检索结果-内蒙古大学图书馆

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Li, Lina Deng, Wenjie Liao, Shengli Qiang, Xue Rong, Yuying Yang, Ying Liu, Shixuan Zhang, Yumei School of Computer Science Shaanxi Normal University Xi'an710100 China Basic Experimental Teaching Center Shaanxi Normal University Xi'an710100 China China United Network Communications Group Co. Ltd. Shaanxi Branch Xi'an710075 China

ISBN: (纸本)9781510680425

Emotion recognition plays a vital role in human-computer interaction. However, traditional approaches relying on manual features extraction can get high accuracy results but limited generalization;furthermore results of emotion recognition using a single modality is unreliable. To address these challenges, a multi-modal emotion recognition model called STM-Net, which leverages the spatial and temporal information from electroencephalography (EEG) and eye movement two modalities is proposed based on convolutional neural networks (CNNs) and long short-term memory networks (LSTMs). A CNN-LSTM based model is designed to learn the spatial-temporal features of emotions in EEG signals. For eye-tracking signals, a corresponding CNN-based model is designed for feature extraction. The features from both modalities are fused and fed into a fully connected network for classification, then comprehensive and accurate emotion recognition results are obtained. Experimental results on the SEED-IV multimodal dataset demonstrate the effectiveness of the proposed approach, with accuracy results reaching up to 99.6%, much higher than other similar multimodal emotion recognition models. © 2024 SPIE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

InLite-HRNet: Efficient Band Convolution Network for Human Pose Estimation

InLite-HRNet: Efficient Band Convolution Network for Human P...

引用

2024 International Conference on Measurement, Communication, and Virtual Reality, MCVR 2024

作者： Zhang, Ziyang Xie, Cui Dong, Junyu Chang, Xiaofeng Wang, Yiguo College of Computer Science and Technology Ocean University of China Qingdao China Basic Teaching Center Ocean University of China Qingdao China

ISBN: (纸本)9781510691773

In the task of fast human pose estimation, to obtain a broader receptive field and more comprehensive pose information, the traditional method is to use a large convolution kernel in a lightweight network to expand the receptive field. However, large convolution kernels bring high computational complexity and are not suitable for fast estimation tasks. To address these problems, this study presents a lightweight human pose estimation network named InLite-HRNet. It uses two orthogonal band kernels in the vertical and horizontal directions instead of a single large convolution kernel, effectively increasing the size of the receptive field without additional computation. This approach decomposes the depth-wise separable convolution of the large convolution kernel into four parallel branches along channel dimensional (a square kernel, two orthogonal band kernels, and identity mapping) and embeds them into a new module SyncroFuse to enhance its feature expression ability. SyncroFuse is the basic component unit of our InLite-HRNet that plays a significant advantage of using large Receptive field to extract features on the high-resolution network. Experimental results show that the proposed network achieves an average accuracy of 71.07% and 87.22% on COCO and MPII human pose estimation datasets, which is better than the existing excellent lightweight networks and comparable to the existing large-scale human pose estimation networks. © 2025 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

Rethinking the Evaluation for Conversational Recommendation ...

引用

2023 Conference on Empirical methods in Natural Language Processing, EMNLP 2023

作者： Wang, Xiaolei Tang, Xinyu Zhao, Wayne Xin Wang, Jingyuan Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China School of Information Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Computer Science and Engineering Beihang University China

ISBN: (纸本)9798891760608

The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs. In this paper, we embark on an investigation into the utilization of ChatGPT for CRSs, revealing the inadequacy of the existing evaluation protocol. It might overemphasize the matching with ground-truth items annotated by humans while neglecting the interactive nature of CRSs. To overcome the limitation, we further propose an interactive Evaluation approach based on LLMs, named iEvaLM, which harnesses LLM-based user simulators. Our evaluation approach can simulate various system-user interaction scenarios. Through the experiments on two public CRS datasets, we demonstrate notable improvements compared to the prevailing evaluation protocol. Furthermore, we emphasize the evaluation of explainability, and ChatGPT showcases persuasive explanation generation for its recommendations. Our study contributes to a deeper comprehension of the untapped potential of LLMs for CRSs and provides a more flexible and realistic evaluation approach for future research about LLM-based CRSs. The code is available at https://***/RUCAIBox/iEvaLM-CRS. © 2023 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Unlocking Maternal Outcome Prediction Potential: A Comprehensive Analysis of the ConvXGB Model Integrating XGBoost and Deep Learning

