检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yu, Feifan Cong, Wenyuan Chen, Xinmin Lin, Yue Wang, Jiqiang Zhejiang Provincial Engineering Research Centre for Special Aircrafts Ningbo315336 China Ningbo Institute of Materials Technology & Engineering CAS Ningbo315201 China University of Chinese Academy of Sciences Beijing101408 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China

Autonomous landing of UAVs in high sea states requires the UAV to land exclusively during the ship deck's "rest period," coinciding with minimal movement. Given this scenario, determining the ship's "rest period" based on its movement patterns becomes a fundamental prerequisite for addressing this challenge. This study employs the Long Short-Term Memory (LSTM) neural network to predict the ship's motion across three dimensions: longitudinal, transverse, and vertical waves. In the absence of actual ship data under high sea states, this paper employs a composite sine wave model to simulate ship deck motion. Through this approach, a highly accurate model is established, exhibiting promising outcomes within various stochastic sine wave combination models. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Training-free image style alignment for self-adapting domain shift on handheld ultrasound devices

arXiv

引用

arXiv 2024年

作者： Zeng, Hongye Zou, Ke Chen, Zhihao Gao, Yuchong Chen, Hongbo Zhang, Haibin Zhou, Kang Wang, Meng Goh, Rick Siow Mong Liu, Yong Jiang, Chang Zheng, Rui Fu, Huazhu School of Information Science and Technology ShanghaiTech University Shanghai China Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai China University of Chinese Academy of Sciences Beijing China National Key Laboratory of Fundamental Science on Synthetic Vision College of Computer Science Sichuan University Chengdu China College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Beth Israel Deaconess Medical Center Harvard Medical School Boston United States Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Department of Orthopedics Zhongshan Hospital Fudan University Shanghai China Shanghai Engineering Research Center of Intelligent Vision and Imaging Shanghai China

Handheld ultrasound devices face usage limitations due to user inexperience and cannot benefit from supervised deep learning without extensive expert annotations. Moreover, the models trained on standard ultrasound device data are constrained by training data distribution and perform poorly when directly applied to handheld device data. In this study, we propose the Training-free Image Style Alignment (TISA) framework to align the style of handheld device data to those of standard devices. The proposed TISA can directly infer handheld device images without extra training and is suited for clinical applications. We show that TISA performs better and more stably in medical detection and segmentation tasks for handheld device data. We further validate TISA as the clinical model for automatic measurements of spinal curvature and carotid intima-media thickness. The automatic measurements agree well with manual measurements made by human experts and the measurement errors remain within clinically acceptable ranges. We demonstrate the potential for TISA to facilitate automatic diagnosis on handheld ultrasound devices and expedite their eventual widespread use. © 2024, CC BY-NC-SA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

MTPL-G2T: Graph-to-Text Generation Task Based on Mixed Template Prompt Learning

MTPL-G2T: Graph-to-Text Generation Task Based on Mixed Templ...

引用

2022 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent technology (WI-IAT)

作者： Jianhe Cen Kun Zhang Jingyuan Li Shiqi Sun Yuanzhuo Wang Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beijing Technology and Business University Beijing China

The Graph-to-Text(G2T) generation tasks are mainly done by pre-training and fine-tuning currently, but the drawback of fine-tuning is that it changes all parameters of the pre-trained model. In this paper, we aim to accomplish the text generation task through prompt learning so that no or a small number of model parameters can be changed. Also, we analyze the impact of three different prompt templates on the generation results. The results show that when the pre-trained language model is large (e.g., T5), prompt learning is competitive with finetuning, but the number of parameters that need to be modified for prompt learning is much smaller than for fine-tuning; meanwhile, compared with text templates and soft templates, using mixed prompt templates can make the model converge faster.

