile uses' quality of experience by 20% latency decreasing and reduce 80% backbone traffic and cloud workload.
With the sustained evolution and expeditious popularization of cloud computing, an ever-increasing number of individuals and enterprises are encouraged to outsource data to cloud servers for reducing management overhead and ease of access. Privacy requirements demand encryption of sensitive information before outsourcing, which, on the other hand, diminishes the usability of data and makes considerable efficient keyword search techniques used on plaintext inapplicable. In this paper, we propose a secure multi-keyword ranked search scheme based on document similarity to work out the problem. In order to achieve the goals of multi-keyword search and ranking search results, we adopt the vector space model and TF-IDF model to generate index and query vectors. By introducing the secure kNN computation, index and query vectors can be encrypted to prevent cloud servers from obtaining sensitive frequency information. For the need of efficiency advancement, we adopt the $B^{+}$ -tree as the basic structure to build the index and construct a similar document collection for each document. Due to the use of our unique index structure, compared to linear search, the search efficiency is more exceptional. Extensive experiments on the real-world document collection are conducted to demonstrate the feasibility and efficiency of the proposed solution.