Journal of Zhejiang University

Articles in Press: <FITEE>

Introduction to Article in Press

Frontiers of Information Technology & Electronic Engineering

ISSN 2095-9184 (print), ISSN 2095-9230 (online)

Accepted manuscript available online (unedited version)

CONTENTS

Prompting class distribution optimization dynamically for semi-supervised sound event detection

Lijian GAO, Qing ZHU, Yaxin SHEN, Qirong MAO, Yongzhao ZHAN

DOI: 10.1631/FITEE.2400061 Downloaded: 596 Clicked: 969 Cited: 0 Commented: 0(p.) <Full Text>

Joint active user detection and channel estimation for massive machine-type communications: a difference-of-convex optimization perspective

Lijun ZHU, Kaihui LIU, Liangtian WAN, Lu SUN, Yifeng XIONG

DOI: 10.1631/FITEE.2400035 Downloaded: 673 Clicked: 1203 Cited: 0 Commented: 0(p.) <Full Text>

Spatio-temporal correlation based incomplete time series traffic prediction for LEO satellite networks

Liang PENG, Jie YAN, Peng WEI, Xiaoxiang WANG

DOI: 10.1631/FITEE.2300873 Downloaded: 613 Clicked: 1261 Cited: 0 Commented: 0(p.) <Full Text>

Space–time processing for inflight broadband connectivity: critical analysis, challenges, and future directions

Amjed ALI, Noor M. KHAN

DOI: 10.1631/FITEE.2400117 Downloaded: 622 Clicked: 884 Cited: 0 Commented: 0(p.) <Full Text>

SRIS-Net: robust image steganography based on feature score maps

Ai XIAO, Zhi LI, Guomei WANG, Long ZHENG, Haoyuan SUN

DOI: 10.1631/FITEE.2400069 Downloaded: 531 Clicked: 1093 Cited: 0 Commented: 0(p.) <Full Text>

Frequency-learning adversarial networks based on transfer learning for cross-scenarios signal modulation classification

Qinyan MA, Jing XIAO, Zeqi SHAO, Duona ZHANG, Yufeng WANG, Wenrui DING

DOI: 10.1631/FITEE.2400080 Downloaded: 518 Clicked: 813 Cited: 0 Commented: 0(p.) <Full Text>

The effect of terminal boundary protection on the spread of computer viruses: modeling and simulation

Kai GAO, Lixin ZHANG, Yabing YAO, Yang YANG, Fuzhong NIAN

DOI: 10.1631/FITEE.2400236 Downloaded: 292 Clicked: 409 Cited: 0 Commented: 0(p.) <Full Text>

Neural mesh refinement

Zhiwei ZHU, Xiang GAO, Lu YU^‡, Yiyi LIAO^‡

DOI: 10.1631/FITEE.2400344 Downloaded: 303 Clicked: 535 Cited: 0 Commented: 0(p.) <Full Text>

MAL: multilevel active learning with BERT for Chinese affective structure analysis

Shufeng XIONG, Guipei ZHANG, Xiaobo FAN, Wenjie TIAN, Lei XI, Hebing LIU, Haiping SI

DOI: 10.1631/FITEE.2400242 Downloaded: 187 Clicked: 248 Cited: 0 Commented: 0(p.) <Full Text>

A UAV-enabled mobile edge computing paradigm for dependent tasks based on a computing power pool

Xuebin LAI, Yan GUO, Ming HE, Hao YUAN, Wei LI, Xiaonan CUI

DOI: 10.1631/FITEE.2400465 Downloaded: 128 Clicked: 152 Cited: 0 Commented: 0(p.) <Full Text>

A ground-based dataset and a diffusion model for on-orbit low-light image enhancement

Yiman ZHU¹, Lu WANG^‡¹, Jingyi YUAN¹, Yu GUO¹

DOI: 10.1631/FITEE.2400261 Downloaded: 222 Clicked: 286 Cited: 0 Commented: 0(p.) <Full Text>

