检索结果-内蒙古大学图书馆

COVID-19 Prediction Model Empowered with Fused Computational Intelligence Technique

IEIE Transactions on Smart Processing and Computing 2025年第1期14卷 109-117页

作者： Khan, Muhammad Adnan Naseer, Iftikhar Ali, Muhammad Nadeem Kim, Byung-Seo Department of Software Faculty of Artificial Intelligence & Software Gachon University Seongnam13120 Korea Republic of Faculty of Computer Science & Information Technology The Superior University Lahore54600 Pakistan Department of Software and Communications Engineering Hongik University Sejong Campus Korea Republic of

The novel Coronavirus (COVID-19) spread rapidly around the world and caused overwhelming effects on the health and economy of the world. It first appeared in Wuhan city of China and was declared a pandemic by the World Health Organization (WHO). Many researchers, as well as experts in clinical and artificial intelligence experts, are working together to control the rapid spread of COVID-19 with early detection. This study focused on intelligent prediction for coronavirus using computational intelligence approaches (IPC-FCIA) like convolutional neural networks, support vector machines, and fuzzy logic techniques. The proposed IPC-FCIA model is based on two sections namely the training section and the validation section. Features fusion and decision-level fusion are used in this study to enhance the performance of the recommended IPC-FCIA model. The proposed model predicts the early detection of COVID-19 in two types COVID-negative and COVID-positive. The benchmark results of the model show an accuracy of 97.66 % on decision-level fusion in the detection of COVID-19. The proposed model can be helpful for medical experts as well as COVID-19-affected patients. © 2025 Institute of Electronics Engineers of Korea. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Collaborative Education Mechanism for software engineering Education in the New Era:Take School of information and software engineering of UESTC as an Example

引用

计算机教育 2025年第3期 95-102页

作者： Linpeng Zhong Yili Li Xueying Yang the School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China JIC Trust Co. Ltd.Chengdu610041China

Building a collaborative education mechanism,improving students’engineering practice and innovation abilities,and cultivating software engineering innovation talents that meet industry needs are of great significance for fully implementing the“Excellent Engineer Education and Training Program”of the Ministry of Education and achieving the goal of building a strong engineering education *** School of information and software engineering of the University of Electronic Science and technology of China(UESTC)has been thoroughly studying and implementing XI Jinping’s thought on socialism with Chinese characteristics and the spirit of the 20th CPC National *** school has steadfastly promoted the Project of Nurturing the Soul of the New *** school has taken moral education as its core,deeply explored the resources of“all staff,throughout the process,in all aspects”,and constructed and implemented the collaborative education *** efforts have laid a solid foundation for cultivating excellent talents in software engineering in the new era.

关键词： software engineering Collaborative education Talent cultivation School-enterprise cooperation

来源：评论

学校读者我要写书评

暂无评论

On Campus Low-cost FSO Communication Link Analysis for Backhaul Connectivity in B5G Communications 37

On Campus Low-cost FSO Communication Link Analysis for Backh...

引用

Free-Space Laser Communications XXXVII 2025

作者： Saeed, Saad Khan, Abdullah Nafis Younis, Usman Faculty of Engineering Information Technology University of the Punjab Arfa Software Technology Park Ferozepur Road Lahore54600 Pakistan

ISBN: (纸本)9781510684584

Increasing demand of high-speed connectivity has challenged the future technologies (5G/B5G) in terms of large bandwidth, ultralow latency, massive coverage, reliable connectivity and rapid deployment. Free space optical (FSO) communication addresses these challenges in a cost effective way due to its unlicensed spectrum, high data-rate and long range. To develop a low-cost indoor FSO link, we present high-speed transceivers based on laser diode and photodiode. The transceiver link has achieved signal transmission up to 65 MHz providing minimum data rate of 130 Mbps using NRZ modulation. Link measurements are performed in an indoor campus environment by employing an optical assembly consisting plano-convex lenses, to achieve a range of 50 meters. An experimental demonstration of a square wave transmission up to 1 MHz is presented along with 53% improved quality of retrieved signal. Moreover, OSNR (13.6 dB) and BER (10−9) parameters are studied to enhance the performance of future FSO networks. © 2025 SPIE.

