检索结果-内蒙古大学图书馆

IEEE Transactions on artificial intelligence 2025年第3期6卷 589-603页

作者： Qiu, Jian-Qiang Zhang, Chun-Yang Chen, C. L. Philip Fuzhou University College of Computer and Data Science Fuzhou350108 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China

Pretrained language models (PLMs) have shown remarkable performance on question answering (QA) tasks, but they usually require fine-tuning (FT) that depends on a substantial quantity of QA pairs. Therefore, improving the performance of PLMs in scenarios with only a small number of training examples, also known as a few-shot setting, is of great practical significance. Current mitigation strategies for the few-shot QA task largely rely on pretraining a QA task-specific language model from scratch, overlooking the potential of foundational PLMs to generate QA pairs, particularly in the few-shot setting. To address this issue, we propose a prompt-based QA data augmentation method aimed at automating the creation of high-quality QA pairs. It employs the PFT method, adapting the question generation process of PLMs to the few-shot setting. Additionally, we introduce a dynamic text filling training strategy. This strategy simulates the progressive human learning process, thereby alleviating overfitting of PLMs in the few-shot setting and enhancing their reasoning capability to tackle complex questions. Extensive experiments demonstrate that the proposed method outperforms existing approaches across various few-shot configurations. 2691-4581 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://***/publications/rights/*** for more information.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Advancements in Bug Traceability: A Systematic Mapping Study

Advancements in Bug Traceability: A Systematic Mapping Study

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Bangchao Hu, Shouya Ye, Luyao Wan, Hongyan Zou, Zhiyuan Li, Xiaoxiao Zhu, Jiaxu School of Computer Science and Artificial Intelligence Wuhan Textile University China

ISBN: (纸本)9781665410205

Traceability refers to the potential for traces to be established (i.e., created and maintained) and used. Bug Traceability (BT) is critical for enhancing software quality, reducing maintenance costs, and boosting team efficiency. To explore the trends and advancements of BT, we conduct a systematic mapping study (SMS). We initially retrieve 4674 citations from 7 databases spanning 2014 to 2023, and 24 primary studies meet the rigorous selection criteria. Our study identifies 6 types of bug trace links, 8 traceability strategies, and 47 bug traceability recovery (BTR) techniques. Among them, 47 BTR techniques can be further classified into 6 categories. At the same time, we perform statistics on 113 datasets and 16 evaluation metrics used to assess the performance of BTR techniques proposed in the primary studies. In evaluating the overall quality of the primary studies, 8 dimensions are utilized to support technology transfer, categorizing the overall quality into 4 levels: poor, middle, good, and excellent, with 79% of primary studies evaluated at a good level. This study not only furnishes a clear definition of BT for scholarly reference, but also highlights that information retrieval (IR), machine learning (ML) and deep learning (DL) techniques are the mainstream techniques used for BTR. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Task Scheduling Algorithm Based on Learning Automata for Cloud Computing 5

A Dynamic Task Scheduling Algorithm Based on Learning Automa...

引用

5th International Seminar on artificial intelligence, Networking and Information technology, AINIT 2024

作者： Shi, Heng Xie, Zhenping School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9798350385557

In the realm of cloud computing, suboptimal usage of system resources and an imbalance in task scheduling can result in inefficient resource utilization and system overload. In response to these challenges, we introduce the Dynamic Task Scheduling Algorithm based on Learning Automata (DTSALA). This algorithm harnesses the adaptive learning mechanism inherent in Learning Automata (DTSALA). Throughout the iterative looping process of the algorithm, the action probability distribution model undergoes continuous updates triggered by reward and punishment signals. The adaptive learning mechanism serves to mitigate resource wastage and prevent system overload by dynamically adjusting task scheduling actions based on prevailing system conditions. To assess the efficacy of the DTSALA algorithm, we conducted simulations comparing its performance with that of other widely used task scheduling algorithms, such as Max-Min, Min-Min, Genetic Algorithm (GA), Whale Optimization Algorithm (WOA), and Hybrid Whale Genetic Algorithm (HWGA). The simulation results unequivocally demonstrate the superior performance of the DTSALA algorithm, showcasing improvements in load balancing rate, task execution time, and system resource utilization when compared to these algorithms. By achieving a heightened load balancing rate, the DTSALA algorithm ensures equitable distribution of tasks across available system resources, thereby optimizing resource utilization. Furthermore, it reduces task execution time through efficient allocation of tasks to appropriate resources, ultimately enhancing the overall system performance and user experience within the cloud computing environment. © 2024 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