XIRAC: an optimized product-oriented near real-time operating system with unlimited tasks and an innovative programming paradigm based on the maximum entropy method

Alireza ZIRAK

DOI: 10.1631/FITEE.2400102 Downloaded: 276 Clicked: 530 Cited: 0 Commented: 0(p.) <Full Text>

A subspace-based few-shot intrusion detection system for the Internet of Things

Zhihui LI^1,2, Congyuan XU², Kun DENG², Chunyuan LIU²

DOI: 10.1631/FITEE.2400556 Downloaded: 182 Clicked: 194 Cited: 0 Commented: 0(p.) <Full Text>

Swarm intelligent computing of electric eel foraging heuristics for fractional Hammerstein autoregressive exogenous noise model identification

Faisal ALTAF¹, Ching-Lung CHANG², Naveed Ishtiaq CHAUDHARY³, Taimoor Ali KHAN⁴, Zeshan Aslam KHAN^4,⁵, Chi-Min SHU⁶, Muhammad Asif Zahoor RAJA³

DOI: 10.1631/FITEE.2400730 Downloaded: 158 Clicked: 194 Cited: 0 Commented: 0(p.) <Full Text>

Optimal federated fusion of multiple maneuvering targets based on multi-Bernoulli filters

Yu XUE, Xi′ an FENG^‡

DOI: 10.1631/FITEE.2400598 Downloaded: 156 Clicked: 187 Cited: 0 Commented: 0(p.) <Full Text>

FedMcon: an adaptive aggregation method for federated learning via meta controller

Tao SHEN¹, Zexi LI¹, Ziyu ZHAO¹, Didi ZHU¹, Zheqi LV¹, Kun KUANG¹, Shengyu ZHANG²^‡, Chao WU^3,⁴^‡, Fei WU¹^‡

DOI: 10.1631/FITEE.2400530 Downloaded: 143 Clicked: 159 Cited: 0 Commented: 0(p.) <Full Text>

Trajectory Poisson multi-Bernoulli filters with unknown detection probability

Xiangfei ZHENG¹, Kaidi LIU¹, Hongwei LI^‡¹

DOI: 10.1631/FITEE.2400606 Downloaded: 130 Clicked: 184 Cited: 0 Commented: 0(p.) <Full Text>

Three-dimensional-printed low-sidelobe dual-band dual-polarized antenna array for Ku-band satellite communications

Yuqi XIA^1-4, Xiupig LI^1-4, Genqiang KOU^1-4, Wenyu ZHAO^1-4, Jie ZHANG^1-4, Muhammad ISHFAQ^1-4, Zihang QI^†^‡^1-4

DOI: 10.1631/FITEE.2400709 Downloaded: 130 Clicked: 141 Cited: 0 Commented: 0(p.) <Full Text>

Reconfigurable intelligent surface-aided secret key generation using autoencoder and K-means quantization

Zhenling LI^†¹, Panpan XU¹, Qiangqiang GAO^2,³, Chunguo LI⁴, Weijie TAN^‡^2,³

DOI: 10.1631/FITEE.2400799 Downloaded: 144 Clicked: 169 Cited: 0 Commented: 0(p.) <Full Text>

Long working distance portable smartphone microscopy for metallic mesh defect detection

Zhengang LU^†^‡^1,², Hongsheng QIN^†^1,², Jing LI^1,^2,³, Ming SUN^†⁴, Jiubin TAN^1,²

DOI: 10.1631/FITEE.2401002 Downloaded: 142 Clicked: 138 Cited: 0 Commented: 0(p.) <Full Text>

Multisensor contrast neural network for prediction of remaining useful life of rolling bearing under scarce labeled data

Binkun LIU^1,^2,^3,⁴, Zhenyi XU^‡^1,^2,³, Yu KANG^3,⁴, Yang CAO^3,⁴, Yunbo ZHAO^‡^3,⁴

