检索结果-内蒙古大学图书馆

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Agarwal, Ankita Kumar, Deepak Singh, Alka Preethi, D. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Mathematics Vivekananda Global University Jaipur India Department of Master of Computer Application Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This paper objectives to research the consequences of coding and compression on network performance. Network coding is the technique of encoding information before it is despatched over a network and has become an outstanding method to enhance community overall performance. Compression then again is used to reduce the size of the data before transmission, ensuing in quicker transmission time. This observe evaluates the effect those techniques have on network overall performance by measuring the bandwidth utilization, throughput, latency, and packet losses. A test becomes conducted to have a look at how the strategies have an effect on one of kind mixtures of information speeds, packet sizes, and facts loading. Results display that both strategies had a fine impact at the community overall performance, with network coding and compression having an extra effect on networks with higher facts hundreds. Moreover, the effects show that community coding had a greater impact on networks with larger packets, while compression had a more effect on networks with smaller packets. This studies gives insight into how community coding and compression can be used to enhance network overall performance. Coding and compression are important components of network performance that have been studied and tested to have a full-size influence on network pace, scalability, and reliability. Coding is used to reduce the amount of data that is sent over a community, by way of reducing the quantity of records frames that need to be sent and growing the performance of the records transfer technique. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Image-Based Sentiment Analysis Using InceptionV3 Transfer Learning Approach

引用

SN computer Science 2023年第3期4卷 242页

作者： Meena, Gaurav Mohbey, Krishna Kumar Kumar, Sunil Chawda, Rahul Kumar Gaikwad, Sandeep V. Department of Computer Science Central University of Rajasthan Ajmer India Department of Computer Science Assam University Silchar India School of Business Woxsen University Hyderabad India Faculty of Computer Science and Application SMPICA Charotar University of Science and Technology Gujrat Anand India

There has been a recent shift from using text-based sentiment analysis in favor of an image-based method. In recent years, transfer learning methods have been widely utilized in developing a comprehensive image sentiment analysis approach. Deep learning algorithms have produced remarkable outcomes in a variety of contexts. Image-based sentiment analysis presents many difficulties, but there also appears to be much space for development. A significant improvement over prior work is provided by an InceptionV3 approach that can easily focus on huge body portions like a human face. This research improves image categorization performance with InceptionV3, a popular deep convolutional neural network, and other deep features. Using a Convolutional Neural Network based on InceptionV3 architecture, we identify and classify emotions using the famous CK + , FER2013, and JAFFE datasets. Experiments reveal that the proposed model achieves 99.5% accuracy on the CK + dataset. Also, the accuracies of JAFFE and FER2013 are 86% and 73%, respectively. A person’s emotional patterns and mental health can be evaluated using this approach. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Artificial Intelligence Deep learning Image sentiment analysis InceptionV3 Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Simulation of orbital decay of LEO satellites due to atmospheric drag during magnetic storms

Simulation of orbital decay of LEO satellites due to atmosph...

引用

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Yu, Haiquan Pang, Yanhua Chen, Bo Feng, Xueshang Wang, Boyi Zhao, Yang Institute of Space Science and Application of Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

In order to understand the effect of geomagnetic activity on the orbits of LEO satellites with different orbital inclinations, we establish a model for the influence of atmospheric drag on the orbital decay of low Earth orbiting (LEO) satellites and simulate the orbital decay of seven LEO satellites during geomagnetic storms. In the simulation, the orbital inclinations of the seven LEO satellites are set to be 30°, 40°,50°, 60°, 70°, 80°, and 88°, respectively. and the initial orbital heights are all 350km. The simulation results show that the seven LEO satellites are affected to different degrees during the geomagnetic storm, satellites with smaller orbital inclinations are more affected. The orbit of the Sat-A satellite with the smallest orbital inclination decreased by 1.794 km during the entire magnetic storm, while the orbit of the Sat-G satellite with the largest orbital inclination decreased by 1.530 km. We compare the local thermospheric atmosphere density on different satellite orbits and found that the atmosphere density on the orbits of LEO satellites with smaller orbital inclinations is greater, which means that LEO satellites with small orbital inclinations experience greater atmospheric drag. We deduce that the reason for this phenomenon is related to the density distribution of the thermospheric background atmosphere. © 2022 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Non-IID federated learning via random exchange of local feature maps for textile IIoT secure computing

引用

Science China(Information Sciences) 2022年第7期65卷 16-31页

作者： Bo PENG Mingmin CHI Chao LIU School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Zhongshan Pool Net Technology Co.Ltd. Zhongshan Fudan Joint Innovation Center Zhengzhou Zhongke Institute of Integrated Circuit and System Application

