Fnetlink Group
Discussion
Started 3 September 2025
Call for papers- IEEE 第六届计算机工程与智能控制学术会议（ICCEIC 2025)
会议征稿：第六届计算机工程与智能控制学术会议（ICCEIC 2025)
Call for papers: IEEE 2025 5th International Conference on Computer Engineering and Intelligent Control (ICCEIC 2025) will be held during October 17-19, 2025 in Guangzhou, China.
Conference website（English): https://ais.cn/u/3eEnMn
重要信息
大会官网(投稿网址）: https://ais.cn/u/3eEnMn
大会时间: 2025年10月17日-19日
地点: 中国-广州
提交检索：IEEE Xplore, EI Compendex, Scopus
会议详情
第六届计算机工程与智能控制学术会议（ICCEIC 2025）将于2025年10月17日至19日在广州举办，聚焦计算机工程与智能控制前沿，涵盖网络安全、硬件系统、软件工程、嵌入式创新等多个核心议题及交叉学科研究。ICCEIC 2025将计算机工程和智能控制领域的创新学者和工业专家聚集到一个共同的论坛上，共享最新科研成果，破解关键问题，展望未来发展。
征稿主题（包括但不限于）
Track I：智能控制与自动化
（控制理论及应用、智能与最优控制系统、系统科学与系统工程、系统建模、分析与综合等）
Track II：计算机网络安全
（计算机原理、计算机体系结构、计算机网络、操作系统原理、数据结构、C语言程序设计、汇编语言程序设计等）
Track III：计算机工程
（先进计算与数据处理、体系结构与软件技术、移动互联与通信技术、安全技术、人工智能及识别技术、图形图像处理、多媒体技术及应用、开发研究与工程应用等）
Track Ⅳ：软件工程
（软件需求、软件维护、软件配置管理、软件工程管理、软件工程过程、软件工程模型与方法、软件质量、软件工程职业实践、软件工程经济学等）
Track V：嵌入式系统
（数字图像压缩、通信协议及编程、网络与信息安全、数字信号处理/处理器、数字电路、计算机组成原理、嵌入式微处理器的结构与应用等）
Track VI：网络工程
（高等数学、线性代数、概率与统计、离散数学、电路与电子学、数字逻辑电路、数据结构、编译原理、操作系统、数据库系统等）
论文出版
ICCEIC 2025所有的投稿都必须经过2-3位组委会专家审稿，经过严格的审稿之后，最终所录用的论文将由IEEE出版社(ISBN: 979-8-3315-5442-2 )出版，收录进IEEE Xplore数据库，见刊后由期刊社提交至EI Compendex和Scopus检索。
参会投稿方式：
1.口头报告：论文一经录用即可注册参会报名口头报告，时间为15分钟。无投稿亦可报名。
2.海报展示：论文一经录用即可注册参会、展示海报，海报尺寸为A1竖版（宽*高：594mm*841mm，JPG/PNG格式，模板点击会议资料下载）。无投稿亦可报名。
3.听众参会：无需提交稿件，直接注册听众参会即可
◆ 投稿入口: https://ais.cn/u/3eEnMn
All replies (1)
Research on an Intelligent Intrusion Detection System Based on Behavioral Analysis
With the continuous evolution of network attack methods, traditional feature-matching-based intrusion detection systems (IDS) are no longer able to cope with complex and volatile security threats. This paper proposes an intelligent intrusion detection system model that integrates user behavior analysis and machine learning techniques. By constructing a multidimensional behavioral feature vector and introducing an anomaly detection algorithm, this system efficiently identifies potential attack behaviors. Experimental results demonstrate that the system outperforms traditional methods in detection accuracy, response speed, and false alarm rate, demonstrating promising practical application prospects.
Against the increasingly complex digital infrastructure, network security issues are becoming increasingly prominent. As a key component of defense systems, intrusion detection systems urgently need to transition from "static rule-based" to "dynamic intelligence." Behavioral analysis technology, by mining user-system interaction patterns, can effectively identify atypical attack behaviors and has become a key direction in intelligent security.
In recent years, researchers have attempted to apply deep learning, graph neural networks, and federated learning technologies to IDS construction. For example, the LSTM-based traffic analysis model proposed by Zeng et al. has demonstrated excellent performance in DDoS detection. However, most methods still rely on large amounts of labeled data, making them difficult to adapt to the data sparsity and attack diversity in real-world environments.
