Communications engineering最新文献_第6页

Data-driven and privacy-preserving risk assessment method based on federated learning for smart grids 基于联合学习的智能电网数据驱动和隐私保护风险评估方法。

Communications engineering Pub Date : 2024-11-02 DOI: 10.1038/s44172-024-00300-6

Song Deng, Longxiang Zhang, Dong Yue

{"title":"Data-driven and privacy-preserving risk assessment method based on federated learning for smart grids","authors":"Song Deng, Longxiang Zhang, Dong Yue","doi":"10.1038/s44172-024-00300-6","DOIUrl":"10.1038/s44172-024-00300-6","url":null,"abstract":"Timely and precise security risk evaluation is essential for optimal operational planning, threat detection, and the reliable operation of smart grid. The smart grid can integrate extensive high-dimensional operational data. However, conventional risk assessment techniques often struggle with managing such data volumes. Moreover, many methods use centralized evaluation, potentially neglecting privacy issues. Additionally, Power grid operators are often reluctant to share sensitive risk-related data due to privacy concerns. Here we introduce a data-driven and privacy-preserving risk assessment method that safeguards Power grid operators’ data privacy by integrating deep learning and secure encryption in a federated learning framework. The method involves: (1) developing a two-tier risk indicator system and an expanded dataset; (2) using a deep convolutional neural network -based model to analyze the relationship between system variables and risk levels; and (3) creating a secure, federated risk assessment protocol with homomorphic encryption to protect model parameters during training. Experiments on IEEE 14-bus and IEEE 118-bus systems show that our approach ensures high assessment accuracy and data privacy. Song Deng and colleagues present a data-driven and privacy preserving risk assessment approach to protect the data privacy of all power grid operators. They demonstrate the feasibility of their method in experiments with IEEE 14-bus and 118-bus systems.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00300-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-level physics informed deep learning for solving partial differential equations in computational structural mechanics 多层次物理信息深度学习，用于求解计算结构力学中的偏微分方程。

Communications engineering Pub Date : 2024-11-01 DOI: 10.1038/s44172-024-00303-3

Weiwei He, Jinzhao Li, Xuan Kong, Lu Deng

{"title":"Multi-level physics informed deep learning for solving partial differential equations in computational structural mechanics","authors":"Weiwei He, Jinzhao Li, Xuan Kong, Lu Deng","doi":"10.1038/s44172-024-00303-3","DOIUrl":"10.1038/s44172-024-00303-3","url":null,"abstract":"Physics-informed neural network has emerged as a promising approach for solving partial differential equations. However, it is still a challenge for the computation of structural mechanics problems since it involves solving higher-order partial differential equations as the governing equations are fourth-order nonlinear equations. Here we develop a multi-level physics-informed neural network framework where an aggregation model is developed by combining multiple neural networks, with each one involving only first-order or second-order partial differential equations representing different physics information such as geometrical, constitutive, and equilibrium relations of the structure. The proposed framework demonstrates a remarkable advancement over the classical neural networks in terms of the accuracy and computation time. The proposed method holds the potential to become a promising paradigm for structural mechanics computation and facilitate the intelligent computation of digital twin systems. Weiwei He and colleagues implement a multi-level physicsinformed neural network to solve partial differential equations, a key problem for efficient structure analysis. Their results improve the accuracy and computation time for solving these problems.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00303-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computational multiphysics modeling of radioactive aerosol deposition in diverse human respiratory tract geometries 放射性气溶胶在不同人体呼吸道几何形状中沉积的多物理场计算模型。

Communications engineering Pub Date : 2024-11-01 DOI: 10.1038/s44172-024-00296-z

Ignacio R. Bartol, Martin S. Graffigna Palomba, Mauricio E. Tano, Shaheen A. Dewji