With the fast development of artificial intelligence(AI) and industrial Internet of Things(IIoT)technologies, it is challenging to deal with the problems of data privacy protection and secure *** recent years, federated learning(FL) is proposed to attack the challenges of learning shared models collaboratively while protecting security based on the data from cross-domain clients. However, data in the real environment is usually not independent and identically distributed(Non-IID) due to the differences in business, working environments, and data acquisition, and thus classic federated methods suffer from significant performance degradation. In this paper, a novel federated framework is proposed for secure textile fiber identification(Fed TFI) via cross-domain texture representation based on high-definition fabric images. In addition to sharing the gradient of Fed TFI, the local patch of feature maps between crossdomain clients is randomly exchanged to build a richer image texture feature distribution while protecting data security simultaneously for secure computing. Furthermore, a texture embedding layer is designed to provide a joint representation through similarity measure between triplet samples in low-dimensional *** verify the effectiveness of the proposed framework, two textile image datasets, i.e., one public and the other we collected, are utilized to construct four Non-IID scenarios, including label skew, feature skew, and two combined skew scenarios. The experimental results confirm the effectiveness of our model to obtain better detection accuracies than benchmarks in four Non-IID scenarios by keeping data privacy for secure computing in fabric IIoT.

关键词： federated learning secure computing industrial Internet of Things (IIoT) machine vision texture encoding image classification Non-IID

来源：评论

学校读者我要写书评

暂无评论

Impact of Glucocorticoid Toxicity Index on Immunosuppressive Management of Inflammatory Bowel Disease 5th

Impact of Glucocorticoid Toxicity Index on Immunosuppressive...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Yadav, Dhyan Chandra Sharma, Sunil Agarwal, Chhaya Mehta, Deepak Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India Department of Biotechnology Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Glucocorticoid toxicity index (GTI) is a useful degree proposed by using a meta-evaluation to assess the chance of systemic glucocorticoid exposure in sufferers laid low with inflammatory bowels illnesses (IBD). The GTI is computed based totally on cumulative glucocorticoid cumulative dose and duration within the first yr. After a prognosis of IBD. The contemporary take a look at objectives to check the literature to decide the utility of GTI in predicting the danger of glucocorticoid toxicity in IBD patients. A literature search turned into conducted to pick out research that evaluated the predictive price of GTI for toxicity in IBD patients. The retrieved articles suggest that cumulative glucocorticoid dose and length prior to three hundred and sixty five days of the diagnosis of IBD have been massive factors related to the prevalence of glucocorticoid toxicity in IBD sufferers. However, different next elements may additionally have an effect on the toxicity of glucocorticoid exposure in IBD patients, along with age, comorbidities, and genetic polymorphisms. Moreover, some of the research, the outcomes validated that GTI can be a valuable device for immunosuppressive management in IBD sufferers to be able to discover patients who're much more likely to revel in systemic toxicity at some stage in immunosuppressive treatment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cumulative Exposure Glucocorticoid

来源：评论

学校读者我要写书评

暂无评论

Evaluating Glucocorticoid Toxicity Index as a Predictor of Intestinal Adhesion Formation After Abdominal Surgery 5th

Evaluating Glucocorticoid Toxicity Index as a Predictor of I...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Tyagi, Pankaj Kumar Beemkumar, N. Agarwal, Ankita Kaushik, Harshita Department of Biotechnology Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

Stomach surgical operation can cause damage to intestinal tissue and is associated with a better risk of adhesive intestinal ailment. The main symptom of the adhesive intestinal disorder is intestinal adhesion, a continual and probably life-threatening hassle. Glucocorticoid use at the time of abdominal surgical procedures has been related to an increase in the danger of adhesive intestinal sickness. In addition to recognizing this disorder’s threat and protecting factors, the existing examination evaluated the Glucocorticoid Toxicity Index (GTI) as a predictor of intestinal adhesion formation in patients’ present process of stomach surgical operation. A prospective discussion was conducted on 220 sufferers who underwent stomach surgical treatment at an urban coaching hospital. The GTI change was measured at the time of the surgical treatment, and the patients were accompanied for one year after their surgery. The consequences of the look showed that there had been a statistically significant affiliation between higher GTI and the occurrence of postoperative intestinal adhesion after a stomach surgical operation. Moreover, the facts confirmed that there had been an additive effect of other chance factors, together with the acute inflammatory procedure or impaired wound healing, on the hazard of adhesion formation while blended with GTI. Those results propose that GTI is a dependable predictor of intestinal adhesion formation after a belly operation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

SS-WSSS: Small-Scale Weakly Supervised Semantic Segmentation for Histopathology Image

SS-WSSS: Small-Scale Weakly Supervised Semantic Segmentation...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Jiatai Han, Guoqiang Zhou, Jingxuan Shi, Zhenwei Liu, Zaiyi Han, Chu South China University of Technology Guangzhou China Shenzhen China South China University of Technology School of Computer Science and Engineering Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China

