检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Jingzhong Li Lin Yang Yuxuan Chen Yixin Yang Yue Jin Kuanta Akiyama National Engineering Research Centre for Automotive Power and Intelligent Control School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science and Engineering Hong Kong University of Science and Technology Kowloon Hong Kong

3D object detection plays an indispensable role in autonomous driving. Most existing methods for 3D object detection from point clouds are LiDAR-based. However, LiDAR may suffer significant performance degradation from poor environmental conditions, such as rainy and foggy weather. Compared to LiDAR, 4D RaDAR is more robust to various environments and can provide velocity information. Nevertheless, its point cloud is sparser and contains more noise. Thus, existing LiDAR-dependent 3D object detection methods cannot be effectively applied to 4D Radar. To cope with this issue, we propose a new framework to improve the 3D object detection performance of 4D Radar, dubbed Pillar-based Dual Attention Network (PillarDAN). Specifically, PillarDAN builds the Global Pillar Attention (GPA) to enhance the feature extraction capability from sparser 4D Radar point clouds. Meanwhile, the Pillar Feature Attention (PFA) is proposed to focus on the truly effective information, thus suppressing the noise of point clouds. We also present an effective 3D coordinate embedding to improve the position awareness of the bird's-eye-view (BEV) feature map. Experimental results on the Astyx HiRes2019 dataset show our PillarDAN achieves effective performance improvement, which is 3.28% higher in 3D mAP and 3.12% higher in BEV mAP than the previous best method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Amplitude-frequency-aware deep fusion network for optimal contact selection on STN-DBS electrodes

引用

science China(Information sciences) 2022年第4期65卷 48-63页

作者： Linxia XIAO Caizi LI Yanjiang WANG Weixin SI Hai LIN Doudou ZHANG Xiaodong CAI Pheng-Ann HENG College of Control Science and Engineering China University of Petroleum (East China) Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Department of Neurosurgery Shenzhen Second People's Hospital School of Medicine Shenzhen University Department of Computer Science and Engineering The Chinese University of Hong Kong

Parkinson's disease(PD) is treated effectively by deep brain stimulation(DBS) of the subthalamic nucleus(STN), using an electrode inserted into the head of a PD patient. The electrode has multiple electrical contacts along its length, so the best may be chosen for selectively stimulating the STN. Neurosurgeons usually determine the optimal stimulated contact via the clinical experience of the neurosurgeon and the motor improvement of PD patients. This is a time-consuming and labor-intensive trial-and-error process. The selection of optimal stimulated contact highly depends on the locations of sweet spots, which are manually identified by the characteristic features of microelectrode recordings(MERs). This paper presents an amplitude-frequency-aware deep fusion network for optimal contact selection on STN-DBS *** method first obtains the amplitude-frequency fusion features by combining the MERs time sequence features and the amplitude sequence features, and then uses the convolutional neural network(CNN) with convolutional block attention module(CBAM) to identify both the border of the STN and the sweet spots to implant the electrode. The optimal stimulated contact can be selected according to the distribution of the sweet spots. Experimental results indicate that, for successful surgeries, neurosurgeons and the proposed AI solution selected the same optimal contacts. Furthermore, the proposed method outperforms the state-of-the-art methods for STN and sweet spot identification. The proposed method shows great potential for optimal contact selection to improve the efficiency of STN-DBS surgery and reduce the dependence on clinicians' experience.

关键词： optimal contact selection sweet spots microelectrode recordings amplitude-frequency feature deep fusion network

来源：评论

学校读者我要写书评

暂无评论

Data-driven Optimal Cooperative Output Regulation of Unknown Linear Discrete-time Multi-agent Systems

Data-driven Optimal Cooperative Output Regulation of Unknown...

引用

Chinese control and Decision Conference, CCDC

作者： Dong Liang Yi Dong Chaoli Wang Engang Tian Department of Control Science and Engineering School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China

The cooperative output regulation problem has been extensively studied on the basis of the distributed observer approach. However, the majority of the existing research assumes that the dynamics is known previously. To remove this condition, the cooperative output regulation problem is further solved via the data-driven framework where the dynamics of the plant is unknown. First, a data-driven distributed observer is established to estimate the state of the leader with unknown dynamics subject to external inputs. Second, the unknown regulator equations are solved using the iterative recurrent neural network approach. Third, the state-based data-driven distributed control law is synthesized to solve the problem. The optimal gains are derived by solving convex optimization problems using input and state data. Finally, a numerical example is presented to verify the feasibility of the proposed framework.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TEMPORAL LOGIC control FOR NONLINEAR STOCHASTIC SYSTEMS UNDER UNKNOWN DISTURBANCES

arXiv

引用

arXiv 2024年

作者： Gracia, Ibon Laurenti, Luca Mazo, Manuel Abate, Alessandro Lahijanian, Morteza Smead Department of Aerospace Engineering Sciences CU Boulder BoulderCO United States Delft Center for Systems and Control Faculty of Mechanical Maritime and Materials Engineering Delft University of Technology Netherlands Department of Computer Science University of Oxford United Kingdom

