检索结果-内蒙古大学图书馆

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Zhao, Peng Xiao, Yan Lei, Yuqing Ren, Yazhou Xu, Zenglin Chongqing Medical University School of Basic Medical Sciences Chongqing China University of Electronic Science And Technology of China School of Computer Science And Engineering Chengdu China University of Electronic Science And Technology of China Shenzhen Institute For Advanced Study Shenzhen China Harbin Institute of Technology Shenzhen School of Computer Science And Technology Shenzhen China Peng Cheng National Lab Center of Artificial Intelligence Shenzhen China

ISBN: (纸本)9798350359145

During the outbreak of COVID-19, it is particularly important to improve clinical decision making for critically ill patients in intensive care units (ICU). Machine learning has become increasingly important in healthcare analysis with the wide adoption of Electronic Health Records (EHR). Many deep learning algorithms, such as Recurrent Neural Networks (RNNs), have been developed to deal with clinical time series data to predict the health status of patients, such as mortality, ventilation, and phenotype, etc. Despite RNN being successful in medical tasks, the special traits of data, such as long temporality, high dimensionality, existence of missing values, and multi-labels, have brought challenges to either shallow or deep learning algorithms. Motivated by the fact that the progress of diseases may vary over time, to address these challenges, we proposed a multi-task attention-guided recurrent neural network for learning sequential features (MASFL) model, which employs recurrent units and an attention mechanism. The recurrent units can memorize the past progressive information of patients after entering ICU, while the attention mechanism can selectively utilize this information for different prediction tasks. Meanwhile, the attention also helps to interpret the relationship between the clinical time series data and the prediction result. Furthermore, in order to solve undesirable local solutions for the patient's length-of-stay task, we develop an ordinal regression loss to address the issue. According to the experiments on MIMIC-III, we demonstrate that the proposed model can improve the prediction performance over state-of-the-art prediction approaches. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection

AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domai...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yipeng Gao Kun-Yu Lin Junkai Yan Yaowei Wang Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab

In this work, we study few-shot domain adaptive object detection (FSDAOD), where only a few target labeled images are available for training in addition to sufficient source labeled images. Critically, in FSDAOD, the data scarcity in the target domain leads to an extreme data imbalance between the source and target domains, which potentially causes over-adaptation in traditional feature alignment. To address the data imbalance problem, we propose an asymmetric adaptation paradigm, namely AsyFOD, which leverages the source and target instances from different perspectives. Specifically, by using target distribution estimation, the AsyFOD first identifies the target-similar source instances, which serves to augment the limited target instances. Then, we conduct asynchronous alignment between target-dissimilar source instances and augmented target instances, which is simple yet effective for alleviating the over-adaptation. Extensive experiments demonstrate that the proposed AsyFOD outperforms all state-of-the-art methods on four FSDAOD benchmarks with various environmental variances, e.g., 3.1% mAP improvement on Cityscapes-to-FoggyCityscapes and 2.9% mAP increase on Sim10k-to-Cityscapes. The code is available at https://***/Hlings/AsyFPD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Scheduling Research for Edge Servers

Reinforcement Learning Scheduling Research for Edge Servers

引用

International Conference on computer Network, Electronic and Automation (ICCNEA)

作者： Yonggui Han Zhongsheng Wang School of Computer Science and Engineering Xi’an Technological University Xi’an China State and Provincial Joint Engineering Lab. of Advanced Network Monitoring and Control Xi'an Technological University Xi'an China

The rapid development of the Internet of Things and big data has brought about massive amounts of data and the need for real-time responses, which traditional computing models can no longer meet. Edge computing comes into being, which pushes computing resources and services closer to the source of data generation so that data can be processed and analyzed closer to the user. The scheduling of siting strategies for edge servers is crucial for improving the performance of edge computing networks. Traditional scheduling methods for siting strategies are often based on rules or optimization algorithms, which lack adaptive and intelligent management of the network *** paper proposes a reinforcement learning DQN-based edge server siting policy scheduling method, which aims to achieve intelligent management and resource optimization of edge computing networks by learning the optimal policy. Experimental results show that the method has significant performance advantages in terms of delay, load balancing and energy consumption. The experiment adopts DQN algorithm, which is based on Q-learning and guides the agent to make decisions by optimizing Q-value function. In this paper, the reinforcement learning scheduling algorithm of edge server is studied and compared with other three algorithms. According to the experimental results, the proposed reinforcement learning scheduling algorithm reduces the delay by 7%, the energy consumption by 3%, and the load balancing by 20% compared with the other three algorithms. This shows that the algorithm has significant advantages in improving system performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DV-Hop Localization Strategy Based on Beacon Node Confidence Analysis

DV-Hop Localization Strategy Based on Beacon Node Confidence...

