Adaptive software systems can assist in reducing food waste and improving food safety by enabling a real-time quality assessment. Such systems include sensors to monitor the food's condition and machine learning-b...
详细信息
ISBN:
(数字)9798350389760
ISBN:
(纸本)9798350389777
Adaptive software systems can assist in reducing food waste and improving food safety by enabling a real-time quality assessment. Such systems include sensors to monitor the food's condition and machine learning-based data analysis to predict the food's quality and shelf life. In particular, monitoring is challenging for several reasons, e.g., the complexity of the food supply chain and dynamically changing environments. Therefore, this work describes and discusses a self-adaptive monitoring system that locates food commodities and adjusts the monitoring activity accordingly to changes in the environment.
Mobile Edge computing (MEC) has been envisioned as a promising distributedcomputing paradigm, where mobile users offload their tasks to edge nodes to decrease the cost of energy and computation. However, most existin...
详细信息
ISBN:
(纸本)9781665449359
Mobile Edge computing (MEC) has been envisioned as a promising distributedcomputing paradigm, where mobile users offload their tasks to edge nodes to decrease the cost of energy and computation. However, most existing works only consider the congestion of wireless channels as the crucial factor influencing the strategy-making process, and ignore the impact of the offloading among edge nodes. In addition, centralized task offloading strategies result in heavy computation complexity in center nodes. Along this line, we take both the congestion of wireless channels and the offloading among multiple edge nodes into consideration to enrich users' offloading strategies. To this end, we first formulate the offloading problem as a multi-user potential game, and then propose a distributed task offloading algorithm to reach an equilibrium state which can also protect individual privacy. Specifically, in the above task offloading algorithm, we propose two subalgorithms to select users for updating strategies: Parallel User Selection Algorithm (PUS) and Single User Selection Algorithm (SUS) in order to substantially accelerate the convergence. Extensive experiments on three real-world data sets validate that the proposed algorithm achieves a Nash equilibrium and effectively decreases the total user cost which is acceptable compared to the optimal solution.
Implementing a wireless mesh network in a real-life scenario requires a significant systems engineering effort to turn a network concept into a complete system. This paper presents an evaluation of a fielded system wi...
详细信息
ISBN:
(数字)9781665495127
ISBN:
(纸本)9781665495134
Implementing a wireless mesh network in a real-life scenario requires a significant systems engineering effort to turn a network concept into a complete system. This paper presents an evaluation of a fielded system within the DARPA Subterranean (SubT) Challenge Final Event that contributed to a 3rd place finish. Our system included a team of air and ground robots, deployable mesh extender nodes, and a human operator base station. This paper presents a real-world evaluation of a stack optimized for air and ground robotic exploration in a RF-limited environment under practical system design limitations. Our highly customizable solution utilizes a minimum of non-free components with form factor options suited for UAV operations and provides insight into network operations at all levels. We present performance metrics based on our performance in the Final Event of the DARPA Subterranean Challenge, demonstrating the practical successes and limitations of our approach, as well as a set of lessons learned and suggestions for future improvements.
As deep learning grows rapidly, model training heavily relies on parallel methods and there exist numerous cluster configurations. However, current preferences for parallel training focus on data centers, overlooking ...
As deep learning grows rapidly, model training heavily relies on parallel methods and there exist numerous cluster configurations. However, current preferences for parallel training focus on data centers, overlooking the financial constraints faced by most researchers. To attain the best performance within the cost limitation, we introduce a throughput-cost metric to accurately characterize clusters' cost-effectiveness. Based on this metric, we design a cost-effective cluster featuring the 3090 with NVLink. The experiment results demonstrate that our cluster achieves remarkable cost-effectiveness in various distributed model training schemes.
Research conducted in LTE and 5G wireless communications systems uses common off-the-shelf hardware components and commercial software defined radio (SDR) hardware. One of the more popular SDR platforms is the Ettus U...
详细信息
ISBN:
(数字)9781665495127
ISBN:
(纸本)9781665495134
Research conducted in LTE and 5G wireless communications systems uses common off-the-shelf hardware components and commercial software defined radio (SDR) hardware. One of the more popular SDR platforms is the Ettus USRP product line which uses the UHD driver and transport protocol framework. System performance can be increased using kernel bypass frameworks along with UHD. This paper investigates UHD with DPDK in an SDR environment using srslTE as the SDR application. We present measurement results using the iperl3 network performance application that show performance improvements when employing a kernel bypass framework to facilitate data transfer over the network interface between the SDR application and the radio hardware.