Research Square

引用

Research Square 2024年

作者： Nwokoro, Chukwudi Obinna Akinnuwesi, Boluwaji Ade Shastri, Sourabh Uzoka, Faith-Michael Inyang, Udoinyang G. Eyoh, Imo J. Duke, Onyeabochukwu Augustine Nwokoro, Kelechi Cynthia Joseph, Kingsley U. Department of Computer Science Faculty of Computing University of Uyo Nigeria Department of Computer Science Faculty of Science and Enginerring Univeristy of Eswatini Kwaluseni South Africa Department of Computer Science and IT University of Jammu Jammu and Kashmir Kathua184104 India Mathematics and Computing Department Mount Royal University Calgary Canada Department of Obstetrician and Gynaecologist University of Nigeria Teaching hospital Enugu state Nigeria Department of Paediatrics University of Port-Harcourt Teaching Hospital River State Nigeria

The significance of maternal health cannot be overemphasized, and the ability to predict maternal outcomes accurately is critical to ensuring the well-being of both mothers and infants. This study presents ConvXGB, a novel predictive model that utilizes a combination of XGBoost, a potent gradient boosting algorithm, and deep learning to extract intricate features. The objective is to enhance precision and robustness of maternal outcome predictions. The study sourced diverse maternal health data from the southern region of Nigeria and implemented Synthetic Minority Oversampling Technique (SMOTE) to address any dataset imbalances. Results obtain demonstrate a significant improvement in model performance, with an accuracy rate of 97.96% across various maternal outcome classes. The recommendations from this study highlight the potential of ConvXGB in advancing maternal health predictive analytics, supporting informed clinical decision-making, and improving resource allocation. Further studies are warranted to explore the broader applicability of ConvXGB in different healthcare domains through outcome analyses and methodological advancements. © 2024, CC BY.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Design of Composite Factor Variance and Component Analysis System Based on Data Analysis Algorithm

Design of Composite Factor Variance and Component Analysis S...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Yue Wang Yiqian Zhang Division of Public Teaching Jinan Vocational College Jinan China Department of Computer Science Jinan Vocational College Jinan China

ISBN: (数字)9798350305463

ISBN: (纸本)9798350305470

It is very difficult to analyze and mine massive and high-dimensional data. Although the current hardware conditions have greatly improved, they still cannot meet the needs of large-scale, high-dimensional data. In medical research, scientific experiments, and biological gene sequencing, a combination of analysis of variance and principal component analysis was used to study the above issues. On this basis, this article started from two main data analysis methods and studied the relevant theories and algorithms of binary analysis of variance and principal component analysis, in order to achieve the analysis of sample data. The experiment proved that the data analysis based on the system in this article can combine the factor load matrix of the main factor variables to evaluate the contribution of each factor in the investment portfolio to the overall risk. Finally, the optimal stock portfolio was 601989, 601601, 600028, 600104, 601857, and 601988.

关键词： High-dimensional data Sequential analysis Data analysis Standardization Big Data Systems support Portfolios

来源：评论

学校读者我要写书评

暂无评论

Analysis of information technology classroom teaching behavior in smart classroom environment 23

Analysis of information technology classroom teaching behavi...

引用

Proceedings of the 2023 6th International Conference on Educational Technology Management

作者： Bing Xiao Yudian Li Junliang Ma Juhou He College of Computer Science Shaanxi Normal University China Key Lab. of Modern Teaching Technology Ministry of Education China