关键词： Space optics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resolution Guidance for Facial Expression Recognition 27th

Dynamic Resolution Guidance for Facial Expression Recogniti...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Songpan Li, Xu School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9783031781247

Facial expression recognition (FER) plays a crucial role in human-computer interaction and emotion analysis. However, recognizing expressions in low-resolution images remains a significant challenge. This paper introduces a practical method called Dynamic Resolution Guidance for Facial Expression Recognition (DRGFER) to effectively recognize facial expressions in images with varying resolutions without compromising the accuracy of the FER model. Our framework comprises two main components: the Resolution Recognition Network (RRN) and the Multi-Resolution Adaptation Facial Expression Recognition Network (MRAFER). The RRN determines the resolution of the input image, and the MRAFER assigns the image to the most suitable facial expression recognition network according to its resolution. We evaluated the performance of DRGFER on two widely used datasets, RAF-DB and FERPlus. The results demonstrate that our method maintains optimal model performance at each resolution and outperforms alternative resolution-handling approaches. The proposed framework exhibits robustness against variations in both resolution and facial expressions, offering a promising solution for real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Emotion Classification Based on Bilingual Feature Fusion 27th

Improving Chinese Emotion Classification Based on Bilingual...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lan, Haocheng Ou, Jie Wang, Zhaokun Tian, Wenhong School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9783031781186

The growing popularity of Chinese social media platforms such as Sina Weibo has created a large number of user generated text content, which is of great value for understanding public emotions. However, the existence of mixed languages in these texts, especially Chinese and English, and mixed expressions pose a major challenge to current emotion classification methods. To address these issues, we propose a Bilingual Feature Fusion Network (BFFN) that leverages the multilingual capabilities of pre-trained language models to enhance the semantic feature extraction of Chinese text. Additionally, we introduce a Bilingual Cross Attention Mechanism (BCAM) that utilizes emotional features as the primary factor to capture cross-lingual emotional information effectively. Furthermore, we employ a lightweight fine-tuning approach that combines Low-Rank Adaptation (LoRA) and Embedding Fine-tuning (LEF) to reduce the complexity of fine-tuning model weights for downstream tasks. Extensive experiments on various datasets demonstrate the superiority of our proposed method, outperforming state-of-the-art models like ERNIE by 1.43% in accuracy. Our work contributes to the advancement of emotion classification in the context of mixed-language communication culture and provides a practical solution for real-world applications. Our code has been published on the open source community Github (https://***/oujieww/BFFN). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Masked hybrid attention with Laplacian query fusion and tripartite sequence matching for medical image segmentation

引用

Neural Computing and Applications 2025年第8期37卷 5891-5911页

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Wang, Xiangxiang Ukot, Akpanika Robert Cai, Jingye School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Medical image segmentation is pivotal in computer-aided diagnosis systems, demanding high precision and contextual understanding. Vision Transformer-based approaches have gained much attention recently due to their excellent performance and ability to capture long-range dependencies in medical images. However, research shows they suffer from inadequate multi-scale feature integration, poor object localization, and inconsistent mask predictions, leading to sub-optimal segmentation performance. This paper addresses these challenges by redefining semantic medical image segmentation through learnable object queries within an enhanced transformer framework with a masked hybrid attention querying mechanism, optimizing multi-scale feature fusion, object localization, and instance-specific segmentation. First, this study presents a novel transformer-based masked hybrid attention mechanism using Laplacian query fusion on learnable query features and incorporating a novel tripartite sequence matching technique as part of the enhanced decoder block to improve the consistency of mask predictions and optimize decoder queries. The designed hybrid multi-head self- and cross-attention mechanisms aim to selectively integrate multi-scale features, ensuring optimal feature combinations for precise segmentation. Secondly, multiple class tokens are incorporated to improve object localization and capture class-specific characteristics within the transformer framework, leveraging the transformer decoders’ ability to learn distinct instance representations. Experimental results and extensive ablation studies demonstrate the effectiveness of the proposed approach on three publicly available datasets, obtaining better segmentation results compared to various state-of-the-art approaches using various evaluation metrics. Specifically, the proposed model achieves a Dice Score of 95.25%, 92.75%, and 85.25% on LUNA, ISIC, and DRIVE datasets, respectively. © The Author(s), under exclusive licence

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

PA2Net: Pyramid Attention Aggregation Network for Saliency Detection 31st

PA2Net: Pyramid Attention Aggregation Network for Saliency ...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yu, Jizhe Liu, Yu Wu, Xiaoshuai Xu, Kaiping Li, Jiangquan DUT School of Software Technology and DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9789819620630

