检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Gao, Shiqi Gong, Tianxiang Lin, Zijie Xu, Runhua Zhou, Haoyi Li, Jianxin SKLCCSE School of Computer Science and Engineering Beihang University China School of Software Beihang University China National University of Singapore Singapore Zhongguancun Laboratory Beijing China

ISBN: (纸本)157735897X

Uncertainty estimation is essential for practical applications such as decision-making, risk assessment, and human-AI collaboration. However, uncertainty estimation in open-ended question-answering (QA) tasks presents unique challenges. The output space for open-ended QA is vast and discrete, and the autoregressive nature of LLMs, combined with the rapid increase in model parameters, makes inference sampling significantly costly. An ideal uncertainty estimation for LLMs should meet two criteria: 1) incur no additional inference cost and 2) capture the semantic dependencies of token-level uncertainty within sequences. We propose a promising solution that converts redundancy into randomness in the extensive parameters of LLMs to quantify knowledge uncertainty. We can obtain token-level Monte Carlo samples without multiple inferences by introducing randomness during a single forward pass. We theoretically analyze the FLUE sampling method and employ a post-processing method to learn the state transitions from token uncertainty to sequence uncertainty. In open-ended QA tasks, we demonstrate that FLUE can achieve competitive performance in estimating the uncertainty of generated sentences without extra inference overhead. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Path planning algorithm for two-dimensional raster maps based on deep reinforcement learning 7

Path planning algorithm for two-dimensional raster maps base...

引用

7th International Conference on Big Data Computing and Communications, BigCom 2021

作者： Li, Jie Zhang, Yuhan Tang, Jiaqi Liu, Xianjie Ibrahim, Abdulhamid Northeastern University Computer Science and Engineering Shenyang China Northeastern University Software College Shenyang China

ISBN: (纸本)9781665442527

Path planning is one of the main research contents of decision control. The problem of path planning can be described as finding a collision free path from the initial state to the target state in the environment. Raster-based path planning is a basic problem in robotics, games and other fields. Traditional path planning methods need to model the environment in advance, and then carry out path planning on the basis of known map information. However, there is a lot of dynamic information in the environment, such as pedestrians, movable objects. It is difficult for traditional algorithms to carry out path planning in the dynamic unknown environment. With the development of deep learning and reinforcement learning, such methods provide a new way to solve the problem of path planning. Aiming at resolving the shortcomings of traditional path planning algorithms, this paper adopts deep reinforcement learning algorithm to carry out path planning for two-dimensional raster maps, and finally validates and evaluates the performance of the algorithm within an efficient simulation environment. © 2021 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Inherent-attribute-aware dual-graph autoencoder for rating prediction

引用

Journal of Information and Intelligence 2024年第1期2卷 82-97页

作者： Yangtao Zhou Qingshan Li Hua Chu Jianan Li Lejia Yang Biaobiao Wei Luqiao Wang Wanqiang Yang School of Computer Science and Technology Xidian UniversityXi'an 710071China Intelligent Financial Software Engineering New Technology Joint Laboratory Xidian UniversityXi'an 710071China Shanghai Fairyland Software Corp. Ltd.Shanghai 200233China

Autoencoder-based rating prediction methods with external attributes have received wide attention due to their ability to accurately capture users'***,existing methods still have two significant limitations:i)External attributes are often unavailable in the real world due to privacy issues,leading to low quality of representations;and ii)existing methods lack considering complex associations in users'rating behaviors during the encoding *** meet these challenges,this paper innovatively proposes an inherent-attribute-aware dual-graph autoencoder,named IADGAE,for rating *** address the low quality of representations due to the unavailability of external attributes,we propose an inherent attribute perception module that mines inductive user active patterns and item popularity patterns from users'rating behaviors to strengthen user and item *** exploit the complex associations hidden in users’rating behaviors,we design an encoder on the item-item co-occurrence graph to capture the co-occurrence frequency features among ***,we propose a dual-graph feature encoder framework to simultaneously encode and fuse the high-order representations learned from the user-item rating graph and item-item co-occurrence *** experiments on three real datasets demonstrate that IADGAE is effective and outperforms existing rating prediction methods,which achieves a significant improvement of 4.51%~41.63%in the RMSE metric.

