检索结果-内蒙古大学图书馆

Positive-Unlabeled Learning with Field of View Consistency for Histology Image Segmentation 1

13th International Conference on Frontier computing, FC 2023

作者： Jia, Xiaoqi Fu, Chong Hou, Jiaxin Qin, Wenjian School of Computer Science and Engineering Northeastern University Shenyang110819 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China

ISBN: (数字)9789819993420

ISBN: (纸本)9789819993413

Histology image annotation is costly and time-consuming. Utilizing Positive and Unlabeled (PU) data for model training offers a more resource-efficient alternative. However, previous methods for PU learning suffer from the noise arising from label assignment to unlabeled data. We observe that predictions on noisy data lack consistency under data augmentation. In this paper, we present Field of View (FoV) consistency regularization for PU segmentation in histology images, which effectively reduces the noise influence by promoting consistent predictions across varying FoVs. Using only 20% of positive labels on the Glas Dataset, our approach outperforms previous methods, achieving a Dice score of 90.69%-almost reaching the fully supervised result of 93.30%. Source code is available at: https://***/lzaya/PU_with_FoV. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

OH-DRL: An AoI-Guaranteed Energy-Efficient Approach for UAV-Assisted IoT Data Collection

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 5009-5022页

作者： Yang, Bowen Yu, Yao Hao, Xin Yeoh, Phee Lep Zhang, Junxiong Guo, Lei Li, Yonghui Northeastern University School of Computer Science and Engineering Ministry of Education Northeastern University and Key Laboratory of Intelligent Computing in Medical Image Shenyang110819 China Deakin University School of Information Technology VIC3216 Australia University of the Sunshine Coast School of Science Technology and Engineering Australia Chongqing University of Posts and Telecommunications School of Communication and Information Engineering Chongqing400065 China University of Sydney School of Electrical and Computer Engineering SydneyNSW2006 Australia

In this paper, we propose a hierarchical optimization approach that guarantees the maximum age of information (AoI) for unmanned aerial vehicle (UAV) assisted Internet-of-Things (IoT) data collection. Our model is based on an energy-efficient simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) beamforming model. We formulate the optimization to minimize the UAV flight energy consumption subject to a maximum average AoI threshold by optimizing the UAV trajectory, IoT device scheduling, and STAR-RIS beamforming. To solve this, we develop an optimization-based hierarchical deep reinforcement learning (OH-DRL) algorithm that decomposes the formulated problem into an inter-cluster UAV visiting policy and STAR-RIS-based intra-cluster IoT scheduling policy. In OH-DRL, we jointly optimize the two policies in a high-level loop and a low-level loop, respectively. In the high-level loop, we design an AoI-guided DRL algorithm to determine the AoI-guaranteed UAV hovering position with minimal flight distance. In the low-level loop, a semidefinite relaxation (SDR)-based optimization algorithm further reduces the UAV’s flying time by minimizing the average AoI. Simulation results validate that OH-DRL achieves better convergence performance and energy-saving efficiency across different network scales. Compared to the state-of-the-art DRL algorithm, OH-DRL reduces the UAV flight energy consumption by 14.4% and decreases the number of training episodes required for convergence by 66%. © 2025 IEEE. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Ensemble Deep Learning Approaches for Liver Tumor Detection and Prediction

Ensemble Deep Learning Approaches for Liver Tumor Detection ...

引用

Ubiquitous computing and Intelligent Information Systems (ICUIS), International Conference on

作者： R. Archana L. Anand Department of Networking and Communication School of Computing College of Engineering and Technology (CET) SRM Institute of Science and Technology Kattankulathur Tamil Nadu

Cancer is a fatal illness with several underlying causes in metabolism and genetics. Liver cancer ranks as the third leading cause of cancer-related mortality globally and the sixth most prevalent illness in terms of total incidence. The liver plays a pivotal part in the physiological functioning of the human body. The liver controls cholesterol homeostasis and stores fat-soluble vitamins. Liver cancer may be treated more effectively if detected and classified early on. Brain, breast, liver, and other tumors may be examined using CT and MRI, two types of imaging technology. Convolutional neural networks (CNNs) have improved medical imaging for identifying and classifying cancer compared to earlier methods. To help radiologists notice anomalies more quickly, this research presents a classification model for recognizing liver tumors utilizing a convolutional neural network (CNN), an enhanced optimization technique, and transfer learning. The MPA (algorithm for detecting marine predators) was the basis for our optimization strategy. Using an improved version of the marine predator's algorithm (IMPA), developed as part of this project, I was able to identify the ideal values for the CNN's meta parameters. The proposed method combines a version of the ResNet50 CNN model that has already been trained with the IMPA algorithm to create the IMPA-ResNet50 architecture. This IMPA offers superior precision than competing optimization techniques accuracy is 99.20%. IMPA modifies the primary discovery and exploitation procedures to zero down on the most relevant features for reliable categorization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Link Prediction of biomedical data using Hetrosim GCN-GAT

