检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hacohen, Guy Weinshall, Daphna School of Computer Science and Engineering The Hebrew University of Jerusalem Israel Edmond & Lily Safra Center for Brain Sciences The Hebrew University of Jerusalem Israel

In the domain of semi-supervised learning (SSL), the conventional approach involves training a learner with a limited amount of labeled data alongside a substantial volume of unlabeled data, both drawn from the same underlying distribution. However, for deep learning models, this standard practice may not yield optimal results. In this research, we propose an alternative perspective, suggesting that distributions that are more readily separable could offer superior benefits to the learner as compared to the original distribution. To achieve this, we present PruneSSL, a practical technique for selectively removing examples from the original unlabeled dataset to enhance its separability. We present an empirical study, showing that although PruneSSL reduces the quantity of available training data for the learner, it significantly improves the performance of various competitive SSL algorithms, thereby achieving state-of-the-art results across several image classification tasks. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A New Identity-Based Encryption Scheme with Accountable Authority Based on SM9 11

A New Identity-Based Encryption Scheme with Accountable Auth...

引用

11th International Conference on Electronics, Communications and Networks, CECNet 2021

作者： Wang, Ke Zhao, Yuan Luo, Song Guan, Zhi MoE Beijing China Department of Computer Science and Technology EECS Peking University Beijing China School of Computer Science and Engineering Chongqing University of Technology Chongqing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (纸本)9781643682402

Accountable authority identity-based encryption (A-IBE) is an extension of identity-based encryption (IBE) in which private key's source can be traced, i.e., whether the key comes from a private key generator or a user. SM9 is an official cryptography standard of China which defines a practical IBE scheme. In this paper, we construct a practical A-IBE scheme from the SM9-IBE scheme. Our A-IBE scheme has public traceability and is proven secure if the based SM9-IBE scheme is secure. Compared with other A-IBE schemes, our A-IBE scheme has better efficiency in encryption and decryption. © 2022 The authors and IOS Press.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

NBWAB: A Model for Text Sentiment Analysis With BERT and ChatGPT

NBWAB: A Model for Text Sentiment Analysis With BERT and Cha...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolei Wang Hongyun Huang Zuohua Ding School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou China Library Center of Multimedia Data Analysis Zhejiang Sci-Tech University Hangzhou China School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Social network texts contain a great deal of sentiment information. Such information reflects the personal attitudes and emotional dispositions for particular topics or events. However, not much comprehensive semantic information and not enough text data are used by traditional text sentiment analysis models, consequently, there are shortcomings in the analysis results. To handle this problem, in this paper, we propose a text sentiment analysis model NBWAB based on BERT-WWM-ATT-BiLSTM text classification. Our optimal model is constructed as follows. BERT-WWM is first used to dynamically encode the character-level and sentence-level features, and then Bi-LSTM is used to capture deeper semantic features of texts. Finally, these results are fused with the relevant multi-dimensional features of texts by multi-head-attention feature fusion skill. To further improve the performance of text sentiment analysis, we employ the ChatGPT data augmentation method to extend training datasets. To show the efficiency of our model, we have conducted experiments on three Chinese datasets: SMP2020-EWECT, Waimai_10k, and Weibo_senti_100k. The accuracy and F1 value of the model on the SMP2020-EWECT dataset (usual) are 80.76% and 77.61%, respectively, the accuracy and F1 value on the Waimai_10k dataset are 92.29% and 91.34%, respectively, and the accuracy and F1 value on the Weibo_senti_100k dataset are 98.10% and 98.24%, respectively. The results show that our model has advantages over the existing models in that more semantic information and more text data are considered for text analysis.

关键词： Training Sentiment analysis Analytical models Accuracy Semantics Training data Chatbots

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sparse Channel Estimation for RIS-Assisted Mmwave Massive MIMO Systems

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Shao, Shuying Lv, Tiejun Du, Siying Zeng, Jie Tan, Fangqing Lin, Zhipeng School of Information and Communication Engineering Beijing100876 China Shandong Institute of Petroleum and Chemical Technology Department of Computer Science and Engineering Dongying257061 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China Guilin University of Electronic Technology School of Information and Communication Guilin541004 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China

