scholarly journals Spiking Neural Network-Based Near-Sensor Computing for Damage Detection in Structural Health Monitoring

2021 ◽  
Vol 13 (8) ◽  
pp. 219
Author(s):  
Francesco Barchi ◽  
Luca Zanatta ◽  
Emanuele Parisi ◽  
Alessio Burrello ◽  
Davide Brunelli ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Damage Detection ◽  
Execution Time ◽  
Sensor Node ◽  
Data Transfer ◽  
Low Cost ◽  
Access Time ◽  
Virtual Sensors ◽  
The Impact ◽  
Spi Interface

In this work, we present an innovative approach for damage detection of infrastructures on-edge devices, exploiting a brain-inspired algorithm. The proposed solution exploits recurrent spiking neural networks (LSNNs), which are emerging for their theoretical energy efficiency and compactness, to recognise damage conditions by processing data from low-cost accelerometers (MEMS) directly on the sensor node. We focus on designing an efficient coding of MEMS data to optimise SNN execution on a low-power microcontroller. We characterised and profiled LSNN performance and energy consumption on a hardware prototype sensor node equipped with an STM32 embedded microcontroller and a digital MEMS accelerometer. We used a hardware-in-the-loop environment with virtual sensors generating data on an SPI interface connected to the physical microcontroller to evaluate the system with a data stream from a real viaduct. We exploited this environment also to study the impact of different on-sensor encoding techniques, mimicking a bio-inspired sensor able to generate events instead of accelerations. Obtained results show that the proposed optimised embedded LSNN (eLSNN), when using a spike-based input encoding technique, achieves 54% lower execution time with respect to a naive LSNN algorithm implementation present in the state-of-the-art. The optimised eLSNN requires around 47 kCycles, which is comparable with the data transfer cost from the SPI interface. However, the spike-based encoding technique requires considerably larger input vectors to get the same classification accuracy, resulting in a longer pre-processing and sensor access time. Overall the event-based encoding techniques leads to a longer execution time (1.49×) but similar energy consumption. Moving this coding on the sensor can remove this limitation leading to an overall more energy-efficient monitoring system.

Impact of Duty-Cycling

2020 ◽  
pp. 1557-1579
Author(s):  
Nassima Bouadem ◽  
Rahim Kacimi ◽  
Abdelkamel Tari
Keyword(s):  
Sensor Node ◽  
Low Cost ◽  
Research Topic ◽  
Wireless Sensor ◽  
Energy Availability ◽  
Duty Cycling ◽  
Save Energy ◽  
Fruitful Research ◽  
The Impact

Wireless Sensor Networks (WSNs) became omnipresent in our daily life. As a result, they have emerged as a fruitful research topic, because of their advantages, especially their low cost and easy deployment. However, these attractive merits imply that available resources, especially energy, in each sensor node have to be wisely used through different network dynamics. Beside other techniques, duty-cycling (DC) is the first widely used one to save energy in WSNs. However, due to the continuous changes, mainly in the energy availability, the nodes have to operate in a very low DC which is a required strategy in many applications in order to keep the network operational. This article presents a detailed survey that provides an interesting view of different DC schemes which are proposed to tackle the specific WSN challenges, and it also gives a novel classification of DC schemes that includes the most recent techniques. The last part aims to investigate the impact of the low DC on both the network and the application layer.

scholarly journals Energy-aware adaptive offloading of soft real-time jobs in mobile edge clouds

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Joaquim Silva ◽  
Eduardo R. B. Marques ◽  
Luís M.B. Lopes ◽  
Fernando Silva
Keyword(s):  
Energy Consumption ◽  
Real Time ◽  
Execution Time ◽  
Computation Offloading ◽  
Energy Aware ◽  
Available Bandwidth ◽  
Adaptive Computation ◽  
Cloud Servers ◽  
Cloud Infrastructures ◽  
The Impact

