检索结果-内蒙古大学图书馆

Methods for Predictive Performance Improvement of Deep Learning systems for Aerial Building Roof Detection with Multispectral Images

学校读者我要写书评

暂无评论

Methods for Predictive Performance Improvement of Deep Learn...

2023 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement systems and Applications, CIVEMSA 2023

作者： Churi, A. Megherbi, D.B. University of Massachusetts Center for Human/Machine Intelligence Networking Distributed Systems Department of Electrical and Computer Engineering LowellMA United States

ISBN: (纸本)9781665434454

In this paper, we present a dilated convolutional neural network-based deep learning system for the challenging problem of building accurate roof pixel detection from city aerial multispectral images in the visible and infrared spectral bands. The proposed system uses an automatic spectral band selection strategy and an automatic histogram-based threshold-finding method to improve the network's prediction accuracy performance. Current existing systems train a single model on all the cities of interest data at once. These systems also usually use only RGB bands and avoid post-processing of the predicted images for increased prediction accuracies. In this paper, we present the following solutions to these object detection challenges, 1) we propose and implement a separate model for each city dataset, 2) we propose an optimal band selection strategy to choose the most informative visible-infrared bands from multispectral images, 3) we propose an adaptive and automatic histogram-based optimal threshold finding technique for building roof object segmentation. Our results show that having a separate model for each city rather than only one model for all the combined cities increases the system's performance by 20.77% in building roof pixel prediction in any of the cities considered. We show that our system also has a 35.6% increase in F1 score compared to its state-of-The-Art counterpart, the winning implementation of the SpaceNet building detection national challenge, which took place in 2017. © 2023 IEEE.

关键词： Object recognition

Methods for Predictive Performance Improvement of Deep Learning systems for Aerial Building Roof Detection with Multispectral Images

学校读者我要写书评

暂无评论

Methods for Predictive Performance Improvement of Deep Learn...

IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement systems and Applications

作者： A. Churi D. B. Megherbi Department of Electrical and Computer Engineering Center for Human/Machine Intelligence Networking and Distributed Systems University of Massachusetts Lowell MA USA

In this paper, we present a dilated convolutional neural network-based deep learning system for the challenging problem of building accurate roof pixel detection from city aerial multispectral images in the visible and infrared spectral bands. The proposed system uses an automatic spectral band selection strategy and an automatic histogram-based threshold-finding method to improve the network's prediction accuracy performance. Current existing systems train a single model on all the cities of interest data at once. These systems also usually use only RGB bands and avoid post-processing of the predicted images for increased prediction accuracies. In this paper, we present the following solutions to these object detection challenges, 1) we propose and implement a separate model for each city dataset, 2) we propose an optimal band selection strategy to choose the most informative visible-infrared bands from multispectral images, 3) we propose an adaptive and automatic histogram-based optimal threshold finding technique for building roof object segmentation. Our results show that having a separate model for each city rather than only one model for all the combined cities increases the system's performance by 20.77 % in building roof pixel prediction in any of the cities considered. We show that our system also has a 35.6% increase in F1 score compared to its state-of-the-art counterpart, the winning implementation of the SpaceNet building detection national challenge, which took place in 2017.

关键词：

Network Message Field Type Clustering for Reverse Engineering of Unknown Binary Protocols

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kleber, Stephan Kargl, Frank Stute, Milan Hollick, Matthias Institute of Distributed Systems Ulm University Germany Secure Mobile Networking Lab Technical University of Darmstadt Germany

Reverse engineering of unknown network protocols based on recorded traffic traces enables security analyses and debugging of undocumented network services. One important step in protocol reverse engineering is to determine data types of message fields. Existing approaches for binary protocols (1) lack comprehensive methods to interpret message content and determine the data types of discovered segments in a message and (2) assume the availability of context, which prevents the analysis of complex and lower-layer protocols. Overcoming these limitations, we propose the first generic method to analyze message field data types in unknown binary protocols by clustering of segments with the same data type. Our extensive evaluation shows that our method in most cases provides clustering of up to 100% precision at reasonable recall. Particularly relevant for use in fuzzing and misbehavior detection, we increase the coverage of message bytes over the state-of-the-art to 87% by almost a factor of 30. We provide an open-source implementation to allow follow-up works. Copyright © 2022, The Authors. All rights reserved.

