检索结果-内蒙古大学图书馆

IEEE International Conference on systems, Man and Cybernetics

作者： Jayabrata Chowdhury Venkataramanan Shivaraman Sumit Dangi Suresh Sundaram P B Sujit Robert Bosch Centre for Cyber-Physical Systems Indian Institute of Science Bangalore Department of Aerospace Engineering Indian Institute of Science Bangalore Department of Data Science & Engineering and Electrical Engineering & Computer Sci-ence Indian Institute of Science Education and Research Bhopal

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Autonomous Vehicle (AV) decision-making in ur-ban environments is inherently challenging due to the dynamic interactions with surrounding vehicles. For safe planning, AV/ego must understand the weightage of various spatiotemporal interactions in a scene. Contemporary works use colos-sal transformer architectures to encode interactions mainly for trajectory prediction, resulting in increased computational complexity. To address this issue without compromising spatiotemporal understanding and performance, we propose the simple Deep Attention Driven Reinforcement Learning (DAD-RL) framework, which dynamically assigns and incorporates the significance of surrounding vehicles into the ego's RL-driven decision-making process. We introduce an AV-centric spatiotemporal attention encoding (STAE) mechanism for learning the dynamic interactions with different surrounding vehicles. To understand map and route context, we employ a context encoder to extract features from context maps. The spatiotemporal representations combined with contextual encoding provide a comprehensive state representation. The resulting model is trained using the Soft-Actor Critic (SAC) algorithm. We evaluate the proposed framework on the SMARTS urban benchmarking scenarios without traffic signals to demonstrate that DAD-RL outperforms recent state-of-the-art methods. Furthermore, an ablation study underscores the importance of the context-encoder and spatiotemporal attention encoder in achieving superior performance.

关键词： Heuristic algorithms Decision making Reinforcement learning Transformers Feature extraction Encoding Spatiotemporal phenomena Trajectory Safety Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

An Embedded Low-Cost Solution for a Fog Computing Device on the Internet of Things

An Embedded Low-Cost Solution for a Fog Computing Device on ...

引用

International Conference on Fog and Mobile Edge Computing (FMEC)

作者： Pietro D’Agostino Massimo Violante Gianpaolo Macario Department of Control and Computer Engineering (DAUIN) Politecnico di Torino Torino Italy AROL Closure Systems Torino Italy

The adaptability of devices can be significant for a customer that inserts them in an industrial production line. The ability to modify an object bought along with a machine that can be personalized with its features can change how they want to do measurements for different reasons, like predictive maintenance. Fog computing local centers already exist in the market, but they are usually on-the-shelf products with no margin of change for any user. However, with the usage of Docker and containers, this can change. This paper describes a fog computing local central called Concentrator, which can not only execute its essential functions built-in by the producer but also be customized by the user to add in the elaborations on other external sensors, expanding its capabilities and usage. We wanted to improve the device already tested on a Linux PC on a Raspberry Pi and try its performance and characteristics, seeing if it could be transformed into an embedded architecture and an industrial feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling Fault Dynamics of Interdependent Assets in Complex Urban Environments Using Open-Data: Extended Version

引用

SN computer science 2025年第6期6卷 1-14页

作者： Di Pietro, Antonio Cavedon, Francesco Stergiopoulos, George Rosato, Vittorio Department of Energy Technologies and Renewable Sources ENEA Rome Italy Department of Computer Science University of Verona Verona Italy Department of Information and Communication Systems Engineering University of Aegean Neo Karlovasi Greece Department of Engineering University Campus Bio-Medico of Roma Rome Italy

Dependency effects between Critical Infrastructure (CI) elements are essential for predicting the impact of disturbances, but such data is often scarce. This study builds a dependency network of critical sectors using open data and guidelines from the US and EU Directives on Critical Infrastructures. Focusing on the Marche region (Italy), particularly the city of Ancona, the network is analyzed to identify key nodes critical for preventing cascading failures. Centrality measures highlight essential infrastructure like hospitals and transport hubs, which are crucial for network resilience. The insights provided can support decision-makers in prioritizing interventions and developing strategies to enhance infrastructure resilience and mitigate the risk of cascading failures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection

arXiv

引用

arXiv 2024年

作者： Tang, Hao Li, Zechao Zhang, Dong He, Shengfeng Tang, Jinhui The School of Computer Science and Engineering Nanjing University of Science and Technology No 200 Xiaolingwei Nanjing210094 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The School of Computing and Information Systems Singapore Management University Singapore

