检索结果-内蒙古大学图书馆

massive MIMO transmission for LEO satellite communications

学校读者我要写书评

暂无评论

arXiv 2020年

作者： You, Li Li, Ke-Xin Wang, Jiaheng Gao, Xiqi Xia, Xiang-Gen Ottersten, Björn National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211100 China Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States University of Luxembourg Luxembourg CityL-2721 Luxembourg

Low earth orbit (LEO) satellite communications are expected to be incorporated in future wireless networks, in particular 5G and beyond networks, to provide global wireless access with enhanced data rates. Massive multiple-input multiple-output (MIMO) techniques, though widely used in terrestrial communication systems, have not been applied to LEO satellite communication systems. In this paper, we propose a massive MIMO transmission scheme with full frequency reuse (FFR) for LEO satellite communication systems and exploit statistical channel state information (sCSI) to address the difficulty of obtaining instantaneous CSI (iCSI) at the transmitter. We first establish the massive MIMO channel model for LEO satellite communications and simplify the transmission designs via performing Doppler and delay compensations at user terminals (UTs). Then, we develop the low-complexity sCSI based downlink (DL) precoder and uplink (UL) receiver in closed-form, aiming to maximize the average signal-to-leakage-plus-noise ratio (ASLNR) and the average signal-to-interference-plus-noise ratio (ASINR), respectively. It is shown that the DL ASLNRs and UL ASINRs of all UTs reach their upper bounds under some channel condition. Motivated by this, we propose a space angle based user grouping (SAUG) algorithm to schedule the served UTs into different groups, where each group of UTs use the same time and frequency resource. The proposed algorithm is asymptotically optimal in the sense that the lower and upper bounds of the achievable rate coincide when the number of satellite antennas or UT groups is sufficiently large. Numerical results demonstrate that the proposed massive MIMO transmission scheme with FFR significantly enhances the data rate of LEO satellite communication systems. Notably, the proposed sCSI based precoder and receiver achieve the similar performance with the iCSI based ones that are often infeasible in practice. Copyright © 2020, The Authors. All rights reserved.

关键词： Satellite communication systems

Lightweight Image Super-Resolution with Enhanced CNN

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tian, Chunwei Zhuge, Ruibin Wu, Zhihao Xu, Yong Zuo, Wangmeng Chen, Chen Lin, Chia-Wen Bio-Computing Research Center Harbin Institute of Technology Shenzhen ShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition ShenzhenGuangdong518055 China Peng Cheng Laboratory ShenzhenGuangdong518055 China School of Computer Science and Technology Harbin Institute of Technology HarbinHeilongjiang150001 China Department of Electrical and Computer Engineering University of North Carolina CharlotteNC28223 United States Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan

Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts of convolutions and parameters usually consume high computational cost and more memory storage for training a SR model, which limits their applications to SR with resource-constrained devices in real world. To resolve these problems, we propose a lightweight enhanced SR CNN (LESRCNN) with three successive sub-blocks, an information extraction and enhancement block (IEEB), a reconstruction block (RB) and an information refinement block (IRB). Specifically, the IEEB extracts hierarchical low-resolution (LR) features and aggregates the obtained features step-by-step to increase the memory ability of the shallow layers on deep layers for SISR. To remove redundant information obtained, a heterogeneous architecture is adopted in the IEEB. After that, the RB converts low-frequency features into high-frequency features by fusing global and local features, which is complementary with the IEEB in tackling the long-term dependency problem. Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image. The proposed LESRCNN can obtain a high-quality image by a model for different scales. Extensive experiments demonstrate that the proposed LESRCNN outperforms state-of-the-arts on SISR in terms of qualitative and quantitative evaluation. The code of LESRCNN is accessible on https://***/hellloxiaotian/LESRCNN. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

Relative attributing propagation: Interpreting the comparative contributions of individual units in deep neural networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Nam, Woo-Jeoung Gur, Shir Choi, Jaesik Wolf, Lior Lee, Seong-Whan Department of Computer and Radio Communications Engineering Korea University Department of Artificial Intelligence Korea University School of Computer Science Tel Aviv University Facebook AI Research Graduate School of Artificial Intelligence KAIST

