检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Chen, Jianyu Wang, Zhongyuan Zeng, Kangli Zou, Qin Liang, Chao Xu, Zengmin Wu, Gang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin541004 China College of Information Engineering Tarim University Alar843300 China Shenzhen518060 China

Gait recognition attracts extensive attention as biotechnology for identifying subjects from a distance without their cooperation. Since gait is not easily camouflaged and successive motion trajectories facilitate the identification of subjects, capturing critical temporal information is particularly important for gait recognition. Compared with architectures that extract temporal features individually and then perform late fusion, 3D CNNs are more suitable for extracting continuous relationships between frames in gait sequences. Hence, in this paper, we propose a novel 3D architecture called robust spatiotemporal 3D convolutional neural network (RST3D) to collaboratively extract spatiotemporal correlations in gait sequences. Specifically, we propose a full-scale 3D convolutional block that fully considers the orthogonal relationships in multiple dimensions based on the original 3D convolution, thus it can extract more potential gait spatiotemporal features. Next, to further enhance the temporal modeling capability of the network, we propose a temporal pyramidal attention block to capture the most discriminative motion representations from different ranges of gait silhouettes. Experiments on CASIA-B, OUMVLP, GREW and Gait3D datasets demonstrate that our proposed method outperforms the state-of-the-art gait methods. Furthermore, compared to the existing 3D CNN-based gait recognition methods, our approach exhibits superior performance in several complex gait conditions. © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Maser: Multi-Order Attention and Semantic-Enhanced Representation Model for Complex Text Recommendation

SSRN

引用

SSRN 2023年

作者： Lai, Pei-Yuan Dai, Qing-Yun Liao, De-Zhang Yang, Zhe-Rui Liao, Xiao-Dong Wang, Chang-Dong School of Information Engineering Guangdong University of Technology Guangzhou China South China Technology Commercialization Center Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

In some recommendation platforms, the recommended items are composed of complex text, and the target users are also described by the complex text. These texts are usually long, highly specialized, logically structured, and have significant differences, such as recommending technical demands of enterprises to researchers. Although some recommendation methods based on text representation can be used to solve this problem, such as Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTM), they may encounter challenges from different perspectives, e.g., path connectivity of representations, and the relationship between representations and recommended items. The complex text recommendation is an important problem that remains largely unsolved. In order to overcome the aforementioned challenges, we propose a novel complex text recommendation model via Multi-order Attention and Semantic Enhanced Representation (MASER). Specifically, we extend the entity information of users and items with encyclopedia data. Semantic enhancement is adopted to build a knowledge graph, and a multi-order attention mechanism is used to distinguish the importance of extension. Extensive experiments have been conducted on real datasets, confirming the advantages of the MASER model and the attention mechanism's effectiveness on complex text recommender systems. © 2023, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Dual efficient reversible data hiding using Hamming code and OPAP

引用

Journal of Information Security and Applications 2023年 76卷

作者： Kim, Cheonshik Yang, Ching-Nung Zhou, Zhili Jung, Ki-Hyun Department of Computer Engineering Sejong University Seoul Korea Republic of Department of Computer Science and Information Engineering National Dong Hwa University Taiwan School of Computer and Software & Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210000 China Department of Software Convergence Andong National University Gyeongbuk 36729 Korea Republic of

Dual image based RDH is a separate research area of the traditional RDH method, which has been continuously studied by several researchers over the past decade. In the research of dual RDH, extension of the traditional RDH algorithm or methods of improving the existing DH algorithm to dual RDH have been proposed. Hamming code (HC) is a method used as a DH method, but it is not applied to RDH. In this paper, we propose a dual RDH method using Hamming codes. Previously, Jana et al. proposed HC(7,4)-based dual RDH, but in terms of performance, it showed a weakness that did not reach the performance of the previously proposed RDH. In this paper, we propose a dual RDH scheme using Hamming code and OPAP. As previously suggested by Jana et al. The performance of dual RDH of HC(7,4) has been greatly improved. In this paper, HC(3,1) is used to significantly improve data hiding capacity and image quality, i.e., since this method conceals 2-bit secret data in 3 pixels using the OPAP method and the Hamming code, the embedding rate is 1.0 bpp and the average of the two marked images is measured as 51 dB. With the efficiency of the proposed coding method, it is possible to maintain high image quality. As a result of the experiment, our proposed data hiding capacity greatly outperformed the method proposed by Jana et al., and compared to the existing methods, it was almost similar in capacity and showed good performance in terms of image quality. © 2023 Elsevier Ltd

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Exploring Innovations in Autonomous robotics and Mechatronics: Application in Manufacturing and Healthcare

Exploring Innovations in Autonomous Robotics and Mechatronic...

