检索结果-内蒙古大学图书馆

9th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2023

作者： Wang, Ye Shi, Chenxiao Li, Lijie Guo, Manyuan College of Computer Science and Technology Harbin Engineering University Harbin China Harbin Institute of Technology Software Engineering Co. Ltd. Harbin China

ISBN: (纸本)9789819959709

The goal of cross-domain named entity recognition is to transfer models learned from labelled source domain data to unlabelled or lightly labelled target domain datasets. This paper discusses how to adapt a cross-domain sentiment analysis model to the field of named entity recognition, as the sentiment analysis model is more relevant to the tasks and data characteristics of named entity recognition. Most previous classification methods were based on a tokenwise approach, and this paper introduces entity boundary information to prevent the model from being affected by a large number of nonentity labels. Specifically, adversarial training is used to enable the model to learn domain-confusing knowledge, and contrastive learning is used to reduce domain shift problems. The entity boundary information is transformed into a global boundary matrix representing sentence-level target labels, enabling the model to learn explicit span boundary information. Experimental results demonstrate that this method achieves good performance compared to multiple cross-domain named entity recognition models on the SciTech dataset. Ablation experiments reveal that the method of introducing entity boundary information significantly improves KL divergence and contrastive learning. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Object Detection Model for UAV Aerial images Based on TS-YOLOv8 11

Design and Implementation of Object Detection Model for UAV ...

引用

11th Joint International Information technology and Artificial Intelligence Conference, ITAIC 2023

作者： Wang, Shi Li, Jiao Chen, Jiahui Liu, Xinshu Xie, Chenlu Liu, Xiangju College of Computer and Communication Engineering Qilu Institute of Technology Jinan China College of Artificial Intelligence and Software Liaoning Petrochemical University Fushun China

ISBN: (纸本)9798350333664

The main task of UAV aerial object detection is to accurately detect and locate objects using rectangular boxes in aerial images or videos. Due to factors such as shooting height and angle, small objects and overlapping objects account for a large proportion of aerial photography objects. Current UAV aerial photography object detection models may encounter missed detection issues when detecting these two types of objects. In response to the above issues, this paper proposes a TS-YOLOv8 UAV aerial photography object detection model. This model adds a tiny object detection layer on the basis of YOLOv8n to solve the problem of missed detection of small objects. Secondly, the Soft-NMS algorithm is used to optimize the candidate boxes of YOLOv8n to solve the problem of missed detection of mutually occluding objects. The experimental results on the VisDrone2019 dataset show that the proposed TS-YOLO unmanned aerial vehicle aerial photography object detection model can effectively solve the problem of missed detection of small and mutually occluding objects. © 2023 IEEE.

关键词： Object Detection Soft-NMS UAV Aerial Images YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Early Diagnosis of Lung Tumors for Extending Patients’ Life Using Deep Neural Networks

引用

computers, Materials & Continua 2023年第7期76卷 993-1007页

作者： A.Manju R.Kaladevi Shanmugasundaram Hariharan Shih-Yu Chen Vinay Kukreja Pradip Kumar Sharma Fayez Alqahtani Amr Tolba Jin Wang Department of Computer Science and Engineering SRM Institute of Science and TechnologyRamapuramChennaiIndia Department of Computer Science and Engineering Saveetha Engineering CollegeChennaiIndia Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabadIndia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin 64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin 64002Taiwan Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjabIndia Department of Computing Science University of AberdeenAberdeenUK Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh 12372Saudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadh 11437Saudi Arabia School of Computer&Communication Engineering Changsha University of Science&TechnologyChangshaChina