关键词： Rating prediction Graph convolutional network Autoencoder Inherent attribute aware

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach Using Survey and Ism Analysis for Security Coding Risks and Best Practices for Gsd Enterprises

SSRN

引用

SSRN 2023年

作者： Khan, Rafiq Ahmad Akbar, Muhammad Azeem Alzahrani, Abdulrahman Habibullah, Safa Alwageed, Hathal Salamah Alzahrani, Musaad School of Software Northwestern Polytechnical University Shaanxi Xian710129 China Software Engineering Research Group Department of Computer Science & IT University of Malakand Pakistan Software engineering LUT University Finland Information Systems and Technology Department College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia College of Computer and Information Sciences Jouf University Sakaka42421 Saudi Arabia Department of Computer Science Al-Baha University Al-Baha65799 Saudi Arabia

Context: Global software development (GSD) offers quality results, cost-effectiveness, and uninterrupted project delivery. However, integrating security into GSD remains a ***: This study aims to enhance security in GSD projects by developing a hybrid approach using an empirical survey and Interpretive Structural Model (ISM).Methods: Initially, we conduct a systematic literature review and questionnaire survey with 50 GSD security experts. Moreover, 13 experts were invited to analyze the interrelationships among the practices using ***: Initially, we identified 13 major security-coding risks and 82 practices to mitigate these risks. The ISM analysis revealed that out of the identified security-coding practices, "never submit security measures to illegitimate authority", "avoiding buffer overflow and format string vulnerabilities", "control the brute force attack", and "identify a middleman attack" were considered fully dependent. While "avoid revealing information to achieve a secure design" is entirely independent within the GSD security coding ***: The study aids GSD professionals in assessing readiness in establishing contractual trust, understanding the current process pros and cons, and addressing urgent issues in secure software development processes. © 2023, The Authors. All rights reserved.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Exploring Aspects of Agile software Development Risk – Results from a MLR 1

引用

29th European Systems, software and Services Process Improvement, EuroSPI 2022

作者： Nolan, Aaron Strickland, Ben Quinn, Adam Gallagher, Kyle Yilmaz, Murat Clarke, Paul M. School of Computing Dublin City University Dublin Ireland Department of Computer Engineering Gazi University Ankara Turkey Lero the Science Foundation Ireland Research Center for Software Lero Ireland

ISBN: (数字)9783031155598

ISBN: (纸本)9783031155581

Agile software development methods are widely used by software organisations, focusing on short developmental life cycles and customer satisfaction through the iterative and incremental development of software products. Despite their popularity, these methods present risks that may be underappreciated. This paper examines certain risks attributed to agile software development, with a focus on the lack of documentation, scope creep, technical debt and job satisfaction. Through the application of a multivocal literature review, we find that agile software development can greatly benefit projects. However, when agile methods are implemented inappropriately or sub-optimally, projects risk over-spending, delayed or defective software, employee turnover, and overall decreased productivity. Understanding the risks associated with agile software development can help practitioners to achieve higher efficiency and success in their software development projects. © 2022, Springer Nature Switzerland AG.

关键词： Job satisfaction

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Based Single Finger-Vein Recognition 6th

Ensemble Deep Learning Based Single Finger-Vein Recognition

引用

6th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2021

作者： Liu, Chongwen Qin, Huafeng Yang, Gongping Shen, Zhengwen Wang, Jun School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing400067 China School of Software Engineering Shandong University Jinan250101 China China University of Mining and Technology Jiangsu Xuzhou221116 China

ISBN: (纸本)9789811692468

Finger-vein biometrics has been extensively investigated for personal verification. Single sample per person (SSPP) finger-vein recognition is one of the open issues in finger-vein recognition. In this paper, a deep ensemble learning method is proposed for SSPP finger-vein recognition. To the best of our knowledge, this is the first work proposed for finger-vein identification with single finger-vein sample per person. First, we generate different feature maps from an input image, based on which multiple independent deep learning based classifiers are proposed for finger-vein identification. Second, a shared learning scheme is investigated among classifiers to improve their feature representation captivity. Third, an approach is proposed to adjust learning speed of weak classifiers, so that all classifiers achieve best performance at the same time. Finally, a deep ensemble learning method are proposed by combing all weak classifiers. The experimental results on two public finger-vein databases show that our approach outperforms its all classifiers and existing approaches, and achieves the state-of-the-art recognition results. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

MMR-HAD: Multi-scale Mamba Reconstruction Network for Hyperspectral Anomaly Detection

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Fu, Xiyou Zhang, Ting Cheng, Juan Jia, Sen Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Shaanxi Key Laboratory of Optical Remote Sensing and Intelligent Information Processing Xi'an710119 China