关键词： Training Intelligent agents Task analysis Tuning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based MIMO Transmission with Precoding and Radio Transformer Networks

引用

Procedia computer science 2021年 187卷 396-401页

作者： Wenqi Cui Anming Dong Yi Cao Chuanting Zhang Jiguo Yu Sufang Li School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan 250353 China Shandong Provincial Key Laboratory of Computer Networks Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250014 China School of Information Science and Engineering University of Jinan Jinan 250022 China Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia

In this paper, we study MIMO transmission schemes based on deep learning (DL). We propose a novel DL-based MIMO communication structure by combing a beamforming network at the transmitter side and a radio transformer network (RTN) at the receiver side. Compared with the classical DL-based MIMO communication systems, the interference is potentially mitigated by a precoding network and a RTN network, which is thus beneficial to improve the performance of signal detection. Simulation results show that the proposed scheme outperforms the classical MIMO transmission schemes in terms of bit error rate (BER).

关键词： Deep Learning Multiple-Input Multiple Output (MIMO) Precoding Radio Transformer Network

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning-Based Artificial Voice Box

A Novel Machine Learning-Based Artificial Voice Box

引用

Advanced Technologies in Intelligent Control, Environment, Computing & Communication engineering (ICATIECE), International Conference on

作者： Naveen Kumar Priya Nandihal Madhumala R B Piyush Kumar Pareek Nikshepa T Sowmya S R Department of Computer Applications (BCA) Dr NSAM First Grade College (Affiliated to Bangalore City University) Bengaluru Dept of Computer Science and Design Dayananda Sagar Academy of Technology and Management Bangalore Department of ISE Dayananda Sagar Academy of Technology and Management Bangalore Department of Artificial Intelligence and Machine Learning Nitte Meenakshi Institute of Technology Bengaluru Department of Information Science and Engineering Dayananda Sagar Academy of Technology and Management Bangalore

ISBN: (纸本)9781665493970

Patients may experience a great deal of discomfort while undergoing rigorous medical procedures for the identification of vocal abnormalities. As a result, there has been a lot of interest in automated speech recognition and disorder detection approaches in recent years, and these methods have shown to be effective. Voice recordings have been acquired from the Saarbruecken Voice Database for the purpose of this study. The signals undergo preprocessing using Hybrid Wiener Filter Discrete Wavelet Transforms in order to de-noise and eliminate any silence that may have been there (HWFDWT). Cat Swarm Optimization is used to extract features, and Mel Frequency Cepstrum Coefficients are taken into account (CSOMFCC). Classification using Modified Optimized Back Propagation Network Disorder voice Classification is then used to sort the features in the end (MOBPNDC). In terms of Accuracy, Precision, Recall, F-Measure, and Time period, the classification scheme beats the current Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN) approaches. The neural speech system is a gadget that enables individuals who are unable to talk to communicate their thoughts and emotions with the outside world. It is a piece of equipment that can record the electric pulses that are generated by the brain and turn them into a synthetic voice. - Provide an overview of the concept or solution that you want to build. The electrical activity of the brain will be recorded and then sent into a synthesiser. The Synthesizer will convert the signal into voice when it has finished decoding it. The voice that has been deciphered is then supplied to an artificial voice box. The brain's electrical activity is used to generate an artificial voice, which is then output via the box.

关键词： Support vector machines Backpropagation Wiener filters Synthesizers Transforms Speech recognition Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of the Use of Machine Learning Techniques to Optimize the Information Retrieval Process

A Comprehensive Analysis of the Use of Machine Learning Tech...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： S. Hemelatha Kalanandhini. G Prasad B. Chaudhari Rajeev Sharma Jambi Ratna Raja Kumar Dipannita Mondal Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Management Mangalayatan University Aligarh India Department of Computer Engineering Genba Sopanrao Moze College of Engineering Balewadi Pune Maharashtra India Artificial Intelligence And Data Science Department Dr. D.Y.Patil College Of Engineering And Innovation Talegaon