The medical community has more concern on lung cancer *** experts’physical segmentation of lung cancers is time-consuming and needs to be *** research study’s objective is to diagnose lung tumors at an early stage to extend the life of humans using deep learning ***-Aided Diagnostic(CAD)system aids in the diagnosis and shortens the time necessary to detect the tumor *** application of Deep Neural Networks(DNN)has also been exhibited as an excellent and effective method in classification and segmentation *** research aims to separate lung cancers from images of Magnetic Resonance Imaging(MRI)with threshold *** Honey hook process categorizes lung cancer based on characteristics retrieved using several *** this principle,the work presents a solution for image compression utilizing a Deep Wave Auto-Encoder(DWAE).The combination of the two approaches significantly reduces the overall size of the feature set required for any future classification process performed using *** proposed DWAE-DNN image classifier is applied to a lung imaging dataset with Radial Basis Function(RBF)*** study reported promising results with an accuracy of 97.34%,whereas using the Decision Tree(DT)classifier has an accuracy of 94.24%.The proposed approach(DWAE-DNN)is found to classify the images with an accuracy of 98.67%,either as malignant or normal *** contrast to the accuracy requirements,the work also uses the benchmark standards like specificity,sensitivity,and precision to evaluate the efficiency of the *** is found from an investigation that the DT classifier provides the maximum performance in the DWAE-DNN depending on the network’s performance on image testing,as shown by the data acquired by the categorizers themselves.

关键词： Lung tumor deep wave auto encoder decision tree classifier deep neural networks extraction techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Fusion and Decomposition Network for Single Image Deraining

引用

IEEE Transactions on Image Processing 2024年 33卷 191-204页

作者： Wang, Qiong Jiang, Kui Wang, Zheng Ren, Wenqi Zhang, Jianhui Lin, Chia-Wen Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Sun Yat-sen University School of Cyber Science and Technology Guangzhou510275 China Hangzhou Dianzi University College of Computer Science and Technology Hangzhou310018 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu30013 Taiwan

Convolutional neural networks (CNNs) and self-attention (SA) have demonstrated remarkable success in low-level vision tasks, such as image super-resolution, deraining, and dehazing. The former excels in acquiring local connections with translation equivariance, while the latter is better at capturing long-range dependencies. However, both CNNs and Transformers suffer from individual limitations, such as limited receptive field and weak diversity representation of CNNs during low efficiency and weak local relation learning of SA. To this end, we propose a multi-scale fusion and decomposition network (MFDNet) for rain perturbation removal, which unifies the merits of these two architectures while maintaining both effectiveness and efficiency. To achieve the decomposition and association of rain and rain-free features, we introduce an asymmetrical scheme designed as a dual-path mutual representation network that enables iterative refinement. Additionally, we incorporate high-efficiency convolutions throughout the network and use resolution rescaling to balance computational complexity with performance. Comprehensive evaluations show that the proposed approach outperforms most of the latest SOTA deraining methods and is versatile and robust in various image restoration tasks, including underwater image enhancement, image dehazing, and low-light image enhancement. The source codes and pretrained models are available at https://***/qwangg/MFDNet. © 1992-2012 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

mRS-DBFT: An improved consensus mechanism suitable for end-edge-cloud hybrid trust models 5

mRS-DBFT: An improved consensus mechanism suitable for end-e...

引用

5th International Conference on Frontiers technology of Information and computer, ICFTIC 2023

作者： Zhai, Xue Pang, Shanchen Qiao, Sibo Yu, Shihang Qingdao Institute of Software College Computer Science and Technology Qingdao China Tiangong University School of Mechanical Engineering Tianjin China

ISBN: (纸本)9798350309034

As a three-terminal collaborative architecture of terminal, edge and cloud, end-edge-cloud is jointly participated by multiple institutions or organizations, and has the characteristics of a hybrid trust architecture of 'partially trustworthy, globally untrustworthy'. Traditional consensus algorithm designs are mostly used in relatively unified trust model environments and do not provide a mechanism for cross-organizational cooperation. Therefore, they cannot effectively solve the trust and consensus issues between organizations. We propose an improved DPoS-PBFT consensus mechanism based on reputation scoring (mRS-DBFT). The core idea of the mRS-DBFT is to add a reputation scoring mechanism based on the DPOS-PBFT consensus algorithm. The reputation score is calculated based on factors such as the node's historical behavior, contribution, and credibility. Nodes with higher reputation score have greater influence and decision-making power in the consensus process. This mechanism can solve the problem of mutual distrust among nodes of different organizations in the end-edge-cloud architecture, and each node participates in the consensus process based on its reputation score, thus forming a credible and consistent system, achieving cross-organizational consensus, and ensuring node trust and data consistency in an open end-edge-cloud environment. The experimental results demonstrate that the mRS-DBFT consensus algorithm helps select nodes with higher stability to participate in the consensus by evaluating the reputation of computing devices, it can reduce fluctuations in delay and improve the stability of the consensus process. © 2023 IEEE.

