检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Industrial Technology, ICIT 2022

作者： Dhanawansa, Vidushani Samarasinghe, Pradeepa Yogarajah, Pratheepan Gardiner, Bryan Karunasena, Anuradha Sri Lanka Institute of Information Technology Faculty of Computing Sri Lanka Engineering and Intelligent Systems Ulster University School of Computing United Kingdom

ISBN: (纸本)9781728119489

This paper presents a systemic analysis on the implications of the loss function, batch size and optimiser function applied within the multi-output regression problem domain of Head Pose estimation. To the best of our knowledge, prior comparative analysis of this calibre has primarily focused on the image classification problem domain, with limited analysis on the optimisation of hyperparameters influencing the performance of a Convolutional Neural Network (CNN) for regression. This motivates the current study which proposes a vanilla regression model based on the EfficientNet models of varying depths between EfficientNet BO and B5, and experiments on multiple protocols incorporating the benchmark datasets of BIWI, 300W-LP and AFLW2000. Therefore, the main contributions of the paper include a study on the impact of: loss functions for models of varying depths;batch sizes for significantly less and more complex models;and different optimiser functions on the model performance. The investigation of the effect of Mean Squared Error (MSE), Mean Absolute Error (MAE) and Huber loss functions on the performance of the models suggested that MAE and Huber loss (d=1.0) yield optimal performance regardless of the model complexity. The comparative analysis based on batch sizes ranging between 8 and 128 evidenced that moderate batch sizes of 16 and 32 yield an optimal performance on less complex models, while large batch training complements more complex models across all tested loss functions, an observation not evident in previous work. Finally, it was proven that the Adam optimiser function generates a minimal loss and is void of overfitting, outperforming other optimiser functions of Stochastic Gradient Descent, RMSProp, AdaGrad and Adam. © 2022 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Time Series Forecasting Using State Space Models 24th

Machine Learning for Time Series Forecasting Using State Sp...

引用

24th International Conference on intelligent Data engineering and Automated Learning, IDEAL 2023

作者： Sanchez-Bornot, Jose M. Sotero, Roberto C. School of Computing Engineering and Intelligent Systems Ulster University Derry/Londonderry United Kingdom Department of Radiology and Hotchkiss Brain Institute University of Calgary CalgaryAB Canada

ISBN: (纸本)9783031482311

State-space models (SSMs) are becoming mainstream for time series analysis because their flexibility and increased explainability, as they model observations separately from unobserved dynamics. Critically, using SSMs based on multivariate autoregressive equations enhances understanding of system evolution and its dynamical interactions. However, some challenges remain unsolved, such as estimation in large-scale scenarios, with very noisy data, and model selection. Here, we explore a state-space alternating least squares (SSALS) algorithm for time series forecasting, demonstrating its application with simulated and real data, and how to solve model selection in noisy scenarios with a novel cross-validation technique. Altogether, testing this methodology with time series forecasting is ideal to demonstrate its strengths and weaknesses, and appreciate its advantages compared to current methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios

Evaluating Software Development Agents: Patch Patterns, Code...

引用

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

作者： Zhi Chen Lingxiao Jiang Centre for Research on Intelligent Software Engineering School of Computing and Information Systems Singapore Management University

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and interacting with external environments, offer promising solutions to complex software engineering tasks. However, while much research has evaluated code generated by large language models (LLMs), comprehensive studies on agent-generated patches, particularly in real-world settings, are lacking. This study addresses that gap by evaluating 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues from SWE-Bench Verified, focusing on their impact on code quality. Our analysis shows no single agent dominated, with 170 issues unresolved, indicating room for improvement. Even for patches that passed unit tests and resolved issues, agents made different file and function modifications compared to the gold patches from repository developers, revealing limitations in the benchmark's test case coverage. Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities; while some agents increased code complexity, many reduced code duplication and minimized code smells. Finally, agents performed better on simpler codebases, suggesting that breaking complex tasks into smaller sub-tasks could improve effectiveness. This study provides the first comprehensive evaluation of agent-generated patches on real-world GitHub issues, offering insights to advance AI-driven software development.

关键词： Gold Codes Large language models Computer bugs Focusing Complexity theory Security Reliability Software development management Software engineering

来源：评论

学校读者我要写书评

暂无评论

Method for Classification of Cancers with Partial Least Squares Regression as Feature Selector with Kernel SVM

Method for Classification of Cancers with Partial Least Squa...

