检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Jun Yan, Zhiqiang Zeng, Hao Zhu, Zexuan Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350386226

Aptamers are single-stranded DNA or RNA oligonucleotides that selectively bind to specific targets, making them valuable for drug design and diagnostic applications. Identifying the interactions between aptamers and target proteins is crucial for these applications. The systematic evolution of ligands by exponential enrichment process, traditionally used for this purpose, is challenging and time-consuming. The resulting aptamers often suffer from limitations in stability and diversity. Computational approaches have shown promise in aiding the discovery of high-performance aptamers, but existing methods are usually constrained by insufficient training data and limited generalizability. Recently, advancements in pre-training large language models have offered a new avenue to mitigate the dependency on large datasets. In this study, we propose a novel method to predict aptamer-protein interactions using large language models within a contrastive learning framework. Experimental results demonstrate that our method exhibits superior generalization and outperforms existing approaches. This method holds promise as a powerful tool for predicting aptamer-protein interactions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Multi-Agent Proximal Policy Based Resource Allocation in Clustered IoV Networks 10

Collaborative Multi-Agent Proximal Policy Based Resource All...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Raza, Arif Xiang, Junfan Khan, Salabat Shrivastava, Shivanshu Ashraf, M. Wasim Abbas Wang, Lu Shenzhen University College of Computer Science and Software Engineering Shenzhen China Shenzhen University College of Electronics and Information Engineering Shenzhen China Qilu Institute of Technology College of Computer and Information Engineering Jinan China Rajiv Gandhi Institute of Petroleum Technology Department of Electrical and Electronics Engineering Amethi India Hanjiang Normal University School of Mathematics and Computer Science Shiyan China

ISBN: (纸本)9798331520861

The Internet of Vehicles (IoV) necessitates efficient resource management to meet the growing demands for high data rates, low latency, and real-time communication in Intelligent Transportation Systems (ITS). This paper presents a novel multiagent reinforcement learning framework based on the Proximal Policy Optimization (PPO) algorithm for optimizing resource allocation in clusters of cells within IoV networks. The framework dynamically allocates transmission power and bandwidth across base stations, each acting as a collaborative agent. Extensive simulations demonstrate that the multi-agent PPO approach outperforms other reinforcement learning algorithms, including Soft Actor-Critic (SAC) and Advantage Actor-Critic (A2C), regarding throughput, power efficiency, dynamic bandwidth allocation, and overall network performance. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

On the Adversarial Robustness of Hierarchical Classification

On the Adversarial Robustness of Hierarchical Classification

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Ran Zeng, Simeng Wu, Wenhui Jia, Yuheng Ng, Wing W. Y. Wang, Xizhao School of Mathematical Sciences Shenzhen University Shenzhen518060 China College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China School of Computer Science and Engineering Southeast University Nanjing211189 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9781665410205

Deep neural networks (DNNs) have demonstrated remarkable success on various learning problems, but they face a formidable challenge in the form of adversarial attacks. Especially, when dealing with complex classification tasks for numerous classes with a hierarchical structure, the adversarial robustness of a DNN model may drop seriously. In this paper, we investigate the adversarial robustness of DNN models on such complex classification tasks. In response, we propose a two-stage hierarchical classification framework, which is composed of a coarse-grained classifier and a series of fine-grained classifiers. A data correction sampling module is designed between the two stages, in order to mitigate the influence of misclassification caused by the coarse-grained classifier;and a discriminative filter learning module is employed in the fine-grained classification, in order to gain better distinguish abilities among fine-grained categories. Experiments on the well-known dataset CIFAR-100 and a newly-constructed hierarchical dataset mini-ImageNet76 demonstrate that employing a hierarchical framework can effectively improve the model robustness on such complex classification tasks. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Biometric Recognition Neural Networks with Branch Attention Mechanisms 2

Multimodal Biometric Recognition Neural Networks with Branch...

