检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sun, Weisong Miao, Yun Li, Yuekang Zhang, Hongyu Fang, Chunrong Liu, Yi Deng, Gelei Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Computing and Data Science Nanyang Technological University Singapore Singapore School of Computer Science and Engineering University of New South Wales Sidney Australia School of Big Data and Software Engineering Chongqing University Chongqing China

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of code-related tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLM-based code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs’ model settings (including top_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs’ abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types (e.g., procedural and object-oriented programming languages). Finally, we unexpectedly find that CodeLlama-Instruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code implementation details and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of *** Codes 68-04 Copyright © 202

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Research and development of two-factor authentication methods using neural networks 4

Research and development of two-factor authentication method...

引用

4th IEEE International Conference on Smart Information Systems and Technologies, SIST 2024

作者： Darbek, Temirkhan Mukasheva, Assel Bissembayev, Alibek Gnatyuk, Sergiy Mukammejanova, Dinargul The Department of Information Systems and Cybersecurity Almaty university of power engineering and telecommunications Almaty Kazakhstan The School of Information Technology and Engineering Kazakh-British Technical University Almaty Kazakhstan The School of Information Technology and Engineering Kazakh British Technical University Almaty Kazakhstan The Faculty of Cybersecurity Computer and Software Engineering at National Aviation University National Aviation University Kyiv Ukraine The Department of Artificial Intelligence and Big Data Kazakh National University named after Al-Farabi Almaty Kazakhstan

ISBN: (纸本)9798350374865

This article is devoted to the research and development of innovative two-factor authentication (2FA) methods using neural networks. 2FA plays a key role in ensuring the security of data and accounts in the modern digital world, and the use of neural networks opens up new prospects in strengthening protection and improving the user experience. The article presents an analysis of existing 2FA methods, identifies their limitations, and discusses the advantages of using neural networks in this area. The main focus is on the development of new authentication algorithms based on deep learning, providing effective anomaly detection and support for a dynamic adaptive approach. In the context of the article, the issues of privacy and data security are also considered, as well as the possibilities of applying the developed methods in various fields, including finance, medicine and the Internet of Things. The results of the study represent a significant contribution to the field of digital. © 2024 IEEE.

关键词： biometric authentication deep learning digital security identification Neural networks

来源：评论

学校读者我要写书评

暂无评论

big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

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

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (big-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/big-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Learned Video Compression with Spatial-Temporal Optimization

Learned Video Compression with Spatial-Temporal Optimization

引用

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

作者： Yiming Wang Qian Huang Bin Tang Wenting Liu Wenchao Shan Qian Xu College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China

Previous optical flow based video compression is gradually replaced by unsupervised deformable convolution (DCN) based method. This is mainly due to the fact that the motion vector (MV) estimated by the existing optical flow network is not accurate and may introduce extra artifacts. However, DCN based method is difficult for training owing to the lack of explicit guidance in the feature space. In this work, we propose a learned video compression with spatial-temporal optimization. Specifically, we first propose the spatial-temporal motion refinement module to improve the accuracy of MV estimated by the optical flow network for prediction. Then, we propose the In-loop filter module to remove compression artifacts and improve the reconstructed frame quality. Finally, comprehensive experimental results demonstrate our proposed method outperforms the recent learned methods on three benchmark datasets. Moreover, our method also beats the H.266/VVC in terms of MS-SSIM metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Establish a smart healthcare system with AIoT for Chinese Medicine 10

Establish a smart healthcare system with AIoT for Chinese Me...

引用

10th International Conference on Orange Technology, ICOT 2022

作者： Wei, Chun-Cheng Chen, Ching-Wen Hung, Lon-Chen School of Software and Big Data Changzhou College of Information Technology China Lunghwa University of Science and Technology Department of Multimedia and Game Science Taoyuan Taiwan Lunghwa University of Science and Technology Department of Electronic Engineering Taiwan

ISBN: (纸本)9781665454193

This study establishes an intelligent medical system for diagnosis and treatment of Chinese medicine. Temperature and heart rate were measured using a variety of Internet of things technologies, including the WeMos D1 Mini with ESP8266 integrated and thermistors, and then the resistance was learned to relate to temperature via a neural network. In addition, the AD8232 biomedical sensor and the WeMos D1 Mini were used for ECG measurements and heart rate conversion. A self-written mobile application designed with multiple units to collect data from a variety of patients. The tongue diagnosis unit can recognize the characteristics of tongue substance and coating. The pulse examination unit adopts the five layer pulse method of Yaowangmai pulse. The inquiry unit adopts the syndrome differentiation method of Dr. Shaogong Shen. These IoT data, information if the patient's tongue diagnosis, five-layer pulse examination data and various inquiry data can all be read and transmitted to the cloud. The intelligent medical system of Chinese medicine in this study can also make preliminary treatment recommendations based on a variety of patient data and provide corresponding treatment drugs © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation Random Vector Functional Link for White Blood Cell Classification