In this paper, we consider the problem of designing a novel ATTack scheme under charger cApture attaCK(ATTACK) in wireless rechargeable sensor networks. That is, there are a number of wireless chargers with directiona...
详细信息
ISBN:
(纸本)9781728143514
In this paper, we consider the problem of designing a novel ATTack scheme under charger cApture attaCK(ATTACK) in wireless rechargeable sensor networks. That is, there are a number of wireless chargers with directional antenna and rechargeable directional devices deployed in the 2D plane. An intelligent adversary selects a limited number of chargers to be captured and adjust the compromised chargers' power factor such that the overall attacking utility of devices is maximized. To solve our ATTACK problem, we investigate an attacking algorithm with a constant approximation ratio with lightweight timing complexity. We conduct simulation experiments to verify the performance of our proposed attacking algorithm. The results shows that our proposed attacking algorithm can outperform the comparison algorithm by 69.95%.
This paper proposes a remote monitoring and decision-making system for intelligent ships based on edge computing and distributed algorithms. Relying on the high bandwidth and low latency characteristics of 5 G communi...
详细信息
ISBN:
(数字)9798350389418
ISBN:
(纸本)9798350389425
This paper proposes a remote monitoring and decision-making system for intelligent ships based on edge computing and distributed algorithms. Relying on the high bandwidth and low latency characteristics of 5 G communication, real-time data processing and remote monitoring of ship operation status are realized. The system localizes a large amount of sensor data through edge computing, and combines distributed algorithms to improve data fusion and decisionmaking efficiency. Data transmission supported by 5G communication provides technical guarantee for seamless connection between ships and shore-based monitoring centers. Through real-time analysis of ship sensor data, the system can predict potential faults and optimize navigation strategies. Model simulation results show that the distributed algorithm based on edge computing has significant advantages in improving data processing speed, reducing decision response time by 15% and improving monitoring accuracy by 8.5%. This study provides technical support for remote monitoring and autonomous decision-making of intelligent ships, and verifies the broad application prospects of $\mathbf{5 G}$ communication in the field of maritime communications.
In recent years, many educational institutions have adopted information systems such as e-Learning platforms and groupware. However, these existing information systems often have significant installation, operation, a...
In recent years, many educational institutions have adopted information systems such as e-Learning platforms and groupware. However, these existing information systems often have significant installation, operation, and maintenance costs. Moreover, on-premise systems require expensive servers and cloud computingsystems can accumulate high maintenance expenses. To address this issue, we have proposed that utilizes idle resources (idle computers) in an organization's information system. One of the characteristics of idle computers is that communication lines can be connected or disconnected at arbitrary times according to the operations of the original users. In general, the distributed system uses an idle computer as an unstable resource. However, our proposed system requires tolerating them as normal behaviors, and it requires a test environment for this problem. In this paper, we propose a load-testing environment to use idle computers having unstable behaviors in a distributed system. We also implemented and applied the proposed environment to a distributed e-Learning system. The result shows efficiency in showing behavior of unstable behaviors of idle computers to developers.
The sensor Sharing Marketplace (SenShaMart) enables IoT applications to find IoT sensors, which are owned and managed by other parties, integrate them, and pay for using their data. To provide corresponding services t...
The sensor Sharing Marketplace (SenShaMart) enables IoT applications to find IoT sensors, which are owned and managed by other parties, integrate them, and pay for using their data. To provide corresponding services that implement that FAIR (Findable, Accessible, Interoperable, Reusable) principles of IoT, SenShaMart incorporates a specialized blockchain that manages all the information its services need to allow different parties in IoT to describe, query, integrate, pay for, and use IoT sensors and their data. The paper presents the SenShaMart's architecture, implementation, evaluation, and demonstration.
With the rapid development of sensor technology and Internet technology, the amount of data collected in meteorological and scientific fields has soared. The data stored in NetCDF format is faced with the challenges o...
详细信息
ISBN:
(数字)9798350388077
ISBN:
(纸本)9798350388084
With the rapid development of sensor technology and Internet technology, the amount of data collected in meteorological and scientific fields has soared. The data stored in NetCDF format is faced with the challenges of being damaged, difficult to recover, and frequent calls to disk resources. Although Hadoop distributed storage solutions have obvious advantages, HDFS based file system tools cannot be directly used for data processing due to their lack of support for the NetCDF format. Therefore, this article delves into the storage and write mechanism and block architecture of HDFS, and extends the read and write interface of NetCDF data to improve data portability, access efficiency, and sharing convenience, thereby providing strong support for scientific computing.
暂无评论