引用

2022 International Conference for Advancement in Technology, ICONAT 2022

作者： Koul, Nimrita Manvi, Sunilkumar S Gardiner, Bryan School of Computer Science and Engineering REVA University Bangalore India School of Computing Engineering and Intelligent Systems Ulster University Northern Ireland United Kingdom

ISBN: (纸本)9781665425773

Classification of cancers according to the exact place of origin in the body is an important research problem that is being addressed both clinically and computationally. Application of data science and machine learning to a vast volume of imaging and genomics data regarding cancers has enabled computational researchers to accurately classify the tumor samples according to their place of origin. In current work, we developed a method to classify tumors using partial least squares regression as feature selector and support vector machine classifiers. We have evaluated our approach on three cancer gene expression datasets and found classification accuracies of 100% in some circumstances. The comparison is conducted with standard classification methods like Decision Trees and simple Support Vector Machines with respect to standard performance parameters and the time taken for classification. The comparison in terms of training and testing accuracies and the time taken for classification results show that our method performs consistently better than conventional methods. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Directed Brain Network Transformer for Psychiatric Diagnosis 27th

Directed Brain Network Transformer for Psychiatric Diagnosis

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhu, Xu Qi, Zhiwei Yue, Kun Su, Yunshan Duan, Liang School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China School of Education Yunnan University Kunming China Department of Radiology Affiliated Hospital of Yunnan University Kunming China

ISBN: (纸本)9783031781940

Human brain is a complex organ that consists of billions of neurons and trillions of connections among the neurons. To describe the correlations among the time series of the brain regions, we model the brain as a functional brain network to diagnose psychosis. However, traditional methods of functional brain network construction are usually noisy and do not consider the causal relationships among brain regions. To obtain the causal relationships and improve diagnosis interpretability, we propose a directed brain network Transformer (DBNT) for psychiatric diagnosis. First, the causal relationships in the blood-oxygen-level-dependent time series of brain regions are extracted to generate a directed brain network. Then, the feature encoding method is proposed to obtain local and global features of the brain networks by using the DBNT. Experimental results demonstrate that the accuracy of DBNT increases by 8.1% and 6.4% compared to state-of-the-art methods on two large-scale brain network datasets. DBNT also highlights the brain regions associated with psychosis and provides interpretation for diagnosis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Multi-food source differential salp swarm algorithm 23

Multi-food source differential salp swarm algorithm

引用

2023 International Conference on Computer, Vision and intelligent Technology, ICCVIT 2023

作者： Lin, Anping Shi, Yaoting Zhang, Wenfen Liu, Dong Lan, Yulin School of Physics and Electronic Electrical Engineering Xiangnan University Chenzhou423000 China School of Computer and Artificial Intelligence Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou China

ISBN: (纸本)9798400708701

Salp swarm algorithm (SSA) divides the population into leaders and followers, and employs two different search methods to achieve steady convergence. However, the search methods adopted by SSA are relatively simple, hence SSA always trapped by local optima on complex multimodal problems. To improve the exploration of SSA, this paper proposes a multi-food source differential salp swarm algorithm (MFD-SSA) by transferring multi-leader mechanism and differential mutation strategy into SSA. MFD-SSA regards a portion of high fitness individuals as food sources and employ them for updating the position of leaders, the differential evolution mutation and the chaotic crossover are adopted to enhance swarm diversity. Then, the differential mutation and crossover operator are employed for enlarging search range. The MFD-SSA is tested on CEC2017 test suite and compared with five SSA variants and five other meta-heuristics. The test results indicate that MFD-SSA bears strong exploration, it outperforms five SSA variants and five meta-heuristics. On Planetary gear train design problem, MFD-SSA performs better than other five SSA variants too. © 2023 ACM.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

引用

IEEE Transactions on Circuits and systems for Video Technology 2023年第2期33卷 713-727页

作者： Li, Jiawei Liu, Jinyuan Zhou, Shihua Zhang, Qiang Kasabov, Nikola K. Ministry of Education School of Software Engineering Dalian University Key Laboratory of Advanced Design and Intelligent Computing Dalian116622 China Dalian University of Technology School of Software Technology Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1010 New Zealand Ulster University Intelligent Systems Research Center LondonderryBT52 1SA United Kingdom

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an end-to-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-of-the-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://***/lok-18/LCNDR. © 1991-2012 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Research into Curriculum Construction Platform of Computer Major Based on intelligent Algorithm 12th

Research into Curriculum Construction Platform of Computer M...