Link Prediction of biomedical data using Hetrosim GCN-GAT

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： R Mythili N Parthiban Department of DataScience and Business Systems School of Computing SRM Institute of Science and Technology College of Engineering and Technology Kattankulathur Tamilnadu India

With the emergence of large number of Electronic Medical Records (EMRs), the researchers turned their attention towards the prediction, recommendation systems with these available data. This paper deals with the input of the patient details and the drugs administered to them for the different health conditions. The Drug to Drug Interaction (DDI) prediction is essential in order to avoid the unintended adverse reactions and making the drugs less effective. It is represented in the form of graphs with nodes and edges/links. Link prediction is often used to detect the existence of link or edges present in between the specified nodes. Graph Neural Network based algorithm HetrosimGCN-GAT is proposed to address the underlying link prediction tasks. A heterogeneous network is initially built using the drug-drug, protein-protein similarity matrices and drug protein matrices. The embedded representation of the drug and protein is then obtained using the graph convolutional neural network (GCN). Graph attention mechanism provides a weighting factor for every connect in order to assess the significance or highlight the contribution of distinct neighbourhood nodes to the central node. The unknown DDI and Drug Protein Interaction is predicted by applying the inner product decoder. The performance of HetrosimGCN-GAT is evaluated against the baseline methods and its outperforms the baseline methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion LMS for Distributed Estimation over Wireless Networks with Inter-Node Interference Perturbation

arXiv

引用

arXiv 2023年

作者： Moallem, Mohammadjavad Mirzazadeh Korki, Mehdi Babol Noshirvani University of Technology Babol Iran School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne Australia

In this paper, we investigate the diffusion least mean square (DLMS) algorithm over fading channel, where in addition to channel noise and path-loss the inter-node-interference (INI) among neighboring nodes of a host node is also taken into account. We also analyze the mean-square convergence behavior of DLMS algorithm, under such condition. In addition, based on an upper bound of the derived network MSD, an optimization problem is defined to find an optimal combination strategy. Furthermore, the adaptive version of the proposed combination strategy is presented. Simulation results corroborate the theoretical findings and indicate the superiority of the proposed combination methods over some previously reported algorithms. © 2023, CC BY.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Advancing Linguistic Frontiers with mBERT Fine-Tuning for Hindi and English Named Entity Recognition Using HiNER and WikiNEuRal Datasets

Advancing Linguistic Frontiers with mBERT Fine-Tuning for Hi...

引用

International Conference on computing and Networking technology (ICCNT)

作者： Anubhav Chauhan Tathagat Agrawal Ajeet Singh School of Computing Science and Engineering Vellore Institute of Technology - VIT Bhopal University Bhopal-Indore Highway Sehore Madhya Pradesh India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

In the realm of computational linguistics, the ability to accurately recognize named entities in text data stands as a cornerstone for numerous applications, ranging from information retrieval to sentiment analysis. This research work aims to push the boundaries of Named Entity Recognition (NER) specifically across Hindi and English languages by leveraging the transformative capabilities of the multilingual BERT (mBERT) model. Utilizing the HiNER and WikiNEuRal datasets, we embark on a meticulous fine-tuning process, where the mBERT model undergoes rigorous adaptation to excel in identifying named entities within both linguistic contexts. Over the course of three epochs, with a strategic selection of hyperparameters, our approach not only showcases the adaptability of mBERT across languages but also demonstrates its superiority by outperforming existing state-of-the-art models in the domain of NER. Through comprehensive experimentation and evaluation, our findings justify the effectiveness of fine-tuned mBERT in navigating the complexities of multilingual entity recognition, presenting a significant step forward in the advancement of linguistic frontiers.

