检索结果-内蒙古大学图书馆

4th International Conference on Advances in Electrical engineering and computer Applications, AEECA 2023

作者： Huang, Yinqi Zhou, Wenjiang Li, Liang Lyu, Ting Xu, Haitao Univerisity of Science and Technology Beijing School of Computer and Communication Engineering Beijing China China Academy of Information and Communications Technology Beijing China Shunde Innovation School Univerisity of Science and Technology Beijing School of Computer and Communication Engineering Beijing China

ISBN: (纸本)9798350308082

With the development of machine learning and big data technologies, distributed training has become an important way to improve computational efficiency. However, in the distributed training environment, the performance difference between workers and the interference of unrelated tasks may lead to the uneven load of the system and cause the 'straggler phenomenon'. Therefore, how to solve the straggler phenomenon and achieve load balancing of the system is a pressing problem of distributed training. To address the shortcomings of the existing parallel computing model DSSP, this paper proposes a load-balancing strategy for DDP, which effectively reduces the load difference by adjusting the batch size and data size of workers in the training process. Then, to explore the correlation between data size in DDP and synchronization threshold in DSSP in dynamic adjustment, we perform multi-task learning for the two dynamic adjustment strategies and integrate the proposed Joint Multi-Task Prediction scheme on DSSP to implement a new parallel computing model ESP. extensive experiments The results show that ESP can not only guarantee the model accuracy but also effectively improve the training speed in distributed training. © 2023 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Cross-Domain Slot Filling with Retrieval Augmented In-Context Learning

Zero-Shot Cross-Domain Slot Filling with Retrieval Augmented...

引用

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

作者： Song, Mengxiao Liu, Tingwen Li, Quangang Ma, Duohe Sun, Ming Tian, Ling Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

Zero-shot cross-domain slot filling is becoming increasingly important due to its ability to generalize to new domains without the need for annotating domain-specific data, which aligns well with the requirements of industrial deployments. Recent advanced works deal with this task through question answering framework and make remarkable progress. However, they always rely on human efforts to manually construct question templates or prompts for all slot types, which is not only labor consuming, but also experience context inconsistency issue between the manual example and the specific test instance. To alleviate this problem, we introduce a retriever designed to extract reference samples from the training sets, serving as demonstrations to guide the model in generating the target slot entity through in-context learning. Building upon this retriever, we propose a retrieval-augmented generative framework that automatically constructs and tailors prompts to each specific test instance, eliminating the need for manual efforts. Experiment results verify that our approach attains the state-of-the-art. © 2025 IEEE.

关键词： slot filling spoken language understanding zero-shot cross-domain

来源：评论

学校读者我要写书评

暂无评论

Ia-Mstm: Improved Adaptive Moment Estimation Enabled Mixed Attention-Based Long Short-Term Memory For Crop Yield Prediction 3

Ia-Mstm: Improved Adaptive Moment Estimation Enabled Mixed A...

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Vani, B.V. Guruprakash, C.D. Sri Siddhartha Academy of Higher Education Sri Siddhartha Institute of Technology Saraswathipuram Information Science and Engineering Karnataka Tumakuru572105 India Sri Siddhartha Institute of Technology Department Computer Science and Engineering Karnataka Tumakuru572105 India

ISBN: (纸本)9798350364569

Crop yield prediction has sought tremendous attention in recent years several approaches were developed for crop yield prediction. However, these techniques created certain limitations in real-time applications including a reduction in relative errors, and low prediction accuracy. Therefore, this research proposed a deep learning technique known as improved Adaptive Moment estimation enabled mixed attention-based long short-term memory (IA-MSTM) to predict crop yields. The mixed attention techniques combine the advantages of channel attention with the hard attention mechanism (HAM), which can capture long-term dependencies that are crucial for understanding crop growth dynamics over time. Additionally, the improved repeated Loss-based Adam optimizer adapts the learning rate during training, leading to quicker convergence compared to traditional methods. The performance of the IA-MSTM achieves a minimal error value in terms of Mean Absolute Error (MAE) of 2.00 for TP 90. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