The integration of reconfigurable intelligent surfaces (RISs) with millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems holds significant promise for future wireless communication methods aiming to achieve high-speed data transmission and expand communication coverage. However, channel estimation (CE) in RIS-assisted wireless communication systems faces many challenges due to the limited signal processing capability of the RIS. Existing methods often fail to fully capture the non-uniform sparsity of mmWave channels. To address this limitation, we propose an adaptive sparse CE scheme involving two progressive algorithms, i.e., normalized least mean squares–log sum (NLMS-LOG) and normalized least mean squares–normalized least mean fourth–log sum (NLMS-NLMF-LOG), for RIS-assisted mmWave massive MIMO systems. The proposed scheme selectively adjusts the channel coefficients to improve the accuracy of the estimation, enabling more efficient exploitation of the inherent non-uniform sparsity in mmWave channels. The NLMS-LOG algorithm innovatively incorporates a log-sum penalty term into the cost function of the NLMS algorithm, thereby increasing the convergence rate. Building upon NLMS-LOG, the NLMS-NLMF-LOG algorithm employs a mixed error function to achieve superior performance across different SNR conditions. The simulation results demonstrate that the proposed scheme outperforms existing methods, such as the NLMS, sparse exponential forgetting window least mean square, and sparse hybrid adaptive filtering algorithms, in terms of CE accuracy and convergence speed. © 1967-2012 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Geometric Feature-Driven Metric Learning for 3D Craniofacial Superimposition

Geometric Feature-Driven Metric Learning for 3D Craniofacial...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qingdong Long Junli Zhao Fuqing Duan Chengyuan Wang Xuesong Wang Lijie Geng Zhenkuan Pan Mingquan Zhou College of Computer Science and Technology Qingdao University Qingdao China School of Artificial Intelligence Beijing Normal University Beijing China National and Local Joint Engineering Research Center for Cultural Heritage Digitization School of Information Science and Technology Northwest University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Craniofacial superimposition is a crucial forensic science technique to identify human remains by matching skulls to facial images. However, this task is challenging due to significant morphological differences between skulls and faces, limited paired samples, and high data dimensionality. We proposed a geometric feature-driven metric learning method for craniofacial superimposition to address these issues. Firstly, we extracted geometric features, including depth, curvature, and elevation of 3D craniofacial data, to generate 2D maps of structured representations enriched with geometric details. Next, we novelly designed a Triplet Network for geometric feature-driven metric learning, which leverages triplet loss to learn discriminative embeddings and effectively handle the limited paired data problem. By incorporating the Sinkhorn Distance as an additional constraint, we aligned the skull and face data distributions, enhancing the matching precision. We conducted extensive experiments on a 3D craniofacial dataset, achieving a maximum accuracy of 99.45% on curvature maps, surpassing state-of-the-art methods. Our code will be available after publication at https://***/Lqd-js/cranial-superimposition.

关键词： Measurement Learning systems Three-dimensional displays Accuracy Forensics Signal processing Feature extraction Robustness Speech processing Faces

来源：评论

学校读者我要写书评

暂无评论

Efficient Tree-based Parallel Algorithms for N-Body Simulations Using C++ Standard Parallelism 24

Efficient Tree-based Parallel Algorithms for N-Body Simulati...

引用

Proceedings of the SC '24 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis

作者： Thomas Lane Cassell Tom Deakin Aksel Alpay Vincent Heuveline Gonzalo Brito Gadeschi School of Computer Science University of Bristol Bristol UK Engineering Mathematics and Computing Lab Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany GPU Architecture NVIDIA Munich Germany

ISBN: (纸本)9798350355543

The Barnes-Hut approximation for N-body simulations reduces the time complexity of the naive all-pairs approach from O(N2) to O(N log N) by hierarchically aggregating nearby particles into single entities using a tree data structure. This inherently irregular algorithm poses substantial challenges for performance portable implementations on multi-core CPUs and GPUs. We introduce two portable fully-parallel Barnes-Hut implementation strategies that trade-off different levels of GPU support for performance: an unbalanced concurrent octree, and a balanced bounding volume hierarchy sorted by a Hilbert spacefilling curve. We implement these algorithms in portable ISO C++ using parallel algorithms and concurrency primitives like atomics. The results demonstrate competitive performance on a range of CPUs and GPUs. Additionally, they highlight the effectiveness of the par execution policy for highly concurrent irregular algorithms, outperforming par_unseq on CPUs and GPUs with Independent Thread Scheduling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction: Divine Religions algorithm: a novel social-inspired metaheuristic algorithm for engineering and continuous optimization problems

引用

Cluster Computing 2025年第5期28卷 1-2页

作者： Mozhdehi, Ali Toufanzadeh Khodadadi, Nima Aboutalebi, Mohaddeseh El-kenawy, El-Sayed M. Hussien, Abdelazim G. Zhao, Weiguo Nadimi-Shahraki, Mohammad H. Mirjalili, Seyedali Faculty of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran Department of Civil Architectural and Environmental Engineering University of Miami Coral Gables USA Department of Computer Engineering Azad University of Lahijan Lahijan Iran School of ICT Faculty of Engineering Design and Information & Communications Technology (EDICT) Bahrain Polytechnic Isa Town Bahrain Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer and Information Science Linköping University Linköping Sweden Faculty of Science Fayoum University Fayoum Egypt School of Water Conservancy and Hydropower Handan China Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Centre for Artificial Intelligence Research and Optimization Torrens University Australia Fortitude Valley Australia University Research and Innovation Center (EKIK) Obuda University Budapest Hungary

来源：评论

学校读者我要写书评

暂无评论

Experimental results on FMCW radar based Human Recognition using only Doppler information

Experimental results on FMCW radar based Human Recognition u...

