Artificial intelligence(AI)models are promising to improve the accuracy of wireless positioning systems,particularly in indoor environments where unpredictable radio propagation channel is a great challenge.Although g...Artificial intelligence(AI)models are promising to improve the accuracy of wireless positioning systems,particularly in indoor environments where unpredictable radio propagation channel is a great challenge.Although great efforts have been made to explore the effectiveness of different AI models,it is still an open problem whether these models,trained with the data collected from all base stations(BSs),could work when some BSs are unavailable.In this paper,we make the first effort to enhance the generalization ability of AI wireless positioning model to adapt to the scenario where only partial BSs work.Particularly,a Siamese Network based Wireless Positioning Model(SNWPM)is proposed to predict the location of mobile user equipment from channel state information(CSI)collected from 5G BSs.Furthermore,a Feature Aware Attention Module(FAAM)is introduced to reinforce the capability of feature extraction from CSI data.Experiments are conducted on the 2022 Wireless Communication AI Competition(WAIC)dataset.The proposed SNWPM achieves decimeter-level positioning accuracy even if the data of partial BSs are unavailable.Compared with other AI models,the proposed SNWPM can reduce the positioning error by nearly 50%to more than 60%while using less parameters and lower computation resources.展开更多
2019年Metalearners for Estimating Heterogeneous Treatment Effects using Machine Learning的发表引发了世界因果推断理论的研究热情。目前,机器学习与因果推断论中的许多统计模型已被广泛应用。本文采用文献资料法、数理统计分析...2019年Metalearners for Estimating Heterogeneous Treatment Effects using Machine Learning的发表引发了世界因果推断理论的研究热情。目前,机器学习与因果推断论中的许多统计模型已被广泛应用。本文采用文献资料法、数理统计分析方法、案例研究法等研究方法,研究推演现代因果推断理论中较为知名的Uplift因果模型在体育中的应用场景,其中Uplift因果模型包括S-learner(单模型)、T-learner(双模型)、X-learner(交叉训练模型)。结果显示,在体育消费随机对照实验中应用Uplift因果模型,可以基于基本模型进一步推导出各变量因素之间的因果关系,验证并分析自变量对因变量变化的影响;率先在体育消费市场研究与实验中应用Uplift因果模型可以填补我国体育消费实验数据分析方法的空缺。展开更多
矿山场景数据是智慧矿山建设和智能管理的基础数据,如何利用包括遥感影像在内的多源数据快速识别和提取出复杂的矿山场景是重要的研究方向。采用2020年Sentinel-2影像、GF-6影像、GF-2影像进行最优数据集筛选,使用2023年谷歌影像(Google...矿山场景数据是智慧矿山建设和智能管理的基础数据,如何利用包括遥感影像在内的多源数据快速识别和提取出复杂的矿山场景是重要的研究方向。采用2020年Sentinel-2影像、GF-6影像、GF-2影像进行最优数据集筛选,使用2023年谷歌影像(Google image)数据扩充数据集,并与深度学习算法相结合,建立了2种露天煤矿场地识别模型。研究主要结论:(1)利用10 m Sentinel-2影像、8 m GF-6原始影像、2 m GF-6融合影像、3.2 m GF-2原始影像、0.8 m GF-2融合影像建立矿山识别模型,量化选择不同数据产生的模型精度。结果显示,遥感图像空间分辨率从10 m增加到0.8 m,通过相同的方法建立的矿山场景识别模型的精度逐渐提高。其中使用0.8 m空间分辨率的GF-2融合影像建立的矿山场景识别模型的精度最高,平均精准度P_(A)和(MIOU,Mean Intersection over Union)分别达到了0.702和0.824。(2)从多源遥感图像中采集了3162个多场景、多时段、多尺度矿山场景样本对所有样本进行统一融合处理,建立了矿山场地场景识别模型(MSSRM,Mine Site Scene Recognition Model)和矿山场地边界识别模型(MSBRM,Mine Site Boundary Recognition Model)。MSSRM的P_(A)达到了0.758,MSBRM平均交并比达到0.864。(3)对比了Faster R-CNN(FasterRegion-basedConvolutionalNeuralNetwork)、YOLO-v5(YouOnlyLookOnce-v5)、DETR(Detection Transformer)3种目标识别方法与Mask R-CNN、U-Net、DeepLabV3+三种图像分割方法建立的煤矿场地识别模型精度,其中,DETR方法建立的识别模型与Faster R-CNN和YOLO-v5相比P_(A)分别提高了7.6%和8.3%。DeepLabV3+建立的分割模型与Mask R-CNN和U-Net相比MIOU分别提高了14%和10.8%。(4)建立了从大范围的遥感影像中自动化、智能化、批量化识别矿山场地场景并绘制矿山场地边界的方法,以干旱、半干旱典型矿区(鄂尔多斯)露天煤矿场地识别应用为例,验证了智能识别矿山场景边界方法的性能,模型制图精度达到了0.817。展开更多