In this paper, we present a novel framework to synthesize robust strategies for discrete-time nonlinear systems with random disturbances that are unknown, against temporal logic specifications. The proposed framework is data-driven and abstraction-based: leveraging observations of the system, our approach learns a high-confidence abstraction of the system in the form of an uncertain Markov decision process (UMDP). The uncertainty in the resulting UMDP is used to formally account for both the error in abstracting the system and for the uncertainty coming from the data. Critically, we show that for any given state-action pair in the resulting UMDP, the uncertainty in the transition probabilities can be represented as a convex polytope obtained by a two-layer state discretization and concentration inequalities. This allows us to obtain tighter uncertainty estimates compared to existing approaches, and guarantees efficiency, as we tailor a synthesis algorithm exploiting the structure of this UMDP. We empirically validate our approach on several case studies, showing substantially improved performance compared to the state-of-the-art. © 2024, CC BY.

关键词： Temporal logic

来源：评论

学校读者我要写书评

暂无评论

A Horizontal Federated Learning Approach to IoT Malware Traffic Detection: An Empirical Evaluation with N-BaIoT Dataset 26

A Horizontal Federated Learning Approach to IoT Malware Traf...

引用

26th International Conference on Advanced Communications Technology, ICACT 2024

作者： Do, Phuc Hao Le, Tran Duc Vishnevsky, Vladimir Berezkin, Aleksandr Kirichek, Ruslan The Bonch-Bruevich Saint-Petersburg State University of Telecommunications Saint-Petersburg Russia Danang Architecture University Da Nang Viet Nam University of Telecommunications Department of Communication Networks and Data Transmission at Bonch-Bruevich Saint-Petersburg State Russia University of Science and Technology The University of Danang Da Nang Viet Nam The University of Danang University of Science and Technology Information Technology Faculty Danang Viet Nam V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Institute of Control Sciences of Russian Academy of Sciences Russia Bonch Bruevich Saint Petersburg State University of Telecommunications Department of Programming Engineering and Computer Science Russia

ISBN: (纸本)9791188428120

The increasing prevalence of botnet attacks in IoT networks has led to the development of deep learning techniques for their detection. However, conventional centralized deep learning models pose challenges in simultaneously ensuring user data privacy and detecting botnet attacks. To address this issue, this study evaluates the efficacy of Federated Learning (FL) in detecting IoT malware traffic while preserving user privacy. The study employs N-BaIoT, a dataset of real-world IoT network traffic infected by malware, and compares the effectiveness of FL models using Convolutional Neural Network, Long Short-Term Memory, and Gated Recurrent Unit models with a centralized approach. The results indicate that FL can achieve high performance in detecting abnormal traffic in IoT networks, with the CNN model yielding the best results among the three models evaluated. The study recommends the use of FL for IoT malware traffic detection due to its ability to preserve data privacy. © 2024 Global IT Research Institute - GIRI.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Trade-off Between Execution Time and Memory Consumption in Fuzzy Average-Utility Mining

Trade-off Between Execution Time and Memory Consumption in F...

引用

International Conference on Awareness science and Technology (iCAST)

作者： Tzung-Pei Hong Meng-Ping Ku Yu-Chuan Tsai Wei-Ming Huang Shu-Min Li Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan Library and Information Center National University of Kaohsiung Kaohsiung Taiwan Department of Electrical and Control China Steel Inc. Kaohsiung Taiwan

Fuzzy utility mining considers high-utility fuzzy itemsets as valuable knowledge by integrating quantities of items, their profits, and meaningful fuzzy terms derived by quantities according to membership functions. In fuzzy utility mining, the utility value of a fuzzy itemset in a transaction will always be greater than or equal to those of its subsets, so the measurement of fuzzy utility is an unfair evaluation method. Therefore, the fuzzy average-utility mining problem was issued in 2020, and three solutions were proposed to solve fuzzy average-utility itemsets as two-phase fuzzy average-utility algorithm (TPFAU), two-phase method with tree-based structure (HFAUIM) and one-phase approach with tree-based structure (FHFAUIM), respectively. The second and third methods decrease the candidates generated compared to the first. However, the sorting strategy for mining steps for the last two approaches is based on the frequencies of items in a database and then inserting items of a transaction into a tree in descending order of their frequencies, thus spending more computing time on deriving the actual fuzzy utility value of itemsets. To overcome the above-mentioned problem, this paper adopts a different sorting strategy with a tree-based structure and then by using it to design an algorithm named IFHFAUIM to mine high fuzzy average-utility itemsets. It reduces the storage of required fuzzy utility values in tree nodes and recovers them through tree traversal. Computational experiments show that the proposed method could make a good trade-off between execution time and memory usage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using the Pre-Large Concept for Maintaining High Fuzzy Utility Itemsets