引用

12th International Conference on Frontier computing, FC 2022

作者： Xie, Hui Wei, Li School of Computer and Artificial Intelligence Xiangnan University Hunan Chenzhou China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou China

ISBN: (纸本)9789819914272

Under the development background of educational curriculum reform, personalized curriculum design has become the key content of current reform of the computer major. In this context, this research carries out a design of a curriculum construction platform for the computer major based on intelligent algorithm. Through the user curriculum design module and personalized curriculum design optimization module design, the technological innovation of computer related discipline curriculum construction is realized. Based on the data collected of teachers and students’ subject behaviors and combined with data modeling, intelligent algorithms and other means, it is possible to realize the differentiated construction of subject curriculums and the purpose of personalized education. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification based on Multi Physiological Signals Using Hybrid Fusion Strategy 30

Emotion Classification based on Multi Physiological Signals ...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Wan, Jiacheng Fang, Yinfeng Guo, Chunsheng Ju, Zhaojie Zhou, Dalin Hangzhou Dianzi University Pinghu Digital Technology Innovation Research Institute School of Communication Engineering Hangzhou China University of Portsmouth Intelligent Systems and Biomedical Robotics Group School of Computing PortsmouthPO1 3HE United Kingdom

ISBN: (纸本)9798350391916

The demand for emotion recognition is increasing not only in daily life but also in professional domains such as disease diagnosis and clinical rehabilitation. By monitoring non-invasive physiological signals of patients, providing timely feedback on their emotional state can significantly aid in patient recovery and subsequent expert treatment evaluation. In this study, we propose a mutual fusion approach utilizing both feature fusion and decision fusion techniques for emotion classification. Firstly, statistical knowledge-based methods were employed to select physiological signals and extract highly correlated and complementary features for feature-level fusion. Subsequently, a similarity weight, based on feature selection and statistical analysis, was incorporated into the decision fusion process. Our proposed method yielded promising results, achieving 82.5% accuracy and 75.2% macro f1 score for three-class classification (neutral vs. stress vs. amusement), 95.4% accuracy and 94.6% macro f1 score for two-class classification (stress vs. non-stress) using publicly available data from the WESAD dataset. These results demonstrate that employing a mutual fusion approach outperforms single fusion methods in emotion classification tasks. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

A General Method for Power Equipment State Classification Using Time Series Data Based on Attention Mechanism

A General Method for Power Equipment State Classification Us...

引用

2023 IEEE International Conference on Power Science and Technology, ICPST 2023

作者： Zhao, Wenqing Wang, Jifa Chen, Rui Liu, Liang Xu, Lijiao North China Electric Power University School of Control and Computer Engineering Engineering Research Center of Intelligent Computing for Complex Energy Systems Ministry of Education Baoding China North China Electric Power University School of Control and Computer Engineering Baoding China

ISBN: (纸本)9798350311358

With refinement of power equipment, the identification and classification of its operation states is quite important for the stable operation of the system. As the power equipment states are rather complicated, it is difficult to realize general classification due to the limitation of data types and model characteristics when using deep learning. In the light of this, based on the time series data of various power equipment, an equipment state classification method is proposed by combining Recurrent Neural Network (RNN), Long short-term memory (LSTM) and attention mechanism. Firstly, RNN is used as the bottom frame network, and the LSTM core network integrating attention mechanism is added to construct the complex Feature Extraction Module (FEM). Secondly, main feature extraction is implemented in the LSTM network integrated with attention mechanism. Then, the extracted features are input into the complex FEM model and trained to match the evaluation state and obtain the evaluation results. In this paper, confusion matrix, F1micro and accuracy are used as evaluation indexes. Three cases were selected to verify the method and five groups of comparison models were set for each case. Results show that the proposed method has good accuracy in power equipment state classification and also has strong generalization ability in other data classification. © 2023 IEEE.

关键词： Long short-term memory

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：