检索结果-内蒙古大学图书馆

IEEE International Conference on Edge Computing (EDGE)

作者： Yuting Yang Andrea Merlina Weijia Song Tiancheng Yuan Ken Birman Roman Vitenberg dept. Computer Science Cornell University Ithaca USA dept. Informatics University of Oslo Norway dept. Computer Science Cornell University USA

ISBN: (数字)9798350368499

ISBN: (纸本)9798350368505

We consider AI inference and generative query processing in distributed systems: an increasingly popular edgecomputing use case. In such systems, coscheduling of GPU memory management and task placement represents a promising opportunity. We propose Navigator, a novel framework that unifies these functions to reduce job latency while using resources efficiently, placing tasks where data dependencies will be satisfied collocating tasks from the same job (when this will not overload the host or its GPU), and efficiently managing GPU memory Comparison with other state of the art schedulers shows a significant reduction in completion times while requiring the same amount or even fewer resources. In one case, just half the servers were needed for processing the same workload.

关键词： Schedules Energy consumption Navigation Query processing Memory management Graphics processing units Servers

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Autonomous Vehicles 1

Reinforcement Learning for Autonomous Vehicles

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Sharma, Vinod Kumawat, Parwati Kumar, Pankaj Yaminipriya, S. Chamarthi, Subbarao Kumar, Jitendra SLP College Dept of CSE Gwalior India Madhav University Dept. of Commerce & Management Pindwara India Dhanalakshmi Srinivasan College of Engineering Dept. of Biomedical Engineering Coimbatore India Lingayas Vidyapeeth Dept. of Mechanical Engineering Faridabad India J.S. University Dept. of Computer Science Shikohabad India

ISBN: (纸本)9798350356816

Reinforcement Learning (RL) has emerged as a transformative technology for autonomous vehicles, enabling sophisticated decision-making systems that enhance driving safety, efficiency, & adaptability. This paper explores the application of RL algorithms in the context of autonomous vehicle control, focusing on the development of intelligent agents capable of learning optimal driving policies through interaction with complex environments. The study reviews various RL techniques, including Deep Q-Learning, Policy Gradient methods, & Actor-Critic frameworks, evaluating their effectiveness in addressing key challenges such as real-time decision making, dynamic environment adaptation, & multi-agent interactions. Emphasis is placed on the design of reward functions, exploration strategies, & simulation environments, which are crucial for training robust & reliable autonomous driving systems. Case studies demonstrate the application of RL in scenarios such as lane-keeping, adaptive cruise control, & collision avoidance. The paper also discusses advancements in simulation platforms & hardware acceleration that facilitate scalable RL experiments. By integrating theoretical insights with practical implementations, this work provides a comprehensive overview of current developments in RL for autonomous vehicles & identifies future research directions aimed at overcoming limitations & achieving safer, more efficient. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HR-VEAW: A Human Rights Violation Exploration, Analytics, and Warning System

HR-VEAW: A Human Rights Violation Exploration, Analytics, an...

引用

2022 Workshops of the EDBT/ICDT Joint Conference, EDBT/ICDT-WS 2022

作者： Zhang, Xiaozhong Xu, Jiawei Keskin, Merve Colaresi, Michael P. Zadorozhny, Vladimir I. Chrysanthis, Panos K. Dept. of Computer Science University of Pittsburgh United States Dept. of Informatics & Network Science University of Pittsburgh United States Dept. of Political Science University of Pittsburgh United States

The availability of information from social media, such as tweets, and human rights monitors, such as Amnesty International, Human Rights Watch, and the US State Department has led to new opportunities to measure repression and human rights protections in higher resolution. In this paper, we present HR-VEAW, a Human Rights Violation Exploration, Analytics, and Warning system, to support understanding of social conflict dynamics and human rights violations/protections with quantitative data. After briefly discussing HR-VEAW’s data acquisition and analysis components, we demonstrate how it visualizes rich spatio-temporal and conceptual information, enabling the examination of changes in patterns of violation and protection in aggregate over time, or across both space and time. This way HR-VEAW helps to explain social instability and conflicts and to guide decision-making, theorizing, and predictions. © 2022 Copyright for this paper by its authors.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