针对边缘计算环境下人工智能(Artificial Intelligence,AI)模型训练效率低下的问题,提出了基于边缘云计算的混合并行训练框架(Edge-Cloud based Hybrid Parallel Training Framework,ECHPT).ECHPT能在终端设备、边缘服务器和云计算中心...针对边缘计算环境下人工智能(Artificial Intelligence,AI)模型训练效率低下的问题,提出了基于边缘云计算的混合并行训练框架(Edge-Cloud based Hybrid Parallel Training Framework,ECHPT).ECHPT能在终端设备、边缘服务器和云计算中心之间实现AI模型和数据样本的自适应调度.ECHPT将模型计算和数据任务调度问题建模为训练时间最小化的优化问题,设计了调度算法对优化问题进行求解.实现了由设备、边缘服务器和云服务器组成的硬件原型.实验结果表明,与现有框架相比,ECHPT可以有效缩短AI模型的训练时间.展开更多
In the new round of IT revolution, the AI industry has become a new engine driving economic growth. In such a context, major developed countries actively prepare and plan for this industry, and China also attaches gre...In the new round of IT revolution, the AI industry has become a new engine driving economic growth. In such a context, major developed countries actively prepare and plan for this industry, and China also attaches great importance to next-generation AI development. At present, the China's nextgeneration AI industry has distinctive shortcomings in the development of core chips, basic algorithms and corresponding talents. China should make full use of its enormous advantages and favorable conditions in technology and sensibly choose from a development model of business innovation, fast iteration, application layer driving base layer, and self-developed technology standards. By drawing on the experience of developed countries, China can accelerate its building and improvement of government supported mechanisms, upgrade its system of venture capital and services, enhance the advancement of basic research in chips and algorithms, and invest more in the cultivation and introduction of next-generation AI talents in a bid to quickly strengthen the core competitiveness of the China's next-generation AI industry.展开更多
基金supported by National Natural Science Foundation of China (No. 62076251)sponsored by IMT-2020(5G) Promotion Group 5G+AI Work Group+3 种基金jointly sponsored by China Academy of Information and Communications TechnologyGuangdong OPPO Mobile Telecommunications Corp., Ltdvivo Mobile Communication Co., LtdHuawei Technologies Co., Ltd
文摘Artificial intelligence(AI)models are promising to improve the accuracy of wireless positioning systems,particularly in indoor environments where unpredictable radio propagation channel is a great challenge.Although great efforts have been made to explore the effectiveness of different AI models,it is still an open problem whether these models,trained with the data collected from all base stations(BSs),could work when some BSs are unavailable.In this paper,we make the first effort to enhance the generalization ability of AI wireless positioning model to adapt to the scenario where only partial BSs work.Particularly,a Siamese Network based Wireless Positioning Model(SNWPM)is proposed to predict the location of mobile user equipment from channel state information(CSI)collected from 5G BSs.Furthermore,a Feature Aware Attention Module(FAAM)is introduced to reinforce the capability of feature extraction from CSI data.Experiments are conducted on the 2022 Wireless Communication AI Competition(WAIC)dataset.The proposed SNWPM achieves decimeter-level positioning accuracy even if the data of partial BSs are unavailable.Compared with other AI models,the proposed SNWPM can reduce the positioning error by nearly 50%to more than 60%while using less parameters and lower computation resources.
