检索结果-内蒙古大学图书馆

?-net: Dual supervised medical image segmentation with multi-dimensional self-attention and diversely-connected multi-scale convolution

引用

NEUROCOMPUTING 2022年 500卷 177-190页

作者： Xu, Zhenghua Liu, Shijie Yuan, Di Wang, Lei Chen, Junyang Lukasiewicz, Thomas Fu, Zhigang Zhang, Rui State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology China Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health Hebei University of Technology China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science University of Oxford United Kingdom Department of Health Management Center 983 Hospital of Joint Logistics Support Force China www.ruizhang.info

Although U-Net and its variants have achieved some great successes in medical image segmentation tasks, their segmentation performances for small objects are still unsatisfactory. Therefore, in this work, a new deep model, co-Net, is proposed to achieve more accurate medical image segmentations. The advancements of co-Net are mainly threefold: First, it incorporates an additional expansive path into U-Net to import an extra supervision signal and obtain a more effective and robust image segmentation by dual supervision. Then, a multi-dimensional self-attention mechanism is further developed to highlight salient features and suppress irrelevant ones consecutively in both spatial and channel dimensions. Finally, to reduce semantic disparity between the feature maps of the contracting and expansive paths, we further propose to integrate diversely-connected multi-scale convolution blocks into the skip connections, where several multi-scale convolutional operations are connected in both series and parallel. Extensive experimental results on three abdominal CT segmentation tasks show that (i) co-Net greatly outperforms the state-of-the-art image segmentation methods in medical image segmentation tasks;(ii) the proposed three advancements are all effective and essential for co-Net to achieve the superior performances;and (iii) the proposed multi-dimensional self-attention (resp., diversely-connected multi scale convolution) is more effective than the state-of-the-art attention mechanisms (resp., multi-scale solutions) for medical image segmentations. The code will be released online after this paper is formally accepted. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Medical image segmentation Dual supervision Multi-dimensional self-attention Diversely-connected multi-scale convolution

来源：评论

学校读者我要写书评

暂无评论

A QoE-Aware Adaptive Energy-Efficient Transmission Scheduling Method 30

A QoE-Aware Adaptive Energy-Efficient Transmission Schedulin...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Yuan, Yankun Wang, Lin Xiao, Chonghui Liu, Zijuan Dang, Fan Wang, Xu Zhao, Haitian Miao, Xin Yanshan University School of Information Science and Engineering China National Computer Network Emergency Response Technical Team/Coordination Center of China China Tsinghua University Department of Automation and BNRist China Tsinghua University Global Innovation Exchange China Tsinghua University School of Software and BNRist China

ISBN: (纸本)9798331515966

In this paper, we propose a dynamic data transmission strategy for smart home environments that aims to optimize the Quality of Experience (QoE) by adaptively adjusting the data upload frequency based on the predicted trends in sensor data. Using the home wireless sensors monitoring dataset, we implement a deep learning model for accurate time series forecasting. In addition, an anomaly detection mechanism is used to identify critical events, requiring more frequent data uploads when important changes are detected. The QoE is quantified through a weighted average of several influencing factors, including data timeliness, timely upload of critical events, and transmission frequency. Our optimization objective is to maximize QoE while minimizing the number of transmissions, with an emphasis on reducing energy consumption through intelligent scheduling. The results demonstrate that our approach effectively balances data timeliness, transmission efficiency, and energy savings, leading to improved user satisfaction in smart home applications. © 2024 IEEE.

关键词： Adaptive algorithm Anomaly detection Energy conservation IoT LSTM Models QoE

来源：评论

学校读者我要写书评

暂无评论

Text Classification Algorithm for Medical Adverse Events Based on Deep Learning 1

Text Classification Algorithm for Medical Adverse Events Bas...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Yan, Yandong Wang, Hao Zhang, Jiayu Song, Xinyu Lou, Yiwei Dai, Tengyu Wang, Lanhui Lv, Ming School of Software & Microelectronic Peking University Beijing China Chinese Pla General Hospital Health Department Beijing China School of Computer Science Peking University Beijing China Medical Supplies Center of Pla General Hospital Department of Medical Engineering Beijing China