RGB-Thermal Salient Object Detection (RGB-T SOD) aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images. A key challenge lies in bridging the inherent disparities between RGB and Thermal modalities for effective saliency map prediction. Traditional encoder-decoder architectures, while designed for cross-modality feature interactions, may not have adequately considered the robustness against noise originating from defective modalities, thereby leading to suboptimal performance in complex scenarios. Inspired by hierarchical human visual systems, we propose the CONTRINET, a robust Confluent Triple-Flow Network employing a "Divide-and-Conquer" strategy. This framework utilizes a unified encoder with specialized decoders, each addressing different subtasks of exploring modality-specific and modality-complementary information for RGB-T SOD, thereby enhancing the final saliency map prediction. Specifically, CONTRINET comprises three flows: two modality-specific flows explore cues from RGB and Thermal modalities, and a third modality-complementary flow integrates cues from both modalities. CONTRINET presents several notable advantages. It incorporates a Modality-induced Feature Modulator (MFM) in the modality-shared union encoder to minimize inter-modality discrepancies and mitigate the impact of defective samples. Additionally, a foundational Residual Atrous Spatial Pyramid Module (RASPM) in the separated flows enlarges the receptive field, allowing for the capture of multi-scale contextual information. Furthermore, a Modality-aware Dynamic Aggregation Module (MDAM) in the modality-complementary flow dynamically aggregates saliency-related cues from both modality-specific flows. Leveraging the proposed parallel triple-flow framework, we further refine saliency maps derived from different flows through a flow-cooperative fusion strategy, yielding a high-quality, full-resolution saliency map for the final prediction. To evaluate the ro

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Innovations in Image Forensics: Designing a Smart Learning Based Methodology for Forgery Detection over Digital Images 1

Innovations in Image Forensics: Designing a Smart Learning B...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Ramkumar, G. Pithamber, K. Srilakshmi, C.H. Rathika, S. Anni Princy, B. Kandaswamy, Vijay Anand Saveetha University Department of ECE Tamil Nadu Chennai India MLR Institute of Technology Department of Electronics and Communication Engineering Hyderabad Dundigal India R.M.D. Engineering College Department of Computer Science and Business Systems Tamil Nadu Kavaraipettai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Master of Business Administration Tamil Nadu Chennai India Panimalar Engineering College Department of Artificial Intelligence and Machine Learning Tamil Nadu Chennai India R.M.K. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Kavaraipettai India

ISBN: (纸本)9798350365016

Detecting forgery in digital images is crucial for several reasons. Firstly, with the widespread use and accessibility of image editing tools, individuals can easily manipulate digital images, raising concerns about the authenticity and integrity of visual information. This study introduces a novel approach, termed SFVGG, for detecting forgery in digital images by leveraging a smart learning methodology. The SFVGG method integrates the robust features of SIFT, the clustering capabilities of Fuzzy C-Mean clustering, and the deep learning process of VGG19. Through a synergistic combination of these techniques, the proposed forgery detection system achieves a comprehensive and effective solution. The methodology was implemented using Python, showcasing its practical applicability. Remarkably, the SFVGG framework demonstrates a high accuracy of 94.5%, underscoring its effectiveness in identifying forged content within digital images. This research represents a significant advancement in digital image forgery detection, offering both a sophisticated methodology and practical implementation. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Mesothelioma: Early Detection and Treatment

Machine Learning for Mesothelioma: Early Detection and Treat...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Bhavika Garg Tarun Jain Vijay Shankar Sharma Department of Computer Science and Engineering Manipal University Jaipur Department of IOT & Intelligent Systems Manipal University Jaipur