PLG-IQB: Parallel LSTM-GRU with Improved QuickBundles for Vessel Trajectory Prediction 9

PLG-IQB: Parallel LSTM-GRU with Improved QuickBundles for Ve...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Chen, Xueqin Yang, Jinlong School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9798350376548

With the advancement of intelligent transportation systems, ship automatic identification system (AIS) data contains rich maritime traffic information. Utilizing this information effectively contributes to enhancing the efficiency of ship trajectory prediction. Traditional deep learning trajectory prediction algorithms often focus on improving the accuracy of short-term prediction models while neglecting the thorough utilization of navigational features, thereby limiting the achievement of longer-term trajectory prediction. To address the current inability of ship trajectory prediction to perform long-term forecasts, this study proposes an improved QuickBundles clustering algorithm for extracting navigational features. Subsequently, this navigational information is integrated into a parallel LSTM-GRU prediction model to achieve longer-term ship trajectory prediction. Experiments are conducted using data from the Houston-Galveston Bay area obtained from open sources (https://***), and the results demonstrate that the PLG-IQB algorithm performs well in long-term trajectory prediction. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Improved Proximal Policy Optimization Algorithm for Controller Design in Hybrid UAVs∗

Improved Proximal Policy Optimization Algorithm for Controll...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Qi, Mingyu Zheng, Hongyuan Zhai, Xiangping Bryce Zhu, Qi School of Computer Science and Technology School of Artificial Intelligence School of Software at Nanjing University of Aeronautics and Astronautics Nanjing211106 China

ISBN: (纸本)9781665410205

Drones have become an indispensable tool in our daily lives. While fixed-wing and rotary-wing drones are common types, each comes with its own set of advantages and disadvantages. Hybrid drones, however, combine the strengths of both types, enabling vertical takeoff and landing, hovering, and remote flight. Nonetheless, the aerodynamics of hybrid drones are exceedingly intricate, leading to a sluggish pace in their development. In this article, we propose a neural network controller design, employing the reinforcement learning Proximal Policy Optimization (PPO) algorithm to train the controller. Additionally, we integrate an attention mechanism into the network's input section to emphasize the speed variable, thereby enhancing the data processing and improving the model performance and efficiency. Experimental results demonstrate that our approach yields a controller with superior stability and optimal value. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Reinforcement Learning Framework for Stock Market Prediction 4

A Hybrid Deep Reinforcement Learning Framework for Stock Mar...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Anjaneyulu, Gudla Reddy, Pundru Chandra Shaker Praveen, Pappula School of Computer Science and Artificial Intelligence Sr University Warangal India

ISBN: (纸本)9798350352931

Predicting and trading stock values is an intriguing and intricate area of study that keeps getting more and more attention. Generating quick and accurate decisions is essential for generating money in the stock market. Advanced predictive algorithms, made possible by technological advancements, are changing the way investors approach their work. A key component of this shift is the increasing use of automated decision-making processes driven by historical data analysis, especially in the context of individual stocks. Researchers have recently focused on deep reinforcement learning algorithms, which have shown encouraging results and could lead to better stock market forecasts. This paper presents a groundbreaking method that differs from the current models that are based on ANN and LSTM algorithms. Precisely for stock market anticipation, this research constructs a revolutionary architecture by merging ANN, LSTM, and NLP approaches with the deep-Q-network(DQN). This cutting-edge architecture relies on a plethora of stock market data, particularly that pertaining to gold stocks. Extensive dataset validation of the generated model's predictive prowess demonstrates its capacity to estimate the initial stock rate for the upcoming day. In the end, this research adds new dimensions to the field of stock market prediction and provides significant insights. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Based on Feature Decoupling and Domain Adaptation 5

Federated Learning Based on Feature Decoupling and Domain Ad...

