首页|时序数据图像化:战术意图识别及可移植框架

时序数据图像化:战术意图识别及可移植框架

扫码查看
通过将时序编码为图像,提出了一种结合曲线滤波技术和EfficientNetV2图像识别网络的鲁棒且可移植的战术意图识别框架.曲线滤波技术可以有效地减少大量时域特征、模型参数和训练时间的冗余,基于此,提出了一种改进的格拉姆角场方法将时序编码为图像,提高了卷积神经网络的特征提取能力.EfficientNetV2网络能够有效地处理意图图像,并成为预训练模型,使得在不同系统之间进行迁移学习成为可能.实验结果表明,所提框架相对于机器学习及深度学习等方法提高了0.99%以上的准确率,具有更好的性能、可扩展性、鲁棒性和可迁移性.
Timing data visualization:tactical intent recognition and portable framework
By transforming time series into images,a robust and transferable tactical intent recognition framework was proposed,which integrated curve filtering technology and the EfficientNetV2 image recognition network.Curve filtering technology effectively reduced redundancy in numerous time-domain features,model parameters,and training time,an enhanced Gramian angular field(GAF)method was proposed to encode time series into images,enhancing the feature extraction capabilities of convolutional neural networks.The EfficientNetV2 network was adept at processing intent im-ages and could serve as a pre-trained model,facilitating transfer learning across different systems.Experimental results demonstrate that the proposed framework achieves over 0.99%higher accuracy compared to machine learning and deep learning methods,exhibiting superior performance,scalability,robustness,and transferability.

time series codingintention recognitionimage classificationcurve filteringGramian angular fieldEffi-cientNetV2

宋亚飞、李乐民、权文、倪鹏、王科

展开 >

空军工程大学防空反导学院,陕西 西安 710051

复杂航空系统仿真重点实验室,北京 100076

时序编码 意图识别 图像分类 曲线滤波 格拉姆角场 EfficientNetV2

国家自然科学基金国家自然科学基金国家自然科学基金陕西省自然科学基金陕西省高等学校科协青年人才托举计划陕西省高等学校科协青年人才托举计划陕西省创新能力支撑计划

6180621961703426618761892021JM-22620190108202201062020KJXX-065

2024

通信学报
中国通信学会

通信学报

CSTPCD北大核心
影响因子:1.265
ISSN:1000-436X
年,卷(期):2024.45(8)