检索结果-内蒙古大学图书馆

2024 International conference on intelligent Robots and Systems

作者： Wu, Jason Wang, Ziqi Ouyang, Xiaomin Jeong, Ho Lyun SampLawski, Colin Kaplan, Lance M. Marlin, Benjamin Srivastava, Mani Univ Calif Los Angeles Los Angeles CA 90065 USA Univ Massachusetts Amherst Amherst MA USA US DEVCOM Army Res Lab Adelphi MD USA Amazon Seattle WA USA

ISBN: (纸本)9798350377712;9798350377705

Localization is a critical technology for various applications ranging from navigation and surveillance to assisted living. Localization systems typically fuse information from sensors viewing the scene from different perspectives to estimate the target location while also employing multiple modalities for enhanced robustness and accuracy. Recently, such systems have employed end-to-end deep neural models trained on large datasets due to their superior performance and ability to handle data from diverse sensor modalities. However, such neural models are often trained on data collected from a particular set of sensor poses (i.e., locations and orientations). During real-world deployments, slight deviations from these sensor poses can result in extreme inaccuracies. To address this challenge, we introduce FlexLoc, which employs conditional neural networks to inject node perspective information to adapt the localization pipeline. Specifically, a small subset of model weights are derived from node poses at run time, enabling accurate generalization to unseen perspectives with minimal additional overhead. Our evaluations on a multimodal, multiview indoor tracking dataset showcase that FlexLoc improves the localization accuracy by almost 50% in the zero-shot case (no calibration data available) compared to the baselines. The source code of FlexLoc is available in https://***/nesl/FlexLoc.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cooperative Localization in Hybrid Active and Passive Wireless sensor networks With Unknown Tx Power

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第13期10卷 11869-11887页

作者： Chen, Yang Zhao, Yubin Li, Xiaofan Xu, Cheng-Zhong Sun Yat Sen Univ Sch Microelect Sci & Technol Zhuhai 519082 Peoples R China Jinan Univ Sch Intelligent Syst Sci & Engn Zhuhai 519070 Peoples R China Univ Macau State Key Lab IoTSC Macau Peoples R China Univ Macau Dept Comp & Informat Sci Macau Peoples R China

Hybrid active and passive wireless sensor networks (HWSNs) gain advantages in extending the network lifetime and reducing the overall cost. Because the passive sensors without battery harvest the energy from distributed active sensor signal beam, and only a few active sensors can maintain a large-scale network. Thus, how to track the passive sensor's location is essential for network management. Since the active sensors are sparsely deployed, cooperative localization which employs passive sensors to locate themselves together is a promising solution. In this article, we analyze the energy beam generated by the active sensors on the cooperative localization accuracy of the passive sensors. We consider the spatial-temporal cooperative localization based on the received signal strength (RSS) model with unknown Tx power information of each sensor due to the limited processing capabilities, circuit complexity, and energy constraints. We formulate the Fisher information matrix (FIM) and the corresponding Cramer-Rao lower bound (CRLB) for the static fully connected network and dynamic spatial-temporal recursive network. Accordingly, energy beamforming schemes are proposed to optimize localization accuracy and energy efficiency problems. For the optimal localization problem, we derive the closed-form solution of the optimal energy beamforming wave. For the optimal energy efficiency problem, we propose a semidefinite programming (SDP) solution to achieve optimal energy consumption with a self-calibration method, which can address the over-relax problem. Extensive simulation results indicate that our proposed beamforming schemes have high localization accuracy and lower power consumption compared with the existing power allocation-based schemes.

关键词： Cooperative localization energy efficiency Fisher information matrix (FIM) semidefinite programming (SDP) wireless power transfer (WPT)

来源：评论

学校读者我要写书评

暂无评论

Localization in sensor networks Using Distributed Low-Rank Matrix Completion 49

Localization in Sensor Networks Using Distributed Low-Rank M...

引用

49th IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Fan, Yufan Pesavento, Marius Tech Univ Darmstadt Commun Syst Grp Darmstadt Germany

ISBN: (纸本)9798350344868;9798350344851

Localization in terrestrial and non-terrestrial networks plays an important role in various applications, such as autonomous driving, robotics, and unmanned aerial vehicles. Although the relative distances between neighboring devices can be directly detected by embedded sensors, the relative distances between non-neighboring devices are usually not available, which results in a sparse version of the Euclidean Distance Matrix (EDM). Since the complete EDM is low-rank and the information of the relative distances is distributed over the network, we consider a distributed localization approach based on the low-rank matrix completion using the singular value thresholding algorithm. The proposed approach is carried out in a distributed manner as the singular values and singular vectors are estimated by the distributed eigenvalue decomposition. It avoids gathering all information in a central server and only requires direct communication and distance estimation between neighboring sensors. Hence, the distance information acquired in each sensor and the coordinates of the sensors are kept private to the sensor. The proposed distributed low-rank matrix completion approach is also applicable, e.g., in the distributed recommendation system.

