检索结果-内蒙古大学图书馆

3rd International Seminar on Artificial Intelligence, Networking, and Information technology, AINIT 2022

作者： Liu, Shengxi Li, Ze Tao, Xiaomei College of Computer Engineering Henan Institute of Economy and Trade Henan Zhengzhou China School of information science and engineering Guilin University of Technology Guangxi Guilin China School of Computer Science and Engineering School of Software Guangxi Normal University Guangxi Guilin China

ISBN: (数字)9781510662971

ISBN: (纸本)9781510662964

With the rapid development of artificial intelligence technology, emotion recognition has been applied in all aspects of life, using eye movement tracking technology for emotion recognition has become an important branch of emotion computing. In order to explore the relationship between eye movement signals and learners' emotional states in the online video learning environment, we used machine learning and convolutional neural network methods to recognize eye movement signals, and classify learners' emotional states into two categories, positive and negative. The study of eye movement data under different time windows mainly includes four stages: data collection, data preprocessing, classifier modeling, training and testing. In this paper, a Eye-movement Feature Extraction Classification Network(EFECN) based on convolutional neural network is proposed for small sample data and the classification of emotion state based on eye movement. The eye movement data were transformed into images through cross-modal conversion as input of multiple different deep convolutional neural networks, and the emotional states were classified in positive and negative directions. The accuracy was used as the evaluation index to evaluate and compare the different models. The accuracy of the eye movement emotion recognition model reached 72% in the SVM model and 91.62% in the EFECN model. Experimental results show that the convolutional neural network based on deep learning has a significant improvement in recognition accuracy compared with traditional machine learning methods. © 2023 SPIE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Disease Forecast on Different Farms Using Sensing Agricultural Robot with XAI 13

Improving Disease Forecast on Different Farms Using Sensing ...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Terada, Kenji Fujinami, Kaori Tokyo University of Agriculture and Technology Polytechnic University Grad. School of Bio-Functions and Systems Science Tokyo Japan Tokyo University of Agriculture and Technology Div. of Advanced Information Technology and Computer Science Tokyo Japan

ISBN: (纸本)9798350355079

Preventing diseases in crops and fruit trees is an urgent issue in the fight against global food shortages. If a disease occurs, it is highly possible that it may have spread throughout the farm before being detected by the farmer. Therefore, in this study, to facilitate early disease forecasting, we propose using a sensing agricultural robot that can meticulously observe environmental alterations that could serve as potential disease indicators. In addition, because the forecast results for a different farm showed a decrease in recall compared to the farm where the images were collected, we employed explainable artificial intelligence (XAI) for feature analysis. We confirmed an improvement in the recall through simple feature selection. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Prime-valent one-regular graphs of order 28p

Italian Journal of Pure and Applied Mathematics

引用

Italian Journal of Pure and Applied Mathematics 2025年第53期 129-137页

作者： Li, De-Xue Guo, Song-Tao Henan Polytechnic Institute Nanyang473000 China School of Mathematics and Statistics Henan University of Science and Technology Luoyang471023 China

A graph is one-regular if its full automorphism group acts on its arcs regularly. In this paper, we classify connected one-regular graphs of prime valency and order 28p for each prime p, and prove that there is only one sporadic graph: the Z7-cover CQ7 of the three dimensional hypercube Q3 with valency 3. © 2025 Forum-Editrice Universitaria Udinese SRL. All rights reserved.

关键词： arc-transitive graph one-regular graph symmetric graph

来源：评论

学校读者我要写书评

暂无评论

Feature Selection in High-Dimensional Set-Valued Decision System

Feature Selection in High-Dimensional Set-Valued Decision Sy...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Zhengjiang Wu Ruimin Li Tao Lian Xuyang Wu School of Software Henan Polytechnic University Jiaozuo China School of Computer Science and Technology Henan Polytechnic University Jiaozuo China

In the decision system, the lower approximation set keeps expanding with adding features dynamically. But when enough features are added, the lower approximation set stabilizes. This provides a criterion for feature selection in high-dimensional decision set. Semi-monolayer covering rough set is an approximate representation of uncertain knowledge in set-valued decision system. This paper proposes a feature selection algorithm for high-dimensional set-valued decision system based on incremental update theory (abbr. SMCDA). Specifically, the trend of lower DA0 approximation set under the variation of features in the set-value information system is described, and the incremental limit of the lower DA0 approximation set is illustrated. The incremental algorithm of the lower DA0 approximation under the variation of features is designed. Next, the lower DA0 approximation set is continuously updated using the incremental algorithm until stable. At this point, the already added features are the result of feature selection for SMCDA. Experimental results show that the SMCDA algorithm has a good feature reduction effect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Extended Rough Set Model of Graph Structure for Incomplete Information System Using Spark