ISBN: (纸本)9798400716676

With the continuous development of education informatization, more and more primary and secondary schools in our country introduce smart classrooms for information technology teaching. In order to have a deeper understanding of the current situation of information technology classroom teaching behaviors in the context of smart classrooms, this study selects 10 high-quality information technology teaching videos in high schools as the research objects, and relies on the improved smart classroom teaching behavior coding system. Nvivo 11 qualitative analysis software was used to label and analyze the teaching behavior of 10 classes. It is found that teachers and students mainly use teaching, resource presentation and question and answer in the teaching process, in which teachers' activities are more frequent than students' activities, and teachers guide students to think and participate in learning through questioning and technology application. The teaching process of teachers' questions and students' responses has been normalized, but it mainly focuses on closed questions. At the same time, in the information technology classroom in the smart classroom environment, the proportion of teachers and students applying technology has been significantly improved, and the teaching atmosphere has also shown a good state. However, only the use of smart classroom equipment has not improved the teaching mode, and it is difficult to achieve the "student-centered" teaching concept of information technology courses, and it is unable to effectively guide students to think. To this end, we should introduce advanced teaching concepts, improve the quality of classroom question-answering, stimulate students' autonomy and creativity, strengthen teacher-student interaction, and create an open, equal and creative teaching environment.

关键词： Information technology classroom Smart classroom teaching behavior analysis

来源：评论

学校读者我要写书评

暂无评论

Deriving Modernity Signatures of Codebases with Static Analysis

SSRN

引用

SSRN 2023年

作者： Admiraal, Chris van den Brink, Wouter Gerhold, Marcus Zaytsev, Vadim Zubcu, Cristian Technical Computer Science University of Twente Enschede Netherlands Formal Methods & Tools University of Twente Enschede Netherlands

This paper addresses the problem of determining the modernity of software systems by analysing the use of new language features and their adoption over time. We propose the concept of modernity signatures to estimate the age of a codebase, naturally adjusted for maintenance practices, such that the modernity of a regularly updated system would be above that of a more recently created one which neglects current features and best practices. This can provide insights into coding practices, codebase health and the evolution of software languages. We present case studies on PHP and Python code, demonstrating the effectiveness of modernity signatures in determining the age of a codebase without executing the code or performing extensive human inspection. The paper describes the technical implementation details of generating the modernity signature for both of these languages, including the use of existing tools like the PHP parser and Vermin. The findings suggest that modernity signatures can aid developers in many ways from choosing whether to use a system or how to approach its maintenance, to assessing usefulness of a language feature, thus providing a valuable tool for source code analysis and manipulation. © 2023, The Authors. All rights reserved.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Influence of the Sequence of Drilling Fields on the Maximum Total Gas Production

Influence of the Sequence of Drilling Fields on the Maximum ...

引用

International Conference on Management of Large-Scale System Development (MLSD)

作者： Alexander Skiba Department of Mathematical Methods of Regional Programming Federal Research Center "Computer Science and Control" of RAS Moscow Russia

We analyze an aggregated dynamic model for the development of gas fields. The same company consistently drills all fields. We pose and solve the problem of maximizing accumulated gas production over a predetermined pe...

关键词：

来源：评论

学校读者我要写书评

暂无评论

XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models

arXiv

引用

arXiv 2024年

作者： Cambria, Erik Malandri, Lorenzo Mercorio, Fabio Nobani, Navid Seveso, Andrea School of Computer Science and Engineering Nanyang Technological University Singapore Dept. of Statistics and Quantitative Methods University of Milano-Bicocca Milan Italy

In this survey, we address the key challenges in Large Language Models (LLM) research, focusing on the importance of interpretability. Driven by increasing interest from AI and business sectors, we highlight the need for transparency in LLMs. We examine the dual paths in current LLM research and eXplainable Artificial Intelligence (XAI): enhancing performance through XAI and the emerging focus on model interpretability. Our paper advocates for a balanced approach that values interpretability equally with functional advancements. Recognizing the rapid development in LLM research, our survey includes both peer-reviewed and preprint (arXiv) papers, offering a comprehensive overview of XAI’s role in LLM research. We conclude by urging the research community to advance both LLM and XAI fields together. © 2024, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Investment Planning in the Region

Investment Planning in the Region

引用

International Conference on Management of Large-Scale System Development (MLSD)

作者： Alexander Solomatin Department of Mathematical Methods of Regional Programming Federal Research Center "Computer Science and Control" of RAS Moscow Russia

The principle of multiplicity is introduced for the components of the investment planning process. Some algorithms are given that ensure the process of investment planning at the regional level: the formation of integrated assessments of investment projects, automated generation of projects, multicriteria evaluation and selection of projects, taking into account the mutual influence of projects, optimizing the composition of projects, and taking into account financing restrictions. The features of the program system intended for the formation of plans for the territorial and sectoral development of the region are considered.

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：