检索结果-内蒙古大学图书馆

Lightweight Task-Oriented Semantic communication Empowered by Large-Scale AI Models

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

Applying LSTM for River's Water Level Forecasting as Potential Flood Indication: A Case Study in Greece 15

Applying LSTM for River's Water Level Forecasting as Potenti...

引用

15th International Conference on Information, Intelligence, systems and Applications, IISA 2024

作者： Tziolas, Theodoros Papageorgiou, Elpiniki Papageorgiou, Konstantinos Zardas, Georgios Lekidis, Alexios Panagiotis, Papazoglou University of Thessaly Dept. of Energy Systems Gaiopolis Campus Larisa41500 Greece University of Thessaly Dept. of Electrical and Computer Engineering Volos Greece National and Kapodistrian University of Athens Dept. of Architecture and Computer and Communication Simulation Systems Chalkida Greece

ISBN: (纸本)9798350368833

Floods can have significant life-threatening and economic impacts on human societies. Flood forecasting with data-driven methods is a crucial aspect of disaster risk management, providing valuable insights into potential flood events and allowing for timely mitigation measures. This work illustrates the application of a Long Short-Term Memory (LSTM) neural network for short-term forecasting of a river's water level. The water treatment data used for training the LSTM models were gathered from Sperchios river, located in central Greece. Historical time-series data in a half-hour interval of the river's water level, water velocity, and area precipitation were utilized for the development of the proposed scheme. The developed model is deployed in the backend of a web application for half-hour ahead predictions of the river's water level that are visualized in the frontend. The post-analysis of the deployed forecasting model indicates that it consistently delivers forecasts with minimal error and demonstrates high accuracy in recent flood events. © 2024 IEEE.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

Fast Energy Estimation Through Partial Execution of HPC Applications 29

Fast Energy Estimation Through Partial Execution of HPC Appl...

引用

29th IEEE International Conference on Application-Specific systems, architectures and Processors, ASAP 2018

作者： Salinas-Hilburg, Juan Carlos Zapater, Marina Moya, Jose M. Ayala, Jose L. Dept. of Computer Architecture and Automation Complutense University of Madrid Madrid Spain Lausanne Switzerland Integrated Systems Laboratory Technical University of Madrid Madrid Spain CCS-Center for Computational Simulation Madrid Spain

ISBN: (纸本)9781538674796

In order to optimize the energy use of servers in Data Centers, techniques such as power capping or power budgeting are usually deployed. These techniques rely on the prediction of the power and execution time of applications. These data are obtained via dynamic profiling which requires a full execution of the application. This is not feasible in High Performance Computing (HPC) applications with long execution times. In this paper, we present a methodology to estimate the dynamic CPU and memory energy consumption of an application without executing it completely. Our methodology merges static code analysis information and dynamic profiling via the partial execution of the application. We do so by leveraging the concept of application signature, defined as a reduced version of the application in terms of execution time and power profile. We validate our methodology with a set of CPU -intensive, memory-intensive benchmarks and multi-threaded applications in a presently shipping enterprise server. Our energy estimation methodology shows an overall error below 8.0% when compared to the dynamic energy of the whole execution of the application. Also, our energy estimation methodology allows to estimate the energy of multi-threaded applications with an RMSE equal to 12.7% when compared to the dynamic energy from the complete parallel execution. © 2018 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Applying LSTM for River's Water Level Forecasting as Potential Flood Indication: A Case Study in Greece

Applying LSTM for River's Water Level Forecasting as Potenti...

引用

International Conference on Information, Intelligence, systems and Applications (IISA)

作者： Theodoros Tziolas Elpiniki Papageorgiou Konstantinos Papageorgiou Georgios Zardas Alexios Lekidis Papazoglou Panagiotis Dept. of Energy Systems University of Thessaly Gaiopolis Campus Larisa Greece Dept. of Electrical and Computer Engineering University of Thessaly Volos Greece Dept. of Architecture and Computer and Communication Simulation Systems National and Kapodistrian University of Athens Chalkida Greece

ISBN: (数字)9798350368833

ISBN: (纸本)9798350368840

关键词： Training Precipitation Biological system modeling Prevention and mitigation Neural networks Predictive models Rivers Floods Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards

arXiv

引用

arXiv 2021年

作者： Calvo-Fullana, Miguel Paternain, Santiago Chamon, Luiz F.O. Ribeiro, Alejandro The Dept. of Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain The Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States The Excellence Cluster for Simulation Technology University of Stuttgart Stuttgart Germany The Dept. of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA United States

