检索结果-内蒙古大学图书馆

4th International Conference on Information Communication and Signal Processing, ICICSP 2021

作者： Huang, Gehang Liu, Xinwei HDU-ITMO Joint Institute Hangzhou Dianzi University Hangzhou China College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China

ISBN: (纸本)9781665407571

Most of image quality metrics are designed for degraded images, and their performance are highly correlated with the human visual system. The rapid development of image enhancement techniques raises a new issue: how to evaluate the performance of image enhancement methods? It is obvious that many benefits can be obtained if existing image quality metrics can be applied to the performance evaluation of image enhancement algorithms. However, quite a few studies have investigated such an issue. In this paper, we conduct psychophysical experiments to investigate the performance of existing image quality metrics on enhanced images. Two databases that specifically designed for enhanced images are selected in the experiments for the collection of subjective evaluation results. The objective evaluation results are obtained from six selected image quality metrics. By calculating the correlation between subjective and objective results we can answer the question: the performance of existing selected image quality metrics is low on enhanced images. © 2021 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

CPLS: Optimizing the Assignment of LLM Queries

CPLS: Optimizing the Assignment of LLM Queries

引用

International Conference on software Maintenance (ICSM)

作者： Yueyue Liu Hongyu Zhang Zhiqiang Li Yuantian Miao School of Information and Physical Sciences The University of Newcastle Newcastle Australia School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science Shaanxi Normal University Shaanxi China

ISBN: (数字)9798350395686

ISBN: (纸本)9798350395693

Large Language Models (LLMs) like ChatGPT have gained significant attention because of their impressive capabilities, leading to a dramatic increase in their integration into intelligent software engineering. However, their usage as a service with varying performance and price options presents a challenging trade-off between desired performance and the associated cost. To address this challenge, we propose CPLS, a framework that utilizes transfer learning and local search techniques for assigning intelligent software engineering jobs to LLM-based services. CPLS aims to minimize the total cost of LLM invocations while maximizing the overall accuracy. The framework first leverages knowledge from historical data across different projects to predict the probability of an LLM processing a query correctly. Then, CPLS incorporates problem-specific rules into a local search algorithm to effectively generate Pareto optimal solutions based on the predicted accuracy and cost. To evaluate the proposed approach, we conduct extensive experiments on LLM-based log parsing, a typical software maintenance task. Our experimental results demonstrate that CPLS outperforms the baseline methods, providing solutions with the highest accuracy in 14 out of 16 instances. Compared to the baselines, CPLS achieves an accuracy improvement ranging from 1.24% to 485.54%, or reduces costs by 15.21% to 89.09% while maintaining the highest accuracy achieved by the baselines.

关键词： software maintenance Costs Accuracy Source coding Transfer learning software algorithms Predictive models Search problems Prediction algorithms software engineering

来源：评论

学校读者我要写书评

暂无评论

OptLLM: Optimal Assignment of Queries to Large Language Models

OptLLM: Optimal Assignment of Queries to Large Language Mode...

引用

IEEE International Conference on Web Services (ICWS)

作者： Yueyue Liu Hongyu Zhang Yuantian Miao Van-Hoang Le Zhiqiang Li School of Information and Physical Sciences The University of Newcastle Newcastle Australia School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science Shaanxi Normal University Shaanxi China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Large Language Models (LLMs) have garnered considerable attention owing to their remarkable capabilities, leading to an increasing number of companies offering LLMs as services. Different LLMs achieve different performance at different costs. A challenge for users lies in choosing the LLMs that best fit their needs, balancing cost and performance. In this paper, we propose a framework for addressing the cost-effective query allocation problem for LLMs. Given a set of input queries and candidate LLMs, our framework, named OptLLM, provides users with a range of optimal solutions to choose from, aligning with their budget constraints and performance preferences, including options for maximizing accuracy and minimizing cost. OptLLM predicts the performance of candidate LLMs on each query using a multi-label classification model with uncertainty estimation and then iteratively generates a set of non-dominated solutions by destructing and reconstructing the current solution. To evaluate the effectiveness of OptLLM, we conduct extensive experiments on various types of tasks, including text classification, question answering, sentiment analysis, reasoning, and log parsing. Our experimental results demonstrate that OptLLM substantially reduces costs by 2.40% to 49.18% while achieving the same accuracy as the best LLM. Compared to other multi-objective optimization algorithms, OptLLM improves accuracy by 2.94% to 69.05% at the same cost or saves costs by 8.79% and 95.87% while maintaining the highest attainable accuracy.

