检索结果-内蒙古大学图书馆

A Graph Neural Network Recommendation Based on Long-and Short-Term Preference

Computer systems science & engineering 2023年第12期47卷 3067-3082页

作者： Bohuai Xiao Xiaolan Xie Chengyong Yang School of Information Science and Engineering Guilin University of TechnologyGuilin541004China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of TechnologyGuilin541004China Network and Information Center Guilin University of TechnologyGuilin541004China

The recommendation system(RS)on the strength of Graph Neural Networks(GNN)perceives a user-item interaction graph after collecting all items the user has interacted *** the RS performs neighborhood aggregation on the graph to generate long-term preference representations for the user in quick ***,user preferences are *** the passage of time and some trend guidance,users may generate some short-term preferences,which are more likely to lead to user-item interactions.A GNN recommendation based on long-and short-term preference(LSGNN)is proposed to address the above *** consists of four modules,using a GNN combined with the attention mechanism to extract long-term preference features,using Bidirectional Encoder Representation from Transformers(BERT)and the attention mechanism combined with Bi-Directional Gated Recurrent Unit(Bi-GRU)to extract short-term preference features,using Convolutional Neural Network(CNN)combined with the attention mechanism to add title and description representations of items,finally inner-producing long-term and short-term preference features as well as features of items to achieve *** experiments conducted on five publicly available datasets from Amazon,LSGNN is superior to state-of-the-art personalized recommendation techniques.

关键词： Recommendation systems graph neural networks deep learning data mining

来源：评论

学校读者我要写书评

暂无评论

User Interface for Natural Voice Quality of Alaryngeal Speech 13

User Interface for Natural Voice Quality of Alaryngeal Speec...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Onodera, Etsuki Wakatsuki, Naoto Ebihara, Tadashi Maeda, Yuka University of Tsukuba Graduate School of Science and Technology Tsukuba Japan University of Tsukuba Institute of System and Information Engineering Tsukuba Japan

ISBN: (纸本)9798350355079

Various alaryngeal voicing methods have been devised and put to practical use for people who lost the ability to speak normally due to the removal of the larynx. The objective of this study is to improve the quality of alaryngeal speech so that people who have lost their voices can communicate more freely. For the purpose, it is necessary to create a system that can control nonverbal information such as voice quality with the same degree of subtlety as normal speech. As a first step, we developed a prototype interface that allows the user to control the pitch of vocalizations with the rotation of the wrist. We believe that this interface will allow the user to control the pitch of vocalizations as desired, without requiring special training. In fact, the author's own trial use of the interface showed that after 30 minutes of practice, the accuracy of pitch control was improved, and to some extent, the speaker was able to speak at the desired pitch. The author also tried singing with the system. The results suggested the possibility of improvement in singing as well as normal singing. Therefore, the proposed interface was shown to be suitable for pitch control. © 2024 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Fine grained image recognition algorithm based on CNN-Transformer and paired interaction 4

Fine grained image recognition algorithm based on CNN-Transf...

引用

4th International Conference on Neural Networks, information and Communication engineering, NNICE 2024

作者： Wang, Yu Zhang, Hong Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9798350394375

A new fine-grained image recognition algorithm (P-ResViT, Paired Interaction Res50-ViT) based on CNN-Transformer is proposed to address the issue of existing fine-grained image recognition methods based on convolutional neural networks (CNN) lacking attention mechanisms and difficulty in accurately locating key regions, as well as weak ability to extract contextual information and global features. This algorithm introduces paired interaction attention mechanisms to supplement external attention. This algorithm can utilize the self attention mechanism of the Vision Transformer and the external attention mechanism formed by paired image inputs during training to achieve precise positioning, while preserving the inductive bias and local feature extraction capabilities of CNN. Firstly, the fine-tuning improved ResNet-50 completes local feature extraction and obtains high-resolution feature maps. Secondly, the Transformer encodes the tokenized image blocks of the feature map as input sequences for extracting global context. Finally, the Transformer completes global feature extraction and outputs the classification sequence. In addition, two external attention mechanisms were introduced by inputting image pairs during training, including collaborative attention mechanisms for similar images and cross attention mechanisms for heterogeneous images, fully utilizing the correlation information between images. After experimental evaluation, the P-ResViT proposed in this article has reached advanced levels in three fine-grained image datasets CUB, CAR, and AIR. © 2024 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON THE INFLUENCE OF THE FORM OF STIFFENED STRUCTURE ON THE CONTAINMENT CAPABILITY OF AUXILIARY POWER UNIT CASING

RESEARCH ON THE INFLUENCE OF THE FORM OF STIFFENED STRUCTURE...