关键词： Network security

Hybrid-MELAu: A Hybrid Mixing Engineered Linguistic Features Framework Based on Autoencoder for Social Bot Detection

学校读者我要写书评

暂无评论

Informatica (Slovenia)

Informatica (Slovenia) 2022年第6期46卷 143-158页

作者： Hamida, Zineb Ferhat Refoufi, Allaoua Drif, Ahlem Giordano, Silvia Networks and Distributed Systems Laboratory Department of Computer Science University of Sétif 1 Sétif Algeria Networking Lab SUPSI University of Applied Sciences of Southern Switzerland Lugano Switzerland

Social bots are defined as computer algorithms that generate massive amounts of obnoxious or meaningful information. Most bot detection methods leverage multitudinous characteristics, from network features, temporal dynamics features, activities features, and sentiment features. However, there has been fairly lower work exploring lexicon measurement and linguistic indicators to detect bots. The main purpose of this research is to recognize the social bots through their writing style. Thus, we carried out an exploratory study on the effectiveness of only a set of linguistic features (17 features) exploitable for bot detection, without the need to resort to other types of features. And we develop a novel framework in a hybrid fashion of Mixing Engineered Linguistic features based on Autoencoders (Hybrid-MELAu). The semi-supervised Hybrid-MELAu framework is composed of two essential constituents: the features learner and the predictors. We establish the features learner innovated on two powerful structures: a) the first is a Deep dense Autoencoder fed by the Lexical and the Syntactic content (DALS) that represents the high order lexical and syntactic features in latent space, b) the second one is a Glove-BiLSTM autoencoder, which sculpts the semantic features;subsequently, we generate elite elements from the pre-trained encoder part from each latent space with transfer learning. We consider a sample of 1 Million from Cresci datasets to conduct our linguistic analysis comparison between the writing style of humans and bots. With this dataset, we observe that the bot's textual lexical diversity median is greater than the human one and the syntactic analysis based on speech-tagging shows a creative behavior in human writing style. Finally, we test the model's robustness on several public dataset (celebrity, pronbots-2019, and political bots). The proposed framework achieves a good accuracy of 92.22%. Overall, the results shown in this paper, and the related discussion, ar

关键词： Classification (of information)

From Earth to Space: A First Deployment of 5G Core Network on Satellite

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xing, Ruolin Ma, Xiao Zhou, Ao Dustdar, Schahram Wang, Shangguang State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Distributed Systems Group TU Wien Vienna1040 Austria

Recent developments in the aerospace industry have led to a dramatic reduction in the manufacturing and launch costs of low Earth orbit satellites. The new trend enables the paradigm shift of satellite-terrestrial integrated networks with global coverage. In particular, the integration of 5G communication systems and satellites has the potential to restructure next-generation mobile networks. By leveraging the network function virtualization and network slicing, the orbital 5G core networks will facilitate the coordination and management of network functions in satellite-terrestrial integrated networks. We are the first to deploy a lightweight 5G core network on a real-world satellite to investigate its feasibility. We conducted experiments to validate the onboard 5G core network functions. The validated procedures include registration and session setup procedures. The results show that the 5G core network can function normally and generate correct signaling. Copyright © 2022, The Authors. All rights reserved.

关键词： Orbits

SatCooper: Enhancing Cooperative Inference Analytics for Satellite Service via Multi-exit DNNs

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Qiyang Wang, Shangguang Guan, Jinglong Donta, Praveen Kumar Ma, Xiao Prasad, RangaRao Venkatesha Dustdar, Schahram Liu, Xuanzhe Peking University School of Computer Science Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Stockholm University Department of Computer and Systems Sciences Kista16455 Sweden Beiyou Shenzhen Institute Shenzhen China Netherlands TU Wien Distributed System Group Wien1040 Austria UPF Barcelona Spain

As a key technology of intelligent satellite-enabled services in B5G or 6G networks, deploying Deep Neural Networks (DNN) models on satellites has been a notable trend, catering to the daily demand for extensive computing-intensive and latency-sensitive tasks. The computing resources are strategically deployed on satellites where sensor data is generated or collected, facilitating the fine-grained computational inference of DNN-based tasks. However, no prior study has comprehensively explored the crucial inference challenges-e.g., the trade-off between the number of tasks completed and accuracy and partitioning models in multi-exit models-in the resource-constrained space environment. Effective scheduling frameworks cater to various streams of inference tasks are scarce because inference performance may deviate from the ideal situation due to changes in task system status, such as task profiles and network state. To this end, we first formulate a gain-aware in-orbit computing inference problem to strike a proper trade-off between inference latency and the number of tasks completed by dynamically selecting optimal early exit points and model partitioning points. We propose an offline dynamic programming-based algorithm that provides an effective solution when comprehensive system details are to be predicted. We have developed an online learning-based method to schedule inference tasks with uncertain and dynamic system statuses in real-world situations. Our evaluation shows that, compared to baseline methods, the online learning-based algorithm can improve task gain by an average of 87.3% across various tasks. © 2002-2012 IEEE.