With the development of deep convolutional neural networks (CNNs), salient object detection has become increasingly mature. Existing methods primarily enhance model performance by deepening and widening U-shaped networks. However, these methods typically consider the top-level features of bottom-up processes as global context, which is suboptimal and limited. This limitation arises because existing CNNs do not consider long-range dependencies, focusing more on local convolution operations. Additionally, the implicit interaction between complementary features in the top-down process fails to effectively learn the structural properties and semantic information, and it inevitably introduces significant noise. To address these issues, this paper adopts the idea of attention mechanisms to restore the object integrity in a more explicit manner while avoiding the introduction of irrelevant factors. First, we design a Global Context Enhancement (GCE) module to further enhance object localization and global context modeling by learning the correlations among deep features. Subsequently, an attention-based Pyramid Aggregation Decoder progressively merges multi-level adjacent features by learning their pairwise correspondences, gradually learning local details and global representations. Furthermore, a Noise Filter Block (NF) is integrated into the PAD to suppress background noise interference. Experimental results on five benchmark datasets show that our model performs favorably compared to 15 state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study 31

Do Current Video LLMs Have Strong OCR Abilities? A Prelimina...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Fei, Yulin Gao, Yuhui Xian, Xingyuan Zhang, Xiaojin Wu, Tao Chen, Wei School of Software Engineering Huazhong University of Science and Technology China Information Hub Hongkong University of Science and Technology Guangzhou China

ISBN: (纸本)9798891761964

With the rise of multi-modal large language models, accurately extracting and understanding textual information from video content-referred to as video-based optical character recognition (Video OCR)-has become a crucial capability. This paper introduces a novel benchmark designed to evaluate the video OCR performance of multi-modal models in videos. Comprising 1,028 videos and 2,961 question-answer pairs, this benchmark proposes several key challenges through 6 distinct sub-tasks: (1) Recognition of text content itself and its basic visual attributes, (2) Semantic and Spatial Comprehension of OCR objects in videos (3) Dynamic Motion detection and Temporal Localization. We developed this benchmark using a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement, balancing efficiency, cost, and data quality. Our resource aims to help advance research in video LLMs and underscores the need for improving OCR ability for video LLMs. The benchmark will be released on https://***/YuHuiGao/***. © 2025 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

Enhancing Large Language Model Inference Efficiency via Lookahead Cache Filtering

Enhancing Large Language Model Inference Efficiency via Look...

引用

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

作者： Ou, Jie Chen, Yueming Jiang, Shuaihong Tian, Wenhong School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

The large Key-Value (KV) cache is a significant challenge in deploying Large Language Models (LLMs). Current research addressing these issues employs cache compression techniques, which we find suffer from information loss and the "lost-in-the-middle" problem. We propose the Lookahead Cache Filtering (LCF), which retains the full cache in host memory to keep complete details, using the Important Key-Value Lookahead Prediction by Approximate Sorting and the Gather-based Matrix Multiplication on CPU, to filter important KV cache to reduce the overhead of loading cache to GPU and improve the throughput of inference. Finally, we use the Multi-Scale Pyramid information Fusion mechanism to enhance information fusion to further improve the effectiveness of inference results. Experiments demonstrate that LCF effectively maintains accuracy without introducing additional latency while reducing memory requirements. Our code will be available on GitHub. © 2025 IEEE.

关键词： Approximate Sorting Important Key-Value Lookahead information Fusion Lost-in-the-Middle Operator Fusion on CPU

来源：评论

学校读者我要写书评

暂无评论

A Progressive Spectral Correction and Spatial Compensation Network for Pansharpening

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 10772-10785页

作者： Liu, Rixian Lu, Hangyuan Chi, Biwei Yang, Yong Huang, Shuying Jinhua University of Vocational Technology College of Information Engineering Jinhua321007 China Tiangong University School of Computer Science and Technology Tianjin300387 China Tiangong University School of Software Tianjin300387 China

Pansharpening aims to produce a high resolution multispectral image by fusing a panchromatic image with a low-resolution multispectral image. Current pansharpening methods often overlook the significant modality differences between source images and lack interaction between them, resulting in spatial-spectral distortions. To address these issues, we proposed a novel progressive spectral correction and spatial compensation network for pansharpening. The network comprises a spectral correction branch, a spatial compensation branch, and a spectral-spatial fusion (SSF) branch. In the spectral correction branch, we designed a local spectral reinforcement (LSR) module and a global spectral rectification (GSR) module to keep the spectral fidelity. The LSR module is designed to reinforce the unique local information from different kinds of spectral features, while the GSR module captures long-range dependency and rectifies the spectral features with a cross-attention mechanism. In the spatial compensation branch, we designed a multiscale dilated adaptive feature extraction module guided by spectral and spatial attention to extract useful spatial details, and the details are progressively compensated into the SSF branch to better keep spatial fidelity. The SSF branch is designed to interact with spectral correction branch and spatial compensation branch to mitigate the modal difference and progressively optimize the spectral-spatial information. Comprehensive experiments show that the proposed method outperforms current state-of-the-art pansharpening methods. © 2008-2012 IEEE.

关键词： Remote sensing

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：