ISBN: (纸本)9798350358780

The management of medical adverse events is an important topic in the field of healthcare. The classification of medical adverse events is the primary link in adverse event management. However, the research on medical adverse event classification technology is still in its early stages, mainly using rules or machine learning methods, and the prediction accuracy is not high enough. To address the above issues, this paper explores the application of deep learning in medical adverse event text classification tasks and proposes a hybrid model that combines deep pyramid convolution and cyclic convolution network structures to achieve category classification of adverse events. This model has two feature extraction modules: deep pyramid convolution and cyclic convolution. These two modules extract features in parallel using BERT word vectors as inputs, and then concatenate the features. The experiment shows that the model has good performance in adverse event classification. In order to further improve the effectiveness of adverse event text classification, this paper proposes two improved models, BRDCN and BRDHW, based on the hybrid model. The BRDCN model abstracts the concatenated features by adding a convolutional network after the feature extraction module to further extract features from the concatenated tensor. The experiment shows that the multi classification performance of adverse event cate-gories in the BRDCN model has improved compared to before improvement. The BRDHW model refers to the gate control structure of the highway network and sets a gate control matrix. This matrix is used to fuse the features extracted by the two modules. The experiment shows that the BRDHW model's multi classification performance of adverse event categories has been further improved. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split Federated Learning Scheme for Non-IID Data 7

Efficient Privacy-Preserving ML for IoT: Cluster-Based Split...

引用

7th Cyber Security in Networking Conference, CSNet 2023

作者： Arafeh, Mohamad Wazzeh, Mohamad Ould-Slimane, Hakima Talhi, Chamseddine Mourad, Azzam Otrok, Hadi Department of Software and It Engineering Montreal Canada Department of Mathematics and Computer Science Canada New York University Division of Science Abu Dhabi United Arab Emirates Cyber Security Systems and Applied Ai Research Center Lebanese American University Department of Csm Beirut Lebanon Khalifa University Department of Eecs Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350342871

This paper proposes a scheme addressing the challenges of integrating privacy-preserving distributed machine learning in the Internet of Things (IoT) context while improving the efficiency of the learning process and accelerating the convergence of the model. Specifically, it addresses the presence of non-independent and identically distributed (Non-IID) data and device heterogeneity, which occurs during parallel training and are common characteristics of IoT environments. In this context, SplitFed is a privacy-preserving technique that combines Federated Learning (FL) and Split Learning (SL) to enable fast and privacy-preserving model training on IoT devices. Through parallelism, FL allows fast and parallel model training. Furthermore, SL enables weak devices to train models through model splitting. However, SplitFed suffers from the increasing convergence time due to the FL parallelism introducing Non-IID and stragglers issues. In this paper, we aim to address the aforementioned problems by proposing a clustering parallelization scheme. As such, similar clients are combined based on their weight divergence and considered a single FL unit addressing the Non-IID problem. Moreover, to improve time efficiency and overcome the stragglers' presence, we offer a second clustering stage that separates clients by efficiency and uses FedAsync for model aggregation. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Smart Energy Management System Using Machine Learning

引用

computers, Materials & Continua 2024年第1期78卷 959-973页

作者： Ali Sheraz Akram Sagheer Abbas Muhammad Adnan Khan Atifa Athar Taher M.Ghazal Hussam Al Hamadi School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of SoftwareGachon UniversitySeongnamGyeonggido13120Korea Department of Computer Science COMSATS University IslamabadLahore CampusLahore54000Pakistan School of Information Technology Skyline University CollegeSharjah1797United Arab Emirates Network and Communication Technology Lab Center for Cyber SecurityFaculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangiSelangor43600Malaysia College of Engineering and IT University of DubaiDubaiUnited Arab Emirates