关键词： Adaptation models Sentiment analysis Text recognition Navigation Computational modeling Named entity recognition Linguistics Information retrieval Distance measurement Context modeling

来源：评论

学校读者我要写书评

暂无评论

Temperature Variation Modelling in Mushroom Growing Hall with IAN-Bidirectional GRU Model 4

Temperature Variation Modelling in Mushroom Growing Hall wit...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Kalpanadevi, D. Devi, S. Nandhini Silas Stephen, D. Jadhav, Sunita Ali Khan, P.M.D. Muralidharan, J. School of Science Gitam University Department of Computer Science Karnataka India V. S. B. Engineering College Department of Cse Karudayanpalayam Tamilnadu Karur India Panimalar Engineering College Department of Electrical and Electronics Engineering Tamilnadu Chennai India Krishna Mahavidyalaya Rethare Bk Department of Botany Maharashtra Satara India School of Computing Mohan Babu University Andhra Pradesh Tirupati India Kpr Institute of Engineering and Technology Department of Ece Tamilnadu Coimbatore India

ISBN: (纸本)9798331540364

Modern developments in computing and electronics have made intelligent systems suitable for use in the mechanization of agricultural processes. This proposed used multilayered perceptron and radial basis function networks to forecast the temperature shifts in the mushroom cultivation chamber based on independent variables including water temperature, ambient temperature, water tap, fresh air and circulation air dampers, and water tap. Preprocessing, feature extraction, and training the model are the three phases that comprise this proposed method. Reflectance calibration, normalization, and spectral smoothing are the steps involved in data preprocessing. Feature extraction made quick work of extracting information from mushroom photos by employing the SIFT algorithm. The proposed model was trained using an IAN-Bidirectional GRU. When compared to more conventional approaches, the proposed methodology is superior. The method's application resulted in a 93.75% improvement in accuracy. © 2024 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Solar Energy Harvesting and Management in IoT Nodes Using Deep Self-Organizing Maps 2

Intelligent Solar Energy Harvesting and Management in IoT No...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Shinkar, Anita Rajkumar Joshi, Drumil Praveen, R.V.S. Rajesh, Yelisela Boopalan, K. Singh, Dharmendra Dr. D.Y. Patil College of Engineering Department of Computer Engineering Maharashtra Varale India Southern Power Birmingham Alabama Monitoring & Diagnostics Department India Digital Engineering and Assurance Telangana Hyderabad India KLEF Department of Computer Science & Engineering Andhra Pradesh India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology School of Computing Tamilnadu India School of Management Sciences Department of Applied Sciences & Humanities Lucknow India

ISBN: (纸本)9798331534950

Smart city energy generation must be efficient and dependable. As a result of studies conducted in this field, reliable control schemes for microgrid management have been developed, which seamlessly integrate with smart building management systems. In order for a building microgrid's solar energy system to recover from problems, this article suggests reliable controllers and the hardware to install them. Training models and Internet of Things (IoT) sensors provide the backbone of this proposed approach. When it comes to organizational and industrial contexts, sensors have evolved significantly with the introduction of the IoT. Pressure, optical, temperature, chemical sensors, and proximity are just a few examples of the many types of data that IoT devices may collect and send through sensor networks, allowing for greater efficiency. The model achieves a 91.37% accuracy rate in solar energy harvesting prediction after being trained using the Extended DSOM. © 2024 IEEE.

关键词： Conformal mapping

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Sensing-Communication Integration System in Industrial Automation Based on FDA and PA 25

Design and Optimization of Sensing-Communication Integration...

引用

25th IEEE International Conference on Industrial technology, ICIT 2024

作者： Feng, Freddy Y.P. Mi, De Guan, Mingxiang Sun, Lichao Tang, Hui Liu, Chang Xiao, Pei Lu, Chen Shenzhen Institute Of Information Technology Shenzhen China College Of Computing Birmingham City University Birmingham United Kingdom School Of Engineering Lancaster University Lancaster United Kingdom Extend Robotics Limited Reading United Kingdom Institute For Communication Systems University Of Surrey Guildford United Kingdom

ISBN: (纸本)9798350340266

Industrial automation is a rapidly evolving field that aims to improve efficiency, productivity, and safety in various verticals. The integration of sensing and communication technologies has become crucial in this automation process. Re-cent advancements in Frequency Diverse Array (FDA) antennas have shown promising performance advantages over traditional phased array antennas in certain aspects, e.g., the FDA-based radar can focus its beam in both angle and range domains simultaneously. In this paper, we propose a novel architecture for sensing-communication integration in the context of industrial automation, where FDA antennas are employed as the radar sensing array, while phased array antennas are utilized for communication purposes. The integration of FDA antennas brings benefits such as more accurate object detection, improved spatial resolution, and efficient data transmission. We present a comprehensive analysis of the proposed architecture, including design considerations, system modeling, and performance evalu-ation. The results demonstrate the potential of FDA antennas in enhancing the sensing-communication integration in industrial automation, leading to improved efficiency, productivity, and safety in industrial environments. © 2024 IEEE.

关键词： Integration

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：