AbstractWe present a model for measuring the impact of offloading soft real-time jobs over multi-tier cloud infrastructures. The jobs originate in mobile devices and offloading strategies may choose to execute them locally, in neighbouring devices, in cloudlets or in infrastructure cloud servers. Within this specification, we put forward several such offloading strategies characterised by their differential use of the cloud tiers with the goal of optimizing execution time and/or energy consumption. We implement an instance of the model using Jay, a software framework for adaptive computation offloading in hybrid edge clouds. The framework is modular and allows the model and the offloading strategies to be seamlessly implemented while providing the tools to make informed runtime offloading decisions based on system feedback, namely through a built-in system profiler that gathers runtime information such as workload, energy consumption and available bandwidth for every participating device or server. The results show that offloading strategies sensitive to runtime conditions can effectively and dynamically adjust their offloading decisions to produce significant gains in terms of their target optimization functions, namely, execution time, energy consumption and fulfilment of job deadlines.

scholarly journals Damage Detection and Localization from Dense Network of Strain Sensors

2016 ◽  
Vol 2016 ◽  
pp. 1-13 ◽  
Author(s):  
Simon Laflamme ◽  
Liang Cao ◽  
Eleni Chatzi ◽  
Filippo Ubertini
Keyword(s):  
Damage Detection ◽  
Damage Identification ◽  
Low Cost ◽  
Strain Sensors ◽  
Dense Network ◽  
Virtual Sensors ◽  
Large Structures ◽  
Complex Engineering ◽  
Detection And Localization

Structural health monitoring of large systems is a complex engineering task due to important practical issues. When dealing with large structures, damage diagnosis, localization, and prognosis necessitate a large number of sensors, which is a nontrivial task due to the lack of scalability of traditional sensing technologies. In order to address this challenge, the authors have recently proposed a novel sensing solution consisting of a low-cost soft elastomeric capacitor that transduces surface strains into measurable changes in capacitance. This paper demonstrates the potential of this technology for damage detection, localization, and prognosis when utilized in dense network configurations over large surfaces. A wind turbine blade is adopted as a case study, and numerical simulations demonstrate the effectiveness of a data-driven algorithm relying on distributed strain data in evidencing the presence and location of damage, and sequentially ranking its severity. Numerical results further show that the soft elastomeric capacitor may outperform traditional strain sensors in damage identification as it provides additive strain measurements without any preferential direction. Finally, simulation with reconstruction of measurements from missing or malfunctioning sensors using the concepts of virtual sensors and Kriging demonstrates the robustness of the proposed condition assessment methodology for sparser or malfunctioning grids.

scholarly journals Passive Strategies to Improve the Comfort Conditions in a Geodesic Dome

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 663
Author(s):  
Frank Florez ◽  
Pedro Fernández de Córdoba ◽  
John Taborda ◽  
Juan Carlos Castro-Palacio ◽  
José Luis Higón-Calvet ◽  
...  
Keyword(s):  
Mathematical Model ◽  
Energy Consumption ◽  
Low Cost ◽  
Internal Temperature ◽  
Lumped Parameter ◽  
Principal Factors ◽  
Passive Strategies ◽  
The Impact ◽  
The Mathematical Model ◽  
Geodesic Dome

Non-conventional thermal zones are low-cost and ecology friendly alternatives to the housing needs of populations in various situations, such as surviving natural disasters or addressing homelessness. However, it is necessary to guarantee thermal comfort for occupants, while aiming to minimize energy consumption and wastage in refrigeration systems. To reduce the cooling requirements in non-conventional thermal zones it is necessary to model the structure and analyze the principal factors contributing to internal temperature. In this paper, a geodesic dome is modellingusing the lumped parameter technique. This structure is composed of a wooden skeleton and wooden floor, with a canvas surface as its exterior. The mathematical model was tuned using experimental data, and its parameters were classified using Monte Carlo sensitivity analysis. The mathematical model was used to evaluate the impact on internal temperature and occupants’ comfort when two strategies are considered. The results obtained indicatee internal temperature reductions down to a range of 7% to 11%; this result is reflected directly in the energy used to refrigerate the thermal zone, contributing to the objective of providing houses with lower energy consumption.