引用

International Conference on computer Network, Electronic and Automation (ICCNEA)

作者： Han Shen Zhongsheng Wang School of Computer Science and Engineering Xi'an Technological University Xi'an China State and Provincial Joint Engineering Lab. of Advanced Network Monitoring and Control Xi'an Technological University Xi'an China

To address the problem that the DV-Hop localization model for wireless sensor networks can no longer meet the current localization accuracy requirements, this paper proposes the concept of beacon node trustworthiness to provide ideas and basis for improving the optimization model. Based on the principle of least squares in the localization model, weighted least squares is introduced to present the trustworthiness for beacon nodes with different characteristics. To analyze the characteristics of the trustworthiness of beacon nodes, 18 functions are designed in terms of function instrumentality and decrement able, hierarchical faultiness, etc. Finally, the conclusions obtained from the credibility test are tested with weighted matrix and average hop distance weighting, and the localization error is reduced from 32.68% to 31.78%, with a role rate of 100%. The credibility characteristics of beacon nodes discussed in this paper provide ideas for subsequent optimization of the localization model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BRNES: Enabling Security and Privacy-aware Experience Sharing in Multiagent Robotic and Autonomous Systems

arXiv

引用

arXiv 2023年

作者： Hossain, Md Tamjid La, Hung Manh Badsha, Shahriar Netchaev, Anton The Advanced Robotics and Automation Lab Computer Science and Engineering University of Nevada RenoNV United States Bosch Engineering North America The U.S. Army Corps United States

Although experience sharing (ES) accelerates multiagent reinforcement learning (MARL) in an advisor-advisee framework, attempts to apply ES to decentralized multiagent systems have so far relied on trusted environments and overlooked the possibility of adversarial manipulation and inference. Nevertheless, in a real-world setting, some Byzantine attackers, disguised as advisors, may provide false advice to the advisee and catastrophically degrade the overall learning performance. Also, an inference attacker, disguised as an advisee, may conduct several queries to infer the advisors’ private information and make the entire ES process questionable in terms of privacy leakage. To address and tackle these issues, we propose a novel MARL framework (BRNES) that heuristically selects a dynamic neighbor zone for each advisee at each learning step and adopts a weighted experience aggregation technique to reduce Byzantine attack impact. Furthermore, to keep the agent’s private information safe from adversarial inference attacks, we leverage the local differential privacy (LDP)-induced noise during the ES process. Our experiments show that our framework outperforms the state-of-the-art in terms of the steps to goal, obtained reward, and time to goal metrics. Particularly, our evaluation shows that the proposed framework is 8.32x faster than the current non-private frameworks and 1.41x faster than the private frameworks in an adversarial setting. © 2023, CC BY-NC-SA.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Image Defogging Based on Deep Learning

Research and Implementation of Image Defogging Based on Deep...

引用

International Conference on computer Network, Electronic and Automation (ICCNEA)

作者： Ao Li Zhongsheng Wang School of Computer Science and Engineering Xi’an Technological University Xi’an China State and Provincial Joint Engineering Lab. of Advanced Network Monitoring and Control Xi'an Technological University Xi'an China

Image degradation due to fog and haze is a common problem in the field of life and image research. This article will be designed and implemented of image haze removal algorithm. The traditional methods have some problems such as low brightness, artifact, halo and distortion, but the existing methods based on deep learning have better effect. In this paper, we will propose a de-fogging network model, which is based on adversarial network. The generator in adversarial network is a convolutional neural network with residual network, which reduces the model training parameters and improves the parameter utilization. The discriminator uses the full convolutional network as the discriminator, which enhances the spatial sensitivity of the model to the image. In order to improve efficiency, the discriminator is simplified on the original structure. The loss function of the model is improved so that the model can get better training effect.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Multilevel Degradater Model under Unsupervised Learning

Research on Multilevel Degradater Model under Unsupervised L...

引用

International Conference on computer Network, Electronic and Automation (ICCNEA)

作者： Jieyi Lv Zhongsheng Wang School of Computer Science and Engineering Xi'an Technological University Xi'an China State and Provincial Joint Engineering Lab. of Advanced Network Monitoring and Control Xi'an Technological University Xi'an China