引用

2024 CSAA/IET International Conference on Aircraft Utility systems, AUS 2024

作者： Wu, Ke Xia, Tianxiang Yang, Hongji AVIC Nanjing Engineering Institute of Aircraft System Nanjing China Aviation Science and Technology Key Laboratory of Aviation Mechanical and Electrical System Nanjing China

To study the impact of stiffened structural forms on the high-speed impact resistance and damage modes of GH4169 reinforced auxiliary power unit (APU) casing, a series of high-speed impact simulations were conducted in ANSYS/LS-DYNA software, based on the Johnson-Cook constitutive model and failure model. The simulation results show that as the number of reinforcing ribs increases, the remaining kinetic energy of the projectile decreases, and the energy absorbed by the target plate gradually increases. This is mainly because the reinforcing ribs change the failure form of the target plate, causing a larger range of plastic deformation and thus increasing energy absorption. At the same time, studies have been made on the damage morphology and impact process of the target plate under different impact speeds of the projectile. It has been found that the failure modes of the target plate are different under different impact speeds. The reinforcing ribs can guide the failure form of the target plate towards longitudinal shear failure, which can absorb more energy. Therefore, the use of reinforced design enhances the energy absorption capacity of the APU casing when subjected to blade impacts, helping to improve the containment performance of the APU casing. © The Institution of engineering & technology 2024.

关键词： Fracture mechanics

来源：评论

学校读者我要写书评

暂无评论

Application of Oriented Molecular Imprinting Biosensors in Biomarker Detection

引用

Journal of Analysis and Testing 2024年第4期8卷 553-568页

作者： Tianjian Lv Tiantong Chen Ziyu Zhu Ruilin Haotian Aiqin Luo Axin Liang Key Laboratory of Molecular Medicine and Biotherapy The Ministry of Industry and Information TechnologySchool of Life ScienceBeijing Institute of TechnologyBeijing100081China Department of Biomedical Engineering Chinese PLA General HospitalBeijing100853China

With the rapid development of nanomaterials,the interdisciplinary cross-linking between nanomaterials and biomedical detection is *** based on novel molecular recognition mechanisms are expected to achieve higher molecular recognition specificity and *** them,oriented molecular imprinting biosensors have recently become a research *** molecular imprinting biosensors are biosensors that can be used for specific *** are constructed by modifying template molecules with specific groups to form molecular imprinting microcavities with templateoriented recognition *** with general biosensors,oriented molecular imprinting biosensors have more directional recognition sites and fewer non-specific recognition *** unique advantage provides a higher signal-to-noise ratio for these sensors,which contributes to establishing a clear and intuitive relationship of light,electricity and other detection signals with the content of substances to be measured and has been widely used in biomarker *** this review,the types,principles and synthesis methods of oriented molecular imprinting technology are briefly *** application of oriented molecular imprinting biosensors in biomarker detection is ***,the technical bottleneck and future development trend of oriented molecular imprinting technology in the field of biosensors are discussed and summarized.

关键词： Oriented imprinting Biosensors Biomarker Detection

来源：评论

学校读者我要写书评

暂无评论

An electrically controlled tunable photonic crystal filter based on thin-film lithium niobate

引用

Optoelectronics Letters 2024年第4期20卷 200-204页

作者： WANG Yifan YAO Yuan ZHANG Hao LIU Bo DUAN Shaoxiang LIN Wei Institute of Modern Optics College of Electronic Information and Optical EngineeringNankai UniversityTianjin 300350China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Nankai UniversityTianjin 300350China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai 519000China Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology Nankai UniversityTianjin 300350China

In this paper,we present an electrically controlled tunable narrowband filter based on a thin-film lithium niobate two-dimensional(2D)photonic *** filter incorporates a photonic crystal microcavity structure within the straight waveguide,enabling electronic tuning of the transmitted wavelength through added electrode *** optimized microcavity filter design achieves a balance between high transmission rate and quality factor,with a transmission center wavelength of 1551.6 nm,peak transmission rate of 96.1%,and quality factor of ***,the filter can shift the central wavelength of the transmission spectrum by applying voltage to the electrodes,with a tuning sensitivity of 13.8 pm/*** proposed tunable filter adopts a simple-to-fabricate air-hole structure and boasts a compact size(length:11.57μm,width:5.27μm,area:60.97μm^(2)),making it highly suitable for large-scale *** features make the filter promising for broad applications in the fields of photonic integration and optical communication.