An Extended Rough Set Model of Graph Structure for Incomplet...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Zhengjiang Wu Tao Lian Ruimin Li Xuyang Wu School of Software Henan Polytechnic University Jiaozuo China School of Computer Science and Technology Henan Polytechnic University Jiaozuo China

In the process of data cleaning, there are problems of high difficulty and low efficiency for processing IIS (incomplete information system) that has large size data. As this problem, distributed IMR (DIMR) is a method with data preprocessing capability for distributed IIS. We propose a distributed extended rough set of graph structure (DRSG) based on DIMR using Spark to accelerate parallel processing of IIS under big data. Specifically, we introduce the concepts of reliable element and controversial element, and establish a connection through non-symmetric similarity relation. Then, a graph structure with hierarchical relationship is proposed. And the path from the reliable element to the controversial element replaces the block in DIMR to calculate the approximation set. Finally, a parallel algorithm is proposed and the experiments show that DRSG reduces the resources required for computing and improves the speed in Spark. A comparative analysis has been conducted comprehensively to assess the performance of the proposed algorithm with DIMR on 8 datasets. And the results show that DRSG has faster speed. And the dependency is similar to or higher than DIMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MpoxMamba: A Grouped Mamba-based Lightweight Hybrid Network for Mpox Detection

MpoxMamba: A Grouped Mamba-based Lightweight Hybrid Network ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yue, Yubiao Xue, Jun Liang, Haihuang Li, Zhenzhang Wang, Yufeng School of Biomedical Engineering Guangzhou Medical University Guangzhou China School of Computer Science and Technology Anhui University Hefei China School of Mathematics and Systems Science Guangdong Polytechnic Normal University Guangzhou China Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9798350368741

Due to the lack of effective mpox detection tools, the mpox virus continues to spread worldwide and has been once again declared a public health emergency of international concern by the World Health Organization. Lightweight deep learning model-based detection systems are crucial to alleviate mpox outbreaks since they are suitable for widespread deployment, especially in resource-limited scenarios. However, the key to its successful application depends on ensuring that the model can effectively model local features and long-range dependencies in mpox lesions while maintaining lightweight. Inspired by the success of Mamba in modeling long-range dependencies and its linear complexity, we proposed a lightweight hybrid architecture called MpoxMamba for efficient mpox detection. MpoxMamba utilizes depth-wise separable convolutions to extract local feature representations in mpox skin lesions and greatly enhances the model's ability to model the global contextual information by grouped Mamba modules. Notably, MpoxMamba's parameter size and FLOPs are 0.77M and 0.53G, respectively. Experimental results on two widely recognized benchmark datasets demonstrate that MpoxMamba outperforms state-of-the-art lightweight models and existing mpox detection methods. Importantly, we developed a web-based online application to provide free mpox detection. The source code of MpoxMamba and the developed online application are available at https://***/YubiaoYue/MpoxMamba. © 2025 IEEE.

关键词： Deep Leraning Lightweight Model Mpox Detection Vision Mamba

来源：评论

学校读者我要写书评

暂无评论

Encoder-Decoder Calibration for Multimodal Machine Translation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 3965-3973页

作者： Tayir, Turghun Li, Lin Li, Bei Liu, Jianquan Lee, Kong Aik Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Northeastern University School of Computer Science and Engineering Shenyang110004 China NEC Corporation Video Insights Discovery Research Group Visual Intelligence Research Laboratories Tokyo999001 Japan The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Kowloon999077 Hong Kong

The main purpose of multimodal machine translation (MMT) is to improve the quality of translation results by taking the corresponding visual context as an additional input. Recently many studies in neural machine translation have attempted to obtain high-quality multimodal representation of encoder or decoder via attention mechanism. However, attention mechanism does not always accurately identify the decisive input for each prediction, which leads to an unsatisfactory multimodal information fusion. To this end, we propose an encoder-decoder (Enc-Dec) calibration method which can automatically calibrate the image and text fusion representation in the encoder, and find the decisive input to the translation in the decoder. We validate our model on the MMT dataset Multi30K. Experimental results show that our method significantly outperforms several recent baselines for both English-German and English-French translation tasks in terms of BLEU and METEOR. © 2020 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Enhancing Suicide Risk Detection with a Multisource Data Filtering and Fusion Optimization Framework (MDF-FOF)