关键词： consensus mechanism delegated proof of stake end-edge-cloud computing practical byzantine fault tolerance reputation scoring

来源：评论

学校读者我要写书评

暂无评论

In silico prediction methods of self-interacting proteins:an empirical and academic survey

引用

Frontiers of computer Science 2023年第3期17卷 199-216页

作者： Zhanheng CHEN Zhuhong YOU Qinhu ZHANG Zhenhao GUO Siguo WANG Yanbin WANG College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China School of Computer Science Northwestern Polytechnical UniversityXi’an 710129China Institute of Machine Learning and Systems Biology School of Electronics and Information EngineeringTongji UniversityShanghai 201804China School of Cyber Science and Technology Zhejiang UniversityHangzhou 310058China

In silico prediction of self-interacting proteins(SIPs)has become an important part of *** is an urgent need to develop effective and reliable prediction methods to overcome the disadvantage of high cost and labor intensive in traditional biological wet-lab *** goal of our survey is to sum up a comprehensive overview of the recent literature with the computational SIPs prediction,to provide important references for actual work in the *** this review,we first describe the data required for the task of DTIs ***,some interesting feature extraction methods and computational models are presented on this topic in a timely ***,an empirical comparison is performed to demonstrate the prediction performance of some classifiers under different feature extraction and encoding ***,we conclude and highlight potential methods for further enhancement of SIPs prediction performance as well as related research directions.

关键词： proteomics self-interacting proteins feature extraction prediction model

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

Anomaly detection using deep learning approach for IoT smart city applications

引用

Multimedia Tools and Applications 2025年第17期84卷 17929-17949页

作者： Shibu, S. Kirubakaran, S. Remamany, Krishna Priya Ahamed, Suhail Chitra, L. Kshirsagar, Pravin R. Tirth, Vineet Department of Electronics and Communication Engineering Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Computer Science and Engineering CMR College of Engineering and Technology Telangana Hyderabad501401 India Engineering Department College of Engineereing and Technology University of Technology an Applied Sciences PC Musandam811 Oman Machine Learning Software Engineer Paragon Semvox GmbH Saarland Kirkel Germany Department of Electrical and Electronics Engineering Aarupadai Veedu Institute of Technology Vinayaka Missions Research Foundation Tamil Nadu Chennai603104 India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Maharashtra Nagpur India Department of Mechanical Engineering College of Engineering King Khalid University Asir Abha61421 Saudi Arabia

With the advancements of IoT devices, many smart applications start to rule this era. In particular, smart cities has been adapted and realized by many countries around the world. In smart cities, vas amount of data is generated at every second. This vast data need a transmission medium which could be wireless standard. However, security is the main concern in such applications since the smart transmission always binds with anomalies. The existing anomaly detection systems need improvement in accuracy due to inefficient feature extraction and selection procedure. This paper proposes an accurate anomaly detection technique that built upon deep learning approach. We proposed a Combined Deep Q-Learning (CDQL) algorithm for anomaly detection. Priory, optimal features are selected by using Spider Monkey Optimizer (SMO). With the optimal features, CDQL detects anomalies accurately. In addition, the CDQL algorithm learns the environment in order to monitor the network data continuously. This continuous monitoring and optimum features helps in accuracy improvement up to 98%. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Low-Resource Language Literature Using Data Processing and Deep Learning