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Patipon Petchtone Denchai Worasawate Tiwat Pongthavornkamol Kazuhiko Fukawa Yuyuan Chang Department of Electrical Engineering Faculty of Engineering Kasetsart University Bangkok Thailand National Electronic and Computer Technology Center National Science and Technology Development Agency Pathum Thani Thailand School of Engineering Tokyo Institute of Technology Tokyo Japan

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

The demand of indoor human identification systems that prioritize privacy has led to an increased interest in wireless sensing devices such as radar. Several studies have identified distinctive characteristics of human movement that cause Doppler signatures, which can be used for subject identification. Following them, this paper proposes an alternative machine learning approach for human identification, which uses only Doppler information from each subject by using FMCW radar. Experimental results in the two-subject scenarios show that the proposed method can achieve an accuracy of 96.2% (±1.1%) when data for both training and verification are obtained from the same scenarios, while an accuracy of 67.0% (±2.8 % ) can be achieved when data for the verification are obtained from different scenarios

关键词： Wireless communication Training Wireless sensor networks Privacy Accuracy Doppler radar Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Short-Term Load Forecasting with TDCI: Temporal Decomposition and Channel Independence 7

Short-Term Load Forecasting with TDCI: Temporal Decompositio...

引用

7th International Conference on Electrical, Mechanical and computer engineering, ICEMCE 2023

作者： Li, Wenxue Cheng, Chi Xu, Peihua Liu, Renfeng Zhang, Yun Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Prov. Wuhan430205 China Wuhan Institute of Technology Hubei Provincial Key Laboratory of Intelligent Robot Hubei Prov. Wuhan430205 China Hubei Meteorological Service Center Wuhan430079 China School of Educational Information Technology Central China Normal University Faculty of Artificial Intelligence Education Wuhan430079 China School of Mathematics and Computer Science Wuhan Polytechnic University Wuhan430023 China

ISBN: (纸本)9798350382877

Given the substantial load fluctuations, pronounced stochasticity, and non-linearity influenced by factors like weather and temperature in power load forecasting, we present a short-term load forecasting model based on TDCI. This model introduces several enhancements to boost forecasting accuracy. Firstly, TDCI employs temporal decomposition, separating time-series data into seasonal and trend components, enabling the capture of inherent seasonal patterns and long-term trends that significantly impact load forecasting accuracy. Additionally, the incorporation of locality-sensitive hashing attention efficiently processes relevant temporal patterns, enhancing model performance while reducing computational complexity. Lastly, a channel independence approach is applied to each variable, allowing tailored processing based on individual feature characteristics. This adaptive feature handling ensures effective capture of distinct properties, thereby enhancing forecasting accuracy. Experimental evaluations on a real-world power load dataset demonstrate the superior forecasting precision of our proposed model compared to existing models. © 2023 IEEE.

关键词： Electric power plant loads

来源：评论

学校读者我要写书评

暂无评论

Convenient noncooperative speckle-correlation imaging method

引用

Chinese Optics Letters 2023年第3期21卷 41-46页

作者：朱书阅衣文军付美城祁俊力朱梦均陈欣张洪玉杜俊逸王平刘菊李修建 College of Science National University of Defense TechnologyChangsha 410073China Xi'an Satellite Control Center Xi'an 71043China Tiansun Laboratory Changsha 410073China School of Computer Science and Technology Xidian UniversityXi'an 7100China College of Electronic Science National University of Defense TechnologyChangsha 410073China Hunan Institute of Traffic Engineering Hengyang 421099China

For speckle-correlation-based scattering imaging,an iris is generally used next to the diffuser to magnify the speckle size and enhance the speckle contrast,which limits the light flux and makes the setup ***,we experimentally demonstrate a non-iris speckle-correlation imaging method associated with an image resizing *** experimental results demonstrate that,by estimating an appropriate resizing factor,our method can achieve high-fidelity noncooperative speckle-correlation imaging by digital resizing of the raw captions or on-chip pixel binning without *** method opens a new door for noncooperative high-frame-rate speckle-correlation imaging and benefits scattering imaging for dynamic objects hidden behind opaque barriers.

关键词： speckle correlation image resizing pixel binning

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：