关键词： Distributed localization low-rank matrix completion distributed eigenvalue decomposition

来源：评论

学校读者我要写书评

暂无评论

Jointly Optimizing Age of information and Energy Consumption in Double-IRS-Assisted Wireless networks

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 10722-10735页

作者： Li, Min Fu, Xuan Dong, Miao Wang, Heng Chongqing Univ Posts & Telecommun Key Lab Ind Internet Things & Networked Control Chongqing 400065 Peoples R China

Age of information (AoI) is a crucial metric for data freshness in 5G ultrareliable low-latency communication systems. It is affected by various factors, such as the channel quality, the energy of the nodes, and so on. To overcome the severe path losses and environmental obstacles, intelligent reconfigurable surface (IRS) is adopted to reconfigure signal propagation environments, thereby mitigating the significant losses and creating additional signal reflection links. Different from the existing research on AoI in IRS-assisted wireless networks, which overlooks the impact of energy consumption on AoI and assumes ideal phase shift models, we investigate the entire process of data generation to arrival and propose a double-IRS cooperative scheme for data transmission with practical phase shift models in blocked wireless networks. The joint optimization problem of the long-term average AoI and node energy consumption is formulated. Given the nonconvexity of the joint optimization problem, we decompose it into an outer data transmission scheduling problem and an inner double-IRS phase shift optimization using a two-layer optimization framework. Then, we use the deep Q-network algorithm to solve the outer problem. For the inner problem, we propose a penalty-based alternating optimization (PB-AO) algorithm to solve the coupling between double-IRS phase shifts and the nonconvex constraints of practical phase shift models. The extensive simulation results verify the effectiveness of the proposed PB-AO algorithm in optimizing double-IRS phase shifts under the practical phase shift model and demonstrate the superiority of our double-IRS cooperative data transmission scheme compared with other benchmark ones.

关键词： Optimization Energy consumption Wireless networks sensors Data communication Heuristic algorithms Array signal processing Data models Job shop scheduling Wireless sensor networks Age of information (AoI) deep Q-network (DQN) intelligent reconfigurable surface (IRS) phase shift model wireless networks

来源：评论

学校读者我要写书评

暂无评论

ESMDP: Encrypted ML Framework for Secure Medical Data processing 3rd

ESMDP: Encrypted ML Framework for Secure Medical Data Proces...

引用

3rd International conference on Network Security and Blockchain Technology

作者： Reddy, B. Pradeep Kumar Chatterjee, Ayantika Indian Instutite Technol Kharagpur Kharagpur W Bengal India

ISBN: (纸本)9789819780501;9789819780518

In this age of Internet of Things (IoT), remote health monitoring and out-of-hospital treatment is not a distant dream. Wearable medical sensors and smartphones in the current IoT-driven environment allow for real-time monitoring of important health markers, with data quickly sent to distant specialists for analysis. Moreover, due to the onset of technological advancements like Electronic Health Records (EHR), IoT-enabled devices, Public Open health Data (POD), Linked Opened Data (LOD), remote health monitoring, vast quantities of information created in this domain as big data in health care. intelligent storage and analysis of this big data may lead to generate critical insights for future predictions. The storage challenge of big data can be mitigated by the use of cloud computing. However, processing of Personal Health information (PHI) on remote medical servers or cloud raises serious concern about the security of critical PHI. One immediate solution is for the information proprietors to transmit and store their delicate information in encrypted form. However, traditional encryption schemes do not support processing on that encrypted form of data. To take full advantage of cloud computing and outof-hospital treatment, there should be a solution to process on that encrypted form of data directly. In this paper, we propose a framework which supports secure data transmission from medical sensors to distant cloud server or remote medical organizations, secure processing on that data to provide distant medical treatments and perform secure machine learning-based analytics on such sensor-generated datasets. For this secure processing, we use Fully Homomorphic Encryption(FHE) scheme, which supports direct processing on encrypted data. Our implementation shows the proposed secure framework is capable of disease detection remotely in an encrypted domain confirming PHI data confidentiality. The framework also supports performing encrypted machine learning algorithm on clo

关键词： IoT Security eHealth Fully homomorphic encryption (FHE)