DOI: 10.1631/FITEE.2400753 Downloaded: 70 Clicked: 73 Cited: 0 Commented: 0(p.) <Full Text>

Q-space-coordinate-guided neural networks for high-fidelity diffusion tensor estimation from minimal diffusion-weighted images

Maokun ZHENG^†, Zhi LI^†^‡, Long ZHENG^� , Weidong WANG^† , Dandan LI, Guomei WANG

DOI: 10.1631/FITEE.2400766 Downloaded: 74 Clicked: 96 Cited: 0 Commented: 0(p.) <Full Text>

SAPER-AI accelerator: systolic array based power-efficient reconfigurable AI accelerator

Fahad bin MUSLIM^†^‡¹ , Kashif INAYAT^†², Muhammad zain SIDDIQI^†¹ , Safiullah KHAN³,Tayyeb MAHMOOD⁴ , Ihtesham ul ISLAM⁵

DOI: 10.1631/FITEE.2400867 Downloaded: 71 Clicked: 59 Cited: 0 Commented: 0(p.) <Full Text>

Pseudo-evolute curves and caustic surfaces

Hande Nur DALKILIÇ^‡¹ , Yusuf YAYLI²

DOI: 10.1631/FITEE.2400930 Downloaded: 69 Clicked: 88 Cited: 0 Commented: 0(p.) <Full Text>

Miniaturized diplexer with wide-stopband based on half-mode SIW

Ziyu ZHOU, Gang DONG^‡ , Xinqing LEI, Zhangming ZHU

DOI: 10.1631/FITEE.2400944 Downloaded: 66 Clicked: 69 Cited: 0 Commented: 0(p.) <Full Text>

AOI-OPEN: federated operation and control for DAO-based trustworthy and intelligent AOI ecology

Yansong CAO ^’¹, Yutong WANG^’² , Jing YANG^’² , Yonglin TIAN^‡² , Jiangong WANG², Fei-Yue WANG^1,²

DOI: 10.1631/FITEE.2400975 Downloaded: 66 Clicked: 76 Cited: 0 Commented: 0(p.) <Full Text>

Recognition method for underwater communication signals that mimic dolphin whistles using phase-shifting modulation

Qingwang YAO¹, Jiajia JIANG^†^‡¹, Xiaolong YU², Zhuochen LI¹, Xiaozong HOU¹, Xiao FU¹, Fajie DUAN¹

DOI: 10.1631/FITEE.2400572 Downloaded: 23 Clicked: 36 Cited: 0 Commented: 0(p.) <Full Text>

Analysis of Pareto equilibrium inmulti-objective games using the semi-tensor product

Fanyueyang ZHANG, Jun ′ e FENG ^‡

DOI: 10.1631/FITEE.2400945 Downloaded: 5 Clicked: 9 Cited: 0 Commented: 0(p.) <Full Text>

A comprehensive survey of physical adversarial vulnerabilities in autonomous driving systems

Shuai ZHAO, Boyuan ZHANG, Yucheng SHI, Yang ZHAI, Yahong HAN, Qinghua HU

DOI: 10.1631/FITEE.2300867 Downloaded: 596 Clicked: 1055 Cited: 0 Commented: 0(p.) <Full Text>

A novel frequency protection interval adjustment method based on Doppler frequency offset pre-compensation for space-based Internet of Things

Qingquan LIU, Lihu CHEN, Songting LI, Yiran XIANG, Baokang ZHAO

DOI: 10.1631/FITEE.2400033 Downloaded: 530 Clicked: 1001 Cited: 0 Commented: 0(p.) <Full Text>

A survey of binary code representation technology

Taiyan WANG, Qingsong XIE, Lu YU, Zulie PAN, Min ZHANG

DOI: 10.1631/FITEE.2400088 Downloaded: 493 Clicked: 729 Cited: 0 Commented: 0(p.) <Full Text>

