检索结果-内蒙古大学图书馆

Tensor MIMO Perfect-Equalizer Design Using New Projection-Based Method and Approximation-Error Analysis

IEEE Systems Journal 2024年第1期18卷 668-679页

作者： Chang, Shih-Yu Wu, Hsiao-Chun Kao, Yi-Chih San Jose State University Department of Applied Data Science San JoseCA95192 United States Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Chungli32003 Taiwan National Yang Ming Chiao Tung University Network and System Division Information Technology Service Center Hsinchu30010 Taiwan

As real environments are quite complex, multiple-input-multiple-output (MIMO) channels should be characterized by the multidimensional-multirelational models. Tensor linear algebra has been emerging as a powerful and promising tool for such MIMO channel modeling and estimation. However, to the best of our knowledge, there hardly exists any algebraic framework of MIMO channel equalization when the channel is modeled as an arbitrary-dimensional transfer tensor (a tensor whose entries are all rational z-functions). In this work, we first propose a new method based on the projection, namely, 'projection-based method,' to determine whether a given transfer tensor is a full-rank tensor or not and carry out the inversion of an invertible transfer tensor. Our idea is employing the projection subspace of the system transfer tensor to simplify the pertinent inversion process. Second, we design the finite-impulse-response (FIR) realization to approximate the inverse of an arbitrary transfer tensor such that all entries of the approximated inverse transfer tensor are finite-degree polynomials of z. Third, we also analyze the computational and memory complexities required by our proposed new projection-based method for checking the full-rank condition of a given transfer tensor and for undertaking the tensor inversion. Our developed new theories and analysis in this work can be applied to determine the FIR model-orders of an approximated inverse MIMO transfer tensor often encountered in signal processing, control, communications, etc. © 2007-2012 IEEE.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

Single-shot single-beam coherent Raman scattering thermometry based on optically induced air lasing

引用

Light(science & applications) 2024年第12期13卷 3253-3260页

作者： Xu Lu Yewei Chen Francesco Mazza Siyi He Zihan Li Shunlin Huang Quanjun Wang Ning Zhang Bo Shen Yuzhu Wu Jinping Yao Ya Cheng State Key Laboratory of High Field Laser Physics Shanghai Institute of Optics and Fine MechanicsChinese Academy of SciencesShanghai 201800China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Faculty of Aerospace Engineering Delft University of TechnologyKluyverweg 12629 HS DelftThe Netherlands Institute of Modern Optics Nankai UniversityTianjin 300350China School of Microelectronics Shanghai UniversityShanghai 200444China

Thermometric techniques with high accuracy,fast response and ease of implementation are desirable for the study of dynamic combustion environments,transient reacting flows,and non-equilibrium ***,single-shot singlebeam coherent Raman scattering(SS-CRS)thermometry is developed,for the first time to our knowledge,by using air lasing as a *** show that the air-lasing-assisted CRS signal has a high signal-to-noise ratio enabling single-shot measurements at a 1 kHz repetition *** SS-CRS thermometry consistently exhibits precision of<2.3%at different temperatures,but the inaccuracy grows with the increase in *** high measurement repeatability,1 kHz acquisition rate and easy-to-implement single-beam scheme are achieved thanks to the unique temporal,spectral and spatial characteristics of air *** work opens a novel avenue for high-speed CRS thermometry,holding tremendous potential for fast diagnostics of transient reacting flows and plasmas.