{"title":"Computational multiphysics modeling of radioactive aerosol deposition in diverse human respiratory tract geometries","authors":"Ignacio R. Bartol, Martin S. Graffigna Palomba, Mauricio E. Tano, Shaheen A. Dewji","doi":"10.1038/s44172-024-00296-z","DOIUrl":"10.1038/s44172-024-00296-z","url":null,"abstract":"The evaluation of aerosol exposure relies on generic mathematical models that assume uniform particle deposition profiles over the human respiratory tract and do not account for subject-specific characteristics. Here we introduce a hybrid-automated computational workflow that generates personalized particle deposition profiles in 3D reconstructed human airways from computed tomography scans using Computational Fluid and Particle Dynamics simulations. This is the first large-scale study to consider realistic airways variability, where 380 lower and 40 upper human respiratory tract 3D geometries are reconstructed and parameterized. The data is clustered into nine groups using random forest regression. Computational fluid and particle dynamics simulations are conducted on these representative geometries using a realistic heavy-breathing respiratory cycle and radioactive iodine-131 as a source term. Monte Carlo radiation transport simulations are performed to obtain detailed energy deposition maps. Our findings emphasize the importance of personalized studies, as minor respiratory tract variations notably influence deposition patterns rather than global parameters of the lower airways, observing more than 30% variance in the mass deposition fraction. Shaheen Dewji and colleagues introduce a hybrid-automated computational framework for modelling particles in the human respiratory tract (HRT) with variable geometries. Their method produces patient specific particle deposition profiles that highlights how geometrical characteristics can vary aerosol deposition within the HRT and radiation exposure between patients.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-18"},"PeriodicalIF":0.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00296-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Untethered bistable origami crawler for confined applications 用于密闭应用的无系双稳态折纸爬行器。

Communications engineering Pub Date : 2024-10-30 DOI: 10.1038/s44172-024-00294-1

Catherine Jiayi Cai, Hui Huang, Hongliang Ren

{"title":"Untethered bistable origami crawler for confined applications","authors":"Catherine Jiayi Cai, Hui Huang, Hongliang Ren","doi":"10.1038/s44172-024-00294-1","DOIUrl":"10.1038/s44172-024-00294-1","url":null,"abstract":"Magnetically actuated miniature origami crawlers are capable of robust locomotion in confined environments but are limited to passive functionalities. Here, we propose a bistable origami crawler that can shape-morph to access two separate regimes of folding degrees of freedom that are separated by an energy barrier. Using the modified bistable V-fold origami crease pattern as the fundamental unit of the crawler, we incorporated internal permanent magnets to enable untethered shape-morphing. By modulating the orientation of the external magnetic field, the crawler can reconfigure between an undeployed locomotion state and a deployed load-bearing state. In the undeployed state, the crawler can deform to enable out-of-plane crawling for robust bi-directional locomotion and navigation in confined environments based on friction anisotropy. In the deployed state, the crawler can execute microneedle insertion in confined environments. Through this work, we demonstrated the advantage of incorporating bistability into origami mechanisms to expand their capabilities in space-constraint applications. Catherine Jiayi Cai, Hui Huang and Hongliang Ren design a magnetically actuated bistable origami crawler that can transition between a locomotion and function mode, where each mode can be operated independently. The origami crawler is designed for use in confined spaces such as the gastrointestinal tract.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525557/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142549284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A rapid-convergent particle swarm optimization approach for multiscale design of high-permeance seawater reverse osmosis systems 用于高渗透率海水反渗透系统多尺度设计的快速收敛粒子群优化方法。

Communications engineering Pub Date : 2024-10-22 DOI: 10.1038/s44172-024-00289-y

Ke Chen, Jiu Luo, Junzhi Chen, Yutong Lu, Yi Heng

{"title":"A rapid-convergent particle swarm optimization approach for multiscale design of high-permeance seawater reverse osmosis systems","authors":"Ke Chen, Jiu Luo, Junzhi Chen, Yutong Lu, Yi Heng","doi":"10.1038/s44172-024-00289-y","DOIUrl":"10.1038/s44172-024-00289-y","url":null,"abstract":"Directly solving sophisticated partial differential equation constrained optimization problems is not only extremely time-consuming, but also very hard to find unique optimal solutions. Here, we propose stable and efficient surrogate models for seawater reverse osmosis desalination processes that enable thorough quantitative description of hydrodynamics and local transport characteristics in narrow flow channels. Without iteratively solving complex multi-physics simulation problem taking several hours, the proposed multi-scale design optimization framework significantly reduces the problem complexity by computing the surrogate models in seconds. Moreover, a fast-converging active subspace particle swarm optimization framework is proposed to address the optimal design problem. Compared to the standard particle swarm optimization algorithm, the proposed method enhances the average optimum by 14% and the standard deviation of optimum results for multiple runs is reduced by no less than ten times. The optimized desalination system achieves 9% reduction on energy consumption and 30% improvement on water production efficiency. Ke Chen and colleagues address the optimal design problem for the multiscale design of high-permeability seawater reverse osmosis desalination systems, aiming to develop a stable and efficient surrogate model. This technique enables a quantitative description of hydrodynamics processes and local transport characteristics in narrow flow channels.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11496709/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Insights and innovations to mitigate aviation climate impact by 2030 到 2030 年减轻航空气候影响的见解和创新。

