期刊文献+
共找到4篇文章
< 1 >
每页显示 20 50 100
基于LSTM神经网络的海量边缘计算数据处理方法
1
作者 姚文广 陈思宁 《数字通信世界》 2024年第7期70-72,共3页
传统海量边缘计算数据处理方法直接对海量边缘计算数据实施压缩,未对海量边缘计算数据进行动态合并处理,处理效果差。因此,该文提出基于LSTM神经网络的海量边缘计算数据处理方法,该方法对海量边缘计算数据进行动态合并处理,为决策和应... 传统海量边缘计算数据处理方法直接对海量边缘计算数据实施压缩,未对海量边缘计算数据进行动态合并处理,处理效果差。因此,该文提出基于LSTM神经网络的海量边缘计算数据处理方法,该方法对海量边缘计算数据进行动态合并处理,为决策和应用提供更全面和准确的信息支持;对合并的数据进行压缩,提高处理效率;最后基于LSTM神经网络,实现海量边缘计算数据的处理,实验结果表明该研究方法处理效果更好。 展开更多
关键词 LSTM神经网络 海量边缘计算数据 海量数据 处理方法
下载PDF
煤矿工业数据AI模型自动推理技术
2
作者 张智星 付翔 +6 位作者 张小强 李浩杰 秦一凡 刘萌 孙岩 贾一帆 杨宇琪 《工矿自动化》 CSCD 北大核心 2024年第9期138-143,共6页
煤矿生产过程的智能化主要依托于人工智能(AI)技术分析煤矿工业数据,但单一应用场景AI模型无法适用于煤矿复杂的应用场景,且仅使用分布式计算来处理AI模型输入特征值会导致模型应用效率降低。针对上述问题,提出了一种煤矿工业数据AI模... 煤矿生产过程的智能化主要依托于人工智能(AI)技术分析煤矿工业数据,但单一应用场景AI模型无法适用于煤矿复杂的应用场景,且仅使用分布式计算来处理AI模型输入特征值会导致模型应用效率降低。针对上述问题,提出了一种煤矿工业数据AI模型自动推理技术。该技术架构包括数据层、计算驱动层和模型推理层:数据层采集各类监测数据并统一存储,为计算驱动层提供原始数据;计算驱动层将数据层采集的海量原始数据转换成煤矿应用场景AI模型输入特征值,通过煤矿应用场景AI模型输入特征值双计算引擎自动切换机制,根据数据量自动合理地选择使用基于Spark的分布式计算方式或基于Python的单机计算方式,解决了海量数据计算速度慢、数据应用延迟大的问题;模型推理层将特征值输入应用场景AI模型进行推理,引入煤矿应用场景AI模型多触发方式协同推理机制,通过定时触发、人为交互触发、信号反馈触发3种触发方式,解决了在煤矿复杂的应用条件下单一应用场景AI模型利用效果差的问题。测试和应用结果表明,该技术可实现多应用场景AI模型输入特征值的快速计算,以及不同应用场景AI模型的快速、自动、协同推理。 展开更多
关键词 煤矿人工智能 煤矿工业数据 AI模型推理 海量数据计算 AI模型应用
下载PDF
Relationship between oceanic heat content and sea surface height on interannual time scale 被引量:1
3
作者 张林林 孙澈 胡敦欣 《Chinese Journal of Oceanology and Limnology》 SCIE CAS CSCD 2012年第6期1026-1032,共7页
The relationship between heat content and the interannual time scale is examined with satellite sea surface height (SSH) in the global ocean on altimeter measurements, historical hydrography, and model assimilation ... The relationship between heat content and the interannual time scale is examined with satellite sea surface height (SSH) in the global ocean on altimeter measurements, historical hydrography, and model assimilation outputs. Results show that correlation between altimetric SSH and heat content in the upper 700 m calculated from Ishii data is geographically nonuniform. In the tropical ocean, heat content and SSH are strongly correlated and exhibit nearly the same interannual variations. In the polar ocean, their correlation is relatively weak. Further analysis with Simple Ocean Data Assimilation outputs shows that such nonuniform distribution is not from dynamical origin but from the limited integral depth selected to calculate heat content. The integral depth of 700 m is inadequate to capture variation of the deep main thermocline in the polar region. The halosteric effect also contributes to the nonuniform pattern of correlation, because saline contraction becomes significant in the polar ocean owing to low temperature. 展开更多
关键词 heat content sea surface height (SSH) interannual variation CORRELATION
下载PDF
Views on Piracy: Threats to International Peace
4
作者 Alimen A. Rolando Jeson C. Fernandez Cesar I. Mongan 《Journal of Shipping and Ocean Engineering》 2016年第2期110-116,共7页
The study was conducted to ascertain the views on piracy among marine engineering students and marine officers who had encountered piracy on international waters thereby suggesting threats to international peace. The ... The study was conducted to ascertain the views on piracy among marine engineering students and marine officers who had encountered piracy on international waters thereby suggesting threats to international peace. The respondents of the study were 50, specifically distributed to thirty (30) onboard marine engineering students enrolled for the current school year 2014-2015 and twenty (20) marine officers who had experienced piracy at Somalia and other places. The researchers employed quantitative-qualitative research method design. The questionnaire on "Piracy at Sea" was validated by experts in research, statistics, qualitative research, and maritime international conventions. To test the reliability, this same instrument was pilot-tested among marine officers and students who had been on board international ships. Qualitative data were captured through interviews by using open-ended questions. Frequency count, percentage, and rank were used in this study for descriptive-quantitative statistics. The data were analyzed using appropriate statistics through computer-processed software (SPSS). Qualitative analysis was employed to determine the views of the respondents on piracy so that mitigation measures were elicited for protection of life at sea leading towards international peace among identified HRAs (high-risk areas). Results revealed that seafarers were familiar of piracy. They were aware that piracy usually happens in areas like Somalia water sand other threatening territories. To combat piracy, the participants have pointed out the role of the international community in their concerted effort to help seafarers safeguard their lives specifically during these hard times. Somalia also needs to effectively check their organization by whether or not strict implementation of the Anti Piracy Law was being observed. Full knowledge of piracy, techniques for avoiding it, and surviving pirate attacks are necessary among seafarers. Satellite system called shiplock allows shipping companies to monitor location of ships particularly useful during pirate attacks, hijacks, or ship theft. They also install non-lethal electrical fences around a ship's perimeter to protect them during these times. IMO regulations require ships to send distress signals and warnings covertly in case of pirate attacks. 展开更多
关键词 PIRACY threats international peace maritime university marine engineering students marine officers high-risk areas(HRAs) satellite system international community.
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部