Estimating Missing Information by Cluster Analysis and Normalized Convolution

Guastella, Davide Andrea; Valenti, Cesare

doi:10.1109/rtsi.2018.8548454

Cited by 6 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computation is done close to sensors which acquired information from a direct observation of the physical environment. Figure 1 shows the main steps of our methodology, which is based on two types of agents: • type 1 has fixed perceiving devices and it is associated to a Voronoi region which delimits the rough relevance area of the devices [18]; • type 2 has devices not capable of perceiving the environment for some reason and it needs to cooperate with close working devices to provide information [14].…”

Section: Multi-agent Systems For Edge-based Data Imputationmentioning

confidence: 99%

Edge-Based Missing Data Imputation in Large-Scale Environments

2021

Self Cite

View full text Add to dashboard Cite

Smart cities leverage large amounts of data acquired in the urban environment in the context of decision support tools. These tools enable monitoring the environment to improve the quality of services offered to citizens. The increasing diffusion of personal Internet of things devices capable of sensing the physical environment allows for low-cost solutions to acquire a large amount of information within the urban environment. On the one hand, the use of mobile and intermittent sensors implies new scenarios of large-scale data analysis; on the other hand, it involves different challenges such as intermittent sensors and integrity of acquired data. To this effect, edge computing emerges as a methodology to distribute computation among different IoT devices to analyze data locally. We present here a new methodology for imputing environmental information during the acquisition step, due to missing or otherwise out of order sensors, by distributing the computation among a variety of fixed and mobile devices. Numerous experiments have been carried out on real data to confirm the validity of the proposed method.

show abstract

Section: Multi-agent Systems For Edge-based Data Imputationmentioning

confidence: 99%

Edge-Based Missing Data Imputation in Large-Scale Environments

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…We used a dataset containing real environmental information acquired in the Emilia Romagna region in Italy [21]. In Emilia Romagna region, the prevailing climate is temperate subcontinental, with hot and humid summers followed by cold and harsh winters.…”

Section: A Datasetmentioning

confidence: 99%

“…Fig. 5 shows the distribution of mean temperature values for the first version of the dataset, obtained through a standard normalized convolution: this is a non-direct methodology widely used for filtering incomplete or uncertain data which is based on the separation of both data and operator into a signal part and a certainty part [21]. Fig.…”

Section: A Datasetmentioning

confidence: 99%

“…We compared the results of the endogenous estimation scheme to a pipeline of standard techniques using the same dataset and cross-validation [21]. This pipeline includes Voronoi tessellation to determine the geographical area to which sensors belong, hierarchical clustering to group the sensors that perceive similar information and normalized convolution to estimate missing information.…”

Section: ) Comparison To the State Of The Artmentioning

confidence: 99%

See 1 more Smart Citation

A Cooperative Multi-Agent System for Crowd Sensing Based Estimation in Smart Cities

2020

Self Cite

View full text Add to dashboard Cite

The concept of Smart City has spread as a solution to ensure better access to information and services to citizens, but also as a means to reduce the environmental footprint of cities. To this end, a continuous and wide observation of the environment is necessary to analyze information that enables government bodies to act on the environment appropriately. Moreover, a diffused acquisition of information requires adequate infrastructure and proper devices, which results in relevant installation and maintenance costs. Our proposal enables reducing the number of necessary sensors to be deployed while ensuring that information is available at any time and anywhere. We present the HybridIoT system to cope with the lack of environmental information in the urban context through an estimation technique that integrates heterogeneous data acquired from some different sensors. HybridIoT can be deployed in large-scale contexts and ensures data accessibility even if devices enter or leave the system at any time and everywhere. We compare the results to those obtained by state-of-the-art techniques to assess the validity of our proposal, in particular concerning the properties of openness, large-scale, and heterogeneity, of primary importance in the context of the development of systems to be deployed in the smart city context.

show abstract

“…In this case, it is necessary to provide accurate estimation of the values that ambient devices would provide if they were available. These estimations must be provided at real-time so that users can access to the information at any time [7]. In fact, a continuous monitoring of the environment can be useful when conceiving system to support smart city initiatives [6].…”

Section: Introductionmentioning

confidence: 99%

Estimating Missing Environmental Information by Contextual Data Cooperation

Guastella

Camps

Gleizes

2019

PRIMA 2019: Principles and Practice of Multi-Agent Systems

Self Cite

View full text Add to dashboard Cite

The quality of life of users and energy consumption could be optimized by a complex network of sensors. Nevertheless, smart environments depend on their size, so it is expensive to provide enough sensors at low cost to monitor each part of the environment. We propose a cooperative multi-agent solution to estimate missing environmental information in smart environment when no ad-hoc sensors are available. We evaluated our proposal on a real dataset and compared the results to standard state-of-the-art solutions.

show abstract

Estimating Missing Information by Cluster Analysis and Normalized Convolution

Cited by 6 publications

References 30 publications

Edge-Based Missing Data Imputation in Large-Scale Environments

Edge-Based Missing Data Imputation in Large-Scale Environments

A Cooperative Multi-Agent System for Crowd Sensing Based Estimation in Smart Cities

Estimating Missing Environmental Information by Contextual Data Cooperation

Contact Info

Product

Resources

About