Communications engineering Pub Date : 2024-10-21 DOI: 10.1038/s44172-024-00290-5

Kieran Tait, Marius Wedemeyer, Anwar Khan, Mark Lowenberg, Dudley Shallcross

引用次数: 0

A platform-agnostic deep reinforcement learning framework for effective Sim2Real transfer towards autonomous driving 平台无关的深度强化学习框架，实现自动驾驶的有效 Sim2Real 转移

Communications engineering Pub Date : 2024-10-17 DOI: 10.1038/s44172-024-00292-3

Dianzhao Li, Ostap Okhrin

{"title":"A platform-agnostic deep reinforcement learning framework for effective Sim2Real transfer towards autonomous driving","authors":"Dianzhao Li, Ostap Okhrin","doi":"10.1038/s44172-024-00292-3","DOIUrl":"10.1038/s44172-024-00292-3","url":null,"abstract":"Autonomous driving presents unique challenges, particularly in transferring agents trained in simulation to real-world environments due to the discrepancies between the two. To address this issue, here we propose a robust Deep Reinforcement Learning (DRL) framework that incorporates platform-dependent perception modules to extract task-relevant information, enabling the training of a lane-following and overtaking agent in simulation. This framework facilitates the efficient transfer of the DRL agent to new simulated environments and the real world with minimal adjustments. We assess the performance of the agent across various driving scenarios in both simulation and the real world, comparing it to human drivers and a proportional-integral-derivative (PID) baseline in simulation. Additionally, we contrast it with other DRL baselines to clarify the rationale behind choosing this framework. Our proposed approach helps bridge the gaps between different platforms and the Simulation to Reality (Sim2Real) gap, allowing the trained agent to perform consistently in both simulation and real-world scenarios, effectively driving the vehicle. Dianzhao Li and Ostap Okhrin proposed a deep reinforcement learning framework for transition between various simulated and real-world driving environments. Their method allows for the more effective control of autonomous vehicles in lane following and overtaking tasks.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-14"},"PeriodicalIF":0.0,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00292-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142447897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cryogenic quantum computer control signal generation using high-electron-mobility transistors 利用高电子迁移率晶体管生成低温量子计算机控制信号

Communications engineering Pub Date : 2024-10-15 DOI: 10.1038/s44172-024-00293-2

Alberto Ferraris, Eunjung Cha, Peter Mueller, Kirsten Moselund, Cezar B. Zota

{"title":"Cryogenic quantum computer control signal generation using high-electron-mobility transistors","authors":"Alberto Ferraris, Eunjung Cha, Peter Mueller, Kirsten Moselund, Cezar B. Zota","doi":"10.1038/s44172-024-00293-2","DOIUrl":"10.1038/s44172-024-00293-2","url":null,"abstract":"Multiplexed local charge storage, close to quantum processors at cryogenic temperatures could generate a multitude of control signals, for electronics or qubits, in an efficient manner. Such cryogenic electronics require generating quasi-static control signals with small area footprint, low noise, high stability, low power dissipation and, ideally, in a multiplexed fashion to reduce the number of input/outputs. In this work, we integrate capacitors with cryogenic high-electron mobility transistor (HEMT) arrays and demonstrate quasi-static bias generation using gate pulses controlled in time and frequency domains. Multi-channel bias generation is also demonstrated. Operation at 4 K exhibits improved bias signal variability and greatly reduced subthreshold swing, reaching values of ~6 mV/decade. Due to the very low threshold voltage of 80 mV at 4 K and the steep subthreshold swing, these circuits can provide an advantage over the silicon-based complementary metal-oxide-semiconductor equivalents by allowing operation at significantly reduced drive bias in the low output voltage regime <1 V. Together with their high-speed operation, this makes HEMTs an attractive platform for future cryogenic signal generation electronics in quantum computers. Alberto Ferraris and colleagues demonstrate a cryogenic circuit with a InGaAs-based quantum well transistors integrated with capacitors for the application of quantum computers. This system improves over Si CMOS by superior properties at cryogenic temperature and with a lower voltage supply, which is helpful to reduce the power consumption in the qubit control applications.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00293-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142435930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A semi-transparent thermoelectric glazing nanogenerator with aluminium doped zinc oxide and copper iodide thin films 使用掺铝氧化锌和碘化铜薄膜的半透明热电玻璃纳米发电机

