计算机科学 ›› 2021, Vol. 48 ›› Issue (6): 153-158.doi: 10.11896/jsjkx.200500005
钟岳, 方虎生, 张国玉, 王钊, 朱经纬
ZHONG Yue, FANG Hu-sheng, ZHANG Guo-yu, WANG Zhao, ZHU Jing-wei
摘要： 区别于传统光纤传感器、图像识别和Kinect深度图像的旗语动作识别方法,提出了一种基于9轴姿态传感器的旗语动作识别方法。该方法通过佩戴在手腕处的9轴姿态传感器来采集旗语动作的3轴加速度、3轴角速度以及3轴磁偏角数据;在运用卷积神经网络(Convolutional Neural Network,CNN)分类模型的基础上对其中的数据进行预处理,并通过分类识别算法对其进行改进;在数据预处理阶段,利用小波分解与重构函数对采集到的9轴数据进行高频去噪和低频信息提取,通过时间序列加窗进行分割处理,对各动作样本进行维度和长度统一;在特征提取阶段,采用构建的双卷积层、单池化层、单全连接层网络模型对重构数据进行特征提取;在分类识别阶段,提出一种CrossEntropy-Logistic联合损失函数来对5种动作进行迭代训练。实验结果表明,所提方法利用detcoef小波分解与重构函数对信号进行低频细节系数提取并采用一维CNN对降噪后的数据进行特征提取,通过CL联合损失函数对预测损失值和预测概率进行融合,分析所得到的训练准确率与测试准确率,在与各类方法的对比中取得了最高值,其平均训练识别率可达99%以上,测试准确率可达94%。
中图分类号:
| [1]ZHANG J L,WANG L L,RUI T,et al.Flag Language Recognition System Based on ANN [J].Journal of PLA University of Science and Technology(Natural Science),2003(4):65-68. [2]LI P F.The Research of Action Recognition based on Kinect and Application of Semaphore Training[D].Chengdu:Southwest Jiaotong University,2015. [3]REZAIE H,GHASSEMIAN M.An Adaptive algorithm to improve energy efficiency in Wearable activity recognition systems[J].IEEE Sensors Journal,2017,17(16):5315-5323. [4]MA C M,ZHU Q,WANG S,et al.Representation learning fromtime labelled heterogeneous data for mobile crowdsensing[J].Mobile Information Systems,2016,306:22-30. [5]KIM K,CHO Y K.Effective inertial sensor quantity and loca-tions on a body for deep learning-based worker’s motion recognition[J].Automation in Construction,2020,113:27-40. [6]NGUYEN N D,TRUONG P H,JEONG G M.Daily wrist acti-vity classification using a smart band[J].Physiological Measurement,2017,38(9):10-16. [7]SIDDHARTH,SHEKAR,CHEN C.Wavelet denoising of high-bandwidth nanopore and ion channel signals[J].Nano Letters,2019,2:1090-1097. [8]ZHE S,WEI N J.Based on Wavelet Decomposition and Reconstruction Method in Extraction of In-seam Reflection Signal[J].Coal Technology,2019,38(12):55-57. [9]LI J J,YU J P,TAO J.Review of One-Dimensional SignalWavelet De-Noising[J].Journal of Chongqing University of Technology(Natural Science),2016(12):93-89. [10]YANG J B,NGUYEN M N,SAN P P,et al.Deep Convolutional neural networks on multichannel time series for human activity recognition[C]//International Conference on Artificial Intelligence.2015:3995-4001. [11]ZHANG Z,SABUNCU M R.Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels[C]//32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada.2018,11:155-168. [12]LI Z,KAMNITSAS K,GLOCKER B.Overfitting of neural nets under class imbalance:Analysis and improvements for segmentation[J].arXiv:1907.10982,2019. [13]ZHANG X Y,YOU M Y,ZHU J,et al.Face Recognition of Small-Scale Dataset Based on Joint Loss Functions[J].Transactions of Beijing Institute of Technology,2020,40(2):163-168. [14]BOSMAN A S,ENGELBRECHT A,HELBIG M.Visualisingbasins of attraction for the cross-entropy and the squared error neural network loss functions[J].Neurocomputing,2020,400:113-136. [15]NGUYEN-VUONG Q T,GHAMRI-DOUDANE Y,AGOUL-MINE N.On utility models for access network selection in wireless heterogeneous networks[C]//Processings of Network Ope-rations and Management Symposium 2008.Salvador:IEEE,2001:144-151. [16]ZOU X H.Data classification based on Logistic regression[J].Intelligent Computer and Applications,2016,6(6):139-140,143. [17]MEIGNAN D,KNUST S.A neutrality-based iterated localsearch for shift scheduling optimization and interactive reoptimization[J].European Journal of Operational Research,2019,279(2):320-334. [18]LIU H J,ZHANG X,LI M.Determination of the Number of Wavelet Denoising Decomposition Layers in Vehicle Driving dEvaluationf[J].Noise and Vibration Control,2019,39(4):7-11. [19]QIANG L,ZHE W.Image Compression Based on Wavelet Ana-lysis[J].Communications Technology,2010,43(8):236-238,241. |
| [1] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
| [2] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
| [3] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
| [4] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
| [5] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
| [6] | 张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036 |
| [7] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
| [8] | 刘月红, 牛少华, 神显豪. 基于卷积神经网络的虚拟现实视频帧内预测编码 Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network 计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179 |
| [9] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
| [10] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
| [11] | 杨玥, 冯涛, 梁虹, 杨扬. 融合交叉注意力机制的图像任意风格迁移 Image Arbitrary Style Transfer via Criss-cross Attention 计算机科学, 2022, 49(6A): 345-352. https://doi.org/10.11896/jsjkx.210700236 |
| [12] | 杨健楠, 张帆. 一种结合双注意力机制和层次网络结构的细碎农作物分类方法 Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure 计算机科学, 2022, 49(6A): 353-357. https://doi.org/10.11896/jsjkx.210200169 |
| [13] | 王杉, 徐楚怡, 师春香, 张瑛. 基于CNN-LSTM的卫星云图云分类方法研究 Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM 计算机科学, 2022, 49(6A): 675-679. https://doi.org/10.11896/jsjkx.210300177 |
| [14] | 孙福权, 崔志清, 邹彭, 张琨. 基于多尺度特征的脑肿瘤分割算法 Brain Tumor Segmentation Algorithm Based on Multi-scale Features 计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217 |
| [15] | 吴子斌, 闫巧. 基于动量的映射式梯度下降算法 Projected Gradient Descent Algorithm with Momentum 计算机科学, 2022, 49(6A): 178-183. https://doi.org/10.11896/jsjkx.210500039 |
|
||
首页