This explores using a system to gain knowledge of strategies that allow you to optimize the facts retrieval manner. Facts retrieval is a complicated technique; it is becoming even more complicated as advancements in generation have furnished tools to make the gathering, employing, and evaluating information less complicated and faster. Research techniques, including artificial intelligence, neural networks, and machine learning, can speed up records retrieval and improve outcomes' accuracy. This look examines the different machine learning techniques to optimize the facts retrieval process and the advantages and downsides of each technique. Furthermore, this study looks at how gadgetstudying algorithms improve a person's enjoyment of retrieval systems and how their use can be integrated into cutting-edge practices. Subsequently, methods for improving the performance of machine learning algorithms are discussed in addition to capacity destiny directions inside the use of gadget studying to optimize statistics retrieval.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Text Classification Algorithm Based On Combined Machine Learning Models

Real-Time Text Classification Algorithm Based On Combined Ma...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： G. Ravivarman Sulabh Mahajan Sowmiya S Shitij Goyal Rahul Gupta Kirti H. Wanjale Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Quantum University Research Center Quantum University Roorkee Uttarakhand India Adjunct Faculty School of Mangement - PG Management JAIN (Deemed to be University) Bangalore Karnataka Department of Computer Engineering Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Web text categorization is a prominent area of research and a vital technology in the fields of Web information retrieval and data mining. A great deal of attention and quick progress in this field has occurred in recent years. One sort of deep learning model that has been more useful for extracting important characteristics from textual input while reducing model complexity is the convolutional neural network (CNN). In the meanwhile, a time-tested machine learning method known as support vector machine (SVM) has a stellar reputation for reliability and accuracy. By merging an improved CNN with SVM, this research suggests a new method for Web text categorization. Text characteristics are extracted using the CNN model, which has a five-layer network structure. These features are then used for classification as well as forecasting using SVM. This method presents a new approach to Web text categorization using enhanced models by combining the capabilities of convolutional neural networks (CNNs) and support vector machines (SVMs). Applying this method to datasets with mixed text yields outstanding results, all things considered.

关键词： Support vector machines Deep learning Adaptation models Accuracy Machine learning algorithms Text categorization Real-time systems Vectors Classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-Field Transformer for Diabetic Retinopathy Grading on Two-field Fundus Images

Cross-Field Transformer for Diabetic Retinopathy Grading on ...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Hou, Junlin Xu, Jilan Xiao, Fan Zhao, Rui-Wei Zhang, Yuejie Zou, Haidong Lu, Lina Xue, Wenwen Feng, Rui Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing China Fudan University Academy for Engineering and Technology China Shanghai Jiao Tong University Shanghai General Hospital School of Medicine Department of Ophthalmology China Shanghai Eye Hospital Shanghai Eye Diseases Prevention & Treatment Center Shanghai China

ISBN: (纸本)9781665468190

Automatic diabetic retinopathy (DR) grading based on fundus photography has been widely explored to benefit the routine screening and early treatment. Existing researches generally focus on single-field fundus images, which have limited field of view for precise eye examinations. In clinical applications, ophthalmologists adopt two-field fundus photography as the dominating tool, where the information from each field (i.e., macula-centric and optic disc-centric) is highly correlated and complementary, and benefits comprehensive decisions. However, automatic DR grading based on two-field fundus photography remains a challenging task due to the lack of publicly available datasets and effective fusion strategies. In this work, we first construct a new benchmark dataset (DRTiD) for DR grading, consisting of 3,100 two-field fundus images. To the best of our knowledge, it is the largest public DR dataset with diverse and high-quality two-field images. Then, we propose a novel DR grading approach, namely Cross-Field Transformer (CrossFiT), to capture the correspondence between two fields as well as the long-range spatial correlations within each field. Considering the inherent two-field geometric constraints, we particularly define aligned position embeddings to preserve relative consistent position in fundus. Besides, we perform masked cross-field attention during interaction to filter the noisy relations between fields. Extensive experiments on our DRTiD dataset and a public DeepDRiD dataset demonstrate the effectiveness of our CrossFiT network. The new dataset and the source code of CrossFiT will be publicly available at https://***/DU-VTS/DRTiD. © 2022 IEEE.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

An Investigation of IOT-Based Consumer Analytics to Assist Consumer Engagement Strategies in Evolving Markets 3