关键词： scattering lasing beam

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Motion Intention Detection for Robotic Rehabilitation: Evaluating Classification and Regression Algorithms

引用

SN computer science 2024年第8期5卷 1-14页

作者： Khan, Abdul Manan Khan, Fatima Dwivedi, Anshu Kumar Semwal, Vijay Bhaskar Martha, Sheshikala Bijalwan, Vishwanath Department of Aerospace Engineering University of Bristol Bristol United Kingdom Graduate School of Cancer Science and Policy National Cancer Center Ilsan South Korea School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of CSE Maulana Azad National Institute of Technology Bhopal India School of Computer Science & amp Artificial Intelligence SR University Warangal Warangal India Department of Electrical and Electronics Engineering University of West London London United Kingdom

Rehabilitation robots have shown significant efficacy in restoring lost motor functions in stroke survivors by providing compliant assistance during rehabilitation tasks. However, accurately understanding the desired motion intention (DMI) of the subjects is a significant challenge in providing effective robotic assistance. This work aims to determine the desired motion intention (DMI) for compliant robotic assistance through the analysis of upper limb motions using electroencephalography (EEG) signals. A group of fifteen individuals who were in good health carried out six distinct exercises. These movements were categorized using decision trees, random forest, and deep learning algorithms. Using deep learning, we achieved the highest accuracy rates, reaching 82% for movement-to-movement classification and 90% for movement-to-rest classification. The random forest method achieved superior performance compared to the other algorithms in regression tests, with an accuracy rate of 83%. The results demonstrate the effectiveness of our proposed EEG-based classification and regression techniques in detecting DMI for robotic help in *** study was conducted with a small sample size, exclusively involving healthy subjects, which is a critical factor to consider. This may limit the generalizability of the results, particularly when populations with motor impairments are taken into account. However, the study offers valuable insights into the potential of the EEG-based models for real-time rehabilitation applications despite this limitation. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： C-RNN Deep learning Desired motion intention EEG signals Machine learning Rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Offline Handwritten Signature Analysis for Age Classification using Deep Features 4

Offline Handwritten Signature Analysis for Age Classificatio...

引用

4th International Conference for Emerging Technology, INCET 2023

作者： Kumar, Sathish Gornale, Shivanand Patil, Abhijit Rashmi, S. Rani Channamma University Department of Computer Science Belagavi India Gulbarga University PG Center Halhalli Department of Computer Science Line 3 Kalaburagi India West Virginia University Department of Mechanical and Aerospace Engineering MorgantownWV United States

ISBN: (纸本)9798350335750

Handwritten Signatures are prominent and convincing behavioral biometric data, used in many authentication application areas such as commercial, financial data, document analysis, health care, and forensic science etc. Different writing styles, cursive characters, and inconsistency in the shapes make it tougher to identify the writer from a handwritten signature. This problem remains still a challenging task, because of the considerable intra-class variations in handwriting. The proposed work focuses on the classification of the age using the different handwritten signatures collected from male and female writers of different age groups (adolescents (18-60)). In-house of total 6010 signatures were collected from 610 individuals. Experiments were carried out using well known deep neural architecture namely VGG16 model. Classification task carried out in end-to-end framework. The proposed work achieves comparatively better results than the existing methods respectively. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Enhancing action discrimination via category-specific frame clustering for weakly-supervised temporal action localization

引用

Frontiers of Information Technology & Electronic engineering 2024年第6期25卷 809-823页

作者： Huifen XIA Yongzhao ZHAN Honglin LIU Xiaopeng REN School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212013China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agricultural Applications Zhenjiang 212013China Changzhou Vocational Institute of Mechatronic Technology Changzhou 213164China

Temporal action localization (TAL) is a task of detecting the start and end timestamps of action instances and classifying them in an untrimmed video. As the number of action categories per video increases, existing weakly-supervised TAL (W-TAL) methods with only video-level labels cannot provide sufficient supervision. Single-frame supervision has attracted the interest of researchers. Existing paradigms model single-frame annotations from the perspective of video snippet sequences, neglect action discrimination of annotated frames, and do not pay sufficient attention to their correlations in the same category. Considering a category, the annotated frames exhibit distinctive appearance characteristics or clear action ***, a novel method to enhance action discrimination via category-specific frame clustering for W-TAL is proposed. Specifically,the K-means clustering algorithm is employed to aggregate the annotated discriminative frames of the same category, which are regarded as exemplars to exhibit the characteristics of the action category. Then, the class activation scores are obtained by calculating the similarities between a frame and exemplars of various categories. Category-specific representation modeling can provide complimentary guidance to snippet sequence modeling in the mainline. As a result, a convex combination fusion mechanism is presented for annotated frames and snippet sequences to enhance the consistency properties of action discrimination,which can generate a robust class activation sequence for precise action classification and localization. Due to the supplementary guidance of action discriminative enhancement for video snippet sequences, our method outperforms existing single-frame annotation based methods. Experiments conducted on three datasets (THUMOS14, GTEA, and BEOID) show that our method achieves high localization performance compared with state-of-the-art methods.

