检索结果-内蒙古大学图书馆

A coupled multi-task feature boosting method for remote sensing scene classification

Science China(Technological Sciences) 2023年第3期66卷 663-673页

作者： WANG TengFei GU YanFeng GAO GuoMing ZENG XiaoPeng School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin 150001China

The scene classification plays an essential role in processing very high resolution(VHR)images for *** scene classification in remote sensing faces two difficulties:the mismatching features caused by the model overfitting problem and the semantic information losing *** multi-task method helps solve the problems by using the share weights of multiply *** propose a feature boosting method with a multi-task framework that combines the scene classification task and the semantic segmentation task to overcome the *** from the traditional multi-task learning method,the two tasks are coupled together via a weakly supervised learning method so that it does not require the labelled semantic segmentation ***,we proposed a weakly supervised segmentation method to create the interconnection of the segmentation task and the classification *** we achieve a coarse segmentation result which is highly correlated to the classification by the weakly supervised ***,according to the surface distribution of remote sensing,we propose a sparse surface constraint to obtain fine segmentation *** features are obtained by constraining the shared weights of the weakly supervised segmentation ***,we classify the scenes using the fine features and conduct experiments on the public remote sensing scene classification *** results demonstrate that the proposed coupled multi-task model outperforms the stateof-the-art methods on remote sensing scene classification.

关键词： scene classification coupled multi-task feature boosting

来源：评论

学校读者我要写书评

暂无评论

Delay and Packet Loss Reduction by Parameter Optimization Approach in Multipath TCP 2

Delay and Packet Loss Reduction by Parameter Optimization Ap...

引用

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Bhutani, Saurabh Jain, Nitin Mishra, Keerti Bbd University Electronics and Communication Engineering School of Engineering Lucknow India

ISBN: (纸本)9798350364699

Connecting a host or computer network to more than one network is called multi-homing. Presently the availability of multi-homed devices is widespread. It has introduced a common practice to utilize multiple paths TCP (MPTCP) for data transmission for improving performance. However MPTCP helps improve network reliability & bandwidth efficiency, the transmission performance under short-time data transfer was observed to decline as compared to regular TCP communication mode under single path schemes for concurrent subflow data transfer on a shared path because of the aggressive starting behavior of MPTCP. Such strategy is generally uncoupled;each data is processed independently and significantly affects the concurrent traffic. This paper reveals the MPTCP's performance under the impact of parameters depending on timeouts, retry, and wait time that affect the packet losses and delay. To accomplish this task the workflow presented based on simulation using MatLab-based implementation, that is employing the analysis for deriving the appropriate parameter set for minimizing the packet losses and delay in the network and reduces the possibility of congestion, and helps for controlling at end-host in avoiding packet loss for concurrent connections under MPTCP with text data flows application. The experimental results drawn from results obtained from MatLab implementation show that parameter optimization is useful in the significant reduction of delay time and helpful in retaining high throughput. © 2024 IEEE.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Connectivity with Spatial Modulation in mm-wave Multihop Cooperative Relaying System 15

Enhancing IoT Connectivity with Spatial Modulation in mm-wav...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Subhashini, G. Velmurugan, P.G.S. Kirubahini, K. Thiruvengadam, S.J. Ramco Institute of Technology Department of Electronics and Communication Engineering Rajapalayam India Thiagarajar College of Engineering Department of Electronics and Communication Engineering Madurai India