CUSMART:effective parallelization of string-matching algorithms using GPGPU accelerators

Adnan OZSOY, Mengu NAZLI, Onur CANKUR, Cagri SAHIN

DOI: 10.1631/FITEE.2400091 Downloaded: 443 Clicked: 710 Cited: 0 Commented: 0(p.) <Full Text>

Optimization methods in fully cooperative scenarios: a review of multiagent reinforcement learning

Tao YANG, Xinhao SHI, Qinghan ZENG, Yulin YANG, Cheng XU, Hongzhe LIU

DOI: 10.1631/FITEE.2400259 Downloaded: 326 Clicked: 460 Cited: 0 Commented: 0(p.) <Full Text>

Significance extraction based on data augmentation for reinforcement learning

DOI: 10.1631/FITEE.2400406 Downloaded: 230 Clicked: 235 Cited: 0 Commented: 0(p.) <Full Text> <PPT > 1

Chinese summary <> 基于数据增强的显著性提取强化学习

韩玉玺，李德权，杨洋
安徽理工大学人工智能学院，中国淮南市，232000
摘要：深度强化学习在视觉任务中展现了显著的能力，但在输入图像受到干扰信号的情况下，其泛化能力较弱，因此难以将训练有素的智能体应用于新环境中。为了让智能体能区分图像中的噪声信号和重要像素，数据增强技术和辅助网络的建立是有效的解决方案。提出一种新的算法，即增强提取显著性Q值（SEQA），该算法鼓励智能体全面探索未知状态，并将注意力集中在重要信息上。具体来说，SEQA屏蔽干扰特征，提取显著特征，使用评论家损失更新掩码解码网络，从而促使智能体关注重要特征并做出正确决策。在DeepMind控制泛化基准上评估该算法，实验结果表明，该算法极大提高了训练效率和稳定性。同时，在大多数DeepMind控制泛化基准任务中，我们的算法在样本效率和泛化能力方面优于最先进的强化学习方法。

关键词组：深度强化学习；视觉任务；泛化；数据增强；显著性；DeepMind控制泛化基准

Efficient privacy-preserving scheme for secure neural network inference

Liquan CHEN, Zixuan YANG, Peng ZHANG, Yang MA

DOI: 10.1631/FITEE.2400371 Downloaded: 156 Clicked: 269 Cited: 0 Commented: 0(p.) <Full Text>

Reinforcement learning-based privacy-preserving consensus tracking control of nonstrict-feedback discrete-time multi-agent systems

Yang YANG, Fanming HUANG, Dong YUE

DOI: 10.1631/FITEE.2300532 Downloaded: 685 Clicked: 1496 Cited: 0 Commented: 0(p.) <Full Text> <PPT > 1

Chinese summary <> 基于强化学习的非严格反馈离散时间多智能体系统隐私保护一致性跟踪控制

杨杨¹，黄范铭¹，岳东^1,2
¹南京邮电大学自动化学院、人工智能学院，中国南京市，210023
²南京邮电大学碳中和先进技术研究院，中国南京市，210023
摘要：本文研究了一类非严格反馈离散时间多智能体系统的隐私保护一致性跟踪问题。为减轻明文加密和解密之间的误差影响，开发一种改进的Liu加密系统，以确保明文信息恢复良好。采用强化学习技术补偿未知动态和真实信号与解密信号之间的误差。采用反步法和图论知识，设计基于强化学习的隐私保护一致性跟踪控制策略。借助李雅普诺夫稳定性理论，证明多智能体系统的一致跟踪误差和所有信号最终有界。最后，通过仿真实例验证设计控制策略的有效性。

关键词组：多智能体系统；一致跟踪；隐私保护；强化学习

SCFformer: a binary data hiding method against JPEG compression based on spatial channel fusion Transformer

Xintao DUAN, Chun LI, Bingxin WEI, Guoming WU, Chuan QIN, Haewoon NAM

DOI: 10.1631/FITEE.2300762 Downloaded: 617 Clicked: 1220 Cited: 0 Commented: 0(p.) <Full Text>