引用

computers, Materials & Continua 2024年第4期79卷 713-733页

作者： Aizaz Ali Maqbool Khan Khalil Khan Rehan Ullah Khan Abdulrahman Aloraini Department of IT and Computer Science Pak-Austria Fachhochschule:Institute of Applied Sciences and TechnologyHaripur22620Pakistan Software Competence Center Hagenberg Softwarepark 32aHagenberg4232Austria Department of Computer Science School of Engineering and Digital SciencesNazarbayev UniversityAstana010000Kazakhstan Department of Information Technology College of ComputerQassim UniversityP.O.Box 1162BuraydahSaudi Arabia

Sentiment analysis, a crucial task in discerning emotional tones within the text, plays a pivotal role in understandingpublic opinion and user sentiment across diverse *** numerous scholars conduct sentiment analysisin widely spoken languages such as English, Chinese, Arabic, Roman Arabic, and more, we come to grapplingwith resource-poor languages like Urdu literature which becomes a challenge. Urdu is a uniquely crafted language,characterized by a script that amalgamates elements from diverse languages, including Arabic, Parsi, Pashtu,Turkish, Punjabi, Saraiki, and more. As Urdu literature, characterized by distinct character sets and linguisticfeatures, presents an additional hurdle due to the lack of accessible datasets, rendering sentiment analysis aformidable undertaking. The limited availability of resources has fueled increased interest among researchers,prompting a deeper exploration into Urdu sentiment analysis. This research is dedicated to Urdu languagesentiment analysis, employing sophisticated deep learning models on an extensive dataset categorized into fivelabels: Positive, Negative, Neutral, Mixed, and Ambiguous. The primary objective is to discern sentiments andemotions within the Urdu language, despite the absence of well-curated datasets. To tackle this challenge, theinitial step involves the creation of a comprehensive Urdu dataset by aggregating data from various sources such asnewspapers, articles, and socialmedia comments. Subsequent to this data collection, a thorough process of cleaningand preprocessing is implemented to ensure the quality of the data. The study leverages two well-known deeplearningmodels, namely Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), for bothtraining and evaluating sentiment analysis performance. Additionally, the study explores hyperparameter tuning tooptimize the models’ efficacy. Evaluation metrics such as precision, recall, and the F1-score are employed to assessthe effectiv

关键词： Urdu sentiment analysis convolutional neural networks recurrent neural network deep learning natural language processing neural networks

来源：评论

学校读者我要写书评

暂无评论

Predictive Classification Model of Crop Yield Data Using Artificial Neural Network 5

Predictive Classification Model of Crop Yield Data Using Art...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Kanagaraj, R. Elakiya, E. Kumaresan, A. Selvakumar, J. Suganya, J. Shruthi, K. School of Computer Science and Engineering Vellore Institute of Technology Vellore India Vellore Institute of Technology Department of Computer Science and Engineering Chennai India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Mailam Engineering College Mailam India Bosch Global Software Technologies Coimbatore India

ISBN: (纸本)9798350321425

Agriculture is under tremendous pressure to produce more productivity with fewer resources as a result of the expanding global population. Decision-making along the entire supply chain needs to be improved considering competing economic, environmental, and societal demands. Data from satellites, drones, sensors, and other sources must be processed in order to make informed judgments. However, sophisticated machine learning and data analytics methods must be used due to the complexity and volume of the data. This initiative covers crucial duties in yield prediction and precision agriculture. Management zones are areas of a field that have high inter-regional variability and low intra-regional variability, dividing the field into uniform zones for which agronomic practices should be modified independently. For fertilizer optimization and post-harvest logistics, yield prediction is crucial. In order to make up for the nutrients that have been taken out of the soil, fertilizer type and quantity must be adjusted accordingly. The yield data is also essential for enhancing harvesting, shipping, storage, and sales. So, utilizing web scraping and convolution neural networks, the proposed model has been forecast yields from input satellite photos. The result of investigations is illustrated that the artificial neural network algorithm is used to predicting the agricultural data rules and powerfully decrease the error rate from crop yield data. © 2023 IEEE.

关键词： Neural networks

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：