An IoT-based task scheduling optimization scheme considering the deadline and cost-aware scientific workflow for cloud computing

Ma, Xiaojin; Gao, Honghao; Xu, Huahu; Bian, Minjie

doi:10.1186/s13638-019-1557-3

Cited by 122 publications

(72 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CoAP is designed to support application in resource-based web services with simple methods like Get, Put, Post and Delete, typical from HTTP, but simple enough for monitoring application through constrained devices [65]. Scheduling algorithms like the one offered in [66] for cloud services are not considered in this work. The above-described protocols are all designed to achieve the lower communication time for devices allowing the system to use the minimum transmission power and maximizing the system throughput.…”

Section: A Network Descriptionmentioning

confidence: 99%

System Assessment of WUSN Using NB-IoT UAV-Aided Networks in Potato Crops

et al. 2020

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAV) are part of precision agriculture; also, their impact on fast deployable wireless communication is offering new solutions and systems never envisioned before such as collecting information from underground sensors by using low power Internet of Things (IoT) technologies. In this paper, we propose a (Narrow Band IoT) NB-IoT system for collecting underground soil parameters in potato crops using a UAV-aided network. To this end, a simulation tool implementing a gateway mounted on a UAV using NB-IoT based access network and LTE based backhaul network is developed. This tool evaluates the performance of a realistic scenario in a potato field near Bogota, Colombia, accounting for real size packets in a complete IoT application. While computing the wireless link quality, it allocates access and backhaul resources simultaneously based on the technologies used. We compare the performance of wireless underground sensors buried in dry and wet soils at four different depths. Results show that a single drone with 50 seconds of flight time could satisfy more than 2000 sensors deployed in a 20 hectares field, depending on the buried depth and soil characteristics. We found that an optimal flight altitude is located between 60 m and 80 m for buried sensors. Moreover, we establish that the water content reduces the maximum reachable buried depth from 70 cm in dry soils, down to 30 cm in wet ones. Besides, we found that in the proposed scenario, sensors' battery life could last up to 82 months for above ground sensors and 77 months for the deepest buried ones. Finally, we discuss the influence of the sensor's density and buried depth, the flight service time and altitude in power-constrained conditions and we propose optimal configuration to improve system performance. INDEX TERMS Precision agriculture, NB-IoT, unmanned aerial vehicles, wireless underground sensor networks.

show abstract

Section: A Network Descriptionmentioning

confidence: 99%

System Assessment of WUSN Using NB-IoT UAV-Aided Networks in Potato Crops

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Attention mechanisms have achieved immense success in speech recognition, computer vision, natural language processing and exploration of the hierarchical attention mechanism [1,2,22,31,35,37]. The key idea of soft attention is to learn to assign attentive weights (normalized by summing to 1) for a set of features: higher (lower) weights indicate that the corresponding features are informative (less informative) for the end task, which learns and determines the focus areas and enables the model to focus on the most effective information with limited resources.…”

Section: Related Workmentioning

confidence: 99%

A recommendations model with multiaspect awareness and hierarchical user-product attention mechanisms

Dou

Liu

et al. 2020

ComSIS

View full text Add to dashboard Cite

Neural network methods have been trained to satisfactorily learn user/product representations from textual reviews. A representation can be considered as a multiaspect attention weight vector. However, in several existing methods, it is assumed that the user representation remains unchanged even when the user interacts with products having diverse characteristics, which leads to inaccurate recommendations. To overcome this limitation, this paper proposes a novel model to capture the varying attention of a user for different products by using a multilayer attention framework. First, two individual hierarchical attention networks are used to encode the users and products to learn the user preferences and product characteristics from review texts. Then, we design an attention network to reflect the adaptive change in the user preferences for each aspect of the targeted product in terms of the rating and review. The results of experiments performed on three public datasets demonstrate that the proposed model notably outperforms the other state-of-the-art baselines, thereby validating the effectiveness of the proposed approach.

show abstract

“…Hamming-loss [27], Micro-F1 [28] and Macro-averaging are used indicators in multilabel classification tasks [29].…”

Section: Evaluation Metricsmentioning

confidence: 99%

VDRF: Sensing the defect information to risk level of vehicle recall based on bert communication model

You

Zhang

et al. 2020

COMSIS J

View full text Add to dashboard Cite

The recall of defective automobile products is one of the important measures to promote the quality of product quality and protect consumers' pyhsical safety and property security. In order to assess the risk level of defect cases, automobile recall management experts need to analyze and discuss the defect information by personal. A risk level prediction method based on language pre-training Bert model is proposed in this paper, which can transform the defect information into rick level of the vehicle and then predict vehicle recall automatically, in which a seq2seq model is proposed to multi-label the vehicle complaint data. The outputs of the seq2seq model combined with other static and dynamic information are used as the input of the Bert communication model. Substantial comparative experiments of different feature combinations on different methods show that the proposed VDRF method achieves F1 value with 79% in vehicle recall risk prediction, which outperforms the traditional method.

show abstract

An IoT-based task scheduling optimization scheme considering the deadline and cost-aware scientific workflow for cloud computing

Cited by 122 publications

References 44 publications

System Assessment of WUSN Using NB-IoT UAV-Aided Networks in Potato Crops

System Assessment of WUSN Using NB-IoT UAV-Aided Networks in Potato Crops

A recommendations model with multiaspect awareness and hierarchical user-product attention mechanisms

VDRF: Sensing the defect information to risk level of vehicle recall based on bert communication model

Contact Info

Product

Resources

About