NLP using Wordnet Database for Monitor the Social Platform in Digital Forensic Investigation 14

NLP using Wordnet Database for Monitor the Social Platform i...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Senthil, P. Alagumuthukrishnan, S. Kannan, K.S. CMR College of Engineering & Technology Department of Computer Science and Engineering Kandlakoya Medchal Road Hyderabad501401 India CMR Institute of Technology Department of Computer Science and Engineering Kandlakoya Medchal Road Hyderabad501401 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Krishnankoil626126 India

Cyberbullying has made people too vulnerable to hatred and abuse which makes cyberbullying an important subject of matter all over the world. We propose a framework that prevents the use from using abusive words and predict user crime probability in social application with the help of one of the machine learning technique Natural Language Processing (NLP). NLP plays an important role in analyzing the given words and find out the alternative meaning and provide which category these words belongs to with the help of the WordNet database. In the previous system, social application user information is processed and kept aside and required is action not taken. We proposed an application that solves that existing system issue and provides a solution by making a complaint on the user in the social application. The proposed system consists of three application social book, social admin, crime reporting. First social book is social media application that provides activities like adding friends posting status and etc. Second social admin has the control of the whole social media application admin has all details of the user and so on Third crime application contains two-part public and police this application acts as a compliant system to our application where public user can raise a complaint against a person in social application to take some action. © Grenze Scientific Society, 2023.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

A nano-sheet graphene-based enhanced thermal radiation composite for passive heat dissipation from vehicle batteries

引用

Nano Materials science 2024年第4期6卷 443-455页

作者： Ji-Xiang Wang Christopher Salmean Jiaxin Li Chaojie Lei Jun Li Mingliang Zhong Bo Qi Yufeng Mao Hebei Key Laboratory of Man-machine Environmental Thermal Control Technology and Equipment Hebei Vocational University of Technology and EngineeringHebei 054000PR China College of Electrical Energy and Power EngineeringYangzhou UniversityYangzhou225009PR China Department of Mechanical and Aerospace Engineering The Hong Kong University of Science and TechnologyKowloonHong Kong SARPR China China Academy of Launch Vehicle Technology Beijing100076PR China Beijing Sino-Spark Technology Co. Ltd.Beijing100191PR China School of Environmental Science and Engineering Suzhou University of Science and TechnologySuzhou215009PR China Institute of Optics and Electronics Chinese Academy of SciencesChengdu610209PR China National Key Laboratory of Optical Field Manipulation Science and Technology Chinese Academy of SciencesChengdu610209PR China Taizhou Wavexploration Energy Ltd. Taizhou225513PR China Department of Electrical and Computer Engineering University of TorontoTorontoM5S3G4Canada

In response to thermal runaway(TR)of electric vehicles,recent attention has been focused on mitigation strategies such as efficient heat dredging in battery thermal *** management with particular focus on battery cooling has been becoming increasingly *** usually happened when an electric vehicle is unpowered and *** this state,traditional active battery cooling schemes are disabled,which can easily lead to dangerous incidents due to loss of cooling ability,and advanced passive cooling strategies are therefore gaining ***,we developed an enhanced thermal radiation material,consisting of~1μm thick multilayered nano-sheet graphene film coated upon the heat dissipation surface,thereby enhancing thermal radiation in the *** surface was characterized on the nanoscale,and tested in a battery-cooling *** found that the graphene-based coating's spectral emissivity is between 91% and 95% in the mid-infrared region,and thermal experiments consequently illustrated that graphene-based radiative cooling yielded up to15.1% temperature reduction when compared to the uncoated *** the novel graphene surface to augment a heat pipe,the temperature reduction can be further enlarged to 25.6%.The new material may contribute to transportation safety,global warming mitigation and carbon neutralization.