ISBN: (纸本)9798350370249

The fifth generation - 5G enabled Internet of Things (IoT) will be the promising technologies to enhance our lives by efficiently and smartly using the existing resources. The number of Internet of things Devices (IoD) in the near future is expected to be in terms of billions. IoD applications are expected to be delivering massive data in cellular networks. Millimeter wave (mm-wave) communications are a key enabler for the next generation of IoD, providing the necessary bandwidth and low latency to support a wide range of applications and a massive number of connected devices. Mm-wave signals have higher propagation loss and are more susceptible to obstacles like buildings and trees. Also, energy efficient IoD is the major requirement in 5G technologies. This paper investigates the benefits of multi-hop transmission among IoD devices and utilizes Multiple Input Multiple Output (MIMO) technology combined with a novel modulation technique called Spatial Modulation (SM) to mitigate higher propagation losses and enhance energy efficiency. The Line of Sight (LoS) and Non-LoS (NLoS) between IoD is modelled as Nakagami-m fading channel, since it is the general fading model fit in to a wide range of fading statistics by adjusting its fading parameter. This paper investigates the outage performance of SM in mm-wave multi-hop cooperative relaying for IoD. It derives a closed-form expression for the outage probability in multi-hop cooperative relaying within the IoD context. The proposed system's performance is validated through MATLAB simulations. © 2024 IEEE.

关键词： Internet of Things Devices Millimeter-wave Multihop Nakagami-m fading Outage probability Spatial modulation

来源：评论

学校读者我要写书评

暂无评论

Principal component fusion based unexposed biological feature enhancement of fundus images

引用

Multimedia Tools and Applications 2024年 1-14页

作者： Singh, Neha Bhandari, Ashish Kumar Department of Electronics and Communication Engineering National Institute of Technology Patna Patna800005 India

In the field of ophthalmology, digital images play an important role for automatic detection of various kind of eye diseases. Digital images in the field image enhancement are the first stage to assisting ophthalmologist for diagnosis. As a result, various algorithms, and methods for the enhancement of retinal images have been developed, which may face obstacles that are common in augmentation processes, such as false edges and weak illuminated that obscure image particulars. To eliminate such issues, this paper projected a novel framework for unexposed retinal image. The proposed paper uses multiscale Gaussian function for estimation of illumination layer from unexposed color retinal image and then it is corrected by gamma method. Further to this, the principal component analysis (PCA) is utilized here to generate fused enhance result for unexposed retinal images. Then, contrast limited technique is employed here for further edge and contextual details improvement. When compared to several enhancement-based state-of-the-art procedures, experimental results show that the suggested method produces results with good contrast and brightness. The significance of the proposed method that this method may help ophthalmologists screen for unexposed retinal illnesses more efficiently and build better automated image analysis for healthcare diagnosis. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Efficient Routing Protocol with Localization Based Priority&Congestion Control for UWSN

引用

Computers, Materials & Continua 2023年第3期74卷 4747-4768页

作者： S.Sandhiyaa C.Gomathy Electronics and Communication of Engineering SRM Institute of Science and TechnologyVadapalaniChennai600026TNIndia

The nodes in the sensor network have a wide range of uses,particularly on under-sea links that are skilled for detecting,handling as well as *** underwater wireless sensor networks support collecting pollution data,mine survey,oceanographic information collection,aided navigation,strategic surveillance,and collection of ocean samples using detectors that are submerged ***,congestion routing,and prioritizing the traffic is the major issue in an underwater sensor *** scheme differentiates the different types of traffic and gives every type of traffic its requirements which is considered regarding network *** of localization error using the proposed angle-based forwarding scheme is explained in this *** choose the shortest path to the destination using the fitness function which is calculated based on fault ratio,dispatching of packets,power,and distance among the *** work contemplates congestion conscious forwarding using hard stage and soft stage schemes which reduce the congestion by monitoring the status of the energy and buffer of the nodes and controlling the *** study with the use of the ns3 simulator demonstrated that a given algorithm accomplishes superior performance for loss of packet,delay of latency,and power utilization than the existing algorithms.

关键词： Congestion aware routing angle-based forwarding scheme fitness function hard stage soft stage scheme

来源：评论

学校读者我要写书评

暂无评论

Optimization of Traffic System using Adaptive Response First Come First Serve

Optimization of Traffic System using Adaptive Response First...