On the Efficiency of Querying and Storing RDF Documents

2011 ◽  
pp. 354-385
Author(s):  
Maria-Esther Vidal ◽  
Amadís Martínez ◽  
Edna Ruckhaus ◽  
Tomas Lampo ◽  
Javier Sierra
Keyword(s):  
Query Processing ◽  
Execution Time ◽  
Time Complexity ◽  
Low Cost ◽  
Data Access ◽  
Optimization Techniques ◽  
Experimental Results ◽  
Access Time ◽  
Alternative Representation ◽  
Rdf Data

In the context of the Semantic Web, different approaches have been defined to represent RDF documents, and the selected representation affects storage and time complexity of the RDF data recovery and query processing tasks. This chapter addresses the problem of efficiently querying and storing RDF documents, and presents an alternative representation of RDF data, Bhyper, which is based on hypergraphs. Additionally, access and optimization techniques to efficiently execute queries with low cost, are defined on top of this hypergraph based representation. The chapter’s authors have empirically studied the performance of the Bhyper based techniques, and their experimental results show that the proposed hypergraph based formalization reduces the RDF data access time as well as the space needed to store the Bhyper structures, while the query execution time of state-the-of-art RDF engines can be sped up by up to two orders of magnitude.

scholarly journals Energy consumption of mobile data transfer – Increasing or decreasing? Evaluating the impact of technology development & user behavior

10.29007/ddrc ◽  
2018 ◽  
Author(s):  
Hanna Pihkola ◽  
Mikko Hongisto ◽  
Olli Apilo ◽  
Mika Lasanen ◽  
Saija Vatanen
Keyword(s):  
Energy Consumption ◽  
Consumer Behavior ◽  
Mobile Networks ◽  
Energy Demand ◽  
Energy Use ◽  
Data Transfer ◽  
Continuous Growth ◽  
Mobile Data ◽  
Trade Offs ◽  
The Impact

Mobile data consumption in Finland is among the highest in the world. Increase in mobile data usage has been rapid and continuous growth is foreseen. While the energy consumed per transmitted gigabyte has substantially decreased, it seems that the absolute annual energy consumption related to mobile operators’ activities has started to increase. Simultaneously, consumer behavior is changing. While new end-user devices are more and more energy-efficient, we use more and more time with mobile devices. Is increasing usage outweighing achieved energy savings? What kinds of options are available for tackling increasing energy demand?This paper discusses current and future trends related to energy consumption of mobile data transfer and mobile networks in Finland. Using a top-down approach and publicly available data, an illustrative trend (kWh/gigabyte) for the energy consumption of transmitted mobile data was constructed for the years 2010-2016. In addition, energy consumption related to mobile data transfer is discussed from a life cycle perspective, considering both direct and indirect energy use and challenges in conducting such assessments. Contributions of relevant technological and social developments (radio network technology transformations from 4G to 5G and consumer behavior) are analyzed considering possible trade-offs and pointing out aspects that require future studies.

scholarly journals Sensor Fusion and Convolutional Neural Networks for Indoor Occupancy Prediction Using Multiple Low-Cost Low-Resolution Heat Sensor Data

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1036
Author(s):  
Simon Arvidsson ◽  
Marcus Gullstrand ◽  
Beril Sirmacek ◽  
Maria Riveiro
Keyword(s):  
Energy Consumption ◽  
Low Cost ◽  
Sensor Data ◽  
Low Resolution ◽  
Real Time Processing ◽  
Privacy Concerns ◽  
Sensor Field ◽  
Heat Sensor ◽  
Occupancy Prediction ◽  
The Impact

Indoor occupancy prediction is a prerequisite for the management of energy consumption, security, health, and other systems in smart buildings. Previous studies have shown that buildings that automatize their heating, lighting, air conditioning, and ventilation systems through considering the occupancy and activity information might reduce energy consumption by more than 50%. However, it is difficult to use high-resolution sensors and cameras for occupancy prediction due to privacy concerns. In this paper, we propose a novel solution for predicting occupancy using multiple low-cost and low-resolution heat sensors. We suggest two different methods for fusing and processing the data captured from multiple heat sensors and we use a Convolutional Neural Network for predicting occupancy. We conduct experiments to assess both the performance of the proposed solutions and analyze the impact of sensor field view overlaps on the prediction results. In summary, our experimental results show that the implemented solutions show high occupancy prediction accuracy and real-time processing capabilities.

Sign in / Sign up

Export Citation Format

Share Document