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Cooperation-Based Deep Reinforcement Learning for Multisensor Perception Communication System in HSR Tunnel Scenario

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2025年第3期73卷 1816-1832页

作者： Liu, Tanda Hu, Fengye Ling, Zhuang Li, Cheng Liang, Ying-Chang Jilin Univ Coll Commun Engn Changchun 130012 Peoples R China Mem Univ Dept Elect & Comp Engn St John NF A1B 3X5 Canada Mem Univ Dept Comp Sci St John NF A1B 3X5 Canada Univ Elect Sci & Technol China Ctr Intelligent Networking & Commun CINC Chengdu 611731 Peoples R China

The rapid development of High-Speed Railway (HSR) puts higher requirements on comprehensive perception and reliable transmission in tunnel scenarios. To realize efficient and reliable perception information transmission of HSR in the tunnel, we propose a multisensor perception communication system, which consists of an Access Point (AP) deployed on each carriage for perception information transmission and self-powered wireless sensors. The AP remote transmits the perception information through the leaky cable deployed in the tunnel. We construct an optimization problem for minimizing the transmission time of the whole system's perception information in the multi-network system and the adjacent area of the carriage. A Multi-Agent Cooperation-based Deep Reinforcement Learning (MA-CDRL) algorithm is proposed to get the optimal scheduling strategy for reducing the transmission time. We construct the CDRL neural network for the algorithm to introduce the states of other APs, resulting in the system making more efficient transmission strategies. In the simulations, the proposed algorithm gets a better performance than the comparison algorithms and is verified in various dynamic HSR scenarios, such as different travel speeds and sensor distributions.

关键词： sensors Wireless sensor networks Wireless communication Communication systems Optical fiber cables information processing Communication cables High-speed railway (HSR) tunnel scenario multisensor perception communication system multi-agent cooperation-based deep reinforcement learning (MA-CDRL)

来源：评论

学校读者我要写书评

暂无评论

Data collection of wireless sensor network based on trajectory optimization of laser-charged UAV

引用

High-Confidence Computing 2024年第2期4卷 116-128页

作者： Chuanwen Luo Jian Zhang Jin Qian Yi Hong Zhibo Chen Yunan Hou Xiujuan Zhang Yuqing Zhu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing 100083China College of Information Engineering Taizhou UniversityTaizhou 225300China School of Computer Science Qufu Normal UniversityRizhao 276826China Research Center of Applied Mathematics and Machine Intelligence Zhejiang LabHangzhou 311121China Department of Computer Science California State UniversityCA 90032USA

Unmanned Aerial Vehicle(UAV)can be used as wireless aerial mobile base station for collecting data from sensors in UAV-based Wireless sensor networks(WSNs),which is crucial for providing seamless services and improving the performance in the next generation wireless ***,since the UAV are powered by batteries with limited energy capacity,the UAV cannot complete data collection tasks of all sensors without energy replenishment when a large number of sensors are deployed over large monitoring *** overcome this problem,we study the Real-time Data Collection with Lasercharging UAV(RDCL)problem,where the UAV is utilized to collect data from a specified WSN and is recharged using Laser Beam Directors(LBDs).This problem aims to collect all sensory data from the WSN and transport it to the base station by optimizing the flight trajectory of UAV such that realtime data performance is ensured It has been proven that the RDCL problem is *** address this,we initially focus on studying two sub-problems,the Trajectory Optimization of UAV for Data Collection(TODC)problem and the Charging Trajectory Optimization of UAV(CTO)problem,whose objectives are to find the optimal flight plans of UAV in the data collection areas and charging areas,*** we propose an approximation algorithm to solve each of them with the constant ***,we present an approximation algorithm that utilizes the solutions obtained from TODC and CTO problems to address the RDCL ***,the proposed algorithm is verified by extensive simulations.

关键词： Wireless sensor networks Laser-charged UAV Trajectory optimization Data collection

来源：评论

学校读者我要写书评

暂无评论

Joint Sensing and processing Resource Allocation in Vehicular Ad-Hoc networks

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON intelligent VEHICLES 2023年第1期8卷 616-627页

作者： Chattopadhyay, Rajarshi Tham, Chen-Khong Natl Univ Singapore Dept Elect & Comp Engn Singapore 119077 Singapore

The performance of smart vehicle (SV) applications like autonomous driving and in-vehicle augmented reality based traffic information system depends on the Field of View (FoV) and the timely processing of the SVs sensor data. Vehicular networking (VN) technology can enhance the performance of these applications by enabling a SV to access the sensing and processing capabilities of other neighbouring SVs. The processing and storage capacity of a SV is limited compared to cloud servers and the communication link between two SVs is unreliable due to their mobility and the nature of wireless channels. Hence, developing efficient processing and sensing schemes for SVs and VNs can help in optimizing the performance of SV applications. In this paper, we propose Contextual Bandits (CB), Markov decision process (MDP) and deep Q-network (DQN) based sensing and processing schemes for VNs. Simulation results show that the proposed schemes outperform the baseline schemes in a variety of scenarios.