Using the Scatter of Opinions to Predict Responses to Tweets 12

Using the Scatter of Opinions to Predict Responses to Tweets

引用

12th International Congress on Advanced Applied informatics, IIAI-AAI 2022

作者： Suzuki, Tokinori Deguchi, Shintaro Tomiura, Yoichi Kyushu University Dept. of Informatics Fukuoka Japan Kyushu University Dept. of Electrical Engineering and Computer Science Fukuoka Japan

ISBN: (数字)9781665497558

ISBN: (纸本)9781665497558

The importance of social media, such as Twitter and Instagram, has increased as a result of COVID-19: with social media, users can easily communicate with other people. Accordingly, social media have produced both new problems and benefits;these have occasionally occurred with upsurges in reactions owing to the huge numbers of social media followers. "Flaming"is a negative aspect of an upsurge: it is a rapid increase in blame, harassment, and insults directed at a person. Conversely, it is possible to use an upsurge to identify popular topics or trends, which is a positive aspect. Predicting the reactions to a social media post is currently very difficult;however, the aim is to prevent the above problems and provide support by forecasting upsurges at an early stage. We observed that such upsurges were affected by the scatter of opinions in the responses. If there are two groups of conflicting opinions, the original social media post tended to receive both sets of opinions. Toward predicting the reactions to a social media post, this study investigate the relationship between the upsurge and scatter of opinions. We quantify the scatter of opinions in the responses, which we term the scatter of replies. We enter that scatter into multiple regression analysis by means of clustering, and we evaluated our reaction prediction method. We found that for most settings, the correlation coefficient between the predicted and actual values exceeded 0.6, which is a moderate level of correlation. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

High-dose-rate Brachytherapy Planning with Dendrite Cross-Attention UNet

High-dose-rate Brachytherapy Planning with Dendrite Cross-At...

引用

Medical Imaging 2025: Image-Guided Procedures, Robotic Interventions, and Modeling

作者： Saini, Sourav Wei, Yawen Rong, Jingzhao Liu, Xiaofeng Dept. of Radiology and Biomedical Imaging Yale School of Medicine Yale University New Haven 06519 CT United States Dept. of Biostatistics (Health Informatics and Data Science) Yale School of Public Health Yale University New Haven 06519 CT United States Dept. of Department of Biomedical Informatics and Data Science Yale School of Medicine Yale University New Haven 06519 CT United States

ISBN: (纸本)9781510685949

Treatment of cervical cancer commonly involves high-dose-rate brachytherapy (HDR-BT), a procedure that requires precise and efficient planning to achieve the best patient outcomes. Historically, the HDR-BT planning process has been labor-intensive and largely dependent on the expertise of the clinician, resulting in potential inconsistencies in the quality of treatment. To overcome this issue, we propose an innovative method that employs advanced deep-learning models to improve HDR-BT planning. This paper presents the Dendrite CrossAttention UNet (DCA-UNet), which features a sophisticated dendritic structure comprising a primary branch for stacked inputs and three auxiliary branches dedicated to the segmentation of the clinical target volume (CTV), bladder, and rectum. This architecture enhances the model's understanding of organ-at-risk (OAR) areas, thereby improving dose prediction accuracy. Extensive evaluations reveal that DCA-UNet significantly enhances the precision of HDR-BT dose predictions across different applicator types. Our findings indicate that DCA-UNet consistently outperforms both traditional UNet and the more recent SwimUNetr models. By advancing the use of cross-attention mechanisms in deep learning frameworks, this research aids in the standardization of HDR-BT planning and opens up promising possibilities for future advancements in cervical cancer care. © 2025 SPIE

关键词： Brachytherapy Cervical Cancer Deep Learning Dose Prediction Treatment Planning

来源：评论

学校读者我要写书评

暂无评论

Secure aggregation of users' privacy preferences in shared IoT environments 6

Secure aggregation of users' privacy preferences in shared I...

