Liang Hu

We introduce Federated Medical Data Augmentation with Differential Privacy for Medical Assistance (FMDADP-MA), addressing the challenge of limited medical data sharing due to privacy regulations and data isolations. Unlike traditional Generative adversarial networks assuming Independent and Identically Distributed (IID) data, FMDADP-MA facilitates data augmentation in non-IID environments using federated learning. This framework enables medical institutions collaboration across different locations to enrich datasets without centralizing data, overcoming collection and computational constraints. By organizing edge nodes and selecting groups for global training, we minimize data transmission to a central server. Each local model uses two convolutional neural networks to generate and label data, incorporating local differential privacy to safeguard against gradient-based privacy breaches. Our experiments show that increasing participant institutions enhances the global model’s accuracy, boosts local model performance, and diversifies data generation, tackling real-world issues of medical data privacy, imbalance, and under-labeling.

Multi-label causal feature selection has garnered considerable attention for its ability to identify the most informative features while accounting for the causal dependencies between labels and features. However, previous work often overlooks the unique contributions of labels to the target variables in multi-label settings, focusing instead on prioritizing feature variables. Moreover, existing methods typically rely on traditional Markov Blanket (MB) discovery to construct an initial MB, which often fails to explore the most valuable form of spouse variables to feature selection in multi-label scenarios, leading to significant computational overhead due to redundant Conditional Independence (CI) tests required for spouse search. To address these challenges, we propose the Multi-label Causal Feature Selection Method with Optimal Spouses Discovery, MCF-Spouse, which leverages mutual information to quantify the contributions of both labels and features, ensuring the retention of the most informative variables in multi-label settings. Moreover, we systematically analyzes all potential forms of spouse variables to identify the optimal spouse case, significantly reducing the spouse search space and alleviating the time overhead associated with CI tests. Experiments conducted on diverse real-world datasets demonstrate that MCF-Spouse consistently outperforms state-of-the-art methods across multiple metrics, offering a scalable and interpretable solution for multi-label causal feature selection.

With the increasing volume of scientific computation data and the advancement of computer performance, scientific computation is becoming more dependent on the powerful computing capabilities of cloud computing. On cloud platforms, tasks in scientific workflows are assigned to computational resources and executed according to specific strategies. Therefore, workflow scheduling has become a key factor affecting efficiency. This paper proposes a hybrid scientific workflow scheduling algorithm, HICA, to address the scheduling problem of scientific workflows in symmetric homogeneous cloud environments with optimization goals of makespan and cost. HICA combines the Imperialist Competitive Algorithm (ICA) with the HEFT algorithm, integrating HEFT into the initial population of the ICA to accelerate the convergence of the ICA. Experimental results show that the proposed hybrid approach outperforms other algorithms in real-world workflow applications. Specifically, when the workflow scale is 100, the average improvements in makespan and cost are 133.89 and 273.33, respectively; when the workflow scale is 1000, the improvements are 371.62 and 9178.98. The scheduling results for the Earth System Model parameter tuning workflow show that compared to the scenario without using a scheduling algorithm, the makespan and cost were improved by 13% and 21%, respectively.

Trigger-action programming (TAP) is an Internet of Things (IoT) paradigm that enables nonprofessional end-users to automate smart devices by formulating rules, such as “IF you leave home, THEN turn off lights.” As the number of possible rules increases, manually browsing these rules becomes increasingly time-consuming for users. Recently, graph-based recommendation systems have shown promise in automatically suggesting rules, yet they face two issues. First, these studies struggle to identify and differentiate users’ demands (e.g., turning off lights) and intentions (e.g., energy saving). Second, they overlook the issue of sparse user-rule interactions. In this article, we propose LLM4TAP, a large language model (LLM) enhanced TAP rule recommendation framework, to address these issues. Prior to LLM4TAP, a user-rule graph is constructed to represent the interactions between users and rules. Within LLM4TAP, singular value decomposition is first employed to generate an augmented graph, strengthening global structural relationships between users and rules. Next, the reasoning capabilities of LLMs are utilized to infer users’ demands and intentions from the textual descriptions of rules and user-rule interactions, producing representations of these inferred demands and intentions. Finally, a dual representation alignment method is introduced, integrating user demands and intentions derived from LLMs with the global structural information from the augmentation graph within a contrastive learning framework to enhance representation performance. Extensive experiments demonstrate the effectiveness of LLM4TAP, achieving the maximum improvements of 8.96% and 4.72% over the strongest compared methods on the IFTTT and Wyze datasets, respectively.