ISBN: (纸本)9798350386226

Semantic segmentation for histopathology images is one of the fundamental tasks in computational pathology. Due to the high cost of pixel-level annotation acquisition, the weakly supervised semantic segmentation (WSSS) attempts to achieve information-intensive segmentation task for histopathology images to reduce the labeling effort of pathologists by leveraging image-level labels. However, traditional WSSS requires a large-scale training set with image-level labels, which still imposes considerable labeling costs on pathologists. To this end, this work proposes a Small-Scale Weakly Supervised Semantic Segmentation (SS-WSSS) approach to achieve the comparable performance only with small-scale weakly-labeled data to further reduce pathologist's labeling effort. Since histopathology images can easily generate massive unlabeled data, our SS-WSSS aims to learn with the unlabeled data to bridge the information gap. First, we propose a Single-to-Multi Prototype Similarity (S2M-PS) method to generate reliable pseudo-labels for unlabeled data by measuring the similarity between single-label prototypes and multi-label feature maps. Then, we introduce a Cross-Task CoTraining (CT2) method for pseudo-supervision of models with pseudo-labels self-refinement to avoid overfitting to noisy labels. We conduct the experiment on two public datasets to demonstrate the effectiveness of our SS-WSSS. In the experiment, our method achieves comparable performance with SOTA methods only using 30% labeled data. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Smart Grid technology and Renewable Energy Systems 1

Smart Grid Technology and Renewable Energy Systems

引用

1st International Conference on Smart and Sustainable Technologies in Energy and Power Sectors, SSTEPS 2022

作者： Vasisht, Parikshit Ranjan, Sudhakar Jadhav, Rahul J. Rasal, Prasanna R. Nrip, Nripesh Kumar Apeejay Stya University School of Engineering and Technology Haryana Gurugram India Department of Computer Application Pune India

ISBN: (纸本)9781665464147

The idea of "smart grids"has been around for more than ten years, and they are crucial to the digital revolution of the power industry. An overview of smart grids, including terminology, trends, and key features. An energy system known as a "smart grid"employs digital ICT systems to recognise, react to, as well as take necessary action in reply to variations in energy demand and a number of other issues. A new sector of "green economy"devoted to making smart energy consumption into a successful business has been spawned as a result of the abundance of research and innovation areas connected to the smart grid that may be utilised for new business prospects. Electricity users can take an active role in the marketing and self-healing capacities of smart grids. This article outlines the SG architecture and numerous components in an effort to give a general understanding of SG systems. Additionally, it introduces the network infrastructure, interconnection, and modern communications used in SG systems. The article also identifies difficulties and problems that must be resolved for SG to be implemented successfully. Finally, we offer recommendations for new areas for investigation. © 2022 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep learning-based Real-time Migration Strategies for Containers in SDN 6

Efficient Deep learning-based Real-time Migration Strategies...

引用

6th International Conference on Next Generation Data-Driven Networks, NGDN 2024

作者： Huang, Shan Liu, Yanan Li, Yanuo He, Feili Duan, Xiaodong School of Computer Science and Engineering Dalian Minzu University Dalian China Key Laboratory of Big Data Application Technology of the State Ethnic Affairs Commission Dalian China Dalian Ethnic Culture Digital Technology Key Laboratory Dalian China

ISBN: (纸本)9798350388374

Container technology is widely used and improve the efficiency of container real-time migration has become an important research topic. Existing studies mainly focus on optimizing iterative dumping of containers without fully considering the impact of migration node selection on migration efficiency. Software-defined networking (SDN), achieves centralized control of the network by separating the control plane and the forwarding plane. Applying deep learning to SDN makes tasks such as traffic prediction and network optimization more intelligent. This paper proposes Prediction Model based on CLCB (CNN-LSTM-CBAM) uses real-time collected load data as input, extracts feature components of load data using one-dimensional convolutional neural networks, and then predicts using LSTM. To improve prediction accuracy, a lightweight CBAM attention module is introduced, and the prediction results are output through fully connected layers. The Network Traffic Prediction Model based on GCGRU-Conv (GCN-GRU-CNN) considers both spatial and temporal features of network traffic. GCN and GRU are used to extract spatial and temporal features of network traffic, respectively, and then these features are fused together using convolutional neural networks. To address the gradient problem caused by increasing network depth, a residual network structure is introduced. Experimental results show that the method proposed can effectively reduce the container migration time and has better prediction results. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image segmentation with texture-oriented superpixel 2

Image segmentation with texture-oriented superpixel

引用

2nd International Symposium on computer applications and Information Systems, ISCAIS 2023

作者： Song, Dongke Huang, Heming Zhang, Huiyun School of computer science and technology Qinghai Normal University Xining810008 China State Key Laboratory of Tibetan intelligent information processing and application Xining810008 China

ISBN: (纸本)9781510666665

Superpixel segmentation is an image preprocessing technique that uses pixel blocks instead of pixels to improve the efficiency of subsequent image tasks. Existing methods are not sensitive to image texture. To solve this problem, a texture-oriented superpixel (TOS) segmentation method is proposed. Firstly, an adaptive parameter function based on pixel boundary probability is used to calculate the distance. Secondly, a gradual merging strategy is used for merging. And finally, a loop iterative framework is used to optimize the seeds. The experimental results show that TOS can effectively preserve the smaller texture information, generate seeds that are more consistent with image texture, and better detect image texture. © 2023 SPIE.

关键词： Superpixels

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：