Hyperspectral anomaly detection (HAD) aims to identify anomalous objects from hyperspectral images (HSIs) whose spectral features significantly deviate from their surroundings. Existing HAD methods still reconstruct some anomalies during the background reconstruction process, which can seriously affect the detection accuracy. Consequently, inspired by Mamba's ability to effectively model long sequences, we propose a Multi-scale Mamba Reconstruction Network for Hyperspectral Anomaly Detection (MMR-HAD) by enhancing the representation of the background and inhibit anomalies from being reconstructed. MMR-HAD first removes most of the anomalous pixels in hyperspectral images using the Random Mask (RM) strategy, which reduces the interference of anomalous pixels on the background reconstruction and makes the background features more prominent. To further filter out the small amount of residual anomalous pixels, we propose the Multi-scale Dilated Attention Background Enhancement (MDABE) mechanism, which enhances the background representation. Finally, we apply the Multi-scale Dynamic Feature Fusion (MDFF) strategy to reconstruct the background image, further extracting and strengthening the background information, thus obtaining a pure background image. MMR-HAD, which focuses on generating a pure background, has been experimentally validated on seven real hyperspectral datasets. The results demonstrate that it excels in background enhancement and anomaly suppression, significantly improving detection accuracy. Introducing Mamba offers a promising solution for HAD, with substantial potential for practical application. © 1980-2012 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Serverless software engineering – and How to Get There. 1

引用

29th European Systems, software and Services Process Improvement, EuroSPI 2022

作者： McAleese, Stephen McLaughlin, Jordan Conway Detyna, Filip Murashev, Andrey Yilmaz, Murat Clarke, Paul M. School of Computing Dublin City University Dublin Ireland Department of Computer Engineering Gazi University Ankara Turkey Lero The Science Foundation Ireland Research Center for Software Dublin Ireland

ISBN: (数字)9783031155598

ISBN: (纸本)9783031155581

Serverless computing is on the rise but developing software to exploit this space involves a deep rethink of software architecture, deployment, and operation (perhaps also, software development processes and team structures). Central to this revolution, we find a compelling argument for distributed, services-based software architectures. But converting a large, established monolith architecture system to microservices is non-trivial and fraught with both cost and risk. For the many firms with established software systems, this architectural system conversion might be considered the first stop-off on the journey to serverless computing. In tandem, software deployment and production monitoring also require reinvention. The focus of this paper involves an examination of the advantages of microservices architectures, include techniques for migrating from monolith architectures. Through application of a Multivocal Literature Review (MLR), we find that migrating from a monolith architecture to a microservices architecture is risky and non-trivial, but that there are techniques that can be employed to support the transition. We find also that monoliths have their advantages which might be overlooked to some extent in the race to serverless computing. © 2022, Springer Nature Switzerland AG.

关键词： software architecture

来源：评论

学校读者我要写书评

暂无评论

Introduction

Synthesis Lectures on Data Management

引用

Synthesis Lectures on Data Management 2023年 1-13页

作者： Song, Shaoxu Chen, Lei School of Software Tsinghua University Beijing China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Data dependencies, such as functional dependencies (FDs), have been long recognized as integrity constraints in databases [42]. They are firstly utilized in database design [3]. Conventionally, data dependencies are extracted from application requirements for database standardization, and used in database design to ensure data quality. For instance, functional dependencies (FDs) [16] are employed to evaluate whether a relation is in third normal form (3NF) [42] or Boyce-Codd normal form (BCNF) [43]. FDs are extended to multivalued dependencies (MVDs) [13], i.e., every FD is also an MVD, in order to test whether a relation is in fourth normal form (4NF) [55]. Such data dependencies are also used in database query optimization [53, 86]. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimating Chlorophyll Content from Hyperspectral Data Using Gradient Features 23rd

Estimating Chlorophyll Content from Hyperspectral Data Usin...

引用

23rd International Conference on Computational science, ICCS 2023

作者： Ruszczak, Bogdan Wijata, Agata M. Nalepa, Jakub Faculty of Electrical Engineering Automatic Control and Informatics Department of Informatics Opole University of Technology Opole Poland Faculty of Biomedical Engineering Silesian University of Technology Zabrze Poland Faculty of Automatic Control Electronics and Computer Science Department of Algorithmics and Software Silesian University of Technology Gliwice Poland KP Labs Gliwice Poland

ISBN: (纸本)9783031360206

Non-invasive estimation of chlorophyll content in plants plays an important role in precision agriculture. This task may be tackled using hyperspectral imaging that acquires numerous narrow bands of the electromagnetic spectrum, which may reflect subtle features of the plant, and inherently offers spatial scalability. Such imagery is, however, high-dimensional, therefore it is challenging to transfer from the imaging device, store and investigate. We propose a machine learning pipeline for estimating chlorophyll content from hyperspectral data. It benefits from the Savitzky-Golay filtering to smooth the (potentially noisy) spectral curves, and from gradient-based features extracted from such a smoothed signal. The experiments revealed that our approach significantly outperforms the state of the art according to the widely-established estimation quality metrics obtained for four chlorophyll-related parameters. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine 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：