检索结果-内蒙古大学图书馆

IEEE International Conference on Big data

作者： ChengXiang Zhai Siebel School of Computing and Data Science Grainger College of Engineering University of Illinois at Urbana-Champaign USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

We present the vision of LivedataLab and discuss the new research directions and application opportunities it opens up. LivedataLab is envisioned to be a cloud-based open lab infrastructure where research, education, and application development in big data can be integrated in one unified platform, thus accelerating research, technology transfer, and workforce development in big data.

关键词： Technology transfer Collaboration Big data

来源：评论

学校读者我要写书评

暂无评论

Execution of Convolution Coding Method for FPGA in Industrial Automation using VERILOG HDL 7

Execution of Convolution Coding Method for FPGA in Industria...

引用

7th International Conference on computing Methodologies and Communication, ICCMC 2023

作者： Venusamy, Kanagaraj Kannadhasan, S. Vimalesh, A. Chandramohan, P. Shanmugam, M. Priyadarsini, K. Department of Mechatronics Engineering Rajalakshmi Engineering College Chennai India Department of Electronics and Communication Engineering Study World College of Engineering Coimbatore Chennai India Department of Data Science and Business Systems School of Computing SRM Institute of Science & Technology Kattankulathur Chennai India

ISBN: (纸本)9781665464086

In this paper, the performance study of the FPGA-based encoder is delivered and received with little errors given the large number of applications that employ digital communication to store and retrieve data recently. Forward Error Correction units a wireless communication system region that is essential. Several types of encryption methods have been measured, and the error is completely different. Convolution code writing approach, an honest technique used to rectify mistakes during the data transfer. Convolutional encoder area unit compelled to provide the output in the kind of register style with specified positions in the register. The areas in which the region is entirely arranged are likewise shown as arrows. The position of the registers provides probable state transitions wherein example, L is the register's length. Using these facts, the best way to execute of data transmission in digital communication channels is to correct errors in codes. FPGA device utilized in convolutional encoder's hardware implementation. Vivado and XILINX ISE are usedfor performance analysis. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

EmoSync: Facial Emotion Detection for Adaptive Music Playback 3

EmoSync: Facial Emotion Detection for Adaptive Music Playbac...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Devarajan, Devikanniga Rajkumar, K. GITAM Deemed to be University Computer Science and Engineering Nagadenahalli Doddabalpur Karnataka Bangalore561203 India SRM Institute of Science and Technology Department of Data Science and Business Systems School of Computing Tamil Nadu Kattankulathur603 203 India

ISBN: (纸本)9798350372120

This work investigates using Convolutional Neural Networks (CNN) and VGGNet architecture, for realtime emotion detection. Raw data from the FER-2013 dataset is transformed from CSV format into organized image directories, segmented by distinct emotions. The resulting model, equipped with convolutional, pooling, and dense layers, effectively classifies emotions from 48x48 grayscale images. In application, the model overlays detected emotions onto a webcam stream. An integrated music player module synchronizes music with the subject's emotions. Overall, this research explores a comprehensive interactive system focused on recognizing and responding to human emotions. Without further training data, our model, to the best of our understanding, achieves modern single-network accuracy of 74.57% on FER2013 © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Federated Semi-supervised Learning for Medical Image Segmentation with Intra-client and Inter-client Consistency

Federated Semi-supervised Learning for Medical Image Segment...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zheng, Yubin Tang, Peng Ju, Tianjie Wang, Hao Qiu, Weidong Rajapakse, Jagath C. Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai China Shanghai Jiao Tong University College of Basic Medical Sciences Shanghai China Nanyang Technological University College of Computing and Data Science Singapore

ISBN: (纸本)9798350386226

Medical image segmentation plays a vital role in medical image analysis. However, it is impractical to build a large-scale centralized segmentation dataset due to the privacy of medical images. Federated learning (FL) aims to train a shared model of isolated clients without local data exchange which aligns well with the scarcity and privacy characteristics of medical images. Moreover, there is a large amount of unlabeled data in clients due to the difficulty in annotating medical images. Federated semi-supervised learning (FSSL) can leverage the unlabeled data of clients to improve the performance of the global model. Many existing FSSL methods apply the complicated semi-supervised learning protocols and some of them neglect the problem of data heterogeneity in FL. In this paper, we propose a novel federated semi-supervised learning framework for medical image segmentation incorporating intra-client and inter-client consistency learning. The intra-client consistency learning can introduce global data noise in data augmentation which can improve the generalization ability of the model and reduce the impact of data heterogeneity. The inter-client consistency learning is proposed to expand the feature search space and learn the ensemble knowledge of different clients. The two consistency learning mechanisms are achieved with the assistance of a Variational Autoencoder (VAE) trained collaboratively by clients. The experimental results illustrate that our method outperforms the state-of-the-art methods under different FSSL settings. The code is available at https://***/zyb98/FV2IC. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation 41

