Federated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL) framework, which provides edge-level personalization to effectively overcomes non-IID data and alleviates the overfitting in the personalization process. The three-layer framework makes the learning and personalization process more feasible compared to traditional two-layer federated learning, as edge servers typically offer greater computing power and more efficient communication with the cloud server. Specifically, we use the K-Means++ clustering algorithm to group local clients based on their model updates, ensuring that clients with similar data distributions are clustered together and assigned to the same edge server. Each edge server then generates a personalized model by blending the global model with the edge model, which is adaptively updated and optimized through multiple iterations. Additionally, we introduce a novel aggregation rule on the cloud server to produce a global model with improved performance. Experiments on the MNIST, FMNIST, and KMNIST datasets demonstrate that CHPFL effectively overcomes non-IID data distribution and outperforms HPFL, APFL, and FedALA in non-IID settings.

The evolution of artificial intelligence has thrust the Online Judge (OJ) systems into the forefront of research, particularly within programming education, with a focus on enhancing performance and efficiency. Addressing the shortcomings of the current OJ systems in coarse defect localization granularity and heavy task scheduling architecture, this paper introduces an innovative Integrated Intelligent Defect Localization and Lightweight Task Scheduling Online Judge (IDL-LTSOJ) system. Firstly, to achieve token-level fine-grained defect localization, a Deep Fine-Grained Defect Localization (Deep-FGDL) deep neural network model is developed. By integrating Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU), this model extracts fine-grained information from the abstract syntax tree (AST) of code, enabling more accurate defect localization. Subsequently, we propose a lightweight task scheduling architecture to tackle issues, such as limited concurrency in task evaluation and high equipment costs. This architecture integrates a Kafka messaging system with an optimized task distribution strategy to enable concurrent execution of evaluation tasks, substantially enhancing system evaluation efficiency. The experimental results demonstrate that the Deep-FGDL model improves the accuracy by 35.9% in the Top-20 rank compared to traditional machine learning benchmark methods for fine-grained defect localization tasks. Moreover, the lightweight task scheduling strategy notably reduces response time by nearly 6000ms when handling 120 task volumes, which represents a significant improvement in evaluation efficiency over centralized evaluation methods.

Federated learning faces the challenge of non-IID data distribution while the global model doesn’t achieve well for individual clients. To address this challenge, we propose hierarchical personalized federated learning (HPFL) and achieve edge-level personalization, which overcomes non-IID data distribution and alleviates the overfitting of the pesonalization process. The three-layer framework makes the learning and personalization process more feasible than traditional two-layer federated learning since real-world edge servers usually have sufficient computing power than local clients and have efficient communication with the cloud server. In our approach, the personalized model on each edge server is generated by mixing the global model and edge model, which can be updated based on adaptive mixing parameter and optimized after multiple iterations. Experiments on MNIST and FMNIST show that the proposed HPFL overcomes non-IID data distribution, achieves comparable performance to traditional two-layer personalization APFL and outperforms HierFAVG under non-IID data setting.

Antiviral therapies targeting the pandemic coronavirus disease 2019 (COVID-19) are urgently required. We studied an already-approved botanical drug cepharanthine (CEP) in a cell culture model of GX_P2V, a severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-related virus. RNA-sequencing results showed the virus perturbed the expression of multiple genes including those associated with cellular stress responses such as endoplasmic reticulum (ER) stress and heat shock factor 1 (HSF1)-mediated heat shock response, of which heat shock response-related genes and pathways were at the core. CEP was potent to reverse most dysregulated genes and pathways in infected cells including ER stress/unfolded protein response and HSF1-mediated heat shock response. Additionally, single-cell transcriptomes also confirmed that genes of cellular stress responses and autophagy pathways were enriched in several peripheral blood mononuclear cells populations from COVID-19 patients. In summary, this study uncovered the transcriptome of a SARS-CoV-2-related coronavirus infection model and anti-viral activities of CEP, providing evidence for CEP as a promising therapeutic option for SARS-CoV-2 infection.

Summary Finding link/node‐disjoint paths between a pair of nodes is capable of providing Quality of Service and reliable routing which is very critical for mesh‐connected Network‐on‐Chip. State‐of‐art works usually aim at random topologies and multiple constraints. Therefore, it is difficult to optimize their time complexity. In this paper, MDPPIM (Manhattan‐distance‐constrained Disjoint Path Pair Problem in Incomplete Mesh) problem is presented based on Network‐on‐Chip application scenarios. Then, PCDP (Path‐Counting Disjoint Path) algorithm is proposed to solve the MDPPIM problem with low time complexity. Compared with previous disjoint path algorithms, PCDP algorithm does not have to use Dijkstra's algorithm to find a shortest path. It is optimized according to the feature of incomplete mesh such as the regularity of mesh and Manhattan‐distance constraint. Therefore, it is with low time complexity. Numerical results demonstrate the proposed PCDP algorithm's effectiveness and low time complexity.

