简琤峰_教师主页

教师主页移动版

主页 > 浙江省 > 浙江工业大学

简琤峰

个人简介 简琤峰,博士,浙江工业大学计算机科学与技术学院,教授,博士生/硕士生导师,现为中国计算机学会、中国图学会产品信息建模专家委员会委员。相关研究成果已在国内外学术期刊发表学术论文60余篇。研究领域涉及智能制造、人工智能、云计算、机器视觉等。目前主要研究方向为2D/3D数字人建模仿真;3D模型建模检索与语义可视化、大批量混合任务实时调度优化、基于视觉的动态手势语义识别及预测等。已有应用有2D/3D虚拟数字人、数字孪生-3D可视化工厂仿真、永康五金中小企业数字化云平台、手语识别等。学术成果同行验证 Please visit:  Web of Science:https://www.webofscience.com/wos/author/rid/AAF-1918-2019        (Publons: https://publons.com/researcher/3234320/cf-jian/ )ORCID:            https://orcid.org/0000-0002-5231-690X/==================================================================================科研成果1. 虚拟数字人主要涉及:虚拟数字人建模;唇形驱动优化算法;肢体动作捕捉与预测算法;大模型轻量化算法等。Your user agent does not support the HTML5 Video element.Your user agent does not support the HTML5 Video element.       2D数字人视频                                 音频驱动实时唇形生成        应用演示Demo科研成果2. 数字孪生建模与仿真应用演示Demo科研成果4 工业软件云平台科研成果5. 三维模型语义交互与检索长期专注于面向CAD/CAM基础研究-STEP产品信息交换,旨在提供拥有自主知识产权的产品三维模型语义交换方法技术和平台。提出了产品信息语义云粒元重组理论方法,将传统产品信息共享的数据交换语法层次提升到模型特征语义交换层次;结合深度神经网络,提出了面向STEP AP242的设计与制造特征的自动识别技术(国家发明专利201811237688.X:一种基于改进NBA算法的BPNN特征识别方法);自主开发基于WEBGL的STEP三维产品模型语义可视化平台及STEP AP203/AP242语义转换器。   科研成果6. 移动终端动态微手势识别  针对移动终端复杂背景及弱计算力,提出了指尖快速检测算法。实现实时多轨迹动态跟踪及识别。特色:无需深度传感器、无需GPU。核心算法具有完全自主知识产权。(国家发明专利201711077703.4:一种基于改进聚合通道特征的手部检测方法)市场需求是科研的动力所在,我们更看重培养学生理论联系实际应用的能力,欢迎感兴趣的同学加入本团队!联系邮箱:jiancf@zjut.edu.cn 教学与课程 本科生课程:Web前端设计与开发;多媒体技术基础;数字媒体资源管理;计算机图形学;研究生课程:计算理论基础;已发表教学论文(第一作者):1. 支持手势识别的云黑板教学平台研究与实现,现代教育技术,2016,26(12):106-111. (教育类核心期刊)2. 基于行为引导的应用文教学方法及评估体系构建, 远程教育杂志,2008,3:49-52. (教育类核心期刊) 科研项目 * 202403 - 至今 浙江某企业数字孪生;* 202306 - 至今 2D/3D数字警察辅助办案系统;* 202209 - 至今 浙江永康五金中小企业数字化云平台;* 国家自然基金面上项目:面向设计意图在线交换的语义云粒元重组方法研究(No.61672461),主持。* 国家自然基金青年项目:语义网格环境下虚拟组织异构产品信息语义在线重组技术及其应用(No.60603087),主持。* 浙江省科技厅项目:支持移动WEB手势识别的草图协同创意设计平台(No.2014C31081),主持。 科研成果 近五年(2018-2022)科研成果:论文及专利SCI期刊论文:22. A DRL-based Online Real-time Task Scheduling Method with ISSA Strategy,Cluster Computing, online.21. Federated Deep Reinforcement Learning-based Online Task Offloading and Resource Allocation in Harsh Mobile Edge Computing Environment,Cluster Computing, online.20. A meta reinforcement learning-based virtual machine placement algorithm in mobile edge computing,Cluster Computing, online.19. Real-time continuous handwritten trajectories recognition based on a regression-based temporal pyramid network,Journal of Real-Time Image Processing,2024,21(10).18. A hybrid manufacturing scheduling optimization strategy in collaborative edge computing,Evolutionary Intelligence,2024,17(4):1065-1077.17. GNN-based Deep Reinforcement Learning for MBD Product Model Recommendation,International Journal of Computer Integrated Manufacturing,2024,37(1):183-197.16. Online-learning task scheduling with GNN-RL scheduler in collaborative edge computing,Cluster Computing,2024,27(1):589-605.15. QSCC: A Quaternion Semantic Cell Convolution Graph Neural Network for MBD Product Model Classification,IEEE Transactions on Industrial Informatics,2023,19(12):11477-11486.