关键词： Weakly supervised Temporal action localization Single-frame annotation Category-specific Action discrimination

来源：评论

学校读者我要写书评

暂无评论

SciMRC: Multi-perspective Scientific Machine Reading Comprehension 30

SciMRC: Multi-perspective Scientific Machine Reading Compreh...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Xiao Zheng, Heqi Nie, Yuxiang Huang, Heyan Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China State Grid Smart Grid Research Institute Co. Ltd. China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9782493814104

Scientific Machine Reading Comprehension (SMRC) aims to facilitate the understanding of scientific texts through human-machine interactions. While existing dataset has significantly contributed to this field, it predominantly focus on single-perspective question-answer pairs, thereby overlooking the inherent variation in comprehension levels among different readers. To address this limitation, we introduce a novel multi-perspective scientific machine reading comprehension dataset, SciMRC, which incorporates perspectives from beginners, students, and experts. Our dataset comprises 741 scientific papers and 6,057 question-answer pairs, with 3,306, 1,800, and 951 pairs corresponding to beginners, students, and experts respectively. Extensive experiments conducted on SciMRC using pre-trained models underscore the importance of considering diverse perspectives in SMRC and highlight the challenging nature of our scientific machine comprehension tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Key Clues Guided Video Character Social Relationship Recognition Enhanced by LLM

Key Clues Guided Video Character Social Relationship Recogni...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Wenlong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Video Character Social Relationship Recognition (VCSRR) requires a comprehensive consideration about spatio-temporal and multi-modal clues in videos. Most existing methods mainly focus on integrating multi-modal clues and modeling interactions among characters. However, they fail to discover key clues in the complex video data or fully understand the clues related to social relationships. In this article, we propose a novel Large Language Model Enhanced Key Clues Selection (LEKCS) framework to address the aforementioned issues. The core of LE-KCS is to mine multi-scale key clues from the perspectives of time, space and multi-modality, then transfer the knowledge about social relationships of the Large Language Model to VCSRR for understanding the selected clues. We evaluated LEKCS on the MovieGraphs dataset and the experimental results indicate that our proposed LE-KCS achieves state-of-the-art performance. © 2025 IEEE.

关键词： large language model Social relationship recognition video understanding

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Strategic Foresight: Anticipating Future Trends and Modelling Business Strategies

AI-Driven Strategic Foresight: Anticipating Future Trends an...

引用

2024 International Conference on Decision Aid sciences and applications, DASA 2024

作者： Qader Ismail Alnajem, Ahmed Abdel Ibrahim, Amer Abdulrahman, Mayasa M. Abdulrazak Al-Kubaisi, Abdulrazak A. Tawfeq, Jamal Fadhil Khishe, Mohammad Saeed, Ali Baghdad College of Economic Sciences Business Administration Department Iraq College of Information Technology Department of Computer Science and Software Engineering United Arab Emirates College of Engineering Computer Engineering Department University of Baghdad Baghdad Iraq Medical Technical College Department of Medical Instrumentation Technical Engineering Al-Farahidi University Baghdad00965 Iraq Yuan Ze University Innovation Center for Artificial Intelligence Applications Taiwan Jadara University Jadara Research Center Jordan Northern Technical University Computer Center Ninevah Iraq