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs. In this paper, we propose Relative Attributing Propagation (RAP), which decomposes the output predictions of DNNs with a new perspective of separating the relevant (positive) and irrelevant (negative) attributions according to the relative influence between the layers. The relevance of each neuron is identified with respect to its degree of contribution, separated into positive and negative, while preserving the conservation rule. Considering the relevance assigned to neurons in terms of relative priority, RAP allows each neuron to be assigned with a bi-polar importance score concerning the output: from highly relevant to highly irrelevant. Therefore, our method makes it possible to interpret DNNs with much clearer and attentive visualizations of the separated attributions than the conventional explaining methods. To verify that the attributions propagated by RAP correctly account for each meaning, we utilize the evaluation metrics: (i) Outside-inside relevance ratio, (ii) Segmentation mIOU and (iii) Region perturbation. In all experiments and metrics, we present a sizable gap in comparison to the existing literature. Our source code is available in https://***/wjNam/Relative Attributing Propagation. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Ontoscene, a logic-based scene interpreter: Implementation and application in the rock art domain

学校读者我要写书评

暂无评论

arXiv 2019年

作者： BRIOLA, DANIELA MASCARDI, VIVIANA GIOSEFFI, MASSIMILIANO Department of Computer Sciences Systems and Communications University of Milano Bicocca Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy

We present OntoScene, a framework aimed at understanding the semantics of visual scenes starting from the semantics of their elements and the spatial relations holding between them. OntoScene exploits ontologies for representing knowledge and Prolog for specifying the interpretation rules that domain experts may adopt, and for implementing the SceneInterpreter engine. Ontologies allow the designer to formalize the domain in a reusable way, and make the system modular and interoperable with existing multiagent systems, while Prolog provides a solid basis to define complex rules of interpretation in a way that can be affordable even for people with no background in Computational Logics. The domain selected for experimenting OntoScene is that of prehistoric rock art, which provides us with a fascinating and challenging testbed. Under consideration in Theory and Practice of Logic Programming (TPLP). Copyright © 2019, The Authors. All rights reserved.

关键词： Ontology

Deep learning-assisted 3D model for the detection and classification of knee arthritis

学校读者我要写书评

暂无评论

Image and Vision Computing 2025年 160卷

作者： Preethi, D. Govindaraj, V. Dhanasekar, S. Sagayam, K. Martin Ansarullah, Syed Immamul Amin, Farhan de la Torre D'ıez, Isabel Garc'ıa, Carlos Osorio Barrera, Alina Eugenia Pascual Alshammari, Fehaid Salem Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of ECE Kalignar karunanidhi Institute of Technology Coimbatore India Department of ECE Sri Eshwar College of Engineering Coimbatore India Department of ECE Karunya Institute of Technology and Sciences Coimbatore India Department of Management Studies University of Kashmir North Campus Delina Jammu & Kashmir Baramulla193103 India School of Computer Science and Engineering Yeungnam University Gyeongsan38541 Korea Republic of Department of Signal Theory and Communications University of Valladolid Valladolid23200 Spain Universidad Europea del Atl'antico Isabel Torres 21 Santander39011 Spain Riyadh Saudi Arabia King Salman Center for Disability Research Riyadh11614 Saudi Arabia

Osteoarthritis (OA) affects nearly 240 million people worldwide. It is a common degenerative illness that typically affects the knee joint OA causes pain, and functional disability, especially in older adults is a common disease. One of the most common and challenging medical conditions to deal with in old-aged people is the occurrence of knee osteoarthritis (KOA). Manual diagnosis involves observing X-ray images of the knee area and classifying it into different five grades. This requires the physician's expertise, suitable experience, and a lot of time, and even after that, the diagnosis can be prone to errors. Therefore, researchers in the machine learning (ML) and deep learning (DL) domains have employed the capabilities of deep neural network (DNN) models to identify and classify medical images in an automated, faster, and more accurate manner. Combining multiple imaging modalities or utilizing three-dimensional reconstructions can enhance the accuracy and completeness of 2D Images in diagnostic information. Hence to overcome the drawbacks of 2D imaging, the reconstruction of 3D models using 2D images is the main theme of our research. In this paper, we propose a deep learning-based model for the detection and classification of the early diagnosis of arthritis. It is a four-step procedure starting with data collection followed by data conversion. In this step, our proposed model deforms the target's convex hull to produce a 3D model. Herein, a series of 2D photos is utilized, along with surface rendering methods, to create a 3D model. In the third step, the feature extraction is performed followed by mesh refinement. The chamfer loss is optimized based on the rotational shape of the leg bones, and subsequently, the weight of the loss function can be allocated to the target's geometric properties. We have used a modified Gray Level Co-occurrence Matrix (GLCM) for feature extraction. In the fourth step, the image classification is performed and the suggested opti

关键词： Neuroimaging

Battery Aging-Aware Green Cellular Networks with Hybrid Energy Supplies 29

学校读者我要写书评

暂无评论

Battery Aging-Aware Green Cellular Networks with Hybrid Ener...