关键词： Battery thermal management Nano-sheet graphene Functional material Passive cooling Thermal radiation

来源：评论

学校读者我要写书评

暂无评论

Yoga Pose Detection Using Mediapipe and Cue Method

Yoga Pose Detection Using Mediapipe and Cue Method

引用

2024 International Conference on Smart Electronics and Communication Systems, ISENSE 2024

作者： Gatikoppu, Sai Phanindra Pavan Kumar Vimal Subramanian, G. Thamizh Devi, C. Maruthupandi, V. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Virudhunagar India M.A.M College of Engineering and Technology Department of Informaion Technology Tamil Nadu Siruganur India

ISBN: (纸本)9798331528126

Popular exercise like yoga has numerous positive health effects. However, incorrectly executed yoga poses can be harmful and lessen the advantages of the practice. In recent years, yoga positions have been investigated and altered using computer vision techniques. This study introduces a novel Mediapipe-based cue-based computer vision method for improving yoga postures. By finding and recognizing the most crucial body aspects in yoga postures using deep learning algorithms, the suggested method is contrasted with proper alignment. The user is then given instructions on how to change the stance to attain the desired alignment right away by the computer. The proposed method is tested using the dataset of yoga poses, and the accuracy and real-time performance outcomes are promising. In yoga classes, online tutorials, and other situations, the suggested technique might be employed to maximize benefits while lowering risks of injury for practitioners. © 2024 IEEE.

关键词： Cue Method Mediapipe OpenCv OpenPose Pose Correction

来源：评论

学校读者我要写书评

暂无评论

Noise-Mitigated Variational Quantum Eigensolver with Pre-training and Zero-Noise Extrapolation

Noise-Mitigated Variational Quantum Eigensolver with Pre-tra...

引用

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

作者： Sun, Wanqi Xu, Jungang Duan, Chenghua School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350368741

As a hybrid quantum-classical algorithm, the variational quantum eigensolver is widely applied in quantum chemistry simulations, especially in computing the electronic structure of complex molecular systems. However, on existing noisy intermediate-scale quantum devices, some factors such as quantum decoherence, measurement errors, and gate operation imprecisions are unavoidable. To overcome these challenges, this study proposes an efficient noise-mitigating variational quantum eigensolver for accurate computation of molecular ground state energies in noisy environments. We design the quantum circuit with reference to the structure of matrix product states and utilize it to pre-train the circuit parameters, which ensures circuit stability and mitigates fluctuations caused by initialization. We also employ zero-noise extrapolation to mitigate quantum noise and combine it with neural networks to improve the accuracy of the noise-fitting function, which significantly eliminates noise interference. Furthermore, we implement an intelligent grouping strategy for measuring Hamiltonian Pauli strings, which not only reduces measurement errors but also improves sampling efficiency. We perform numerical simulations to solve the ground state energy of the H4 molecule by using MindSpore Quantum framework, and the results demonstrate that our algorithm can constrain noise errors within the range of O(10-2) ∼ O(10-1), outperforming mainstream variational quantum eigensolvers. This work provides a new strategy for high-precision quantum chemistry calculations on near-term noisy quantum hardware. © 2025 IEEE.

关键词： Error mitigation Matrix product states Variational quantum eigensolver Zero-noise extrapolation

来源：评论

学校读者我要写书评

暂无评论

Secured Authentication Scheme for E-Healthcare in SIoT Using ECC and Improved Hash Function 4th

Secured Authentication Scheme for E-Healthcare in SIoT Using...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Arpitha, T. Chouhan, Dharamendra Shreyas, J. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9789819726134

The convergence of Smart Internet of Things (IoT) and security is a new study topic. In this context, a new IoT trend known as Social IoT (SIoT) was examined for this study. The Social IoT has the advantage of connectivity demonstrated within the network of connected things via the IoT. In Social IoT, a wide range of IoT devices, such as wearables or monitoring sensors, are utilized in e-healthcare applications and the risk of identity theft and impersonation is a significant concern. To address this challenge, we propose a scheme that incorporates multi-factor authentication, elliptic curve cryptography (ECC), and hash functions scheme to provide a robust solution for secure and privacy-preserving authentication. Our system provides privacy protection along with mutual authentication and session key negotiation at a considerably low computational cost (of up to 71.04% compared to other existing techniques). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Mutual Coupling Reduction in MIMO Antenna for 5G Application by Self-Decoupled Method 2

Mutual Coupling Reduction in MIMO Antenna for 5G Application...