引用

6th South-East Europe Design Automation, computer Engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2021

作者： Tsagiopoulou, Sofia Spathoulas, Georgios Kakarountas, Athanasios Dept. of Computer Science and Biomedical Informatics University of Thessaly Lamia Greece Gjovik Norway

ISBN: (纸本)9781665427425

Internet of Things (IoT) technology has emerged as a core aspect of everyday life, since the number of deployed devices increases exponentially day by day. IoT offers the automation of many actions and strengthens the standard of societies' living. Despite the comfort and functionality it offers, it presents many risks, mainly related to security and privacy. Users have limited control on IoT devices that monitor their personal data, which poses significant concerns for their privacy. In this paper, we propose a system that focuses on users' privacy in a shared smart environment. It aims at enabling users that physically enter an installation equipped with IoT devices to control (i) whether smart devices monitor data, (ii) to which hosts such data are sent, and (iii) the allowed data detail (through traffic rate). This functionality is applied through monitoring users entering or leaving the smart environment, as their physical presence is detected through the use of fingerprint and motion sensors. To better enhance the privacy of users, their privacy preferences, with respect to the IoT devices operation, are homomorphically encrypted, while the encryption private key is stored on a separate secure component which is isolated from the rest of the network. A proof of concept of the proposed system has been implemented, using Raspberry Pi devices, to prove the validity of the solution and to assess the performance of the system. © 2021 IEEE

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Accelerating FPGA Implementation of Neural Network Controllers via 32-bit Fixed-Point Design for Real-Time Control 14

Accelerating FPGA Implementation of Neural Network Controlle...

引用

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Hingu, Chanakya Fu, Xingang Challoo, Rajab Lu, Jiang Yang, Xiaokun Qingge, Letu University of Nevada Reno Dept. of Electrical and Biomedical Engineering Reno United States Texas A&M University-Kingsville Dept. of Electrical Engineering and Computer Science Kingsville United States University of Houston-Clear Lake Dept. of Computer Engineering Houston United States North Carolina A&T State University Dept. of Computer Science GreensboroNC United States

ISBN: (纸本)9798350304138

This paper focuses on using a 32-bit fixed-point design instead of a 32-bit floating-point representation to implement a neural network controller for the real-time control of a solar inverter by utilizing a Field Programmable Gate Array (FPGA) for faster calculation in real-time environments. Two designs of the tanh (tangent hyperbolic) activation function were implemented using both LookUp Table (LUT) and COordinate Rotation DIgital computer (CORDIC)-based approaches. The MATLAB/Simulink HDL coder toolbox was used in the design. The complete neural network controller was implemented on Intel Altera Cyclone V boards to verify output, resource requirements, and memory allocation on the hardware. Further, the error-bound analysis of the LUT and CORDIC-based approaches was conducted. The accuracy verification shows that the 32-bit fixed-point design has achieved at least 4 decimal accurate digits compared to the actual double format MATLAB calculation. This demonstrates the feasibility and effectiveness of the proposed neural network controller design as a real-time controller. © 2023 IEEE.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

ULung:A Novel Approach for Lung Image Segmentation 6

ULung:A Novel Approach for Lung Image Segmentation

引用

6th International Conference on Computing and informatics, ICCI 2024

作者： Pal, Osim Kumar Roy, Shuvasish Modok, Anup Kumar Teethi, Tajmihir Islam Sarker, Siddhartha Kumer Dept. of Biomedical Engineering University of Kragujevac Kragujevac34000 Serbia Dept. of Electrical and Electronic Engineering American International University-Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering Daffodil International University Ashulia Savar Bangladesh Dept. of Space Communication and Navigation Technology BSMRAAU Old Airport Dhaka Bangladesh