29th IEEE Annual International Symposium on Personal, Indoor and Mobile Radio communications, PIMRC 2018

作者： El-Amine, Ali Al Haj Hassan, Hussein Nuaymi, Loutfi IMT-Atlantique Rennes France Department of Computer and Communications Engineering Faculty of Engineering American University of Science and Technology Beirut Lebanon

ISBN: (纸本)9781538660096

Hybrid energy powered cellular networks are key for proposing green and cost-efficient wireless networks. Yet, the related energy management imposes severe challenges to efficiently manage the power allocation between the Renewable Energy (RE) source, the batteries and the smart power grid. The energy storage element (i.e., battery) is prone to irreversible aging mechanisms, requiring intelligent management that takes into account both the energy cost and requirements preventing battery degradation. In this work, we include this important constraint before proposing an energy management and base stations switch off algorithm for a partially RE-equipped cellular network in a variable electricity price environment. Results show that our algorithm outperforms a benchmark algorithm with a gain up to 20% in terms of electric bill reduction and enhances the battery life time by 35%. © 2018 IEEE.

关键词： Wireless networks

An analog of the Sinc approximation for periodic functions

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ogata, Hidenori Department of Computer and Network Engineering Graduate School of Informatics and Engineering University of Electro-Communications 1-5-1 Chofugaoka Chofu182-8585 Japan

In this paper, we propose an interpolation formula for periodic functions. This formula can be regarded as an analog of the Sinc approximation, which is an interpolation formula for functions defined on the entire infinite interval. Theoretical error analysis and numerical examples show that the proposed formula converges exponentially for analytic periodic *** Codes 65D05 Copyright © 2019, The Authors. All rights reserved.

关键词： Interpolation

Non-orthogonal Multiple Access Enabled Power Allocation for Cooperative Jamming in Wireless Networks 1st

学校读者我要写书评

暂无评论

Non-orthogonal Multiple Access Enabled Power Allocation for ...

1st EAI International Conference on Artificial Intelligence for communications and Networks, AICON 2019

作者： Wu, Yuan Wu, Weicong Wang, Daohang Ni, Kejie Qian, Li Ping Lu, Weidang Meng, Limin State Key Laboratory of Internet of Things for Smart City and Department of Computer and Information Science University of Macau Zhuhai China College of Information Engineering Zhejiang University of Technology Hangzhou310023 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

ISBN: (纸本)9783030229672

In this work, we investigate the non-orthogonal multiple access (NOMA) enabled power allocation for cooperative jamming under a two-user downlink scenario. In particular, we consider that there exists a malicious eavesdropper overhearing the data transmission of the mobile user (MU) with a stronger channel power gain. Meanwhile, exploiting the simultaneous transmission in NOMA, we consider that the other MU with a weak channel power gain provides cooperative jamming to the eavesdropper for enhancing the secure throughput of the stronger MU. In particular, we formulate a power allocation problem to maximize the secure throughput of the strong MU while satisfying the throughput requirement of the weak MU. Despite the non-convexity of the formulated problem, we provide an efficient algorithm to compute the optimal solution (i.e., the power allocations for the two users). Numerical results are provided to validate the effectiveness of our proposed algorithm and the performance of our optimal power allocation scheme. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2019.

关键词： Wireless networks

Deep learning based pedestrian detection at all light conditions 8

学校读者我要写书评

暂无评论

Deep learning based pedestrian detection at all light condit...

8th IEEE International Conference on Communication and Signal Processing, ICCSP 2019

作者： Chebrolu, Koti Naga Renu Kumar, P.N. Department of Electronics and Communications Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India Department of Computer Science and Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9781538675953

Multispectral pedestrian detection is becoming increasingly important in the field of computer vision due to its applications in driver assistance, surveillance, and monitoring. In this paper, we propose a brightness aware model for pedestrian detection using deep learning. A novel brightness aware mechanism depicts various illumination conditions, so as to enable prediction of day/ night scenario. Based on the detection of the brightness aware mechanism, a color or thermal model is used to detect pedestrians under day or night conditions respectively. The proposed method trained on FLIR-ADAS Thermal dataset and PASCAL VOC Color dataset, has achieved a mAP of '81.27%', which outperforms the current state of the art. © 2019 IEEE.

关键词： Luminance