Mesothelioma is an extremely severe cancer that can easily transform into lung cancer. Mesothelioma diagnosis takes several months and treatment, including surgery, is expensive. Given the risk, early detection of Mesothelioma is essential for patient health, as it is connected to asbestos exposure. Various machine learning algorithms has been used in this research paper to compare with accurate results for mesothelioma detection. Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), k Nearest Neighbourhood (k-NN), and Linear Regression (LR) are some of the machine learning methods being used. For this research paper, dataset is available on UCI, called the University of California Irvine [1]. The test dataset contains 264 instances, 35 characteristics and 8 performance measures, which is used to evaluate the classifiers accuracy. The average accuracy of XGB, RF, DT, SGD, LR and Voting Classifier are 100% each. Combing all the classifiers, helps us to break through the Mesothelioma data and the creation of data driven insights to improve patient care.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction: Materials laboratories of the future for alloys, amorphous, and composite materials (MRS Bulletin, (2025), 50, 2, (190-207), 10.1557/s43577-024-00846-y)

引用

MRS Bulletin 2025年 1-2页

作者： Banerjee, Sarbajit Meng, Y. Shirley Minor, Andrew M. Zhang, Minghao Zaluzec, Nestor J. Chan, Maria K.Y. Seidler, Gerald McComb, David W. Agar, Joshua Mukherjee, Partha P. Melot, Brent Chapman, Karena Guiton, Beth S. Klie, Robert F. McCue, Ian D. Voyles, Paul M. Robertson, Ian Li, Ling Chi, Miaofang Destino, Joel F. Devaraj, Arun Marquis, Emmanuelle A. Segre, Carlo U. Liu, Huinan H. Yang, Judith C. Momeni, Kasra Misra, Amit Abdolrahim, Niaz Medvedeva, Julia E. Cai, Wenjun Sehirlioglu, Alp Dizbay-Onat, Melike Mehta, Apurva Graham-Brady, Lori Maruyama, Benji Rajan, Krishna Warner, Jamie H. Taheri, Mitra L. Kalinin, Sergei V. Reeja-Jayan, B. Schwarz, Udo D. Simon, Sindee L. Brown, Craig M. Department of Chemistry and Department of Materials Science & Engineering Texas A & M University College Station United States Pritzker School of Molecular Engineering The University of Chicago Chicago United States Department of Materials Science & Engineering University of California Berkeley Berkeley United States National Center for Electron Microscopy Molecular Foundry Lawrence Berkeley National Laboratory Berkeley United States Center for Nanoscale Materials Argonne National Laboratory Lemont United States Department of Physics University of Washington Seattle United States Department of Materials Science & Engineering The Ohio State University Columbus United States Department of Mechanical Engineering and Mechanics Drexel University Philadelphia United States School of Mechanical Engineering Purdue University West Lafayette United States Department of Chemistry University of Southern California Los Angeles United States Department of Chemistry Stony Brook University The State University of New York Stony Brook United States Department of Chemistry University of Kentucky Lexington United States Department of Physics University of Illinois at Chicago Chicago United States Department of Materials Science & Engineering Northwestern University Evanston Bangladesh Department of Materials Science & Engineering University of Wisconsin–Madison Madison United States Department of Materials Science and Engineering University of Pennsylvania Philadelphia United States Department of Mechanical Engineering and Materials Science Duke University Durham United States Department of Chemistry Creighton University Omaha United States Physical and Computational Sciences Directorate Pacific Northwest National Laboratory Richland United States Department of Materials Science & Engineering University of Michigan–Ann Arbor Ann Arbor United States Department of Physics Illinois Institute of Technology Chicago United States Department of Bioengineering and the Mater

This article was updated to correct Minghao Zhang’s affiliation from "Pritzker School of Molecular engineering, The University of Chicago, Chicago, USA" to "Pritzker School of Molecular engineering, The University of Chicago, Chicago, USA;Argonne National Laboratory, Lemont, USA." Argonne National Laboratory was left off the original publication. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coco-LIC: Continuous-Time Tightly-Coupled LiDAR-Inertial-Camera Odometry using Non-Uniform B-spline

arXiv

引用

arXiv 2023年

作者： Lang, Xiaolei Chen, Chao Tang, Kai Ma, Yukai Lv, Jiajun Liu, Yong Zuo, Xingxing The Institute of Cyber-Systems and Control Zhejiang University Hangzhou China The Department of Computer Engineering Technical University of Munich Germany