关键词： Sentiment analysis Costs Accuracy Uncertainty Web services Large language models Source coding Text categorization Predictive models Resource management

来源：评论

学校读者我要写书评

暂无评论

Assessing Air-Interface dataset Similarity and Diversity for AI-Enabled Wireless Communications

Assessing Air-Interface Dataset Similarity and Diversity for...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Hanning Tang Liusha Yang Rui Zhou Jing Liang Hong Wei Xuan Wang Qingjiang Shi Zhi-Quan Luo Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Wireless Research Department Huawei Company Shanghai China School of Software Engineering Tongji University Shanghai China

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

Ahstract- The integration of artificial intelligence (AI) into wireless communication systems is set to profoundly transform the design and optimization of emerging sixth-generation (6G) networks. The success of AI-driven wireless systems hinges on the quality of the air-interface data, which is fundamental to the performance of AI algorithms. Within data quality assessment (DQA), the measurement of similarity and diversity stands as crucial. Similarity assesses the consistency of datasets in mirroring their intrinsic statistical properties, which is essential for AI model accuracy. In contrast, diversity relates to the models' ability to generalize across various contexts. This paper concentrates on these aspects of DQA and proposes a comprehensive framework for analyzing similarity and diversity in wireless air-interface data. Catering to various data types, such as channel state information (CSI), signal-to-interference-plus-noise ratio (SINR), and reference signal received power (RSRP), the framework is validated using CSI data. Through this validation, we demonstrate the framework's efficacy in improving CSI compression and recovery in Massive Multiple-Input Multiple-Output (MIMO) systems, highlighting its significance and versatility in complex wireless network environments.

关键词： Wireless communication data integrity Conferences Atmospheric modeling Wireless networks Transforms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Deep Target Session Interest Network for Click-Through Rate Prediction

Deep Target Session Interest Network for Click-Through Rate ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hongjiang Zhong Junchao Ma Xiongbao Duan Shuting Gu Junmei Yao College of Big Data and Internet Shenzhen Technology University Shenzhen China College of Applied Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Click-Through Rate (CTR) prediction is one of the core tasks in the recommendation system (RS). In the feature presentation of CTR prediction model, user behavior sequences contain temporal features and implicit interests, which is used for sequential user behavior modeling. There are many deep CTR models on sequential user behavior modeling, while most of them overlook session-based and target-relevant interests. User behavior sequences are composed of multiple sessions, with highly homogeneous user interests within the same session, while user interests across different sessions are heterogeneous. Motivated by the above discoveries, we propose a novel Deep Target Session Interest Network (DTSIN) in this paper. We divide user behavior sequences into multiple original sessions, and append the target item at the end of each original session to obtain target session. Multi-head self-attention is employed to extract target-relevant interests from target sessions. Then, we apply splitting and mean pooling techniques to generate session interests and target interests. Bi-directional GRU (Bi-GRU) is leveraged to capture sequential relationships between session interests. Subsequently, Target Attention (TA) mechanism is used to reallocate the target-related attention scores for session interests, target interests and hidden states. Finally, different features are concatenated and flattened, which is fed into the Multiple Layer Perceptron (MLP) layer for final CTR prediction. Experimental results on the datasets indicate the performance of DTSIN is superior to other state-of-the-art deep CTR models.

关键词： Neural networks Bidirectional control Predictive models Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Evolutionary Reinforcement Learning Algorithm with Early Termination Strategy 24

Adaptive Evolutionary Reinforcement Learning Algorithm with ...

引用

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems

作者： Xiaoqiang Wu Qingling Zhu Qiuzhen Lin Weineng Chen Jianqiang Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400704864

Evolutionary reinforcement learning algorithms (ERLs), which combine evolutionary algorithms (EAs) with reinforcement learning (RL), have demonstrated significant success in enhancing RL performance. However, most ERLs rely heavily on Gaussian mutation operators to generate new individuals. When the standard deviation is too large or small, this approach will result in the production of poor or highly similar offspring. Such outcomes can be detrimental to the learning process of the RL agent, as too many poor or similar experiences are generated by these individuals. In order to alleviate these issues, this paper proposes an Adaptive Evolutionary Reinforcement Learning (AERL) method that adaptively adjusts both the standard deviation and the evaluation process. By tracking the performance of new individuals, AERL maintains the mutation strength within a suitable range without the need for additional gradient computations. Moreover, the proposed AERL approach early terminates unnecessary evaluations and discards experiences arising from poor individuals, thereby resulting in enhanced learning efficiency. Empirical assessments conducted on a variety of continuous control problems demonstrate the effectiveness of the AERL method.