In most super-resolution experiments, because the data set in the real scene cannot meet the quantity requirements, it is necessary to downsample the high-resolution images using the degradation method to obtain the same proportion of low-resolution images. However, because the same degradation method is used to process images, the processing process of low-resolution images is relatively simple, which is easy to cause model solidification in the subsequent training process. After the training is completed, the generalization ability will be generally low due to the single underlying degradation method. This paper uses the SRMD method to build an unsupervised multilevel degradation, and takes advantage of the adduction network generated in unsupervised learning. After extracting image features, it adopts anisotropic Gaussian fuzzy kernel, bi-cubic subsampling and additive Gaussian noise to compose the degradation training data set. Compared with the traditional bi-cubic PNSR, the performance is improved by 5%. The SSIM value is increased by 3%, and the running speed is increased by 7% on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Background Representation for Weakly Supervised Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Yin, Xu Im, Woobin Min, Dongbo Huo, Yuchi Pan, Fei Yoon, Sung-Eui The School of Computing Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of The Faculty of the Department of Computer Science and Engineering Ewha Womans University Seoul03760 Korea Republic of The State Key Lab of CAD and CG Zhejiang University China Zhejiang Lab 310058 China The School of Computer Science Engineering University of Michigan United States The Faculty of School of Computing Korea Advanced Institute of Science and Technology Deajeon34141 Korea Republic of

Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information. Prevalent class activation map (CAM)-based solutions are challenged to discriminate the foreground (FG) objects from the suspicious background (BG) pixels (a.k.a. co-occurring) and learn the integral object regions. This paper proposes a simple fine-grained background representation (FBR) method to discover and represent diverse BG semantics and address the co-occurring problems. We abandon using the class prototype or pixel-level features for BG representation. Instead, we develop a novel primitive, negative region of interest (NROI), to capture the fine-grained BG semantic information and conduct the pixel-to-NROI contrast to distinguish the confusing BG pixels. We also present an active sampling strategy to mine the FG negatives on-the-fly, enabling efficient pixel-to-pixel intra-foreground contrastive learning to activate the entire object region. Thanks to the simplicity of design and convenience in use, our proposed method can be seamlessly plugged into various models, yielding new state-of-the-art results under various WSSS settings across benchmarks. Leveraging solely image-level (I) labels as supervision, our method achieves 73.2 mIoU and 45.6 mIoU segmentation results on Pascal Voc and MS COCO test sets, respectively. Furthermore, by incorporating saliency maps as an additional supervision signal (I+S), we attain 74.9 mIoU on Pascal Voc test set. Concurrently, our FBR approach demonstrates meaningful performance gains in weakly-supervised instance segmentation (WSIS) tasks, showcasing its robustness and strong generalization capabilities across diverse domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

SOFT INJECTABLES USING SMART THREADS FOR DOSE-CONTROLLED DRUG DELIVERY

SOFT INJECTABLES USING SMART THREADS FOR DOSE-CONTROLLED DRU...

引用

2022 Solid-State Sensors, Actuators and Microsystems Workshop, Hilton Head 2022

作者： Alsaedi, Mossab K. Das, Riddha Nejad, Hojatollah Rezaei Sharma, Atul Sonkusale, Sameer Nano Lab. Advanced Technology Laboratory Tufts University MedfordMA United States Department of Chemical and Biological Engineering Tufts University MedfordMA United States Department of Electrical and Computer Engineering Tufts University MedfordMA United States Department of Biomedical Engineering Tufts University MedfordMA United States

ISBN: (纸本)9781940470047

Transdermal drug delivery is a promising alternative to conventional drug delivery approaches, such as oral ingestion and hypodermic injection. Hypodermic injections are often painful, and oral ingestion of drugs requires the administration of doses higher than the needed to compensate for enzymatic degradation and poor absorption of drugs. Current transdermal drug-delivery platforms include microneedles, which resolve the pain aspect of conventional drug delivery approaches. However, microneedle patches are impractical as they are easily peeled off with motion and sweat. In this study, we propose soft injectables comprised of sutures that are loaded with drugs for painless and localized sustained drug delivery in the dermis layer of the skin. They stay in place during the course of delivery and are suitable for any skin type. © 2022 TRF.

关键词： Controlled drug delivery

来源：评论

学校读者我要写书评

暂无评论

Integrating Prior Knowledge with Graph Encoder for Gene Regulatory Inference from Single-cell RNA-Seq Data

Integrating Prior Knowledge with Graph Encoder for Gene Regu...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Li, Jiawei Yang, Fan Wang, Fang Rong, Yu Zhao, Peilin Chen, Shizhan Yao, Jianhua Tang, Jijun Guo, Fei Tianjin University College of Intelligence and Computing Tianjin China AI Lab Tencent Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Central South University School of Computer Science and Engineering Changsha China

ISBN: (纸本)9781665468190

Inferring gene regulatory networks based on single-cell transcriptomes is critical for systematically understanding cell-specific regulatory networks and discovering drug targets in tumor cells. Here we show that existing methods mainly perform co-expression analysis and apply the image-based model to deal with the non-euclidean scRNA-seq data, which may not reasonably handle the dropout problem and not fully take advantage of the validated gene regulatory topology. We propose a graph-based end-to-end deep learning model for GRN inference (GRNInfer) with the help of known regulatory relations through transductive learning. The robustness and superiority of the model are demonstrated by comparative experiments. © 2022 IEEE.

关键词： RNA

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：