引用

2024 International Conference on Signal Processing, Computation, electronics, Power and Telecommunication, IConSCEPT 2024

作者： Amutha, S. Singh, Dhruv Singh, Shashank Shekhar Jhandial, Anant Gupta Krishna, Kunal School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Electronics and Communication Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331540685

In this period of urbanization and adding vehicular traffic, the optimization of business operation systems is consummate to insure both the effectiveness of transportation networks and the safety of commuters. This exploration paper explores the operation of deep literacy ways to revise the field of business operation. By employing the power of deep learning, sensors and timers, our study aims to develop innovative results that ameliorate the delicacy, rigidity, and real- time responsiveness of business control systems. The primary focus of this exploration is to design a comprehensive deep literacy-grounded business operation system that incorporates colorful data sources. By assaying vast quantities of miscellaneous data, the system will acclimatize to dynamic business conditions and offer real- time perceptivity for effective business inflow operation, accident discovery, and traffic relief. The exploration will also explore the integration of machine literacy algorithms for intelligent business signal control, prioritizing green light allocation grounded on real- time demand and business viscosity. The proposed deep literacy result aims to significantly reduce business traffic, minimize trip times, and enhance overall road safety by furnishing optimized business operation strategies. The exploration will concentrate on the practical perpetration of the system in real- world business scripts, with the eventuality to gauge and acclimatize to colorful civic surroundings. This exploration bid seeks to lay the foundation for a future in which business systems seamlessly acclimatize to evolving business patterns, creating safer, more effective transportation networks, and contributing to a sustainable and intelligent civic ecosystem. The proposed dynamic signal control logic is 83.33 % more efficient in utilizing green time compared to the traditional fixed-time system. Estimated reduction in wasted green time is 25%. © 2024 IEEE.

关键词： Traffic signals

来源：评论

学校读者我要写书评

暂无评论

Faster Region Convolutional Neural Network(FRCNN)Based Facial Emotion Recognition

引用

Computers, Materials & Continua 2024年第5期79卷 2427-2448页

作者： J.Sheril Angel A.Diana Andrushia TMary Neebha Oussama Accouche Louai Saker N.Anand Department of Electronics and Communication Engineering Karunya Institute of Technology and SciencesCoimbatore641114India College of Engineering and Technology American University of the Middle EastEgaila54200Kuwait Department of Civil Engineering Karunya Institute of Technology and SciencesCoimbatore641114India

Facial emotion recognition(FER)has become a focal point of research due to its widespread applications,ranging from human-computer interaction to affective *** traditional FER techniques have relied on handcrafted features and classification models trained on image or video datasets,recent strides in artificial intelligence and deep learning(DL)have ushered in more sophisticated *** research aims to develop a FER system using a Faster Region Convolutional Neural Network(FRCNN)and design a specialized FRCNN architecture tailored for facial emotion recognition,leveraging its ability to capture spatial hierarchies within localized regions of facial *** proposed work enhances the accuracy and efficiency of facial emotion *** proposed work comprises twomajor key components:Inception V3-based feature extraction and FRCNN-based emotion *** experimentation on Kaggle datasets validates the effectiveness of the proposed strategy,showcasing the FRCNN approach’s resilience and accuracy in identifying and categorizing facial *** model’s overall performance metrics are compelling,with an accuracy of 98.4%,precision of 97.2%,and recall of 96.31%.This work introduces a perceptive deep learning-based FER method,contributing to the evolving landscape of emotion recognition *** high accuracy and resilience demonstrated by the FRCNN approach underscore its potential for real-world *** research advances the field of FER and presents a compelling case for the practicality and efficacy of deep learning models in automating the understanding of facial emotions.

关键词： Facial emotions FRCNN deep learning emotion recognition face CNN

来源：评论

学校读者我要写书评

暂无评论

LGDF-Net: Local and Global Feature Based Dual-Branch Fusion Networks for Deepfake Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5489-5500页

作者： Long, Min Liu, Zhenyu Zhang, Le-Bing Peng, Fei Guangzhou University School of Electronics and Communication Engineering Guangdong Guangzhou510006 China Changsha University of Science and Technology School of Computer and Communication Engineering Changsha410114 China Huaihua University School of Computer and Artificial Intelligence Huaihua418000 China Guangzhou University School of Artificial Intelligence Guangdong Guangzhou510006 China