Energy management is an inspiring domain in developing of renewable energy ***,the growth of decentralized energy production is revealing an increased complexity for power grid managers,inferring more quality and reliability to regulate electricity flows and less imbalance between electricity production and *** major objective of an energy management system is to achieve optimum energy procurement and utilization throughout the organization,minimize energy costs without affecting production,and minimize environmental *** energy management is an essential and complex subject because of the excessive consumption in residential buildings,which necessitates energy optimization and increased user *** address the issue of energy management,many researchers have developed various frameworks;while the objective of each framework was to sustain a balance between user comfort and energy consumption,this problem hasn’t been fully solved because of how difficult it is to solve *** inclusive and Intelligent Energy Management System(IEMS)aims to provide overall energy efficiency regarding increased power generation,increase flexibility,increase renewable generation systems,improve energy consumption,reduce carbon dioxide emissions,improve stability,and reduce energy *** Learning(ML)is an emerging approach that may be beneficial to predict energy efficiency in a better way with the assistance of the Internet of Energy(IoE)*** IoE network is playing a vital role in the energy sector for collecting effective data and usage,resulting in smart resource *** this research work,an IEMS is proposed for Smart Cities(SC)using the ML technique to better resolve the energy management *** proposed system minimized the energy consumption with its intelligent nature and provided better outcomes than the previous approaches in terms of 92.11% accuracy,and 7.89% miss-rate.

关键词： Intelligent energy management system smart cities machine learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Studies with software Defined Radio Receivers of Aerial Objects On-Board Systems Signals 17

Experimental Studies with Software Defined Radio Receivers o...

引用

17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and computer engineering, TCSET 2024

作者： Khudov, Hennadii Kostianets, Oleksandr Tahyan, Kristina Makoveichuk, Oleksandr Biernik, Yelyzaveta Shevchenko, Yurii Force University Ivan Kozhedub Kharkiv National Air Radar Troops Tactic Department Kharkiv Ukraine Air Force Scientific Center Ivan Kozhedub Kharkiv National Air Force University Kharkiv Ukraine Scientific and Technical University Academician Y. Bugay International Department of Computer Science and Software Engineering Kyiv Ukraine

ISBN: (纸本)9798331520564

The paper proposes experimental studies with software Defined Radio receivers of aerial objects onboard systems signals. It is established that the signals of the following channels are additional sources of signals, for example, of unmanned aerial vehicles: command, telemetric, issuance of targeted information, manual control, satellite navigation. Experimental studies were conducted and signal spectrograms of signals were obtained. The RTL 820T2 model was chosen as the software Defined Radio receiver. For an aerial object coordinates determining that emits the signals, we will use the network of software Defined Radio receivers. So, the resulting measurement error when using the radar and the software Defined Radio network of receivers is determined. We can see that the use of the software Defined Radio network of receivers will increase the overall accuracy of determining the coordinates of an aerial object. © 2024 IEEE.

关键词： Radar receivers

来源：评论

学校读者我要写书评

暂无评论

GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation

arXiv

引用

arXiv 2025年

作者： Shahin, Nada Ismail, Leila Lab Department of Computer Science and Software Engineering College of Information Technology UAE University Al-Ain United Arab Emirates Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates Emirates Center for Mobility Research UAE University Al-Ain United Arab Emirates

Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which exhibits low performance due to the dynamic nature of the sign language. In this paper, we propose a novel Gated-Logarithmic Transformer (GLoT) that captures the long-term temporal dependencies of the sign language as a time-series data. We perform a comprehensive evaluation of GloT with the transformer and transformer-fusion models as a baseline, for Sign-to-Gloss-to-Text translation. Our results demonstrate that GLoT consistently outperforms the other models across all metrics. These findings underscore its potential to address the communication challenges faced by the Deaf and Hard of Hearing community. © 2025, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Exploring Unlabeled Data in Multiple Aspects for Semi-Supervised MRI Segmentation

引用

Health Data science 2024年第1期4卷 177-190页

作者： Qingyuan He Kun Yan Qipeng Luo Duan Yi Ping Wang Hongbin Han Defeng Liu Radiology Department Peking University Third HospitalBeijingChina Peking University Third Hospital Beijing Key Laboratory of Magnetic Resonance Imaging Devices and TechnologyBeijingChina School of Computer Science Peking UniversityBeijingChina Department of Pain Medicine Peking University Third HospitalBeijingChina School of Software and Microelectronics Peking UniversityBeijingChina National Engineering Research Center for Software Engineering Peking UniversityBeijingChina Key Laboratory of High Conffdence Software Technologies(Peking University) Ministry of EducationBeijingChina Department of Obstetrics and Gynecology Peking University Third HospitalBeijingChina Center for Reproductive Medicine Peking University Third HospitalBeijingChina