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： T.Grace Shalini L. Ganeshabu Priyanka Chemudugunta Nagendar Yamsani Ch.Ashok Kumar A. Athiraja Department of Computational Intelligence School of Computing SRM Institute of Science and Technology (SRMIST)Kattankulathur Chengalpattu Tamil Nadu India Department of Robotics and Automation Rajalakshmi Engineering College Rajalakshmi Nagar Thandalam Mevalurkuppam Chennai Tamil Nadu India Department of Robotics and Automation Karpaga Vinayaga College of Engineering and Technology Chengalpattu Tamil Nadu India Department of School of Computer Science and Artificial Engineering SR University Warangal India Department of Mechanical Engineering Malla Reddy Engineering College Main Campus Maisammaguda Hyderabad Telangana India Department of CSE (AIML) Malla Reddy College of Engineering Secunderabad Telangana India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Autonomous robotics and mechatronics have drastically changed the manufacturing and healthcare sectors by increasing productivity, precision, and flexibility. This work addresses the pressing need for new methods to advance these sectors by merging intelligent algorithms with autonomous systems. A hybrid strategy was employed, combining Deep Reinforcement Learning (DRL) and Adaptive Control Systems (ACS), to develop and optimize robotic operations. Extensive studies were conducted to assess the success of this strategy, which demonstrated a 25% reduction in operating expenses and a 30% increase in production efficiency in manufacturing settings. The method produced a precision rate of about 99% in the healthcare industry, which is significantly better than the 93% average of current systems. It also reduced patient recovery times by an estimated 20%. These results highlight the improved performance and promise of ACS with DRL combination in autonomous robotics, which may have revolutionary implications for the manufacturing and healthcare industries. The success, highlighted by economic and medical benefits, demonstrates the efficacy of our methodology and provides a strong platform for future developments in autonomous robotics and mechatronics.

关键词： Industries Technological innovation Mechatronics Service robots Scalability Medical services Manufacturing Adaptive control Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

LGDB-Net: Dual-Branch Path for Building Extraction from Remote Sensing Image

LGDB-Net: Dual-Branch Path for Building Extraction from Remo...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ronghuan Zhang Jing Zhao Ming Li Qingzhi Zou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural Networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch Network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity.

关键词： Accuracy Computational modeling Memory management Neural networks Feature extraction Transformers Sensors Data mining Computational complexity Remote sensing

来源：评论

学校读者我要写书评

暂无评论

High-Efficiency and High-Current GaN-Based Microwave Rectifier for Wireless Strain Sensing and Monitoring

High-Efficiency and High-Current GaN-Based Microwave Rectifi...

引用

作者： Liu, Tao Li, Yang Yang, Jia-Yi Wang, Ting-Ting Wang, Xiao Yang, Lin-An Dickey, Michael Ao, Jin-Ping Hao, Yue Xidian University Key Laboratory for Wide Band-Gap Semiconductor Materials and Devices School of Microelectronics Xi'an710071 China Jiangnan University Engineering Research Center of Internet of Things Technology Applications Ministry of Education Department of Electronic Engineering Wuxi214122 China Xi'an University of Science and Technology College of Computer Science and Technology Xi'an710064 China North Carolina State University Department of Chemical and Biomolecular Engineering RaleighNC27695 United States

In this article, a gallium nitride (GaN) Schottky barrier diode (SBD)-based microwave rectifier with high efficiency, current, and power bandwidth is proposed for wireless strain sensing and monitoring. Solutions including semiconductor devices, rectification circuits, and sensing mechanisms are discussed. A microwave rectifier working at 928 MHz is designed for wireless rectification strain sensing, with a measured power efficiency over 85% and a load resistance lower to 40 Omega based on a customized quasi-vertical GaN SBD. The finger layout and TiN anode make the SBD series resistance reduced to 1.81~Omega , but saturation current enhanced to 11.8 nA, which significantly reduces rectification loss when the load resistance is small. Finally, a rectification strain sensor (RSS) is proposed by dielectric coupling the rectifier and a piezo-permittivity liquid metal elastomer foam (LMEF), with a measured relative output power variation and wireless working distance over 437%/mm and 3 m, respectively. © 1963-2012 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Improving Smart Agriculture Through the Use of Machine Learning to Offer Tailored Crop Forecasts

引用

Remote Sensing in Earth Systems sciences 2024年第1期8卷 74-83页

作者： Patil, R.N. Maroor, Jnaneshwar Pai Dhanke, Jyoti A. Chunduru, Madhava Rao Singh, Mangal Jangir, Pradeep Upadhyay, Shrikant Department of Mechanical Engineering Bharati Vidyapeeth’s College of Engineering Lavale Pune India Department of Business Administration Nitte Institute of Professional Education Nitte (Deemed to Be University) Karnataka Mangaluru India Department of Engineering Science (Mathematics) Bharati Vidyapeeth’s College of Engineering Lavale Pune India Department Of Computer Science And Engineering Koneru Lakshmaiah Educational Foundation Vaddeswaram AP Guntur District India Department of Electronics and Telecommunication Engg. Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Pune India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