Anti-quantumcross-chain identity authentication approach using dynamic group signature

Huifang YU, Mengjie HUANG

DOI: 10.1631/FITEE.2400443 Downloaded: 221 Clicked: 281 Cited: 0 Commented: 0(p.) <Full Text>

Few-shot exemplar-driven inpainting with parameter-efficient diffusion fine-tuning

Shiyuan YANG, Zheng GU, Wenyue HAO, Yi WANG1, Huaiyu CAI, Xiaodong CHEN

DOI: 10.1631/FITEE.2400395 Downloaded: 197 Clicked: 218 Cited: 0 Commented: 0(p.) <Full Text>

Handling polysemous triggers and arguments in event extraction: an adaptive semantics learning strategy with reward–penalty mechanism

Haili LI, Zhiliang TIAN, Xiaodong WANG, Yunyan ZHOU,Shilong PAN, Jie ZHOU, Qiubo XU, Dongsheng LI

DOI: 10.1631/FITEE.2400220 Downloaded: 569 Clicked: 1047 Cited: 0 Commented: 0(p.) <Full Text>

Federated deep reinforcement learning-based computation offloading in a LEOsatellite edge computing system

Min JIA, Jian WU, Xinyu WANG, Qing GUO

DOI: 10.1631/FITEE.2400448 Downloaded: 208 Clicked: 257 Cited: 0 Commented: 0(p.) <Full Text>

Analog-only beamforming for near-fieldmultiuserMIMO communications

Ying WANG, Chenhao QI

DOI: 10.1631/FITEE.2400433 Downloaded: 243 Clicked: 279 Cited: 0 Commented: 0(p.) <Full Text>

Building accurate translation-tailored LLMswith language aware instruction tuning

Changtong Zan, Liang Ding, Li Shen3, Yibing Zhan, Xinghao Yang, Weifeng Liu

DOI: 10.1631/FITEE.2400458 Downloaded: 204 Clicked: 221 Cited: 0 Commented: 0(p.) <Full Text>

A parasitic coupling network concept for mutual coupling utilization in wideband multielement antenna arrays^*#

Xiaojun ZOU, Guangming WANG, Yawei WANG, Wei SONG, Hang ZHU, Ming TAN, Xuguang XU, Guoqin KANG, Binfeng ZONG

DOI: 10.1631/FITEE.2300742 Downloaded: 615 Clicked: 964 Cited: 0 Commented: 0(p.) <Full Text>

Prototype-guided cross-task knowledge distillation

Deng LI, Peng LI, Aming WU, Yahong HAN

DOI: 10.1631/FITEE.2400383 Downloaded: 325 Clicked: 417 Cited: 0 Commented: 0(p.) <Full Text>

Distributedmulti-target tracking with labeled multi-Bernoulli filter considering efficient label matching

Changwen DING, Chuntao SHAO, Siteng ZHOU, Di ZHOU?1, Runle DU, Jiaqi LI

DOI: 10.1631/FITEE.2400582 Downloaded: 207 Clicked: 286 Cited: 0 Commented: 0(p.) <Full Text> <PPT > 1

Deep anomaly detection of temporal heterogeneous data in AIOps: a survey?

Jiayi GU, Zhongnan MA, Hao ZHOU, Yan SU, Miaoru ZHANG, Ke YU, Xiaofei WU

DOI: 10.1631/FITEE.2400467 Downloaded: 258 Clicked: 230 Cited: 0 Commented: 0(p.) <Full Text>

An optimal algorithm for preemptive scheduling on non-simultaneously available uniform machines

Hao ZHOU, Liping CAO, Qi WEi, Zhenyu SHU, Yiwei JIANG

DOI: 10.1631/FITEE.2300767 Downloaded: 534 Clicked: 885 Cited: 0 Commented: 0(p.) <Full Text> <PPT > 3