Background:MRI segmentation offers crucial insights for automatic *** deep learningbased segmentation methods have attained cutting-edge performance,their efffcacy heavily relies on vast sets of meticulously annotated ***:In this study,we propose a novel semi-supervised MRI segmentation model that is able to explore unlabeled data in multiple aspects based on various semi-supervised learning ***:We compared the performance of our proposed method with other deep learning-based methods on 2 public datasets,and the results demonstrated that we have achieved Dice scores of 90.3%and 89.4%on the LA and ACDC datasets,***:We explored the synergy of various semi-supervised learning technologies for MRI segmentation,and our investigation will inspire research that focuses on designing MRI segmentation models.

关键词： analysis labeled designing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multimodal Ensemble Fusion-Based Deep Learning for COVID-19 on Chest Radiographs

引用

computer Systems science & engineering 2023年第10期47卷 873-889页

作者： Mohamed Yacin Sikkandar K.Hemalatha M.Subashree S.Srinivasan Seifedine Kadry Jungeun Kim Keejun Han Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Department of Biomedical Engineering Bannari Amman Institute of TechnologySathyamangalam638401India Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Institute of Biomedical Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai602105India Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea Division of Computer Engineering Hansung UniversitySeoul02876Korea

Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its *** researchers are making persistent efforts to derive probable solutions formanaging the pandemic in their *** of the widespread and effective ways to detect COVID-19 is to utilize radiological images comprising X-rays and computed tomography(CT)*** the same time,the recent advances in machine learning(ML)and deep learning(DL)models show promising results in medical ***,the convolutional neural network(CNN)model can be applied to identifying abnormalities on chest *** the epidemic of COVID-19,much research is led on processing the data compared with DL techniques,particularly *** study develops an improved fruit fly optimization with a deep learning-enabled fusion(IFFO-DLEF)model for COVID-19 detection and *** major intention of the IFFO-DLEF model is to investigate the presence or absence of *** do so,the presented IFFODLEF model applies image pre-processing at the initial *** addition,the ensemble of three DL models such as DenseNet169,EfficientNet,and ResNet50,are used for feature ***,the IFFO algorithm with a multilayer perceptron(MLP)classification model is utilized to identify and classify *** parameter optimization of the MLP approach utilizing the IFFO technique helps in accomplishing enhanced classification *** experimental result analysis of the IFFO-DLEF model carried out on the CXR image database portrayed the better performance of the presented IFFO-DLEF model over recent approaches.

关键词： COVID-19 computer vision deep learning image classification fusion model

来源：评论

学校读者我要写书评

暂无评论

Imputation with Inter-Series Information from Prototypes for Irregular Sampled Time Series

arXiv

引用

arXiv 2024年

作者： Yu, Zhihao Chu, Xu Ma, Liantao Wang, Yasha Zhu, Wenwu Key Laboratory of High Confidence Software Technologies Ministry of Education Beijing China School of Computer Science Peking University Beijing China Department of Computer Science Tsinghua University Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China

Irregularly sampled time series are ubiquitous, presenting significant challenges for analysis due to missing values. Despite existing methods address imputation, they predominantly focus on leveraging intra-series information, neglecting the potential benefits that inter-series information could provide, such as reducing uncertainty and memorization effect. To bridge this gap, we propose PRIME, a Prototype Recurrent Imputation ModEl, which integrates both intra-series and inter-series information for imputing missing values in irregularly sampled time series. Our framework comprises a prototype memory module for learning inter-series information, a bidirectional gated recurrent unit utilizing prototype information for imputation, and an attentive prototypical refinement module for adjusting imputations. We conducted extensive experiments on three datasets, and the results underscore PRIME’s superiority over the state-of-the-art models by up to 26% relative improvement on mean square error. Our code is available at https://***/yzhHoward/PRIME. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

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：