关键词： Dynamic programming

distributed Realtime Rendering in Decentralized Network for Mwar

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Lu, Qiong Liang, Li Zhang, Huabing Huang, Yakun Dustdar, Schahram Key Lab of Film and TV Media Technology of Zhejiang Province Zhejiang Hangzhou310018 China School of Media Engineering Communication University Of Zhejiang Zhejiang Hangzhou310018 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Distributed Systems Group Technische Universität Wien Vienna1040 Austria

Low-latency, real-time rendering of 3D objects is a critical requirement for mobile web-based augmented reality (MWAR) applications. While cloud-based or edge-based server rendering offloading can reduce the latency for mobile devices, a high volume of users' requests in scenarios with user aggregation can overload servers and transmission channels. This can result in a poor user experience due to resource consumption and high latency. This paper presents a decentralized and collaborative real-time rendering offloading network architecture (CRCDnet) to address this issue. CRCDnet makes contributions in the following three areas:(1) In the user aggregation scenario, mobile devices that perform the same services are used as service nodes to perform the offloading of rendering computing, and a collaborative rendering computing network is established.(2) For decentralized network rendering data exchange, a data sharing middle layer based on blockchain key index is used to separate sensitive service data and ensure a secure and trustworthy exchange mechanism.(3) A data request and computing offloading scheduling method for the collaborative rendering computing network is proposed to optimize rendering computation delay. © 2023, The Authors. All rights reserved.

关键词： Augmented reality

Towards Holographic Video Communications: A Promising AI-driven Solution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Yakun Zhu, Yuanwei Qiao, Xiuquan Su, Xiang Dustdar, Schahram Zhang, Ping The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The Department of Computer Science Norwegian University of Science and Technology Gjøvik2815 Norway University of Oulu Oulu90570 Finland The Distributed Systems Group Technische Universität Wien Vienna1040 Austria

Real-time holographic video communications enable immersive experiences for next-generation video services in the future metaverse era. However, high-fidelity holographic videos require high bandwidth and significant computation resources, which exceed the transferring and computing capacity of 5G networks. This article reviews state-of-the-art holographic point cloud video (PCV) transmission techniques and highlights the critical challenges of delivering such immersive services. We further implement a preliminary prototype of an AI-driven holographic video communication system and present critical experimental results to evaluate its performance. Finally, we identify future research directions and discuss potential solutions for providing real-time and high-quality holographic experiences. Copyright © 2022, The Authors. All rights reserved.

关键词： 5G mobile communication systems

Multi-Player Immersive Communications and Interactions in Metaverse: Challenges, Architecture, and Future Directions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Yakun Qiao, Xiuquan Wang, Haowen Su, Xiang Dustdar, Schahram Zhang, Ping State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science Norwegian University of Science and Technology 2815 Gjøvik Norway University of Oulu Oulu90570 Finland Distributed Systems Group Technische Universität Wien Vienna1040 Austria

The metaverse has awakened users’ expectations of an immersive interaction that fuses the virtual digital world and the physical world across space and time. However, the metaverse is still in its infancy, typically expanding multi-player applications (e.g., multi-player games) to implement a prototype with the help of 5G/Beyond 5G, Artificial Intelligence, digital twin, and other enabling technologies. This article reviews the characteristics, key enabling technologies, and driving applications of the state-of-the-art metaverse. We focus on the immersive interactions perspective of the metaverse from the tasks, inputs, and feedback across the users, digital world, and physical world and reveal the key challenges. Afterwards, we present a multi-player interaction prototype platform based on a cloud-edge-device collaborative framework. Also, we evaluate it with centralized and device-to-device (D2D) approaches to verify the efficiency and flexibility of interactions. Finally, we point out future research approaches and discuss potential solutions to enable more stable and higher quality multi-player interactions for metaverse services. Copyright © 2022, The Authors. All rights reserved.

关键词： 5G mobile communication systems