In this paper, we propose an efficient continuous-time LiDAR-Inertial-Camera Odometry, utilizing non-uniform B-splines to tightly couple measurements from the LiDAR, IMU, and camera. In contrast to uniform B-spline-based continuous-time methods, our non-uniform B-spline approach offers significant advantages in terms of achieving real-time efficiency and high accuracy. This is accomplished by dynamically and adaptively placing control points, taking into account the varying dynamics of the motion. To enable efficient fusion of heterogeneous LiDAR-Inertial-Camera data within a short sliding-window optimization, we assign depth to visual pixels using corresponding map points from a global LiDAR map, and formulate frame-to-map reprojection factors for the associated pixels in the current image frame. This way circumvents the necessity for depth optimization of visual pixels, which typically entails a lengthy sliding window with numerous control points for continuous-time trajectory estimation. We conduct dedicated experiments on real-world datasets to demonstrate the advantage and efficacy of adopting non-uniform continuous-time trajectory representation. Our LiDAR-Inertial-Camera odometry system is also extensively evaluated on both challenging scenarios with sensor degenerations and large-scale scenarios, and has shown comparable or higher accuracy than the state-of-the-art methods. The codebase of this paper will also be open-sourced at https://***/APRIL-ZJU/Coco-LIC. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Quality of Experience Aware Task Offloading in Digital Twinning Vehicular Edge Computing

Quality of Experience Aware Task Offloading in Digital Twinn...

引用

International Conference on Distributed Computing in Sensor systems (DCOSS)

作者： Mostakim Jihad Mashraba Tasnim Rodshi Abdullah Al Fahad Palash Roy Md. Abdur Razzaque Mohammad Mehedi Hassan Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Green Networking Research Group University of Dhaka Bangladesh Information Systems Dept. College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

Adopting Digital Twin (DT) technology in vehicular edge computing (VEC) enables efficient capture of real-time state information of applications, thereby addressing complex task scheduling problems. Existing literature studies considered only minimizing service latency for task offloading; however, there is room for exploring strategies to enhance user Quality of Experience (QoE) in timeliness and reliability domains. In this paper, we have developed an optimization framework using Mixed Integer Linear Programming (MILP), namely QuETOD, which minimizes service latency by allocating task execution responsibility to highly reliable and reputed vehicles in a DT-enabled VEC environment. The developed QuETOD framework clusters the vehicles based on the demand-supply theory of economics by considering computing resources and utilizing the multi-weighted subjective logic for getting the proper reputation update of the vehicles. The experimental results of the developed QuETOD system depict significant performance improvement in terms of QoE and reliability compared to the state-of-the-art works as high as 15% and 25%, respectively.

关键词： Processor scheduling Computational modeling Reliability theory Real-time systems Polynomials Quality of experience Servers

来源：评论

学校读者我要写书评

暂无评论

Application Monitoring Using Libc Call Interception

Application Monitoring Using Libc Call Interception

引用

2nd International Conference on Intelligent Computing, Information and control systems, ICICCS 2020

作者： Thuwal, Harish Vashishtha, Utkarsh Department of Computer Science and Engineering IIT Delhi India Department of Computer Science and Information Systems BITS Pilani India

ISBN: (纸本)9789811584428

Generally available application monitoring solutions comprise basic aggregated metrics. This paper collects such metrics in the form of raw data. We have worked out a very primitive piece written in Golang, which manifests results from HTTP/HTTPS calls from/to the system being monitored. This process can be easily extended and applied to various architectures that use the libc library to make low-level system calls to interact with sockets or, in a more basic sense, files. The experimentation and the proof of concept were carried out on various languages, viz. C, Java, Python, and Golang itself using Docker and some classic open-source compilers. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： C (programming language)

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：