The uncertainty of physical parameters is a major factor contributing to poor precipitation simulation performance in Earth system models (ESMs), particularly in tropical and Pacific regions. To address the high computational cost of repetitive ESM runs, this study proposes a multilevel surrogate model-based parameter optimization framework and applies it to improve the precipitation performance of CAM5. A top-level surrogate model using gradient boosting regression trees (GBRTs) was constructed, leveraging the candidate point (CAND) approach applied to balance exploration and exploitation. A bottom-level surrogate model was then built based on a small, selected dataset; we designed a trust region approach to adjust the sampling region during the bottom-level tuning process. Experimental results demonstrate that the proposed method achieves fast convergence and significantly enhances precipitation simulation accuracy, with an average improvement of 19% in selected regions. In integrating optimization results through a nonuniform parameterization scheme and parameter smoothing, substantial improvements were observed in the South Pacific, Niño, South America, and East Asia. Comparisons with remote sensing data confirm that the optimized precipitation simulations do not introduce significant biases to other variables, validating the effectiveness and robustness of the proposed method.

High-performance computing (HPC) plays a crucial role in scientific computing, and the efficient utilization of HPC to accomplish computational tasks remains a focal point of research. This study addresses the issue of parameter tuning for Earth system models by proposing a comprehensive solution based on the concept of scientific workflows. This solution encompasses detailed methods from sensitivity analysis to parameter tuning and incorporates various approaches to enhance result accuracy. We validated the reliability of our methods using five cases in the Single Column Atmosphere Model (SCAM). Specifically, we investigated the influence of fluctuations of 11 typical parameters on 10 output variables. The experimental results show that the magnitude of the impact on the results varies significantly when different parameters are perturbed. These findings will help researchers develop more reasonable parameterization schemes for different regions and seasons.

The rapid expansion of the Internet of Things (IoT) has led to the development of smart homes and automation systems. Trigger-action programming (TAP) has emerged as a prevalent paradigm used in IoT, facilitating the creation of automation rules. However, with the proliferation of TAP rules, the potential for conflicts between them grows significantly, which results in undesired outcomes or even safety risks. In this paper, we propose a Context-aware Conflict Detection Framework for TAP rules, called CCDF-TAP, to identify the potential rule conflicts. Specifically, we incorporate external knowledge and context information during the TAP data preprocessing stage, which is conducive to accurately defining the rule conflicts. Then, based on the above information, the conflict types are defined and a conflict graph is constructed, which establishes a unified format for the rule conflict detection task. Finally, we propose a novel algorithm called Dual-channel Graph Attention Auto-encoders (DualGAA) for efficient conflict detection, which takes the conflict graph as the input and excels in accurately identifying conflicts. Extensive experiments conducted on a comprehensive IFTTT dataset demonstrate the superiority of DualGAA in detecting conflicts, achieving an exceptional accuracy of 98.85% and an F1 score of 98.91%. The contributions of our study offer a comprehensive end-to-end solution for context-aware conflict detection in TAP rules, thereby significantly enhancing the security and dependability of IoT smart home systems.

The single-column model, with its advantages of low computational cost and fast execution speed, can assist users in gaining a more intuitive understanding of the impact of parameters on the simulated results of climate models. It plays a crucial role in the study of parameterization schemes, allowing for a more direct exploration of the influence of parameters on climate model simulations. In this paper, we employed various methods to conduct sensitivity analyses on the 11 parameters of the Single Column Atmospheric Model (SCAM). We explored their impact on output variables such as precipitation, temperature, humidity, and cloud cover, among others, across five test cases. To further expedite experimentation, we utilized machine learning methods to train surrogate models for the aforementioned cases. Additionally, three-parameter joint perturbation experiments were conducted based on these surrogate models to validate the combined parameter effects on the results. Subsequently, targeting the sensitive parameter combinations identified from the aforementioned experiments, we further conducted parameter tuning for the corresponding test cases to minimize the discrepancy between the results of SCAM and observational data. Our proposed method not only enhances model performance but also expedites parameter tuning speed, demonstrating good generality at the same time.