Communications engineering Pub Date : 2024-10-15 DOI: 10.1038/s44172-024-00291-4

Mustafa Majid Rashak Al-Fartoos, Anurag Roy, Tapas K. Mallick, Asif Ali Tahir

{"title":"A semi-transparent thermoelectric glazing nanogenerator with aluminium doped zinc oxide and copper iodide thin films","authors":"Mustafa Majid Rashak Al-Fartoos, Anurag Roy, Tapas K. Mallick, Asif Ali Tahir","doi":"10.1038/s44172-024-00291-4","DOIUrl":"10.1038/s44172-024-00291-4","url":null,"abstract":"To address the pressing need for reducing building energy consumption and combating climate change, thermoelectric glazing (TEGZ) presents a promising solution. This technology harnesses waste heat from buildings and converts it into electricity, while maintaining comfortable indoor temperatures. Here, we developed a TEGZ using cost-effective materials, specifically aluminium-doped zinc oxide (AZO) and copper iodide (CuI). Both AZO and CuI exhibit a high figure of merit (ZT), a key indicator of thermoelectric efficiency, with values of 1.37 and 0.72, respectively, at 340 K, demonstrating their strong potential for efficient heat-to-electricity conversion. Additionally, we fabricated an AZO-CuI based TEGZ prototype (5 × 5 cm²), incorporating eight nanogenerators, each producing 32 nW at 340 K. Early testing of the prototype showed a notable temperature differential of 22.5 °C between the outer and inner surfaces of the window glazing. These results suggest TEGZ could advance building energy efficiency, offering a futuristic approach to sustainable build environment. A thermoelectric glazing prototype made from cost-effective aluminium-doped zinc oxide and copper iodide nanogenerators achieves a 22.5 °C temperature difference on either side of the glaze, harvesting electricity from the differential. Such glazes are critical for increasing energy efficiency in the built environment.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-13"},"PeriodicalIF":0.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00291-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142435962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards a general computed tomography image segmentation model for anatomical structures and lesions 为解剖结构和病变建立通用计算机断层扫描图像分割模型

Communications engineering Pub Date : 2024-10-14 DOI: 10.1038/s44172-024-00287-0

Xi Ouyang, Dongdong Gu, Xuejian Li, Wenqi Zhou, Qianqian Chen, Yiqiang Zhan, Xiang Sean Zhou, Feng Shi, Zhong Xue, Dinggang Shen

{"title":"Towards a general computed tomography image segmentation model for anatomical structures and lesions","authors":"Xi Ouyang, Dongdong Gu, Xuejian Li, Wenqi Zhou, Qianqian Chen, Yiqiang Zhan, Xiang Sean Zhou, Feng Shi, Zhong Xue, Dinggang Shen","doi":"10.1038/s44172-024-00287-0","DOIUrl":"10.1038/s44172-024-00287-0","url":null,"abstract":"Numerous deep-learning models have been developed using task-specific data, but they ignore the inherent connections among different tasks. By jointly learning a wide range of segmentation tasks, we prove that a general medical image segmentation model can improve segmentation performance for computerized tomography (CT) volumes. The proposed general CT image segmentation (gCIS) model utilizes a common transformer-based encoder for all tasks and incorporates automatic pathway modules for task prompt-based decoding. It is trained on one of the largest datasets, comprising 36,419 CT scans and 83 tasks. gCIS can automatically perform various segmentation tasks using automatic pathway modules of decoding networks through text prompt inputs, achieving an average Dice coefficient of 82.84%. Furthermore, the proposed automatic pathway routing mechanism allows for parameter pruning of the network during deployment, and gCIS can also be quickly adapted to unseen tasks with minimal training samples while maintaining great performance. Xi Ouyang et al. developed a unified machine-learning model for multi-task segmentation in computed tomography images. After collating a large dataset composed of over 35K scans, the model presented superior results compared to the state-of-the-art in various tasks.","PeriodicalId":72644,"journal":{"name":"Communications engineering","volume":" ","pages":"1-11"},"PeriodicalIF":0.0,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44172-024-00287-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142431094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0