检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Berger, Uri Abend, Omri Frermann, Lea Stanovsky, Gabriel School of Computer Science and Engineering The Hebrew University of Jerusalem School of Computing and Information Systems University of Melbourne Australia

Incorporating automatically predicted human feedback into the process of training generative models has attracted substantial recent interest, while feedback at inference time has received less attention. The typical feedback at training time, i.e., preferences of choice given two samples, does not naturally transfer to the inference phase. We introduce a novel type of feedback - caption reformulations - and train models to mimic reformulation feedback based on human annotations. Our method does not require training the image captioning model itself, thereby demanding substantially less computational effort. We experiment with two types of reformulation feedback: first, we collect a dataset of human reformulations that correct errors in the generated captions. We find that incorporating reformulation models trained on this data into the inference phase of existing image captioning models results in improved captions, especially when the original captions are of low quality. We apply our method to non-English image captioning, a domain where robust models are less prevalent, and gain substantial improvement. Second, we apply reformulations to style transfer. Quantitative evaluations reveal state-of-the-art performance on German image captioning and English style transfer, while human validation with a detailed comparative framework exposes the specific axes of improvement. Copyright © 2025, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Enhancing student performance prediction: the role of class imbalance handling in machine learning models

引用

Discover computing 2025年第1期28卷 1-34页

作者： Althaqafi, Turki Saleem, Farrukh AL-Ghamdi, Abdullah AL-Malaise Computer Science Department School of Engineering Computing and Design Dar Al-Hekma University Jeddah Saudi Arabia School of Built Environment Engineering and Computing Leeds Beckett University Leeds UK Information Systems Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

The Learning Management System (LMS) is an essential tool for educational institutions that facilitates content delivery, assessments, lecture delivery, and collaboration to enhance the learning experience. This study explores the role of LMS in creating an effective learning environment to improve students’ academic performance. To achieve the main objective of this study, we utilized a dataset [xAPI-Edu-Data] comprising multiple factors, such as academic, psychological, and cognitive engagement. Various machine learning techniques are employed to assess the impact of engagement activities on students’ performance. Initially, a class imbalance issue identified in the dataset and addressed using SMOTE technique. In addition, other resampling strategies applied to compare the effectiveness of proposed work. The model performance evaluated and compared using different evaluation metrics before and after data enrichment. In addition, hyperparameter optimization is conducted using a grid search approach to enhance models’ accuracy. The performance of individual models such as support vector machine (0.81), logistic regression (0.80), and decision tree (0.75) enhanced using the enriched dataset. The integration of multiple base learners into an ensemble model, with random forest as the stacking learner, achieved a weighted precision of 0.83, improving from 0.60 with the original dataset. The implementation of the stacking approach with enriched dataset has identified a better result and improved accuracy by 23%. The key contribution of this study includes identifying the effectiveness of data enrichment in improving prediction accuracy. Moreover, the research highlights the role of student engagement and behavior in measuring academic performance. The proposed model can identify the factors behind low performance, allowing further actions to be taken. Based on the prediction, the educators can work on the associated factors that could be low engagement, participation, or

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Solution to Quantum Process Tomography: Error Analysis and Optimal Design

引用

IEEE Transactions on Information Theory 2025年第3期71卷 1803-1823页

作者： Xiao, Shuixin Wang, Yuanlong Zhang, Jun Dong, Daoyi Mooney, Gary J. Petersen, Ian R. Yonezawa, Hidehiro University of New South Wales School of Engineering and Technology CanberraACT2600 Australia University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China The Australian National University School of Engineering CanberraACT2601 Australia Chinese Academy of Sciences Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing100190 China The Australian National University CIICADA Laboratory School of Engineering CanberraACT2601 Australia The University of Melbourne School of Physics ParkvilleVIC3010 Australia RIKEN Center for Quantum Computing Saitama351-0198 Japan Centre for Quantum Computation and Communication Technology Australian Research Council CanberraACT2600 Australia

Quantum process tomography is a critical task for characterizing the dynamics of quantum systems and achieving precise quantum control. In this paper, we propose a two-stage solution for both trace-preserving and non-trace-preserving quantum process tomography. Utilizing a tensor structure, our algorithm exhibits a computational complexity of O(MLd2) where d is the dimension of the quantum system and M, L(M≥ d2, L≥ d2) represent the numbers of different input states and measurement operators, respectively. We establish an analytical error upper bound and then design the optimal input states and the optimal measurement operators, which are both based on minimizing the error upper bound and maximizing the robustness characterized by the condition number. Numerical examples and testing on IBM quantum devices are presented to demonstrate the performance and efficiency of our algorithm. © 1963-2012 IEEE.