引用

2nd Asia Conference on Advanced Robotics, Automation, and Control engineering, ARACE 2023

作者： Liujun Mingjin, Chen Guoyong Zengxi, Huang Xihua University College of Computer and Software Engineering Chengdu China Sichuan Police College Criminal Science and Technology Department Chengdu China

ISBN: (纸本)9798350328363

It is generally known that compared to unimodal systems, the multi-modal biometric systems can improve recognition accuracy by utilizing the complementary features of multiple biometric. Nevertheless, the modalities used may not always play equally important roles in multi-modal recognition. Especially, in practical application scenarios, it often occurs that some of the biometric samples are contaminated by noise and corruption. In this context, the multi-modal recognition systems should pay more attention to the high-quality modality than the ones with low-quality samples, so as to maintain high accuracy. In this paper, we proposes a multi-branch deep learning network for multi-modal recognition, each branch using one biometric sample as input. To highlight the more important biometric modalities, we propose to embed a branch attention module between branches before multi-modal feature fusion. The branch attention module includes fuse, select, and calibrate steps, which can dynamically calculate the weight of each branch based on its importance. The proposed multi-modal recognition model is tested on a chimeric bimodal dataset with the face and the ear modalities. Our proposed method still achieves 92.76% of rank-1 on the most contaminated dataset;the rest of the experimental results are shown in the Experiment and Performance Analysis section. Our experimental results clearly demonstrate that the proposed branch attention method can improve the multi-modal recognition performance. © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A 3D Designed Portable Programmable Device Using Gas Sensors for Air Quality Checking and Predicting the Concentration of Oxygen in Coal Mining Areas 5th

A 3D Designed Portable Programmable Device Using Gas Sensors...

引用

5th International Conference on Soft Computing and Signal Processing, ICSCSP 2022

作者： Aslamiya, M. Saleena, T.S. Haque, A. K. M. Bahalul Ilyas, P. Muhamed Department of Computer Science Al Jamia Arts and Science College Perinthalmanna India Department of Computer Science Sullamussalam Science College Areekode India Software Engineering LENS LUT University Lappeenranta Finland Sullamussalam Science College Areekode673639 India

ISBN: (纸本)9789811986680

Air pollution has become one of the most dreadful threats to the whole living thing. There are numerous global researches giving lots of attention to the impact of air pollution on health and the environment. One of the issues faced by the coal mining workers is the reduction in the concentration of oxygen due to the increased emission of methane in mining areas. The proposed system is an Arduino based 3D designed portable programmable system with the capability of measuring air quality in the atmosphere using MQ4, MQ7, MQ135 gas sensors, finding the levels of pollutant gasses, and predicting the oxygen level especially in coal mining areas. Increase in methane causes a reduction in oxygen. Based on the sensing values, the system produces appropriate results and gives alerts to the users of the device. A 3D case designed using AutoCAD software envelopes the system, it makes the system more user-friendly. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Coal combustion

来源：评论

学校读者我要写书评

暂无评论

A Nature-Inspired AI Framework for Accurate Glaucoma Diagnosis

引用

computer Modeling in engineering & sciences 2025年第4期143卷 539-567页

作者： Jahanzaib Latif Ahsan Wajahat Alishba Tahir Anas Bilal Mohammed Zakariah Abeer Alnuaim School of Software Northwestern Polytechnical UniversityXi’an710072China Shifa College of Medicine Shifa Tameer-e-millat UniversityIslamabad44000Pakistan College of Information Science and Technology Hainan Normal UniversityHaikou571158China Department of Computer Science and Engineering College of Applied Studies and Community ServiceKing Saud UniversityRiyadh11495Saudi Arabia

Glaucoma,a leading cause of blindness,demands early detection for effective *** AI-based diagnostic systems are gaining traction,their performance is often limited by challenges such as varying image backgrounds,pixel intensity inconsistencies,and object size *** address these limitations,we introduce an innovative,nature-inspired machine learning framework combining feature excitation-based dense segmentation networks(FEDS-Net)and an enhanced gray wolf optimization-supported support vectormachine(IGWO-SVM).This dual-stage approach begins with FEDS-Net,which utilizes a fuzzy integral(FI)technique to accurately segment the optic cup(OC)and optic disk(OD)from retinal images,even in the presence of uncertainty and *** the second stage,the IGWO-SVM model optimizes the SVM classification process,leveraging a gray wolf-inspired optimization strategy to fine-tune the kernel function for superior *** testing on three benchmark glaucoma image databases DRIONS-DB,Drishti-GS,and Rim-One-r3 demonstrates the efficacy of our method,achieving classification accuracies of 97.65%,94.88%,and 93.2%,*** results surpass existing state-of-the-art techniques,offering a promising solution for reliable and early glaucoma detection.

关键词： Glaucoma fundus images machine learning nature-inspired algorithm segmentation classification

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Emotional Design in a Heated Non-Burning Tobacco Product

Research on the Application of Emotional Design in a Heated ...