关键词： evolutionary algorithm evolutionary reinforcement learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Generalized χ2 Divergence for Multisource Information Fusion 6th

A Generalized χ2 Divergence for Multisource Information Fus...

引用

6th International Conference on data Mining and big data, DMBD 2021

作者： Gao, Xueyuan Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (纸本)9789811675010

Divergence measure has been extensively applied in many fields. Basic probability assignment (BPA), instead of probability, is adopted to represent the belief degree of elements in Dempster-Shafer theory. But how to measure the divergence among BPAs is still under research. This paper proposes a novel belief divergence measure based on classic χ2 divergence. Comparing to the existing divergence, the new proposed divergence performs better in measuring discrepancy among BPAs. In addition, the proposed divergence is proved be a bounded, non-degenerated and symmetrical divergence measure. Numerical examples are presented to describe the effectiveness of proposed divergence measure. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Labelrepair: Sequence Labelling for Compilation Errors Repair

Labelrepair: Sequence Labelling for Compilation Errors Repai...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Zhenyu Wu Deheng Yang Yan Lei Huan Xie Minghua Tang Maojin Li School of Big Data & Software Engineering Chongqing University Chongqing China Academy of Military Sciences Beijing China Peng Cheng Laboratory Shenzhen China Kunming University of Science and Technology Kunming China

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

Manual fixing of compilation errors could be a tedious and time-consuming task for novice programmers, and even for experienced ones. In recent years, an increasing number of automated repair techniques have been proposed to guide novice programmers and improve the efficiency of software development. Among them, learning-based automated repair techniques have achieved promising results in terms of repair accuracy. However, existing approaches neglect the time efficiency of patch generation, and often treat the compilation errors repair as a neural machine translation task. The end-to-end repair model decoding cannot be parallelized during the inference stage and suffers from redundant decoding search space. Furthermore, the large search space brought by the model poses a potential risk of semantic tampering. To this end, we propose Labelrepair, a novel repair technique that treats the repair of compilation errors as a sequence labelling task. Labelrepair discards the decoding model and converts the search for patches to a search for the error mapping actions between broken code and patch code pairs. In this way, the search space for patch tokens is plum-meted from the entire vocabulary to the size of edit action labels, and the logical semantics of the original program are preserved to some extent. The time complexity of inference is reduced from $O(n)$ to $O$ (1) owing to the parallel generation of edit action labels. Through a comprehensive evaluation of Labelrepair on two datasets, we demonstrate that Labelrepair is able to generate patches instantly (0.71ms on average), which is 28 times faster than existing end-to-end repair models. Compared with existing edit-based repair models, Labelrepair achieves the state-of-art repair accuracy.

关键词： Vocabulary Codes Accuracy Semantics Maintenance engineering Decoding Labeling

来源：评论

学校读者我要写书评

暂无评论

A Novel Complex Pignistic Belief Transform for Conflict Measure in Complex Evidence Theory 1

引用

6th International Conference on data Mining and big data, DMBD 2021

作者： Zhao, Yangyang Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (数字)9789811674761

ISBN: (纸本)9789811674754

Information fusion has received extensive attention in the past decades, in which the handing of uncertain information is still an open issue. Complex evidence theory (CET) can effectively deal with uncertain information. However, in CET, the measurement of conflict is still a problem to be solved. Therefore, this paper proposes a novel method of measurement method for CET. Firstly, we divide the belief into power sets and propose a complex pignistic belief transform. Then the betting commitment function is designed. Finally, a new betting distance based on betting commitment function is proposed, and some properties of the betting distance are analyzed, including the non-negativeness, nondegeneracy, symmetry, and triangle inequality. The betting distance can be used to measure the conflict between CBBAs. In addition, an example is given to show the advantage of betting distance compared to the conflict coefficient. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Betting commitment Betting distance Complex evidence theory Complex pignistic belief transform Conflict measure

来源：评论

学校读者我要写书评

暂无评论

OptLLM: Optimal Assignment of Queries to Large Language Models

arXiv

引用

arXiv 2024年

作者： Liu, Yueyue Zhang, Hongyu Miao, Yuantian Le, Van-Hoang Li, Zhiqiang School of Information and Physical Sciences The University of Newcastle Newcastle Australia School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science Shaanxi Normal University Shaanxi China

关键词： Sentiment analysis

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：