Target Networks and Over-parameterization Stabilize Off-poli...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Che, Fengdi Xiao, Chenjun Mei, Jincheng Dai, Bo Gummadi, Ramki Ramirez, Oscar A. Harris, Christopher K. Rupam Mahmood, A. Schuurmans, Dale Department of Computing Science University of Alberta Canada School of Data Science The Chinese University of Hong Kong Shenzhen China Google DeepMind United Kingdom School of Computational Science and Engineering Georgia Tech United States Figure Uber United States CIFAR AI Amii

We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturally satisfied for expected updates over the entire state-action space or learning with a batch of complete trajectories from episodic Markov decision processes. Notably, using only a target network or an over-parameterized model does not provide such a convergence guarantee. Additionally, we extend our results to learning with truncated trajectories, showing that convergence is achievable for all tasks with minor modifications, akin to value truncation for the final states in trajectories. Our primary result focuses on temporal difference estimation for prediction, providing high-probability value estimation error bounds and empirical analysis on Baird's counterexample and a Four-room task. Furthermore, we explore the control setting, demonstrating that similar convergence conditions apply to Q-learning. Copyright 2024 by the author(s)

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Convolutional Neural Network Based on L1 Regularization for Segmentation of Coronary Arteries in X-Ray Angiograms 5

An Enhanced Convolutional Neural Network Based on L1 Regular...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Wahid, Fazli Ma, Yingliang Sheikh, Ramla Aamir, Muhammad University of East Anglia School of Computing Sciences Norwich United Kingdom University of Haripur Department of Information Technology Khyber Pakhtunkhwa Pakistan University of Derby Data Science Research Centre Colloge of Science and Engineering Derby United Kingdom

ISBN: (纸本)9798350394764

The automatic segmentation of coronary arteries in X-Ray angiograms has a significant role in identification and detection of various abnormalities in vessels which can be adequately helpful in computer aided diagnosis (CAD) for supporting in analyzing the coronary heart diseases. Previously many machine learning (ML) algorithms and deep learning (DL) models have been applied for this purpose but all of them are suffered from some serious drawbacks when applied in their standardized working formats which leads to low performance of these models. Therefore, in this work an enhanced convolutional neural network named eCNN which is based on L1 regularization has been applied for automatic segmentation of coronary arteries. It has been observed that incorporating L1 regularization with different coefficient values has distinct effects on the working mechanism of CNN architecture resulting in improving its performance. In the proposed method, firstly, Gaussian Matched Filters (GMF) have been applied to enhance the quality of X-Ray angiograms. In segmentation stages, the eCNN has been applied for the segmentation. In this stage, dual L1 regularization (coefficient: 0.001 for convolutional and 0.01 for dense layers) improves model interpretability and generalization, facilitating effective segmentation of arteries. Finally, standard performance evaluation parameters have been used to evaluate the performance of the proposed model and compared with state-of-the-art techniques. © 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

A Scenario-Based data Catalogue for Autonomous Driving Assistance Systems Using Clustering 5

A Scenario-Based Data Catalogue for Autonomous Driving Assis...

引用

5th IEEE International Conference on Advances in Electronics, Computers and Communications, ICAECC 2023

作者： Selvaraj, Surendhar Muthu Kumar, I. Bhaskaran, Sreebha Karthik, R. Balamurugan, Sabari Continental Automotive India Data Solutions Bengaluru India Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Dept of Computer Science & Engineering India Continental Automotive India Bengaluru India

ISBN: (纸本)9798350305449

Autonomous driving assistance systems (ADAS) are developing quickly in terms of the safety of persons and vehicles. Test scenarios are essential for development, simulation, and validation in a typical AD sensor & safety function. As a result, the fleet car of the automobile firm collected the real-world raw data across between 1-2 million kilometers for each sensor generation. Therefore, exact data (i.e., precise data for diverse scenarios like traffic, parking lot, bridge, crossroads, etc.) is essential for carrying out development and validation. To find the precise data among millions of kilometers collected data, automated analytics solutions are enabled such as detection environmental scenes, static & dynamic road participants, scenario detection, etc. and data catalogue will be formed for the respective scenarios based the output got from the (scenario or object detection) using clustering algorithm. The clustering is performed on the raw text data output got from the scene detection and clustered the scenarios based on the similarity. At the end data catalogue is formed for various ADAS scenarios that used to cater various development and validation requirements of higher level of autonomy. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