A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. Hence, there exist constrained reinforcement learning problems for which neither regularized nor classical primal-dual methods yield optimal policies. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods as the portion of the dynamics that drives the multipliers evolution. This approach provides a systematic state augmentation procedure that is guaranteed to solve reinforcement learning problems with constraints. Thus, as we illustrate by an example, while previous methods can fail at finding optimal policies, running the dual dynamics while executing the augmented policy yields an algorithm that provably samples actions from the optimal policy. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The DEVStone Metric: Performance Analysis of DEVS simulation Engines

arXiv

引用

arXiv 2023年

作者： Cárdenas, Román Henares, Kevin Arroba, Patricia Risco-Martín, José L. Wainer, Gabriel A. Integrated Systems Laboratory Universidad Politécnica de Madrid Madrid Spain Dept. of Systems and Computer Engineering Carleton University OttawaON Canada Dpt. of Computer Architecture and Automation Universidad Complutense de Madrid Madrid Spain Center for Computational Simulation Universidad Politécnica de Madrid Madrid Spain

The DEVStone benchmark allows us to evaluate the performance of discrete-event simulators based on the DEVS formalism. It provides model sets with different characteristics, enabling the analysis of specific issues of simulation engines. However, this heterogeneity hinders the comparison of the results among studies, as the results obtained on each research work depend on the chosen subset of DEVStone models. We define the DEVStone metric based on the DEVStone synthetic benchmark and provide a mechanism for specifying objective ratings for DEVS-based simulators. This metric corresponds to the average number of times that a simulator can execute a selection of 12 DEVStone models in one minute. The variety of the chosen models ensures we measure different particularities provided by DEVStone. The proposed metric allows us to compare various simulators and to assess the impact of new features on their performance. We use the DEVStone metric to compare some popular DEVS-based simulators. © 2023, CC BY-SA.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

ST-Diary: A multimedia authoring environment for crowdsourced spatio-temporal events 8

ST-Diary: A multimedia authoring environment for crowdsource...

引用

8th ACM SIGSPATIAL International Workshop on Location-Based Social Networks, LBSN 2015

作者： Ahmad, Akhlaq Afyouni, Imad Murad, Abdullah Rahman, Md. Abdur Rehman, Faizan Ur Sadiq, Bilal Basalamah, Saleh Wahiddin, Mohamed Ridza Kulliyah of Information and Communication Technology International Islamic University Makkah Saudi Arabia College of Engineering and Islamic Architecture Umm Al Qura University Makkah Saudi Arabia KACST GIS Technology Innovation Center Umm Al Qura University Makkah Saudi Arabia Innovation and Entrepreneurship Institute Umm Al Qura University Malaysia College of Computer and Information Systems Umm Al Qura University Makkah Saudi Arabia Dept. of Computer Science LIG University of Grenoble Alpes France

ISBN: (纸本)9781450339759

The intensive use of social media through mobile devices has leveraged the development of digital diary applications that keep track of social events as well as geotagged multimedia content. In a large crowd where users with cultural diversity perform spatiotemporal activities, such geotagged multimedia content facilitates users' navigation through points of interest (POI) based on their preferences. This work presents a crowdsourced geo-spatial multimedia data aggregation tool that allows users to develop diary chapters relevant to forthcoming users' spatio-temporal activities. Our proposed solution provides users with the ability to add POIs through an authoring environment with multiple dimensions, such as spatio-temporal filters, multimedia categories, and event types. Specific application domains such as emergency situations, leisure trips, journalism, and tourism can take benefit of this technique. This authoring environment also visualizes geo-spatial multimedia content for collocated points of interest (CPOI) with moving users' timelines. We plan to integrate our proposed authoring environment as a proof of concept into our existing large-scale crowdsourcing environment that is envisioned to support millions of users during the Hajj 2015 event.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Towards a mobile and context-aware framework from crowdsourced data

Towards a mobile and context-aware framework from crowdsourc...

引用

International Conference on Information and communication Technology for the Muslim World (ICT4M)

作者： Akhlaq Ahmad Md. Abdur Rahman Imad Afyouni Faizan Ur Rehman Bilal Sadiq Mohamed Ridza Wahiddin College of Engineering and Islamic Architecture Umm Al-Qura University Makkah Saudi Arabia Kulliyyah of Information and Communication Technology International Islamic University Kuala Lumpur Malaysia College of Computer and Information Systems Umm Al-Qura University Makkah Saudi Arabia KACST GIS Technology Innovation Center Umm Al-Qura University Makkah KSA Dept. of Computer Science LTG. Universitv of Grenoble Alpes France