关键词： Error analysis

来源：评论

学校读者我要写书评

暂无评论

AUTOTEE: Automated Migration and Protection of Programs in Trusted Execution Environments

arXiv

引用

arXiv 2025年

作者： Han, Ruidong Yang, Zhou Ma, Chengyan Liu, Ye Niu, Yuqing Ma, Siqi Gao, Debin Lo, David School of Computing and Information Systems Singapore Management University Singapore School of Computer Science and Engineering UNSW Sydney Australia

Trusted Execution Environments (TEEs) isolate a special space within a device’s memory that is not accessible to the normal world (also known as Untrusted Environment), even when the device is compromised. Thus, developers can utilize TEEs to provide strong security guarantees for their programs, making sensitive operations like encrypted data storage, fingerprint verification, and remote attestation protected from malicious attacks. Despite the strong protections offered by TEEs, adapting existing programs to leverage such security guarantees is nontrivial, often requiring extensive domain knowledge and manual intervention, which makes TEEs less accessible to developers. This motivates us to design AUTOTEE, the first Large Language Model (LLM)-enabled approach that can automatically identify, partition, transform, and port sensitive functions into TEEs with minimal developer intervention. By manually reviewing 68 repositories, we constructed a benchmark dataset consisting of 385 sensitive functions eligible for transformation, on which AUTOTEE achieves a high F1 score of 0.91. AUTOTEE effectively transforms these sensitive functions into their TEE-compatible counterparts, achieving success rates of 90% and 83% for Java and Python, respectively. We further provide a mechanism to automatically port the transformed code to different TEE platforms, including Intel SGX and AMD SEV, demonstrating that the transformed programs run successfully and correctly on these platforms. © 2025, CC BY-NC-SA.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

Multi-View Test-Time Adaptation for Semantic Segmentation in Clinical Cataract Surgery

引用

IEEE Transactions on Medical Imaging 2025年第5期44卷 2307-2318页

作者： Li, Heng Ou, Mingyang Li, Haojin Qiu, Zhongxi Niu, Ke Fu, Huazhu Liu, Jiang Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China Beijing Information Science and Technology University Computer School Beijing100192 China Institute of High Performance Computing Agency for Science Technology and Research Fusionopolis Way 138632 Singapore Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Shenzhen518055 China

Cataract surgery, a widely performed operation worldwide, is incorporating semantic segmentation to advance computer-assisted intervention. However, the tissue appearance and illumination in cataract surgery often differ among clinical centers, intensifying the issue of domain shifts. While domain adaptation offers remedies to the shifts, the necessity for data centralization raises additional privacy concerns. To overcome these challenges, we propose a Multi-view Test-time Adaptation algorithm (MUTA) to segment cataract surgical scenes, which leverages multi-view learning to enhance model training within the source domain and model adaptation within the target domain. In the training phase, the segmentation model is equipped with multi-view decoders to boost its robustness against variations in cataract surgery. During the inference phase, test-time adaptation is implemented using multi-view knowledge distillation, enabling model updates in clinics without data centralization or privacy concerns. We conducted experiments in a simulated cross-center scenario using several cataract surgery datasets to evaluate the effectiveness of MUTA. Through comparisons and investigations, we have validated that MUTA effectively learns a robust source model and adapts the model to target data during the practical inference phase. © 1982-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Assessing Susceptibility Factors of Confirmation Bias in News Feed Reading 25

Assessing Susceptibility Factors of Confirmation Bias in New...

引用

Proceedings of the 2025 CHI Conference on Human Factors in computing systems

作者： Nattapat Boonprakong Saumya Pareek Benjamin Tag Jorge Goncalves Tilman Dingler School of Computing and Information Systems University of Melbourne Parkville Victoria Australia School of Computing and Information Systems University of Melbourne Melbourne Victoria Australia School of Computer Science and Engineering University of New South Wales Sydney New South Wales Australia School of Computing and Information Systems University of Melbourne Melbourne Australia Industrial Design Engineering Delft University of Technology Delft Netherlands

来源：评论

学校读者我要写书评

暂无评论

Threshold Password-Hardening Updatable Oblivious Key Management

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4799-4814页

作者： Jiang, Changsong Xu, Chunxiang Liu, Zhen Dong, Xinfeng Zhang, Wenzheng University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Singapore Management University School of Computing and Information Systems Bras Basah 188065 Singapore Huzhou313001 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Science and Technology on Communication Security Laboratory Chengdu610041 China

We propose a threshold password-hardening updatable oblivious key management system dubbed TPH-UOKM for cloud storage. In TPH-UOKM, a group of key servers share a user-specific secret key for a user, and assist the user in producing her/his password-derived private key in a threshold and oblivious way, where the password is hardened to resist offline dictionary guessing attacks. Anyone can outsource data protected with the user's password-derived public key to the cloud server, and merely the user holding the correct password can recover the password-derived private key for data access. TPH-UOKM can accomplish decryption of N ciphertexts with the complexity O(1) of communication between a user and the key servers, which outperforms existing schemes. TPH-UOKM supports password update. The cloud server can update all protected data of a user with an update token to be accessible only with the new password, which resists password leakage. We present a two-level proactivization mechanism to periodically update user-specific secret key shares and the key servers to thwart perpetual compromise of them, where the renewal of user-specific secret key shares reduces computation and communication costs compared to existing approaches. Provable security and high efficiency of TPH-UOKM are demonstrated by comprehensive analyses and performance evaluations. © 2005-2012 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