引用

2022 International Symposium on Design Studies and Intelligence engineering, DSIE 2022

作者： Lei, Yu Xiang, Yudi Ye, Ziyi Zhou, Zhiyu Industrial Design Engineering College of Software Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9781643683720

To explore the application of emotional design theory in the design of a new heated non-burning tobacco (HNB) product. Based on Norman's three levels theory of emotional design, this research redesigns HNB products from the aspects of instinct, behavior, and reflection on the appearance of products, interactive experience, and users' deep emotional experience. It makes the product more in line with the temperament and characteristics of the young group, improves the user experience, and meets the emotional needs of users in different scenes. © 2023 The authors and IOS Press.

关键词： Tobacco

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Cardiac Image Segmentation Using a Bicycle VAE with Cross Prior Attention

Semi-Supervised Cardiac Image Segmentation Using a Bicycle V...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Li, Shaojie Zhang, Yifan Yang, Xuan Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9781665468190

This paper proposes a semi-supervised learning framework for cardiac image segmentation based on a bicycle Variational Auto-Encoder (biVAE) architecture by embedding a Prior Transformer and a conditional generative network. Specifically, to enhance the presentation of extracted features, a Transformer with cross attention to prior is embedded in the encoder of our framework, where the global context and anatomical prior are modeled at each layer of the Prior Transformer's decoder to fuse multi-scale features. A biVAE is proposed by employing a conditional generative network, which maps the latent space to the image and maps the image to the latent space again. It makes the encoder of biVAE serve as a good feature representation for cardiac image segmentation. Many experiments on public cardiac MR datasets show that by introducing prior to the Transformer, more powerful features can be extracted in terms of representation, improving our semi-supervised framework's predictive performance. Furthermore, the proposed semi-supervised framework achieves competitive results with state-of-the-art supervised learning-based networks. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Federated Learning-Based and Profit-Driven Service Caching Method 19th

A Novel Deep Federated Learning-Based and Profit-Driven Ser...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Ouyang, Zhaobin Xia, Yunni Peng, Qinglan Li, Yin Chen, Peng Wang, Xu College of Computer Science Chongqing University Chongqing China School of Artificial Intelligence Henan University Zhengzhou China Guangzhou Institute of Software Application Technology Guangzhou China School of Computer and Software Engineering Xihua University Chengdu China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

ISBN: (纸本)9783031545306

Service caching is an emerging solution to addressing massive service request in a distributed environment for supporting rapidly growing services and applications. With the explosive increases in global mobile data traffic, service caching over the edge computing architecture, Mobile edge computing (MEC), emerges for alleviating traffic congestion as well as for optimizing the efficiency of task processing. In this manuscript, we propose a novel profit-driven service caching method based on a federated learning model for service prediction and a deep reinforcement learning mode for yielding caching decisions (FPDRD) in an edge environment. The proposed method is temporal service popularity and user preference-aware. It aims to ensure quality of service (QoS) of delivery of cached service while maximizing the profits of network service providers. Experimental results clearly demonstrate that the FPDRD method outperforms traditional methods in multiple aspects. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Wearable-Based Human Emotion Inference System 2nd

Wearable-Based Human Emotion Inference System

引用

2nd EAI International Conference on Edge Computing and IoT: Systems, Management and Security, ICECI 2021

作者： Zhao, Zirui Zheng, Canlin College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9783031042300

Many emotion recognition methods which have been proposed today have different shortcomings. For example, some methods use expensive and cumbersome special-purpose hardware, such as EEG/ECG helmets, while others based on cameras and speech caused risk of privacy leakage. With the prosperous development and popularization of wearable devices, people tend to be equipped with multiple smart devices, which provides potential opportunities for lightweight emotional perception. Based on this, we take actions on developing universal portable system and multi-source wearable sensing technology devices. This paper designs an emotion recognition framework called MW-Emotion (Multi-source Wearable emotion recognition) featuring on low cost, universality, and portable commercial wearable devices to perceive multi-source sensing data and implement a system. It takes four basic emotions as the research object and implement an emotion recognition to explore deep context innovatively. The experimental results show that MW-Emotion has a recognition accuracy of 85.1% for person-dependent mode. The framework uses the method that different types of data are effectively fused through signal processing. We call it multimodal data fusion technology, which reduces the energy waste caused by data redundancy and effectively resists interference. © 2022, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Emotion Recognition

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：