It is not possible to identify crop illnesses by examining each disease independently. Users may only get forecasts for the most anticipated illnesses with the use of a robust analytic methodology. This study presents a method that can collect, analyze, and identify crop health information all on one platform using an IoT and machine learning-based approach. Food security and the provision of essential raw materials for several industries are both supported by agriculture, which is the most important and basic vocation. Improved crop yields, thanks to new innovative agricultural practices, mean less water wasted and more money in the bank. An intelligent irrigation system that uses a machine learning algorithm to forecast a crop’s water needs is the suggested model. One such rapidly evolving invention is the Internet of Things (IoT), which is now spreading its wings across all geographies. Technological innovation is reaching a new level of practicality in agriculture with the rise of embedded PCs like Arduino. Soil quality monitoring using Arduino, several sensors, and an Android app is shown and accomplished in this study. Temperature, soil moisture level, ammonia, and carbon content limit soil quality in this study. Arduino is used as both a worker and an information processing device, and it is in charge of sensor security. The terminal device is an Android phone. Producers may improve agricultural yields by collecting and analyzing data on weather, soil, seed, and yields of crops, moisture, and gusts of wind in specific areas. Furthermore, a flask-built GUI was used to present crop forecasts derived from a bespoke recommender system. Because of its adaptable design, the system may one day be able to discover the suggested items of other areas. This article uses targeted agricultural data to create five machine-learning approaches that are comparable to one another and to compare and contrast them. © The Author(s), under exclusive licence to Springer Nature Swit

关键词： Decision navigation systems Internet of Things (IoT) Irrigation systems Machine learning algorithms Sensors

来源：评论

学校读者我要写书评

暂无评论

Sparse is Enough in Fine-tuning Pre-trained Large Language Models

arXiv

引用

arXiv 2023年

作者： Song, Weixi Li, Zuchao Zhang, Lefei Zhao, Hai Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Luojia Laboratory Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscillations in the loss landscape and the quasi-sparsity in gradient distribution. Based on this, we propose a gradient-based sparse finetuning algorithm, named Sparse Increment Fine-Tuning (SIFT), and validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning. The code is accessible at https://***/song-wx/SIFT. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Text Semantics to Flexible Design: A Residential Layout Generation Method Based on Stable Diffusion Model

arXiv

引用

arXiv 2025年

作者： Qiu, Zijin Liu, Jiepeng Xia, Yi Qi, Hongtuo Liu, Pengkun Ministry of Education Chongqing400045 China School of Civil Engineering Chongqing University Chongqing400045 China Hong Kong Center for Construction Robotics The Hong Kong University of Science and Technology Hong Kong School of Civil Engineering Xinyu University Jiangxi338004 China Department of Civil and Environmental Engineering Carnegie Mellon University PittsburghPA15213 United States

Flexibility in the AI-based residential layout design remains a significant challenge, as traditional methods like rule-based heuristics and graph-based generation often lack flexibility and require substantial design knowledge from users. To address these limitations, we propose a cross-modal design approach based on the Stable Diffusion model for generating flexible residential layouts. The method offers multiple input types for learning objectives, allowing users to specify both boundaries and layouts. It incorporates natural language as design constraints and introduces ControlNet to enable stable layout generation through two distinct pathways. We also present a scheme that encapsulates design expertise within a knowledge graph and translates it into natural language, providing an interpretable representation of design knowledge. This comprehensibility and diversity of input options enable professionals and non-professionals to directly express design requirements, enhancing flexibility and controllability. Finally, experiments verify the flexibility of the proposed methods under multimodal constraints better than state-of-the-art models, even when specific semantic information about room areas or connections is incomplete. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Mining World Indicators for Analyzing and Modeling the Development of Countries

引用

ACM/IMS Transactions on Data science 2021年第4期2卷 1–27页

作者： Huang, Hong Chi, Mingyuan Song, Yu Jin, Hai The National Engineering Research Center for Big Data Technology and System Key Laboratory of Service Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

The world indicators released by the World Bank or other organizations usually give the basic public knowledge about the world. However, separate and static index lacks the complex interplay among different indicators and thus cannot help us have an overall understanding of the world. To this end, we study the world indicators from a different angle. Firstly, we discover that there exist correlations between indicators either from a static view or from a dynamic view. Moreover, taking the trade and diplomatic relationships into consideration, we construct a multi-relational network to depict the interactions between different countries, and propose a Multiple Relations to Vector (MR2vec) model to study world indicators from a network perspective. The experimental results show the changes of world indicators are predictable with the proposed model, and our proposed MR2vec has wide adaptability in predicting multi-relation networks. © 2022 Copyright held by the owner/author(s).

关键词： Data mining

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：