RUM-NN: A Neural Network Model Compatible with Random Utility Maximisation for Discrete Choice Setups

arXiv

引用

arXiv 2025年

作者： Bagheri, Niousha Ghasri, Milad Barlow, Michael School of Engineering and Technology UNSW Canberra ACT2600 Australia School of Systems and Computing UNSW Canberra ACT2600 Australia

This paper introduces a framework for capturing stochasticity of choice probabilities in neural networks, derived from and fully consistent with the Random Utility Maximization (RUM) theory, referred to as RUM-NN. Neural network models show remarkable performance compared with statistical models;however, they are often criticized for their lack of transparency and interpretability. The proposed RUM-NN is introduced in both linear and non-linear structures. The linear RUM-NN retains the interpretability and identifiability of traditional econometric discrete choice models while using neural network-based estimation techniques. The non-linear RUM-NN extends the model’s flexibility and predictive capabilities to capture nonlinear relationships between variables within utility functions. Additionally, the RUM-NN allows for the implementation of various parametric distributions for unobserved error components in the utility function and captures correlations among error terms. The performance of RUM-NN in parameter recovery and prediction accuracy is rigorously evaluated using synthetic datasets through Monte Carlo experiments. Additionally, RUM-NN is evaluated on the Swissmetro and the London Passenger Mode Choice (LPMC) datasets with different sets of distribution assumptions for the error component. The results demonstrate that RUM-NN under linear utility structure and IID Gumbel error terms can replicate the performance of Multinomial Logit (MNL) model, but relaxing those constraints yields to superior performance for both Swissmetro and LMPC datasets. By introducing a novel estimation approach aligned with statistical theories, this study empowers econometricians to harness the advantages of neural network models. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Hotpatching on the Fly - Mitigating Drone Incidents Arising from Incorrect Configuration

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Han, Ruidong Li, Juanru Ma, Zhuo Lo, David Shaghaghi, Arash Ma, JianFeng Ma, Siqi Xidian University School of Cyber Engineering Xi'an China Singapore Management University School of Computing and Information Systems Singapore Feiyu Security Shanghai China Unsw Sydney School of Computer Science and Engineering Australia

Manufacturers offer adjustable control parameters for flight control systems to accommodate diverse environments and missions. To ensure flight safety, they also develop established boundaries, i.e., range specifications for parameter values. However, even when the configuration parameters fall within the prescribed manufacturer range, they could still lead to instability or even severe incidents like crashes, which are referred to as Range Specification Bugs. Prior research has suggested shrinking the range of parameter values to protect drones from the adverse effects of such bugs. However, narrowing the range of parameters may only reduce the probability of errors and could potentially limit the drone's adaptability. To overcome this limitation, we present an online approach that analyzes a sequence of flight states to detect any potential triggering of bugs and rectify the drone by dynamically adjusting its parameters. We implemented the rectification approach, ConFix, and applied it in current prevalent flight control systems, Ardupilot and PX4. The results demonstrated that ConFix achieved an average rectification success at 80% on average. © 2004-2012 IEEE.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

H-Rum-Nn: A Hybrid Neural Network Model Compatible with the Random Utility Maximisation

SSRN

引用

SSRN 2025年

作者： Bagheri, Niousha Ghasri, Milad Barlow, Michael School of Engineering and Technology UNSW CanberraACT2600 Australia School of Systems & Computing UNSW CanberraACT2600 Australia

Accurate prediction and analysis of travel mode choices are critical for effective transportation planning and have garnered significant attention in research. Traditionally, travel mode choice prediction has been conducted using discrete choice models, some of which have incorporated latent variables to capture subtle human behaviours. This study introduces the Hybrid Neural Network Model compatible with the Random Utility Maximisation (H-RUM-NN) model to incorporate latent variables in a neural network model that is fully compatible with the random utility maximisation theory. A linear version and a nonlinear version of H-RUM-NN are introduced, where the nonlinear structure incorporates the Convolutional Neural Network (CNN). The H-RUM-NN model leverages the flexibility of neural networks to capture any error distribution and incorporates latent variables within the neural network framework. To evaluate the H-RUM-NN model, we applied both synthetic and real datasets, comparing its performance against the traditional Integrated Choice and Latent Variable (ICLV) model. Our synthetic dataset analysis demonstrated that the H-RUM-NN model can accurately recover true parameter values, performing comparably to ICLV. For the real-world application, we utilized stated preference data from employed residents in Sydney, Australia, about their Traffic Information Apps (TIAs) usage. The empirical results revealed that the H-RUM-NN model outperforms ICLV in prediction accuracy and log-likelihood. This superior performance highlights the potential of H-RUM-NN in capturing complex relationships and improving the predictive power of travel mode choice models. © 2025, The Authors. All rights reserved.

关键词：

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：