Domain Adaptation Random Vector Functional Link for White Bl...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Qin Wang Xi-Zhao Wang Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

There's growing recognition of how machine learning can revolutionize the precision and swiftness of clinical diagnoses by improving the classification of white blood cells. However, a machine learning model specialized in white blood cell classification demands access to a large trove of well-annotated data. This poses a challenge, as in the medical field, annotating data comprehensively comes with a high cost in terms of both money and time. To circumvent this, domain adaptation (DA) techniques are employed to leverage similar cell images from related domains, thereby boosting the model's performance in white blood cell classification in specific contexts. Among the myriad DA approaches available for this application, including TCA-based and deep learning methods, all typically suffer from lengthy training durations. Addressing this challenge, we introduce a novel DA method inspired by the random vector functional link (RVFL) network, a type of neural network characterized by its random weights. Our proposed method, named Domain Adaptation Random Vector Functional Link (DA-RVFL), capitalizes on the efficiency of RVFL networks to enhance white blood cell classification. This innovative approach shows some insights for future research in the efficient and effective classification of white blood cells.

关键词： White blood cells Training Deep learning Adaptation models Neural networks Focusing Vectors data models Medical diagnosis Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Wavelet Frequency Laplacian Pyramid Network for Vehicle Logo Super-Resolution 5

Deep Wavelet Frequency Laplacian Pyramid Network for Vehicle...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Yu, Yue She, Kun Kang, Jian Jackson, Jehoiada Shaukat, Hayat Li, Yang University of Electronic Science and Technology of China Information and Software Engineering Chengdu China Sichuan Provincial Big Data Technology Services Center Chengdu China Iqra National University Department of Computer Science Peshawar Pakistan

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

In intelligent transportation systems, generated high-resolution images promote high-level version tasks compared to captured low-resolution vehicle logo images, which lack adequate details. However, the resolution of vehicle logo images is restricted by factors like hardware. Few attempts have been made with the Laplacian pyramid structure, while images can be represented on multi-scale in the wavelet domain. This paper proposes a progressive reconstruction network with a Laplacian pyramid (WLapsrn) structure to predict the sub-bands of wavelet transformed images. Firstly, we adopted a suitable network architecture for feature extraction using residual blocks for the advanced reconstruction network in the wavelet domain. Then, the Texture-Charbonnier loss function is used to achieve highfrequency sub-bands reconstruction. Ultimately, the inverse 2D discrete stationary wavelet transform is applied to generate predicting HR images from mapped coefficients. Extensive objective and subjective evaluations using benchmark datasets demonstrate that the proposed algorithm achieves superior visual effects compared with the state-of-the-art Laplacian-based algorithms. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A new generation method of basic probability assignment based on the normal membership function

A new generation method of basic probability assignment base...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Fu, Yun Tang, Yongchuan Zhou, Deyun Chongqing University College of Computer Science Chongqing400030 China Chongqing University School of Big Data and Software Engineering Chongqing401331 China Northwestern Polytechnical University School of Microelectronics Shaanxi Xi'an710072 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Dempster-Shafer evidence theory is an important technique to fuse uncertain information and make decisions. As the first step of applying the evidence theory in practical applications, the generation of basic probability assignment(BPA) directly affects the subsequent fusion and decision-making. However, it is still a difficult and open issue. This paper proposed a new method to generate BPA with the normal membership function. First, we construct a normal membership function for each class with its mean value and standard deviation of a certain attribute, whose function value represents the probability of a sample belonging to it. According to the rule of the intersection of fuzzy sets, the probability of a sample belonging to the proposition with multiple classes is the minimum function value of the normal membership functions for all relevant classes. Therefore, the BPA for the attribute can be obtained with the rule. Similarly, the BPAs for other attributes can also obtained with the same method. To make decision, the BPAs for all attributes will be combined into a fused BPA with the Dempster combination rule. The final classification result is the proposition with the largest value in it. Finally, we conduct the classification experiments on nine datasets from the UCI dataset and the result shows the superiority and robustness of the proposed method. © 2022 IEEE.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy data via Class-independent Margin in Dual Representation Space 39

Learning with Open-world Noisy Data via Class-independent Ma...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

关键词： Contrastive Learning

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：