ISBN: (纸本)9798350373875

ULung is an innovative medical technology used for segmenting medical images in pulmonary diagnostics. It introduces a modified approach to analyzing and understanding pulmonary conditions. ULung employs cutting-edge deep learning and image processing techniques to isolate intricate characteristics in medical lung images properly. The model uses advanced convolutional neural network architecture as UNet layer stricture to detect abnormalities and delineate anatomical regions reliably. ULung exhibits versatility in handling various lung ailments after extensive training using diverse datasets. The innovative methodology ensures enhanced segmentation performance, enhancing diagnostic precision and expediting medical evaluations. The advent of ULung has greatly enhanced medical imaging, providing clinicians with a potent tool for precise and expeditious lung evaluation. ULung is an impressive advancement in medical image segmentation that can revolutionize standards in respiratory healthcare due to its robustness and adaptability. The model's accuracy achieved using EfficientNetV2 is 99 %, while its precision and recall rates are 98% and 96 %, respectively. The model achieves a Mean Intersection over Union (MeanloU) of 91.48% after the 14th epoch. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of soft computing approaches of zero-day-attack detection

Comparative analysis of soft computing approaches of zero-da...

引用

2022 International Conference on Emerging Trends in Smart Technologies, ICETST 2022

作者： Anwer, Misbah Ahmed, Ghufran Akhunzada, Adnan Hussain, Shahid Khan, Mubashir FAST-NUCES Dept. of Computer Science Karachi Pakistan University Malaysia Sabah Faculty of Computing and Informatics Kota Kinabalu Malaysia Penn State University Dept. of Computer Science Pennsylvania United States NEDUET Dept. of Computer Science Karachi Pakistan

ISBN: (数字)9781665459358

ISBN: (纸本)9781665459358

The Internet of Things (IoT) is growing in fashion with the concept of connecting everything and connecting everything leads to the security issues and affect the performance. An intrusion detection system (IDS) is a system that scans the network traffic and gives notifications in case of any doubtful activity. To circumvent the challenges in the detection of zero-day-multi-class cyber-attack considering the resource constraint nature of IoT devices, a robust intelligent technique is required to identify zero-day vulnerabilities to create early detection and create patches. A novel framework is proposed that will give flexible, adaptive, cost-effective, scalable, and promising solutions. In this Paper comparative study of proposed solutions were discussed and evaluation of existing system specify that federated learning increases the performance in identification of zero-day-attack. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

RADGAZEGEN: RADIOMICS AND GAZE-GUIDED MEDICAL IMAGE GENERATION USING DIFFUSION MODELS

arXiv

引用

arXiv 2024年

作者： Bhattacharya, Moinak Singh, Gagandeep Jain, Shubham Prasanna, Prateek Dept. of Biomedical Informatics Stony Brook University United States Dept. of Radiology Colombia University United States Dept. of Computer Science Stony Brook University United States

In this work, we present RadGazeGen, a novel framework for integrating experts' eye gaze patterns and radiomic feature maps as controls to text-to-image diffusion models for high fidelity medical image generation. Despite the recent success of text-to-image diffusion models, text descriptions are often found to be inadequate and fail to convey detailed disease-specific information to these models to generate clinically accurate images. The anatomy, disease texture patterns, and location of the disease are extremely important to generate realistic images;moreover the fidelity of image generation can have significant implications in downstream tasks involving disease diagnosis or treatment repose assessment. Hence, there is a growing need to carefully define the controls used in diffusion models for medical image generation. Eye gaze patterns of radiologists are important visuo-cognitive information, indicative of subtle disease patterns and spatial location. Radiomic features further provide important subvisual cues regarding disease phenotype. In this work, we propose to use these gaze patterns in combination with standard radiomics descriptors, as controls, to generate anatomically correct and disease-aware medical images. RadGazeGen is evaluated for image generation quality and diversity on the REFLACX dataset. To demonstrate clinical applicability, we also show classification performance on the generated images from the CheXpert test set (n=500) and long-tailed learning performance on the MIMIC-CXR-LT test set (n=23550). © 2024, CC BY.

关键词： Diagnosis

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：