Chinese summary <> 非同时可用同类机可中断调度问题的最优算法

周昊¹，曹丽萍²，魏麒³，舒振宇⁴，蒋义伟²
¹浙江树人学院基础学院，中国杭州市，310015
²浙江工商大学管理工程与电子商务学院，中国杭州市，310018
³宁波财经学院国际经济贸易学院，中国宁波市，315175
⁴浙大宁波理工学院计算机与数据工程学院，中国宁波市，315100
摘要：研究了m台可用时间不同的同类机可中断调度问题，目标是极小化最大完工时间。每台机器都有一个不同的加工速度和可用时间。通过将真实机器转化成虚拟机器的方法给出最优调度目标值的下界。在这些虚拟机器中，可用时间越早的机器在任何时候都有更快的速度。对该问题，给出一个时间复杂度为O(nm+m²)的最优调度算法，并且该算法的中断次数不超过（n代表工件数量）。

关键词组：最优算法；可中断调度；同类机；非同时可用时间

CRGT-SA:an interlaced and spatiotemporal deep learning model for network intrusion detection

Jue CHEN, Wanxiao LIU, Xihe QIU, Wenjing LV, Yujie XIONG

DOI: 10.1631/FITEE.2400459 Downloaded: 282 Clicked: 490 Cited: 0 Commented: 0(p.) <Full Text>

S3Det: A fast object detector for remote sensing images based on analog-spiking neural network conversion

LiChen, FanZhang, Guangwei Xie, Yanzhao Gao, Xiaofeng Qi, Mingqian Sun

DOI: 10.1631/FITEE.2400594 Downloaded: 208 Clicked: 339 Cited: 0 Commented: 0(p.) <Full Text>

Adigital simulation platform with human-interactive immersive design for navigation, motion and teleoperated manipulation ofwork-class remotely operated vehicle?

Fanghao HUANG, Xiao YANG, Xuanlin CHEN, Deqing MEI, Zheng CHEN

DOI: 10.1631/FITEE.2400486 Downloaded: 170 Clicked: 282 Cited: 0 Commented: 0(p.) <Full Text>

An improved error-based observer on repetitive control strategy in electro-optical tracking system

Mai TANG, Wenqiang XIA, Jiuqiang DENG, Yao MAO

DOI: 10.1631/FITEE.2300796 Downloaded: 628 Clicked: 968 Cited: 0 Commented: 0(p.) <Full Text> <PPT > 1

Chinese summary <> 光电跟踪系统中基于重复控制策略改进的误差观测器

唐迈^1,2,3,4，夏文强^1,2,3,4，邓久强^1,2,3,4，毛耀^1,2,3,4
¹中国科学院光场调控科学技术全国重点实验室，中国成都市，610209
²中国科学院光学工程重点实验室，中国成都市，610209
³中国科学院光电技术研究所，中国成都市，610209
⁴中国科学院大学，中国北京市，101408
摘要：光电跟踪系统因其出色的工作性能，已被广泛应用于自由空间环境探测及通信等前沿领域。外界扰动往往会很大程度影响光电跟踪系统的工作精度，随着其应用领域不断拓宽，更复杂的工作条件也带来更复杂的工作环境和扰动情况。本文针对周期性谐波扰动和窄带尖峰周期性扰动两类复杂的扰动情况，提出一种基于重复控制策略改进的误差扰动观测器复合控制结构。这种结构在保证系统稳定性的同时，实现了多重频率处的周期性扰动抑制，弥补了现有扰动抑制方法难以对复杂周期性扰动进行抑制的问题。此外，给出相关证明，并搭建光电系统实验平台，验证了上述控制方法在不同情况下的有效性和可靠性。

关键词组：扰动抑制；误差观测器；重复控制；光电跟踪系统；特殊频率点

Enhanced hippopotamus optimization algorithm for tuningPIDcontrollers

Kailong MOU, Mengjian ZHANG, Deguang WANG, Ming YANG, Chengbin LIANG

DOI: 10.1631/FITEE.2400492 Downloaded: 177 Clicked: 221 Cited: 0 Commented: 0(p.) <Full Text>