(中科院Top期刊)14. KOA-CLSTM-based real-time dynamic hand gesture recognition on mobile terminal,Signal, Image and Video Processing,2023,17(5):1841-1854.13. A novel graph neural networks approach for 3D product model retrieval,International Journal of Computer Integrated Manufacturing,2022,36(3):381-392.12. A high-efficiency learning model for virtual machine placement in mobile edge computing,Cluster Computing, 2022,25(5):3051-3066. 11. RD-Hand: a real-time regression-based detector for dynamic hand gesture,Applied Intelligence, 2022,52:417–428.(IF=5.086)10. A cloud edge-based two-level hybrid scheduling learning model in cloud manufacturing,International Journal of Production Research, 2021,59(16):4836-4850.(中科院Top期刊)9. An Improved Memory Networks Based Product Model Classification Method.International Journal of Computer Integrated Manufacturing,2021,34(3):293-306.(IF=3.076)8. Edge Cloud Computing Service Composition Based on Modified Bird Swarm Optimization in the Internet of Things,Cluster Computing, 2019,22(s4):8079-8087.(IF=1.809)7. Real-time multi-trajectory matching for dynamic hand gesture recognition,IET Image Processing, 2020,14(2):236-244.(IF=2.373) 6. LSTM-based dynamic probability continuous hand gesture trajectory recognition,IET Image Processing, 2019,13(12):2314-2320.(IF=2.373) 5. Mobile terminal trajectory recognition based on improved LSTM model,IET Image Processing, 2019,13(11):1914-1921.(IF=2.373) 4. Mobile Terminal Gesture Recognition Based on Improved FAST Corner Detection,IET Image Processing, 2019,13(6):991-997.(IF=2.373) 3. An Improved Chaotic Bat Swarm Scheduling Learning Model on Edge Computing,IEEE Access, 2019,7(1):58602-58610.(IF=3.367)2. An Improved Mixed Gaussian-based Background Modelling Method for Fast Gesture Segmentation of Mobile Terminals.Traitement du Signal,2018,35(3/4):243-252.(IF=2.589)1. An improved NBA-based STEP design intention feature recognition.Future Generation Computer Systems, 2018,88(6):357-362. (中科院Top期刊)已授权国家发明专利:8. 20220401 一种基于回归检测的实时动态手势轨迹识别方法(ZL 202010539323.3)7. 20211207 基于改进天牛须算法的多机器人路径规划方法(ZL 201911216397.7)6. 20211207 面向多机器人路径规划的增设路径障碍方法(ZL 201911215497.8)5. 20210723 一种基于Grover量子搜索算法的云制造调度方法(ZL 201910527040.4)4. 20210723 一种基于改进学习率的深度学习交通流预测方法(ZL 201810673067.X)3. 20210409 一种基于改进NBA算法的BPNN特征识别方法(ZL 201811237688.X)2. 20210105 一种基于改进聚合通道特征的手部检测方法(ZL 201711077703.4)1. 20191018 一种针对批量云服务请求的两阶段组合与调度方法(ZL 201610747165.4)