引用

2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, ViTECoN 2023

作者： Rashid, Aamir Shah, Syed Shahid Hussain, Irshad Jalal, Muhammad Ramalakshmi, R. Ramachandran, V. University of Engineering and Technology Faculty of Electrical and Computer Engineering Peshawar Pakistan College of Computer and Information Engineering King Saud University Department of Computer Engineering Riyadh Saudi Arabia Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Virudhunagar India Gokaraju Rangaraju Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad500090 India

ISBN: (纸本)9798350347982

This paper shows a simple, compact and small 8×8 MIMO antenna. The ability of MIMO antennas is to broadcast signals in a various patterns and polarizations is extremely advantageous for contemporary communications systems. Excellent diversity gain (DG > 9.99dB), a low envelop correlation coefficient (ECC 0.002), and extremely low mutual coupling (S2l≥ 27) dB are all characteristics of the constructed MIMO antenna. S-boundaries, energy pattern characteristics, maximum gain, diversity gain, and envelop coefficient are used to evaluate the antenna performance. The mutual Coupling is the most basic fundamental parameter for the MIMO antenna, was likewise analyzed and it was observed that its value is under -27dB. self-decoupled MIMO antennas have a loop type ground antenna which reduces the requirement for extra decoupling structures or a postponed tuning method Antennas for ground radiation and loop antenna are magnetic-current and electric-current components, respectively. The suggested MIMO antennas feature a self-decoupled despite the antenna parts being near together, reduced profile and easy fabrication advantages the suggested, a revolutionary approach called MIMO antenna system is expected to offer excellent isolation and minimal mutual coupling, making it suitable for 5G applications. © 2023 IEEE.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Improving Healthcare with Machine Learning and Deep Learning 4

Improving Healthcare with Machine Learning and Deep Learning

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Kothai, G. George Princess, T. Subramani, Nandhagopal Balakrishnan, D. Ravi, P. Amutha, S. Coimbatore India Kpr institute of Engineering and Technology Coimbatore India Coimbatore India KGiSL institute of Technology Coimbatore India Kalasalingam Academy of Research and Education Dept of Computer Science and Engineering Krishnankoil India

ISBN: (纸本)9798331540364

Due to the evolving lifestyle choices and the state of the environment, people nowadays suffer from a wide range of ailments. Consequently, early illness prediction becomes a critical obligation. For doctors, however, making a meaningful prognosis based only on symptoms becomes too difficult. Predicting illness correctly is the hardest problem. ML is crucial in helping to anticipate illnesses and find treatments in order to solve this issue. Using disease data, MRIs, chest X-rays, and diabetes records, machine learning (ML) assists in diagnosing and treating various conditions. Given the patient's symptoms, we utilize techniques such as SVM, Decision Trees, Random Forest Classifier, Gaussian Bayes and Multinomial Bayes, and Gradient Boost to predict illnesses. Given an X-ray image, we employ CNN models such as VGG for image classification with transfer learning to predict if a person has tuberculosis, pneumonia, or is disease-free. Brain MRIs (Magnetic Resonance Imaging) can be used to predict brain tumors. With the aid of Support Vector Machines, we are able to forecast if the patient has a pituitary tumor, meningioma, glioma, or no tumor at all (SVM). Diabetes is predicted using a number of important variables, including age and body mass index (BMI). Random forest classifiers are what we use to determine if a person has diabetes or not. © 2024 IEEE.

关键词： Support vector machines

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：