Data-driven intermittent connection fault diagnosis for complex topology DeviceNet based on Bayesian inference

Longkai WANG, Yong LEI

DOI: 10.1631/FITEE.2400696 Downloaded: 138 Clicked: 223 Cited: 0 Commented: 0(p.) <Full Text>

Shared-weightmultimodal translation model for recognizingChinese variant characters

Yuankang SUN, Bing LI, Lexiang LI, Peng YANG, Dongmei YANG

DOI: 10.1631/FITEE.2400504 Downloaded: 185 Clicked: 186 Cited: 0 Commented: 0(p.) <Full Text>

An efficient multi-Bernoulli filter for tracking multiple maritime dim targets

Liwei SHI, Yunfei GUO, Wenxiong CUI, Yanbo XUE, Yun CHEN

DOI: 10.1631/FITEE.2400449 Downloaded: 391 Clicked: 738 Cited: 0 Commented: 0(p.) <Full Text>

SPJEU: a self-sufficient plaintext-related JPEG image encryption scheme based on a unified key

Ming LI, Wenwen ZHOU, Mengdie WAN, Yushu ZHANG, Yong XIANG

DOI: 10.1631/FITEE.2400721 Downloaded: 162 Clicked: 295 Cited: 0 Commented: 0(p.) <Full Text>

A geographic information encryption system based on chaos-LSTM and chaos sequence proliferation

Jia DUAN, Luanyun HU, Qiumei XIAO, Meiting LIU, Wenxin YU

DOI: 10.1631/FITEE.2300755 Downloaded: 616 Clicked: 1289 Cited: 0 Commented: 0(p.) <Full Text>

Chinese summary <> 基于Chaos-LSTM与混沌序列增殖的地理信息数据加密系统

段佳^1,2，胡娈运^1,2，肖求美³，刘美婷³，于文新³
¹湖南省第三测绘院，中国长沙市，410000
²湖南省地理信息安全与应用工程研究中心，中国长沙市，410000
³湖南科技大学信息与电气工程学院，中国湘潭市，411201
摘要：针对传统混沌加密算法中混沌系统状态与初始状态及参数关联性强，可能导致混沌序列存在周期性的问题，结合混沌系统和LSTM神经网络构建了Chaos-LSTM模型。针对计算机的有限计算精度效应会使长混沌序列出现周期性，使其不适宜对数据量大的对象进行加密的问题，构建了混沌序列增殖(CSP)算法。结合二者，提出了基于Chaos-LSTM与混沌序列增殖的地理信息数据加密通信系统。首先，通过Chaos-LSTM模型输出具有较高谱熵(SE)复杂度的混沌序列；然后，选取较短的混沌序列，通过CSP算法增殖出匹配加密对象的混沌加密序列，并对增殖序列进行随机性分析与测试；最后，以地理图片信息为加密对象，将混沌增殖序列与扩散算法以及置乱算法结合构成加密算法，并将加密系统在ZYNQ平台中实现。软件测试与硬件实验表明该系统具有良好的保密性能与可拓展性，能用于多种加密对象的保密通信，具备良好的应用价值。

关键词组：混沌；长短期记忆神经网络（LSTM）；混沌序列增殖（CSP）；ZYNQ平台；图像加密

Single-layer chiral metasurface for circularly polarized light detection

Xinjie SUN, Xin HE, Zixin CAI, Xiang HAO

DOI: 10.1631/FITEE.2400081 Downloaded: 576 Clicked: 941 Cited: 0 Commented: 0(p.) <Full Text>

A power optimization approach for Mixed Polarity Reed_Muller logic circuits based on multi-strategy fusion memetic algorithm