关键词： tunable tuning waveguide

来源：评论

学校读者我要写书评

暂无评论

Single-mode GaSb-based laterally coupled distributed-feedback laser for CO_(2)gas detection

引用

Chinese Physics B 2023年第10期32卷 443-447页

作者：韩实现严进一曹春芳杨锦杜安天陈元宇刘若涛王海龙龚谦 Key Laboratory of Terahertz Solid State Technology Shanghai Institute of Microsystem and Information TechnologyShanghai 200050China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Shandong Provincial Key Laboratory of Laser Polarization and Information Technology School of Physics and Physical EngineeringQufu Normal UniversityQufu 273165China

We report on a GaSb-based laterally coupled distributed feedback(LC-DFB)laser with Cr gratings operating at 2004 nm for CO_(2)detection *** packaged with single-mode fiber pigtailed,the laser diode operates in the continuous-wave mode in a temperature range from-10℃to 60℃,with a maximum output power of 2 mW and a maximum side-mode suppression ratio over 30 ***-modulated absorption spectroscopy of CO_(2)demonstrates the applicability of the LC-DFB laser to tunable diode laser absorption ***,the diode junction temperature,which is measured by using the wavelength shift method,exhibits a maximum value of 17℃in the single-mode operation range.

关键词： semiconductor lasers quantum wells laser spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Prediction of heat transfer coefficients for steam condensation in the presence of air based on ANN method

引用

International Journal of Advanced Nuclear Reactor Design and technology 2023年第2期5卷 77-85页

作者： Cao, Haoran Cao, Boyang Xia, Congyi Meng, Zhaoming Bian, Haozhi Ding, Ming Heilongjiang Provincial Key Laboratory of Nuclear Power System & Equipment Harbin Engineering University Harbin150001 China School of Nuclear Science and Technology Harbin Engineering University China

Artificial neural network (ANN) methods have been gradually used in the field of nuclear reactor thermal-hydraulics as new methods to improve accuracy or fast prediction. This study establishes a back propagation (BP) neural network model based on the ANN methods to predict the steam condensation heat transfer coefficient outside a heat tube in the presence of air. The main factors affecting condensing heat transfer, such as pressure, air mass fraction, subcooling, and tube diameter, are used as input quantities, and the condensation heat transfer coefficient is used as output quantity. A complete set of neural networks for predicting the heat transfer coefficient for steam condensation in the presence of air is established based on the relevant experimental data collected over the world. The results predicted by the ANN model are compared with the experimental data and those of traditional correlation methods. The data from 2276 experiments are distributed within a ±10% error band at the 95% confidence level. This means that the prediction accuracy of the ANN model is higher than that of the traditional experimental correlation. Therefore, the neural network model developed in this study can be used for the prediction of the heat transfer coefficient for steam condensation in the presence of air. © 2023

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Bald Eagle Search Algorithm with Hierarchical Deep Learning for Internet of Things Assisted Sleep Quality Recognition

引用

SN Computer science 2024年第5期5卷 564页

作者： Duhayyim, Mesfer Al Sharif, Mahir Mohammed Munjal, Muskaan Hilal, Anwer A. Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj 16273 Saudi Arabia Department of Computer Science Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan

Sleep quality prediction in Internet of Things (IoT) involves leveraging a system of interrelated devices to gather as well as analyse related data. Smart devices like wearable devices or smart mattresses endlessly monitor many parameters such as body movement, heart rate, and environmental situations in bedroom. Real-time recommendations and feedback transported to consumers, allowing them to create informed lifestyle changes for superior sleep hygiene. As IoT ecosystem continues to develop, a combination of various data streams as well as classy analytics holds assurance for further refining sleep quality forecasts and improving overall well-being. The article designs a Bald Eagle Search Algorithm with Hierarchical Deep Learning for Internet of Things Assisted Sleep Quality Recognition (BESHDL-SQP) technique. The purpose of the BESHDL-SQP technique is to recognize and classify the quality of the sleep level in the IoT environment. In the presented BESHDL-SQP technique, the preliminary stage of data pre-processing using min–max normalization involved to normalize the input data. For predicting sleep quality, hierarchical long short-term memory (LSTM) technique exploited. Lastly, BES model utilized for optimal hyperparameter selection of LSTM method which helps in attaining enhanced results. To validate better performance of BESHDL-SQP technique, a huge range of simulation analysis is carried out. The extensive results stated that the BESHDL-SQP technique exhibits supreme performance over other models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bald eagle search Internet of things LSTM Sleep quality recognition Smart devices

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

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：