To address the multi-UAV radar cooperative guided search task in the scenarios of large airspace with widespread distribution of cluster targets, an autonomous hierarchical decision-making framework based on multi-agent reinforcement learning is proposed to guide different airborne radar search processes in cooperative search tasks. Firstly, the top-level and bottom-level strategy modules are constructed based on the cooperative airspace set-covering model and search performance optimization models established in the above scenario respectively. Secondly, a cooperative search environment based on real-time beam scheduling is constructed where a complementary scheduling strategy for cooperative radar search beam positions is proposed to minimize cooperative search time and maximize global radar search performance. Finally, the lamaddpg-rgs algorithm is proposed to perform long-short term memory (LSTM) and feature extraction on the variable global observation state sequence, aiming to improve the algorithm training effect and convergence speed. Simulation results show that the trained hierarchical decision-making multi-agents can make precise autonomous decisions rapidly based on local observation states and current search task process. The optimization effect of radar cooperative search performance in above scenario based on proposed algorithm is superior to traditional algorithms.

Surface-mount device (SMD) diodes offer compact size, light weight, and enhanced reliability over traditional diodes but demand higher precision and more complex manufacturing processes. While research often centers on environmental and material factors affecting electronic packaging reliability, the impact of manufacturing processes on device failure is less explored. This study simulates the pin bending process of an SMD diode, analyzing stress conditions on internal structures for two mold design schemes. The distinct geometric features of molds in the two schemes result in different mold motion patterns and contact locations during operation. Notably, comparative analysis reveals that Design Scheme 1 sustains 2.66-fold greater stress concentration in the heat sink structure while demonstrating 2.16-times elevated chip stress levels relative to Design Scheme 2. Through simulation analysis, in conjunction with real-world manufacturing conditions, the primary factors leading to device failure are identified. Under the influence of mold tolerances and processing errors, the chip stress in the SMD diode increases from 23.603 to 188.11 MPa, a value approximately eight times the original stress level. It is emphasized that dimensional tolerances in the production process significantly impact device reliability, and the design of molds must account for these variations. This research offers valuable theoretical insights into ensuring the reliability of pin bending for various SMD devices. Moreover, the simulation outcomes for the SMD diode contribute to a deeper understanding of the internal stresses encountered in other plastic devices during their pin bending stages.

BACKGROUND: Lipid metabolism reprogramming is a hallmark for tumor which contributes to tumorigenesis and progression, but the commonality and difference of lipid metabolism among pan-cancer is not fully investigated. Increasing evidences suggest that the alterations in tumor metabolism, including metabolite abundance and accumulation of metabolic products, lead to local immunosuppression in the tumor microenvironment. An integrated analysis of lipid metabolism in cancers from different tissues using multiple omics data may provide novel insight into the understanding of tumorigenesis and progression. RESULTS: Through systematic analysis of the multiple omics data from TCGA, we found that the most-widely altered lipid metabolism pathways in pan-cancer are fatty acid metabolism, arachidonic acid metabolism, cholesterol metabolism and PPAR signaling. Gene expression profiles of fatty acid metabolism show commonalities across pan-cancer, while the alteration in cholesterol metabolism and arachidonic acid metabolism differ with tissue origin, suggesting tissue specific lipid metabolism features in different tumor types. An integrated analysis of gene expression, DNA methylation and mutations revealed factors that regulate gene expression, including the differentially methylated sites and mutations of the lipid genes, as well as mutation and differential expression of the up-stream transcription factors for the lipid metabolism pathways. Correlation analysis of the proportion of immune cells in the tumor microenvironment and the expression of lipid metabolism genes revealed immune-related differentially expressed lipid metabolic genes, indicating the potential crosstalk between lipid metabolism and immune response. Genes related to lipid metabolism and immune response that are associated with poor prognosis were discovered including HMGCS2, GPX2 and CD36, which may provide clues for tumor biomarkers or therapeutic targets. CONCLUSIONS: Our study provides an integrated analysis of lipid metabolism in pan-cancer, highlights the perturbation of key metabolism processes in tumorigenesis and clarificates the regulation mechanism of abnormal lipid metabolism and effects of lipid metabolism on tumor immune microenvironment. This study also provides new clues for biomarkers or therapeutic targets of lipid metabolism in tumors.

Neural network based multi-task learning has achieved great success on many NLP problems, which focuses on sharing knowledge among tasks by linking some layers to enhance the performance. However, most existing approaches suffer from the interference between tasks because they lack of selection mechanism for feature sharing. In this way, the feature spaces of tasks may be easily contaminated by helpless features borrowed from others, which will confuse the models for making correct prediction. In this paper, we propose a multi-task convolutional neural network with the Leaky Unit, which has memory and forgetting mechanism to filter the feature flows between tasks. Experiments on five different datasets for text classification validate the benefits of our approach.