An Investigation of IOT-Based Consumer Analytics to Assist C...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Jayadeva, Sujay Mugaloremutt Prasad Krishnam, Nagendra Raja Mannar, B. Prakash Dabral, Amar Buddhi, Dharam Garg, Neha Jss Academy of Higher Education & Research Department of Health System Management Studies Faculty of Management Studies India Telangana Hyderabad India St. Theresa Intl College Business Administration Thailand Graphic Era Deemed to Be University Department of Hospitality Management Uttarakhand Dehradun India Uttaranchal University Uttaranchal Institute of Technology India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9798350399264

In order to establish sustainable operations, Internet innovation has been widely adopted in the retail sector;however, certain operational difficulties, such as security and confidentiality have been uncovered in practise. As a result, linked fields must do more thorough theoretical study. In order to compete with online merchants and promote sustainable growth, this study examines how traditional brick and mortar stores might use IoT technology. First, by taking into account the costs of customer inconvenience associated with shopping through various retail partners and the influence of technology, pricing Plans were created for the store and the retailer of concrete blocks, respectively. Furthermore, by contrasting different scenarios, the benefits of internet to retail shops and consumer excess are analysed. After that, the basic models were expanded to take into account consumer - perceived sensitivity regarding IoT technology and price competitiveness in order to test the robustness of the analytical conclusions. Additionally, actual data-based numerical analyses are performed. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

User-experience oriented POI recommendation with pseudo rating

引用

Multimedia Tools and Applications 2025年第16期84卷 16583-16603页

作者： Yi, Kun Yamagishi, Ryu Li, Jiyi Li, Taishan Bai, Zhengyang Ma, Qiang Kyoto Institute of Economic Research Kyoto University Yoshida-honmachi Sakyo-ku Kyoto Kyoto606-8501 Japan Graduate School of Informatics Kyoto University Yoshida-honmachi Sakyo-ku Kyoto Kyoto606-8501 Japan Department of Computer Science and Engineering University of Yamanashi Takeda 4-3-11 Kofu 400- 8511 Yamanashi Japan Research Institute of Non-Timber Forestry Chinese Academy of Forestry Key Laboratory of Non-Timber Forest Germplasm Enhancement & Utilization of State Administration of Forestry and Grassland No. 3 Weiwu Road Jinshui District Zhengzhou450003 China RIKEN Center for Computational Science RIKEN Nihonbashi 1-chome Mitsubishi Bld. 15th floor 1-4-1 Nihonbashi Chuo-ku Tokyo103-0027 Japan Department of Information Science Kyoto Institute of Technology Matsugasaki Sakyo-ku Kyoto Kyoto606-8585 Japan

Point-of-interest (POI) recommendation faces challenges in managing data sparsity and cold-start problems, particularly in terms of personalized recommendation. Firstly, most existing users only visit a small number of POIs, which results in severe data sparsity and makes most conventional methods unsuitable because they require adequate historical data from each user to learn the model. In addition, new users have little or no historical record. Existing ask-to-rate methods for cold start user scenarios treat user answers as historical data, which is inappropriate and causes difficulty in capturing user preferences. Therefore, in this paper, to tackle the data sparsity problem, we propose a user-experience model (UEM) to uncover user behaviors from several aspects. The proposed UEM involves four factors: Who (does it), What (the user does), Where (the user does it), and When (the user does it). In contrast to other methods that model user behavior from individual records, our model introduces a latent variable of user experience to extract similarity among users. This feature makes our model suitable for mitigating the severe sparse-data issue in POI recommendations. Furthermore, to handle the cold-start problem for new users, we propose a pseudo-rating mechanism (PRM) to capture new users’ preferences and recommend POIs. For new users, photos are provided for rating, and these ratings are then used to capture their preferences and estimate the probability of their visits. Extensive experimental results demonstrate that the proposed method achieves better recommendation performance and fairness than the state-of-the-art methods. Moreover, user study results validates that the users’ preferences captured via PRM are satisfactory, and UEM provides satisfactory POI recommendations. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Behavioral research

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：