文摘2019年Metalearners for Estimating Heterogeneous Treatment Effects using Machine Learning的发表引发了世界因果推断理论的研究热情。目前,机器学习与因果推断论中的许多统计模型已被广泛应用。本文采用文献资料法、数理统计分析方法、案例研究法等研究方法,研究推演现代因果推断理论中较为知名的Uplift因果模型在体育中的应用场景,其中Uplift因果模型包括S-learner(单模型)、T-learner(双模型)、X-learner(交叉训练模型)。结果显示,在体育消费随机对照实验中应用Uplift因果模型,可以基于基本模型进一步推导出各变量因素之间的因果关系,验证并分析自变量对因变量变化的影响;率先在体育消费市场研究与实验中应用Uplift因果模型可以填补我国体育消费实验数据分析方法的空缺。
文摘矿山场景数据是智慧矿山建设和智能管理的基础数据,如何利用包括遥感影像在内的多源数据快速识别和提取出复杂的矿山场景是重要的研究方向。采用2020年Sentinel-2影像、GF-6影像、GF-2影像进行最优数据集筛选,使用2023年谷歌影像(Google image)数据扩充数据集,并与深度学习算法相结合,建立了2种露天煤矿场地识别模型。研究主要结论:(1)利用10 m Sentinel-2影像、8 m GF-6原始影像、2 m GF-6融合影像、3.2 m GF-2原始影像、0.8 m GF-2融合影像建立矿山识别模型,量化选择不同数据产生的模型精度。结果显示,遥感图像空间分辨率从10 m增加到0.8 m,通过相同的方法建立的矿山场景识别模型的精度逐渐提高。其中使用0.8 m空间分辨率的GF-2融合影像建立的矿山场景识别模型的精度最高,平均精准度P_(A)和(MIOU,Mean Intersection over Union)分别达到了0.702和0.824。(2)从多源遥感图像中采集了3162个多场景、多时段、多尺度矿山场景样本对所有样本进行统一融合处理,建立了矿山场地场景识别模型(MSSRM,Mine Site Scene Recognition Model)和矿山场地边界识别模型(MSBRM,Mine Site Boundary Recognition Model)。MSSRM的P_(A)达到了0.758,MSBRM平均交并比达到0.864。(3)对比了Faster R-CNN(FasterRegion-basedConvolutionalNeuralNetwork)、YOLO-v5(YouOnlyLookOnce-v5)、DETR(Detection Transformer)3种目标识别方法与Mask R-CNN、U-Net、DeepLabV3+三种图像分割方法建立的煤矿场地识别模型精度,其中,DETR方法建立的识别模型与Faster R-CNN和YOLO-v5相比P_(A)分别提高了7.6%和8.3%。DeepLabV3+建立的分割模型与Mask R-CNN和U-Net相比MIOU分别提高了14%和10.8%。(4)建立了从大范围的遥感影像中自动化、智能化、批量化识别矿山场地场景并绘制矿山场地边界的方法,以干旱、半干旱典型矿区(鄂尔多斯)露天煤矿场地识别应用为例,验证了智能识别矿山场景边界方法的性能,模型制图精度达到了0.817。
文摘针对边缘计算环境下人工智能(Artificial Intelligence,AI)模型训练效率低下的问题,提出了基于边缘云计算的混合并行训练框架(Edge-Cloud based Hybrid Parallel Training Framework,ECHPT).ECHPT能在终端设备、边缘服务器和云计算中心之间实现AI模型和数据样本的自适应调度.ECHPT将模型计算和数据任务调度问题建模为训练时间最小化的优化问题,设计了调度算法对优化问题进行求解.实现了由设备、边缘服务器和云服务器组成的硬件原型.实验结果表明,与现有框架相比,ECHPT可以有效缩短AI模型的训练时间.
基金a staged research result of "Studies on the Development Direction and Impact of a New Industrial Revolution and China’s Corresponding Strategy"(Ref.13&ZD157)a major program funded by National Social Sciences Fund
文摘In the new round of IT revolution, the AI industry has become a new engine driving economic growth. In such a context, major developed countries actively prepare and plan for this industry, and China also attaches great importance to next-generation AI development. At present, the China's nextgeneration AI industry has distinctive shortcomings in the development of core chips, basic algorithms and corresponding talents. China should make full use of its enormous advantages and favorable conditions in technology and sensibly choose from a development model of business innovation, fast iteration, application layer driving base layer, and self-developed technology standards. By drawing on the experience of developed countries, China can accelerate its building and improvement of government supported mechanisms, upgrade its system of venture capital and services, enhance the advancement of basic research in chips and algorithms, and invest more in the cultivation and introduction of next-generation AI talents in a bid to quickly strengthen the core competitiveness of the China's next-generation AI industry.