High efficient net gain and low noise figure based vertical cavity semiconductor optical amplifiers for wavelength division multiplexing applications

引用

Journal of Optical Communications 2025年第2期46卷 247-256页

作者： Prabu, Ramachandran Thandaiah Balasubramanian, Arunsundar Balakrishnan, Nithyasundari Jebanazer, Jeneetha Kandasamy, Mohana Sundaram Govindaswamy, Nishanthi Mahmoud, Rashida Maher Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS Saveetha University Tamilnadu Chennai India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai93104 India Department of ECE S.A. Engineering College Tamilnadu Chennai India Department of ECE Panimalar Engineering College Tamilnadu Chennai India Department of CSE R.M.D. Engineering College Kavarapettai Tamilnadu Chennai India Department of CSE R.M.K. Engineering College Kavarapettai Tamilnadu Chennai India Sohag Institute of Technology Sohag Egypt

This paper has demonstrated the high efficient net gain and low noise figure based vertical cavity semiconductor light amplifiers for wavelength division multiplexing applications. Previous study on the chip reflective gain variations versus SOA current under temperature effects is clarified. We have transferred light semiconductor amplifiers for wavelength multiplexing schemes applications. Amplifier output power is demonstrated with bias current and amplifier active layer region length variations based input signal power of 3, 6.5, 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. The amplifier output noise variations are clarified against the bias current and amplifier active layer region width variations based input signal power of 3, 6.5, 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. The output OSNR variations are studied clearly and deeply against the bias current and amplifier active layer region length variations based input signal power of 3, 6.5, 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. The signal loss is demonstrated versus both active layer width/length and temperature based optimum 30 % gallium core dopant ratio and 28 % arsenide cladding dopant ratio at optimum input signal power of 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. SOA amplifier output power can be enhance with the management of both bias current and input signal power and the reduction of active amplifier length. The amplifier output noise can be enhance with the management of both bias current and input signal power and the reduction of active amplifier width. Output OSNR system can be improved with the management of both bias current and input signal power and the reduction of active amplifier length. The SOA amplifier gain can be improved with the management of both bias current and input signal power and the reduction of active amplifier length. The SOA amplifie

关键词： Noise figure

来源：评论

学校读者我要写书评

暂无评论

GENSIMO - A Generic Framework for Modelling Social Insurance Systems 25th

GENSIMO - A Generic Framework for Modelling Social Insuranc...

引用

25th International Workshop on Multi-Agent-Based Simulation, MABS 2024

作者： de Haan, Fjalar J. Thompson, Jason School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Parkville Australia Melbourne Centre for Data Science The University of Melbourne Parkville Australia Department of Psychiatry Faculty of Medicine Dentistry and Health Sciences The University of Melbourne Parkville Australia

ISBN: (纸本)9783031880162

We report on the design, development and prototype testing of gensimo (GENeric Social Insurance MOdeling), a free and open-source software framework for modelling and simulation of social insurance systems. We discuss the conceptual and software design considerations of the framework in general before demonstrating how it works in detail by setting it up to model a particular social insurance scheme. We then present how we used this prototype set up to model the impact of a policy intervention on the workload of the insurer. While gensimo is under active development and we are a while away from serious verification and validation, this prototype testing shows realistic results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Generative Image Steganography Based on Latent Space Vector Coding and Diffusion Model 1

引用

2nd International Conference on Artificial Intelligence Security and Privacy, AIS and P 2024

作者： Liu, Weisong Yang, Jianfeng Huang, Jiewen El-Latif, Ahmed A. Abd Zhou, Zhili School of Artificial Intelligence Guangzhou University Guangzhou China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China EIAS Data Science Lab College of Computer and Information Sciences and Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh11586 Saudi Arabia

ISBN: (数字)9789819611485

ISBN: (纸本)9789819611478

Image steganography is a technology that embed secret information within a cover image to obtain a stego-image for covert communication. The transmission of undetectable stego-images via social media can facilitate secure and efficient covert communication. Recently, the generative image steganography has achieved promising performance with the rapid development of generative models. However, existing generative image steganography suffers from issues, i.e., the low quality of the generated stego-image and the limited hiding capacity. To address these issues, this paper proposes a generative image steganography scheme based on latent space vector coding and diffusion model. It consists of an optimized diffusion denoising network, the latent space vector coding mapping network, and the information extraction network. In this scheme, the secret information is encoded as a latent space vector, which is then transformed in the input diffusion model to generate the stego-image. Experimental results demonstrate that this scheme achieves superior performance compared with existing generative image steganography methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Vectors

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：