Image segmentation is to partition one given image into different regions. In essence, the procedure of image segmentation is to cluster the pixels into different groups according to the retrieved features. However, artefacts in the given images make the features be contaminated, resulting in poor performance of current segmentation algorithms. Therefore, how to reduce the effect of image artefacts is one hot topic in image processing. In current algorithms, neighbour information is adopted to resist the effect of image artefacts. However, when the image is contaminated with high-level noise, current algorithms also perform poor. Recently, non-local information is introduced to improve the quality of segmentation results, in which pixel relevance between pixels is crucial. In this paper, pixel relevance is measured based on Mahalanobis distance. More specifically, we consider the distribution of different samples and relevance interference between samples in the procedure of computing pixel relevance. Then, a new algorithm based on the novel pixel relevance is proposed, where non-local information can be incorporated into fuzzy clustering for image segmentation. The new algorithm can improve the robustness of corresponding algorithms greatly. Experiments on different noisy images show that the proposed algorithm can retrieve better results than conventional algorithms.

Minimizing the flow completion times (FCTs), especially for the short flows, is widely deemed an important optimization goal in designing data center networks, while flow scheduling strategies play great role in achieving this target. Existing optimal scheduling algorithms severely depend on the prior knowledge of flow size, which is hard to implement in practice. Therefore, it is necessary to estimate the effect of flow scheduling strategies in information-agnostic datacenter networks. In this paper, we simplify the problem of FCTs and propose priority queue based mathematical model to evaluate the performance of different strategies, and derive the expression of FCT. We also present several scheduling strategies for reducing the value of FCT via analysis on the expression. We evaluate and compare these scheduling strategies by numerical and simulation experiments. The results show that the performance can be significantly improved if flow scheduling combines the characteristics of flow size distribution and the principle of providing shortest flow the highest priority.

In this paper, we consider a point-to-point communication network of discrete memoryless channels. In the network, there are a source node and possibly more than one sink node. Information is generated at the source node and is multicast to each sink node. We allow a node to encode its received information before loading it onto an outgoing channel, where the channels are independent of each other. We also allow the nodes to pass along messages asynchronously. In this paper, we characterize the admissibility of single-source multi-sink communication networks. Our result can be regarded as a network generalization of Shannon's result that feedback does not increase the capacity of a discrete memoryless channels (DMCs), and it implies a separation theorem for network coding and channel coding in such a communication network.

The redundancy rate of the Lempel-Ziv algorithm has been widely investigated. Much of the data compression community believed that the redundancy rate of the LZ78 algorithm should be O((log n)-1), where n is the data length. However, until the present paper, this conjecture had not been proved for sources beyond Markov sources. In this paper, we investigate the upper bound on the pointwise redundancy rate of the Lempel-Ziv algorithm for mixing sources and finite-state sources. The technique we applied in this paper is simple. By studying the dictionary tree resulting from the LZ78 algorithm, we derive certain relationships between the self-information of a sequence emitted by a source and the number of phrases resulting from the LZ78 parsing of the sequence. From these relationships, upper bounds on the pointwise redundancy rate of the LZ78 algorithm on mixing sources and finite-state sources can be obtained. These results show that for mixing sources and finite-state sources, the pointwise redundancy rate is upper bounded by O((log n)-1) for the LZ78 algorithm. We also compare our results with previous results of Savari and Kieffer-Yang

The concept of universal network measurement environment (UNME) is proposed, which includes three entities, i.e., the name server, the monitoring center and the probe. The architecture that the entities follow is called the universal network measurement (UNM), which consists of three layers. The key technologies such as component management protocol, network measurement policy protocol and the network measurement cooperative layer are explored and the construction of the probe and the method how to change measurement tools into the UNM probes are introduced. Finally, a real network monitoring & measurement system following UNM is illustrated, and several network measurement applications built on it are introduced.

Consider transmitting a set of information sources through a communication network that consists of a number of nodes. Between certain pair of nodes, there exist communication channels on which information can be transmitted. At a node, one or more information sources may be generated, and each of them is multicast to a set of destination nodes on the network. In this paper, we study the problem of under what conditions a set of mutually independent information sources can be faithfully transmitted through a communication network, for which the connectivity among the nodes and the multicast requirements of the source information are arbitrary except that the connectivity does not form directed cycles. We obtain inner and outer bounds on the zero-error admissible coding rate region in term of the regions /spl Gamma//sub N//sup */ and /spl Gamma/~/sub N//sup */, which are fundamental regions in the entropy space defined by Yeung. The results in this paper can be regarded as zero-error network coding theorems for acyclic communication networks.

Policies are increasingly used to manage large-scale distributed systems. They usually adopt ECA rules that cannot express system state transitions, enable policy servers to perform flexible actions or cooperate efficiently. A logic-based policy definition language, LPDL, is proposed. We define LPDL's syntax, execution model and its semantic that provides a formal framework for policy-based network management. LPDL is proved to have Petri net's expressive power and Turing machine computing power. An administrator can use LPDL to describe a system's analysis and decision functions or encapsulate them into physical codes flexibly based on actual need. Finally, a cooperative network management framework (CNMF), its prototype and application are presented to show that LPDL can meet the requirements of network management's dynamic growth.