Enhancing Suicide Risk Detection with a Multisource Data Fil...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Zheng, Shouwen Zhou, Taiqi Tao, Yingzhi Chen, Junru Wang, Ruofei Liu, Siyuan The Hong Kong Polytechnic University Department of Computing Hong Kong Anhui University School of Computer Science and Technology An Hui China The Hong Kong Polytechnic University Department of Marketing and Management Hong Kong

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362480

Recently, with the popularity of social media platforms, the increase in suicide-related content has triggered great attention on automated suicide risk detection systems. This research proposes a natural language processing model based on RoBERTa, which aims to identify and classify suicide risks in social media posts. Our team propose a "Multisource data filtering and fusion optimization framework"(MDF-FOF), which effectively solves the problem of data imbalance by combining a large language model (LLM) with manual annotation to generate a balanced training sample set. In terms of model construction, we proposed a framework MDF-FOF that utilizes pre-trained RoBERTa for feature extraction and combines it with a self-built EmoBERT for soft label classification. Experimental results show that the recall rate of the proposed framework on the validation set is stable above 0.75, which is better than the existing methods and baseline models. It shows good robustness and excellent performance in tests on datasets from different sources. This study provides a reliable basic framework for multi-feature extraction of user posts in the future. © 2024 IEEE.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Momentary sensor based cricket ball design for bowlers performance analysis

引用

Multimedia Tools and Applications 2024年 1-34页

作者： Balbudhe, Pravin Sharma, Rika Solanki, Sachin Department of Computer Science & amp Engineering Amity School of Engineering and Technology Amity University Raipur Chhattisgarh India Directorate of Technical Education Government Polytechnic Campus Maharashtra Sadar Nagpur India

With rapid development in gaming technology, we have seen different apparatuses helping players, coaches, umpires, refries, and students for better decision-making and performance enhancement. This research work focused on development of the momentary sensors-based cricket ball for capturing minimal details of ball activity which cannot be reviewed or tracked with normal human eyes of cameras. This is more challenging because changes in ball motions are at the highest speed and need a high-speed sensor to track the details. We are presenting the custom-modified cricket ball having a perfect weight proportioned microcontroller and momentary sensor-based logic board inside. This hardware inside is capable of recording every minor rotational, traveler, and geographical information of the ball activity so that the data can be utilized for performance analysis. The experimental result shows that not all the information could be gathered from the single or similar working principal type of sensor, rather it needs the fusion of different sensors and still needs the right time synchronization between all sensor modules to capture the right statistical information. We achieved the result and presented it to the best coaches in the town, to have their opinions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Detection and Recognition of Vehicles Using Indian Driving Datasets 11

Detection and Recognition of Vehicles Using Indian Driving D...

引用

11th IEEE International Conference on Cloud Computing in Emerging Markets, CCEM 2023

作者： Padukote, Yathish H.S. Suresha, R. Manohar, N. Jipeng, Tian Department of Computer Science School of Computing Mysuru Amrita Vishwa Vidyapeetham India Computer Science college Zhongyuan University of Technology Henan Province Zhengzhou China

ISBN: (纸本)9798350360059

Vehicle identification and recognition are essential computer vision tasks with important applications in autonomous driving, traffic management, and surveillance systems. The Indian Driving Dataset (IDD) dataset used in this work was compiled from a variety of driving scenarios in the Indian environment, and it includes a thorough investigation on vehicle detection and recognition. The dataset is meticulously chosen to reflect the difficulties brought on by the state of Indian roads, traffic patterns, and vehicle kinds. In this study, a Faster RCNN method for precise and effective vehicle detection and recognition deep learning approaches by enhancing images using power-law transformation. The collection consists of annotated IDD dataset images taken in a range of lighting situations, urban-rural locales, and camera angles. The testing results demonstrate the effectiveness of the recommended approach, which achieves competitive performance with 79.5% detection accuracy and 76% recognition accuracy. Additionally, the performance of the model is impacted by elements like various lighting situations and various vehicle models. This research offers insightful information about the model's ability to generalise in realistic situations. ©2023 IEEE.

关键词： Image annotation

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：