Multi-task learning has an ability to share the knowledge among related tasks and implicitly increase the training data.However, it has long been frustrated by the interference among tasks.This paper investigates the performance of capsule network for text, and proposes a capsule-based multi-task learning architecture, which is unified, simple and effective.With the advantages of capsules for feature clustering, proposed task routing algorithm can cluster the features for each task in the network, which helps reduce the interference among tasks.Experiments on six text classification datasets demonstrate the effectiveness of our models and their characteristics for feature clustering.

Multi-task learning in text classification leverages implicit correlations among related tasks to extract common features and yield performance gains.However, a large body of previous work treats labels of each task as independent and meaningless one-hot vectors, which cause a loss of potential label information.In this paper, we propose Multi-Task Label Embedding to convert labels in text classification into semantic vectors, thereby turning the original tasks into vector matching tasks.Our model utilizes semantic correlations among tasks and makes it convenient to scale or transfer when new tasks are involved.Extensive experiments on five benchmark datasets for text classification show that our model can effectively improve the performances of related tasks with semantic representations of labels and additional information from each other.

Convolutional neural networks (CNNs) have shown their promising performance for natural language processing tasks, which extract n-grams as features to represent the input. However, n-gram based CNNs are inherently limited to fixed geometric structure and cannot proactively adapt to the transformations of features. In this paper, we propose two modules to provide CNNs with the flexibility for complex features and the adaptability for transformation, namely, transformable convolution and transformable pooling. Our method fuses dynamic and static deviations to redistribute the sampling locations, which can capture both current and global transformations. Our modules can be easily integrated by other models to generate new transformable networks. We test proposed modules on two state-of-the-art models, and the results demonstrate that our modules can effectively adapt to the feature transformation in text classification.

Generative Adversarial Nets are a powerful method for training generative models of complex data, where a Generator and a Discriminator confront with each other and get optimized in a two-player minmax manner. In this paper, we propose the Generative Warfare Nets (GWN) that involve multiple generators and multiple discriminators from two sides to exploit the advantages of Ensemble Learning. We maintain the authorities for the generators and the discriminators to enhance inter-side interactions, and utilize the mechanisms of imitation and innovation to model intra-side interactions among the generators, where they can not only learn from but also compete with each other. Extensive experiments on three natural image datasets show that GWN can achieve state-of-the-art Inception scores and produce diverse high-quality synthetic results.

Data plane network issues, caused by software bugs or hardware failures inside network devices, usually manifest themselves as failed rules, which can be verified by the comparison between actual and desired network behavior. Previous efforts implement this leveraging end-to-end active probing, which falls short on timely locating the exact failure points and identifying responsible rules. With the help of the out-band channel in software-defined network (SDN), per hop active probing can be employed to enable per device or even per rule network behavior comparison to verify the effectiveness of all the rules. Therefore, we present SERVE, an SDN-enabled rule verification framework that automatically identifies data plane network issues with periodic per rule network behavior comparison. By modeling network devices as stateful multi-rooted trees with respect to pipeline processing, a small number of probes can be generated from a per device perspective in a timely manner. We evaluate the performance of SERVE's probe generation and validate SERVE's effectiveness on a small deployment with typical use cases.

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex correlations among three or more tasks. In this paper, we propose a multi-task learning architecture with four types of recurrent neural layers to fuse information across multiple related tasks. The architecture is structurally flexible and considers various interactions among tasks, which can be regarded as a generalized case of many previous works. Extensive experiments on five benchmark datasets for text classification show that our model can significantly improve performances of related tasks with additional information from others.

For cloud network performance profiling, network tomography is useful for deducing the network performance based on end‐to‐end measurement. However, most tomography problems are under‐constrained, thus requires additional assumptions in order to be solvable, which sacrifices the accuracy. On the other hand, packet traces from switches could provide accurate and direct performance measurement, but it is hard to cover the whole network with packet trace analysis per link and flow. In this study, the authors propose ScoutFlow, a method combining software‐defined networking (SDN) flow measurement and end‐to‐end performance tomography, to achieve accurate performance profiling for cloud network while keeping low monitoring overhead. In ScoutFlow, they mirror the flow packet trace using SDN, to solve the under‐constrained problem in tomography. ScoutFlow only requires a small amount of flow mirror traces for the measurement, which leads to much lower overhead of flow mirroring than that of traditional packet‐level monitoring methods. The proposed methodology is evaluated with simulation and testbed experiments, which demonstrates ScoutFlow's scalability and accuracy.

Flash SSDs are being incorporated in many enterprise storage platforms recently. However, the characteristics of the flash SSD are quite different from that of hard disk. The IO strategies in the existing systems should be carefully evaluated. This paper provides an evaluation on the flash-based transaction processing system. Two file systems, traditional in-place update-based file system and log-structured file system, are selected as the representative of two write strategies. Usually, the log-structured file system is believed to play better on flash SSDs. Our experiment shows that the performance results of two database applications are diverse with two file systems on different flash SSDs. We analyze the performance in different configurations. Based on the analysis, we provide our experience on building the flash-based database system to better utilize the performance benefits of flash SSDs.