Using the Pre-Large Concept for Maintaining High Fuzzy Utili...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Tzung-Pei Hong Wei-Teng Hung Yu-Chuan Tsai Wei-Ming Huang Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung Taiwan Library and Information Center National University of Kaohsiung Kaohsiung Taiwan Department of Electrical and Control China Steel Inc. Kaohsiung Taiwan

Utility mining is a popular research field in data mining. It uses item utilities and quantities to fit more into real applications. Fuzzy utility mining has also been proposed to reflect the linguistics of human perceptron for item association. In the past, we proposed a fast-up date-based (FUP-based) approach to maintain high fuzzy utility itemsets for continuously coming transaction data. This paper proposes an algorithm that applies the pre-large strategy on fuzzy utility mining to raise the maintenance performance. Nine cases are considered to maintain the current high fuzzy utility itemsets based on the fuzzy upper-bound utility. The results of the numerical experiments show that our proposed algorithm has better efficiency than the batch and the FUP-based approach in the execution time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self‑Generated Buried Submicrocavities for High‑Performance Near‑Infrared Perovskite Light‑Emitting Diode

引用

Nano-Micro Letters 2023年第8期15卷 355-367页

作者： Jiong Li Chenghao Duan Qianpeng Zhang Chang Chen Qiaoyun Wen Minchao Qin Christopher C.S.Chan Shibing Zou Jianwu Wei Zuo Xiao Chuantian Zuo Xinhui Lu Kam Sing Wong Zhiyong Fan Keyou Yan School of Environment and Energy State Key Lab of Luminescent Materials and DevicesGuangdong Provincial Key Laboratory of Solid Wastes Pollution Control and RecyclingSouth China University of TechnologyGuangzhou 510000People’s Republic of China Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyClear Water BayKowloonHong KongPeople’s Republic of China Department of Physics The Chinese University of Hong KongShatinHong KongPeople’s Republic of China Department of Physics The Hong Kong University of Science and TechnologyClear Water BayKowloon 999077Hong KongPeople’s Republic of China School of Chemistry and Chemical Engineering Guangxi UniversityNanning 530004People’s Republic of China Center for Excellence in Nanoscience(CAS) Key Laboratory of Nanosystem and Hierarchical Fabrication(CAS)National Center for Nanoscience and TechnologyBeijing 100190People’s Republic of China

ABSTRACT Embedding submicrocavities is an effective approach to improve the light out-coupling efficiency(LOCE)for planar perovskite light-emitting diodes(PeLEDs).In this work,we employ phenethylammonium iodide(PEAI)to trigger the Ostwald ripening for the downward recrystallization of perovskite,resulting in spontaneous formation of buried submicrocavities as light output *** simulation suggests the buried submicrocavities can improve the LOCE from 26.8 to 36.2%for near-infrared ***,PeLED yields peak external quantum efficiency(EQE)increasing from 17.3%at current density of 114 mA cm^(−2)to 25.5%at current density of 109 mA cm^(−2)and a radiance increasing from 109 to 487 W sr^(−1)m^(−2)with low *** turn-on voltage decreased from 1.25 to 1.15 V at 0.1 W sr^(−1)m^(−2).Besides,downward recrystallization process slightly reduces the trap density from 8.90×10^(15)to 7.27×10^(15)cm^(−3).This work provides a self-assembly method to integrate buried output coupler for boosting the performance of PeLEDs.

关键词： Perovskite light-emitting diodes Downward recrystallization Buried submicrocavities Light out-coupling efficiency Radiative recombination

来源：评论

学校读者我要写书评

暂无评论

Image Classification with Small Datasets: Overview and Benchmark

arXiv

引用

arXiv 2022年

作者： Brigato, Lorenzo Barz, Björn Iocchi, Luca Denzler, Joachim Department of Computer Control and Management Engineering Sapienza University of Rome Italy Department of Mathematics and Computer Science Friedrich Schiller University Jena Germany

Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a systematic and extensive overview of the state of the art, and a common benchmark to allow for objective comparisons between published methods. This article addresses both issues. First, we systematically organize and connect past studies to consolidate a community that is currently fragmented and scattered. Second, we propose a common benchmark that allows for an objective comparison of approaches. It consists of five datasets spanning various domains (e.g., natural images, medical imagery, satellite data) and data types (RGB, grayscale, multispectral). We use this benchmark to re-evaluate the standard cross-entropy baseline and ten existing methods published between 2017 and 2021 at renowned venues. Surprisingly, we find that thorough hyper-parameter tuning on held-out validation data results in a highly competitive baseline and highlights a stunted growth of performance over the years. Indeed, only a single specialized method dating back to 2019 clearly wins our benchmark and outperforms the baseline classifier. © 2022, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Data poisoning: issues, challenges, and needs

Data poisoning: issues, challenges, and needs

引用

7th IET Smart Cities Symposium (SCS 2023)

作者： Mohammad Aljanabi Alaa Hamza Omran Maad M Mijwil Mostafa Abotaleb El-Sayed M. El-kenawy Sahar Yousif Mohammed Abdelhameed Ibrahim Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science & Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：