With the rapid development of Deepfake technology, social security is facing great challenges. Although numerous Deepfake detection algorithms based on traditional CNN frameworks perform well on specific datasets, they still suffer from overfitting due to an over-reliance on localized artifact information. This limitation leads to degraded detection performance across diverse datasets. To address this issue, this study proposes a dual-branch fusion network called LGDF-Net. LGDF-Net uses a dual-branch structure to process the local artifact features and global texture features generated by Deepfake separately, preserving their unique characteristics. Specifically, the local compression branch utilizes a specially designed local compression module (LCM) that allows the network to focus more accurately on key regions of localized artifacts in Deepfake faces. The global expansion branch enhances the analysis of the global facial context through a global expansion module (GEM), which captures image context information and subtle texture features more comprehensively. Additionally, the proposed multi-scale feature extraction module (MSFE) delves into image features at various scales, enriching the extraction of detailed information. Finally, the multi-level feature fusion strategy (MLFF) improves the integration of local and global features through multiple layers, enabling the network to learn the intrinsic connections between these two types of features. A series of experimental validations demonstrate that the proposed scheme outperforms many existing detection networks in terms of accuracy and generalization ability. © 1991-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Performance optimization of tri-gate junctionless FinFET using channel stack engineering for digital and analog/RF design

引用

Journal of Semiconductors 2023年第11期44卷 89-100页

作者： Devenderpal Singh Shalini Chaudhary Basudha Dewan Menka Yadav Department of Electronics and Communication Engineering Malaviya National Institute of TechnologyJaipurRajasthan-302017India

This manuscript explores the behavior of a junctionless tri-gate FinFET at the nano-scale region using SiGe material for the *** the analysis,three different channel structures are used:(a)tri-layer stack channel(TLSC)(Si-SiGe-Si),(b)double layer stack channel(DLSC)(SiGe-Si),(c)single layer channel(SLC)(S_(i)).The I−V characteristics,subthreshold swing(SS),drain-induced barrier lowering(DIBL),threshold voltage(V_(t)),drain current(ION),OFF current(IOFF),and ON-OFF current ratio(ION/IOFF)are observed for the structures at a 20 nm gate *** is seen that TLSC provides 21.3%and 14.3%more ON current than DLSC and SLC,*** paper also explores the analog and RF factors such as input transconductance(g_(m)),output transconductance(gds),gain(gm/gds),transconductance generation factor(TGF),cut-off frequency(f_(T)),maximum oscillation frequency(f_(max)),gain frequency product(GFP)and linearity performance parameters such as second and third-order harmonics(g_(m2),g_(m3)),voltage intercept points(VIP_(2),VIP_(3))and 1-dB compression points for the three *** results show that the TLSC has a high analog performance due to more gm and provides 16.3%,48.4%more gain than SLC and DLSC,respectively and it also provides better *** the results are obtained using the VisualTCAD tool.

关键词： short channel effects(SCEs) junctionless FinFET analog and RF parameters SiGe

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Signals Characteristics with Least Effect of Optical communication Losses for Dense Optical communication Systems

引用

Journal of Optical communications 2024年第1期45卷 113-117页

作者： Kumar, Chakresh Kumar, Ghanendra University School of Information Communication & Technology Guru Gobind Singh Indraprastha University New Delhi110078 India Department of Electronics and Communication Engineering National Institute of Technology Delhi110040 India

In this paper, the major aim is to enhance the bandwidth and therefore increase the capacity of the optical fibre communication system by reducing the dispersion in the fibre. Dispersion compensation is necessary to reduce losses and cost of the system. In this paper, we are basically focusing on reducing or decreasing chromatic dispersion. Chromatic dispersion is a type of dispersion in which pulse broadening occurs due to delay in different spectral components. We here make use of dispersion compensated fibre (DCF) for reducing the dispersion in the WDM system. Here, we basically use three dispersion compensated techniques (pre-compensation, post-compensation and mix compensation). The comparison in the three models of dispersion compensated technique is made in terms of transmission power vs. Q factor and also transmission power vs. Bit Error Rate. © 2024 Walter de Gruyter GmbH. All rights reserved.

关键词： Chromatic dispersion

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：