ISBN: (纸本)9798350369106

In a generation characterized with the aid of speedy technological advancements, socio-monetary shifts, and environmental challenges, groups need to undertake proactive strategies to stay aggressive and resilient. Strategic foresight, which entails expecting destiny tendencies and modeling enterprise techniques, accordingly, emerges as a vital device in navigating this uncertainty. The trouble this have a look at addresses is the growing trouble groups face in predicting and making ready for destiny disruptions the use of conventional forecasting techniques. The number one goals of this have a look at are to discover the important thing methodologies and gear of strategic foresight, display how those techniques may be implemented to assume destiny tendencies, and offer insights on integrating foresight into enterprise approach formulation. This has a look at contributes to the present frame of information with the aid of using providing a complete evaluation of strategic foresight techniques, which includes environmental scanning, situation planning, the Delphi method, fashion evaluation, SWOT and PESTLE evaluation, and era street mapping. Research findings show that forward-looking strategies provide an organization with the ability to identify potential risks and opportunities, develop adaptive strategies, and achieve long-term growth Specifically, strategic organizations using anticipation reports a 30% increase in the ability to anticipate market fluctuations, a 25% improvement in strategic haste and a 20% reduction in unexpected disruptions, of consumer goods etc. Case studies of various industries demonstrate the practical application and usefulness of forecasting in real-world situations The study concludes that incorporating forward-looking strategies into business planning does not that it not only prepares organizations for future challenges but empowers them to shape their future and ensure sustainable competitive advantage. © 2024 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

A General Chessboard Image Inpainting Method

A General Chessboard Image Inpainting Method

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Xinghui Zhang Yajie Wang Song Liu Yanyan Wu School of Computer Science Shenyang Aerospace University Shenyang China Engineering Training Center Shenyang Aerospace University Shenyang China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

With the continuous advancement of artificial intelligence technology, image inpainting, as an important branch of computer vision, has received widespread attention. The issue that lighting conditions significantly affect the identification and positioning of chess pieces in existing chess-playing robots is addressed in this paper, which proposes a general chessboard image inpainting method—Adversarial Masked Autoencoder (AMAE). This method, which combines Generative Adversarial Networks and Masked Auto-Encoders for joint training, is designed to enhance the quality of chessboard images. First, the masked autoencoder is pre-trained using chessboard images. Then, the pre-trained masked autoencoder is jointly trained with generator and discriminator. The adversarial principle of Generative Adversarial Networks is used to guide the training of the masked Autoencoder. A chessboard image with both clear texture details and global structural information is obtained. Finally, a dataset is created by collecting a large number of Go and Chinese chessboard images under different lighting conditions to validate the effectiveness of the proposed method.

关键词： Training computer vision Autoencoders Lighting Generative adversarial networks Generators Image restoration Data mining Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Precision Harvesting in Cluttered Environments: Integrating End Effector Design with Dual Camera Perception

arXiv

引用

arXiv 2025年

作者： Koe, Kendall Shah, Poojan Kalpeshbhai Walt, Benjamin Westphal, Jordan Marri, Samhita Kamtikar, Shivani Nam, James Seungbum Uppalapati, Naveen Kumar Krishnan, Girish Chowdhary, Girish Computer Science UIUC United States Mechanical Science and Engineering UIUC United States Electrical and Computer Engineering UIUC United States National Center for Supercomputing Applications UIUC United States

Due to labor shortages in specialty crop industries, a need for robotic automation to increase agricultural efficiency and productivity has arisen. Previous manipulation systems perform well in harvesting in uncluttered and structured environments. High tunnel environments are more compact and cluttered in nature, requiring a rethinking of the large form factor systems and grippers. We propose a novel codesigned framework incorporating a global detection camera and a local eye-in-hand camera that demonstrates precise localization of small fruits via closed-loop visual feedback and reliable error handling. Field experiments in high tunnels show our system can reach an average of 85.0% of cherry tomato fruit in 10.98s on average. © 2025, CC BY-NC-ND.

关键词： Fruits

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：