Capturing users' spatio-temporal context by recognizing their interests, locations, history and activities, and thereafter providing context-aware services is a challenging task. In this paper, we propose a spatio-temporal zoning model that takes different context dimensions into account and try to recommend necessary services to users in a personalized way. First, we propose a generic zoning model with unrestricted set of contexts where both spatial and temporal dimensions are relaxed, followed by two semi-restricted zoning models in which either spatial or temporal dimension is relaxed, while the other one is restricted. Finally, we show the model requiring restricted spatio-temporal zoning that applies to the scenario where millions of users need to perform some activities that have to be performed in a certain location and at a certain temporal period. We use the above zoning model for Hajj and Umrah events to define pilgrim's spatio-temporal contexts by capturing their real-time and historic activities through their smartphones' sensory data. This allows to intelligently recommend a set of necessary services to the users. We present a few of the implementations introduced in our proposed system.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

A spatio-temporal multimedia big data framework for a large crowd

A spatio-temporal multimedia big data framework for a large ...

引用

IEEE International Conference on Big Data

作者： Bilal Sadiq Faizan Ur Rehman Akhlaq Ahmad Md. Abdur Rahman Sohaib Ghani Abdullah Murad Saleh Basalamah Ahmad Lbath KACST GIS Technology Innovation Center Umm Al Oura University Saudi Arabia Dept. of Computer Science University of Grenoble Alpes France College of Engineering and Islamic Architecture Umm Al Qura University Saudi Arabia Kulliyah of Information and Communication Technology International Islamic University Kuala Lumpur Malaysia College of Computer and Information Systems Umm Al Qura University Saudi Arabia Innovation and Entrepreneurship Institute Umm Al Qura University Saudi Arabia

Crowdsourced multimedia data poses several challenges when it is collected, stored, indexed, retrieved, and visualized. Examples of crowd source multimedia data are social sensors, vehicle sensors, physical sensors, human sensors, etc. Analyzing such multimodal and diversified crowdsourced data provides very rich understanding about the need of individuals within a crowd. Such understanding makes it possible to tailor services to individuals' needs, also called context-aware services. In this paper, we propose a spatial multimedia big data framework that can collect multimedia data from 1) a very large crowd equipped with multi-sensory smartphones, 2) vehicles, and 3) social networks. A set of multimedia services are offered to users to support their spatio-temporal activities. These include but not limited to 1) simple user interfaces to utilize multimedia services for instant guidance, 2) navigation to points of interests (POI), and 3) efficient and cost effective intra-city rides to users. The big data framework is designed to handle a very large number of multimedia spatio-temporal queries in real-time. The system is a pilot project and will be deployed during the event of Hajj 2015 when over three million pilgrims from all over the world will visit Makkah, Saudi Arabia to perform their Hajj rituals.

关键词： Multimedia communication Big data Sensors Streaming media Multimedia databases Crowdsourcing Semantics

来源：评论

学校读者我要写书评

暂无评论

A framework for crowd-sourced data collection and context-aware services in Hajj and Umrah

A framework for crowd-sourced data collection and context-aw...

引用

ACS/IEEE International Conference on computer systems and Applications

作者： Akhlaq Ahmad Md. Abdur Rahman Faizan Ur Rehman Ahmed Lbath Imad Afyouni Abdelmajid Khelil Syed Osama Hussain Bilal Sadiq Mohamed Ridza Wahiddin College of Engineering and Islamic Architecture Umm Al Qura University Makkah Saudi Arabia Kulliyyah of Information and Communication Technology International Islamic University Malaysia College of Computer and Information Systems Umm Al-Qura University Makkah Saudi Arabia Science and Technology Unit Umm Al-Qura University Makkah Saudi Arabia Dept. of Computer Science University of Grenoble Alpes France Umm Al-Qura University Makkah SA TU Darmstadt Germany

We propose a context aware framework that offers a set of cloud-based services to support a very large Hajj and Umrah crowd by capturing their contexts using smartphones. The proposed framework captures the individual's context, provides a set of adapted services, and allows being in touch with a subset of one's community of interest. We leverage the spatiotemporal sensory data captured by our framework to define users' contexts for optimized services. Our proposed framework is also envisioned to assist the Hajj and Umrah authorities to (1) improve Hajj & Umrah documentation, (2) improve Hajj organization through better understanding of pilgrims' (individual and crowd) spatial and temporal behavior and needs, and (3) protect pilgrims' environment through environmental monitoring. In particular, the developed methods, techniques, and algorithms will support the pilgrimage quality of experience. We have tested our system through end-user subjects and due to apply for the upcoming Hajj events. We present our implementation details and the general impression of end users about our system.

关键词： Context Smart phones Social network services Communities Context-aware services Temperature sensors

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：