Mengyu ZHANG, Zhenxue HE, Yijin WANG, Xiaojun ZHAO, Xiaodan ZHANG, Limin XIAO, Xiang WANG

DOI: 10.1631/FITEE.2400513 Downloaded: 197 Clicked: 219 Cited: 0 Commented: 0(p.) <Full Text> <PPT > 3

Chinese summary <> 一种基于MFMA的MPRM逻辑电路功耗优化方法

张梦雨^1,2，何振学^1,2，王伊瑾^1,2，赵晓君^1,2，张晓丹^1,2，肖利民³，王翔⁴
¹河北农业大学智能农业装备研究院，中国保定市，071001
²河北农业大学河北省农业大数据重点实验室，中国保定市，071001
³北京航空航天大学计算机学院，中国北京市，100191
⁴北京航空航天大学电子信息工程学院，中国北京市，100191
摘要：混合极性Reed-Muller（MPRM）逻辑电路功耗优化是一种典型的组合优化问题。现有功耗优化方法存在收敛速度慢、易陷入局部最优等问题，在实现最佳功耗方面的有效性十分有限。首先，本文提出一种多策略融合模因算法（MFMA），利用黑猩猩优化算法进行全局勘探，利用基于最优位置学习和自适应权重因子的浣熊优化算法（COA-OLA）进行局部探索，最后采用截断选择算法进行新种群选择。其次，基于MFMA提出一种MPRM逻辑电路功耗优化方法，通过寻找最佳极性配置，使得电路功耗最小化。基于MCNC基准电路的实验结果表明，与现有的功耗优化方法相比，本功耗优化方法有显著的改进。MFMA实现最高功耗优化率为72.30%，平均优化率为43.37%。同时，MFMA搜索解的速度更快且质量更好，验证了其在功耗优化方面的有效性和优越性。

关键词组：功耗优化；多策略融合模因算法（MFMA）；混合极性Reed-Muller（MPRM）；组合优化问题

Joint autonomous underwater vehicle and underwater sensor net-works target tracking for underwater applications

Zhaohong LV, Zhenkai ZHANG, Boonchong SEET, Yi YANG

DOI: 10.1631/FITEE.2400869 Downloaded: 162 Clicked: 222 Cited: 0 Commented: 0(p.) <Full Text>

An end-to-end automatic methodology to accelerate the accuracy evaluation of DNN under hardware transient faults

Jiajia JIAO, Ran WEN, Hong YANG

DOI: 10.1631/FITEE.2400547 Downloaded: 346 Clicked: 504 Cited: 0 Commented: 0(p.) <Full Text>

An optimized formula for the two-point resistance of a cobweb resistance network and its potential application

Yu GUAN, Xiaoyu JIANG, Yanpeng ZHENG, Zhaolin JIANG

DOI: 10.1631/FITEE.2400613 Downloaded: 192 Clicked: 246 Cited: 0 Commented: 0(p.) <Full Text>

MH-T2TA: multiple hypothesis algorithm for multi-sensor track-to-track association with intelligent track score

Pingliang XU, Yaqi CUI, Wei XIONG

DOI: 10.1631/FITEE.2400340 Downloaded: 303 Clicked: 411 Cited: 0 Commented: 0(p.) <Full Text>

Minimizing transformer inference overhead using controlling element on Shenwei AI accelerator

Yulong ZHAO, Chunzhi WU, Yizhuo WANG, Lufei Zhang, Yaguang ZHANG,Wenyuan SHEN, Hao FAN, Hankang FANG, Yi QIN, Xin LIU

DOI: 10.1631/FITEE.2400453 Downloaded: 304 Clicked: 462 Cited: 0 Commented: 0(p.) <Full Text>

Active inference of protocol state machines from incomplete message domains

Maohua GUO, Yuefei ZHU, Jinlong FEI

DOI: 10.1631/FITEE.2400487 Downloaded: 360 Clicked: 439 Cited: 0 Commented: 0(p.) <Full Text>