关键词： sensors Task analysis Wireless communication Mathematical models Data models Trajectory Markov processes Vehicular networks autonomous driving distributed sensing Markov decision process edge computing

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization Framework for Mobile Data Collection With Energy Harvesting in Duty-Cycle WSNs

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第7期10卷 6456-6473页

作者： Zhao, Duqiao Liu, Ding Cao, Xudong Xian Univ Technol Dept Control Sci & Control Engn Shaanxi Key Lab Complex Syst Control & Intelligent Xian 710048 Peoples R China

The increased dynamics and complexity of wireless sensor networks (WSNs) raise higher requirements on the flexibility and applicability of data collection algorithms. Therefore, a novel distributed optimization framework for data collection with energy harvesting in duty-cycle (DC) WSNs is developed in this article, which employs the mobile collector (called SenCar) to collect data from the selected sensors (called anchors) to circumvent the bottlenecks caused by the variations of energy distribution. In order to guarantee the optimality of mobile data collection, it is divided into two steps: first, a method for calculating the optimal number of anchors is developed and then an adaptive anchor selection algorithm is proposed to determine those anchors. Second, the mobile data collection problem of DC WSNs is formulated as a delay optimization problem constrained by flow conversation, congestion control, and energy balance. Then, we focus on designing the distributed algorithm to resolve that optimization problem, in which each sensor node only needs to communicate with its neighbors to make decisions without any global information and can locally adjust the information weight of its neighbors. Besides, the accelerated distributed algorithm with the uncoordinated step size is also proposed to improve the convergence rate. Furthermore, the explicit convergence analysis of the proposed algorithm is provided in this article. Finally, the numerical results show that our algorithm can quickly converge to the optimal solution and has obvious superiority in adjusting link flow, storing energy, and extending network lifetime.

关键词： Data collection Wireless sensor networks Energy harvesting Batteries Optimization Distributed databases Energy consumption Distributed optimization duty-cycle (DC) energy harvesting mobile data collection wireless sensor networks (WSNs)

来源：评论

学校读者我要写书评

暂无评论

LSTM-based post-processing for noise reduction in SVD-based particulate matter digital twinning on lightweight embedded devices

引用

ELECTRONICS LETTERS 2024年第4期60卷 e13132-e13132页

作者： Lee, Seungmin Park, Daejin Kyungpook Natl Univ Sch Elect Engn Daegu South Korea Kyungpook Natl Univ Sch Elect & Elect Engn Daegu South Korea

Among various applications of digital twins, measuring particulate matter in the context of air pollution has become increasingly important due to growing interest in atmospheric environments. By obtaining particle count values from analogue-to-digital converter raw data through photodiode and calibrating them, particulate matter values can be acquired. The singular-value-decomposition is efficient transfer function learning method. However, due to the linear nature of the transfer function of singular-value-decomposition, it also conveys noise information, necessitating post-processing to suppress noise. This study proposes a method that utilizes long short-term memory neural networks to effectively stabilize noise based on the output of continuous dust sensor particulate matter distributions. Using the singular value decomposition based particulate matter shows relative root-mean-square error (4.4761, 100%) as a reference, the proposed long short-term memory post-processing demonstrates an improved result (2.9328, 65.52%) compared to other post-processing method: the mean filter (3.6704, 82.00%), low-pass filter (3.7719, 84.27%) and Kalman filter (3.5550, 79.42%). Furthermore, to address the limitation of initial delay in long short-term memory to achieve stable data output, a method of iteratively training the initial input data sample is proposed. For the initial input data, the non-initialization approach exhibited a relative error of 87.57% and it took around 5 samples to predict stable output. In contrast, the proposed iterative training method, applied five times to the initial data sample, achieved a relative error of 9.51% and immediately obtained stable data. Concept of digital twin of dust sensing: (a) High-cost dust sensing system with single high-performance sensor, (b) low-cost dust sensing system with additional low-performance sensors, (c) proposed dust sensing system with low-performance sensor by replicating high-performance sensor. image

关键词： intelligent sensors measurement systems signal processing

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：