引用

5th International Seminar on artificial intelligence, Networking and Information technology, AINIT 2024

作者： Wu, Jie Qian, Xuezhong Song, Wei School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9798350385557

Federated Learning (FL) refers to a machine learning approach in which terminal devices collaborate under a server's coordination to collectively refine a global model using their localized data. However, client data heterogeneity can seriously reduce the performance of FL. To tackle the aforementioned issues, this paper presents FedMIDA, a Federated Learning Optimisation Method that utilizes Feature Decoupling and Domain Adaptation. FedMIDA incorporates a feature decoupling module that employs Minimised Mutual Information Neural Estimation (MINE) to eliminate irrelevant information and noise interference from the classification task. It extracts crucial features for adversarial domain adaptation and dynamically adjusts the data distribution between devices to mitigate the negative impact of data heterogeneity. The experimental results demonstrate that the FedMIDA algorithm can enhance accuracy by up to 7.56% compared to other benchmark algorithms under varying degrees of data heterogeneity. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Construction of Object-Oriented Reverse Analysis and Design Model for the rCore Operating System 4

Construction of Object-Oriented Reverse Analysis and Design ...

引用

4th International Conference on Electronic Information Engineering and computer technology, EIECT 2024

作者： Zhang, Jiawen Shen, Fengshan Jiu, Mingyuan School of Computer Science and Artificial Intelligence Zhengzhou University Zhengzhou China

ISBN: (纸本)9798331528850

Software document is a file that records the composition and workflow of software, and it is an important basis for software maintenance and development. At present, we have the source program of the rCore operating system, but there is no document about the program composition and workflow. In this paper, based on the source program, the module files of the system are analyzed, and the object-oriented composition model and the cooperation model between module functions of the rCore operating system are generated in reverse, which completes the reverse engineering work of the system and lays the foundation for the continuous development and maintenance of the system. © 2024 IEEE.

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Occluded human pose estimation based on limb joint augmentation

引用

Neural Computing and Applications 2025年第3期37卷 1241-1253页

作者： Han, Gangtao Song, Chunxiao Wang, Song Wang, Hao Chen, Enqing Wang, Guanghui School of Electrical and Information Engineering Zhengzhou University Zhengzhou China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Department of Computer Science Toronto Metropolitan University Toronto Canada

Human pose estimation aims at locating the specific joints of humans from the images or videos. While existing deep learning-based methods have achieved high positioning accuracy, they often struggle with generalization in occlusion scenarios. In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies. Specifically, the occlusion blocks are at first employed to randomly cover the limb joints of the human bodies from the training images, imitating the scene where the objects or other people partially occlude the human body. Trained by the augmented samples, the pose estimation model is encouraged to accurately locate the occluded keypoints based on the visible ones. To further enhance the localization ability of the model, this paper constructs a dynamic structure loss function based on limb graphs to explore the distribution of occluded joints by evaluating the dependence between adjacent joints. Extensive experimental evaluations on two occluded datasets, OCHuman and CrowdPose, demonstrate significant performance improvements without additional computation cost during inference. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

RandoMix: a mixed sample data augmentation method with multiple mixed modes

引用

Multimedia Tools and Applications 2025年第8期84卷 4343-4359页

作者： Liu, Xiaoliang Shen, Furao Zhao, Jian Nie, Changhai National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China School of Electronic Science and Engineering Nanjing University Nanjing China

data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our results demonstrate its superior erformance compared to existing techniques such as Mixup, CutMix, Fmix, and ResizeMix. Notably, RandoMix excels in enhancing model robustness against adversarial noise, natural noise, and sample occlusion. The comprehensive experimental results and insights into parameter tuning underscore the potential of RandoMix as a versatile and effective data augmentation method. Moreover, it seamlessly integrates into the training pipeline. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： data augmentation Diversity Mixed-sample RandoMix Robustness

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：