scholarly journals Low-Cost Distributed Acoustic Sensor Network for Real-Time Urban Sound Monitoring

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2119
Author(s):  
Ester Vidaña-Vila ◽  
Joan Navarro ◽  
Cristina Borda-Fortuny ◽  
Dan Stowell ◽  
Rosa Ma Alsina-Pagès
Keyword(s):  
Real Time ◽  
Sensor Network ◽  
Large Scale ◽  
Learning Algorithm ◽  
Low Cost ◽  
Individual Performance ◽  
Sound Recognition ◽  
Continuous Exposure ◽  
Acoustic Sensor ◽  
Deep Learning Algorithm

Continuous exposure to urban noise has been found to be one of the major threats to citizens’ health. In this regard, several organizations are devoting huge efforts to designing new in-field systems to identify the acoustic sources of these threats to protect those citizens at risk. Typically, these prototype systems are composed of expensive components that limit their large-scale deployment and thus reduce the scope of their measurements. This paper aims to present a highly scalable low-cost distributed infrastructure that features a ubiquitous acoustic sensor network to monitor urban sounds. It takes advantage of (1) low-cost microphones deployed in a redundant topology to improve their individual performance when identifying the sound source, (2) a deep-learning algorithm for sound recognition, (3) a distributed data-processing middleware to reach consensus on the sound identification, and (4) a custom planar antenna with an almost isotropic radiation pattern for the proper node communication. This enables practitioners to acoustically populate urban spaces and provide a reliable view of noises occurring in real time. The city of Barcelona (Spain) and the UrbanSound8K dataset have been selected to analytically validate the proposed approach. Results obtained in laboratory tests endorse the feasibility of this proposal.

scholarly journals FIWARE based low-cost wireless acoustic sensor network for monitoring and classification of urban soundscape

2021 ◽  
pp. 108199
Author(s):  
Pau Arce ◽  
David Salvo ◽  
Gema Piñero ◽  
Alberto Gonzalez
Keyword(s):  
Sensor Network ◽  
Low Cost ◽  
Acoustic Sensor

scholarly journals Research on Efficient Deep Learning Algorithm Based on ShuffleGhost in the Field of Virtual Reality

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Bangtong Huang ◽  
Hongquan Zhang ◽  
Zihong Chen ◽  
Lingling Li ◽  
Lihua Shi
Keyword(s):  
Virtual Reality ◽  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
Feature Maps ◽  
Embedded Devices ◽  
Feature Map ◽  
Deep Learning Algorithm ◽  
Proper Design ◽  
The Cost

Deep learning algorithms are facing the limitation in virtual reality application due to the cost of memory, computation, and real-time computation problem. Models with rigorous performance might suffer from enormous parameters and large-scale structure, and it would be hard to replant them onto embedded devices. In this paper, with the inspiration of GhostNet, we proposed an efficient structure ShuffleGhost to make use of the redundancy in feature maps to alleviate the cost of computations, as well as tackling some drawbacks of GhostNet. Since GhostNet suffers from high computation of convolution in Ghost module and shortcut, the restriction of downsampling would make it more difficult to apply Ghost module and Ghost bottleneck to other backbone. This paper proposes three new kinds of ShuffleGhost structure to tackle the drawbacks of GhostNet. The ShuffleGhost module and ShuffleGhost bottlenecks are utilized by the shuffle layer and group convolution from ShuffleNet, and they are designed to redistribute the feature maps concatenated from Ghost Feature Map and Primary Feature Map. Besides, they eliminate the gap of them and extract the features. Then, SENet layer is adopted to reduce the computation cost of group convolution, as well as evaluating the importance of the feature maps which concatenated from Ghost Feature Maps and Primary Feature Maps and giving proper weights for the feature maps. This paper conducted some experiments and proved that the ShuffleGhostV3 has smaller trainable parameters and FLOPs with the ensurance of accuracy. And with proper design, it could be more efficient in both GPU and CPU side.

scholarly journals A Wireless Sensor Network Model for E-Metering and Fault Identification in Smart Water Distribution Systems

2019 ◽  
Vol 8 (10S) ◽  
pp. 227-232
Keyword(s):  
Wireless Sensor Network ◽  
Real Time ◽  
Sensor Network ◽  
Network Model ◽  
Distribution System ◽  
Water Distribution ◽  
Large Scale ◽  
Water Distribution System ◽  
Wireless Sensor ◽  
Smart Water

Water distribution system is a network that supplies water to all the consumers through different means. Proper means of providing water to houses without compromising in quantity and quality is always a challenge. As it is a huge network keeping track of the utilization is difficult for the utility. Hence through this project we come up with a solution to solve this issue. Current technologies like Low Power Wide Area Networks, LoRa and sensor deployment techniques have been in research and were also tested in few rural areas but issues due to hardware deployment and large scale real time implementation was a challenge hence through this system we aim to create and simulate a real time scenario to test a sensor network model that could be implemented in large scale further. This project aims in building a wireless sensor network model for a smart water distribution system. In this system there is bidirectional communication between the consumer and the utility. Each house has a meter through which the amount of water consumed is sent to the utility board. The data has two fields containing the house ID and the data (water consumed); it is being sent to the data collection unit (DCU) which in-turn sends it to the central server so that the consumption is monitored in real time. All this is simulated using NETSIM and MATLAB.

Day-to-day variations in paddy-residue burning and residential heating emissions control aerosol pollution peaks in rural north-west India

2021 ◽  
Author(s):  
Harshita Pawar ◽  
Baerbel Sinha
Keyword(s):  
Air Quality ◽  
Large Scale ◽  
Learning Algorithm ◽  
Low Cost ◽  
Winter Season ◽  
Ambient Air ◽  
Rural Site ◽  
North West ◽  
Daily Average ◽  
Residential Heating

<p>November onwards, the poor air quality over north-west India is blamed on the large-scale paddy residue burning in Punjab and Haryana. However, the emission strength of this source remains poorly constrained due to the lack of ground-based measurements within the rural source regions. In this study, we report the particulate matter (PM) levels at Nadampur, a rural site in the Sangrur district of Punjab that witnesses rampant paddy residue burning, using the Airveda low-cost PM sensors from October to December 2019. The raw PM measurements from the sensor were corrected using the Random Forest machine learning algorithm. The daily average PM<sub>10</sub> and PM<sub>2.5</sub> mass concentration at Nadampur correlated well  (r > 0.7) with the daily sum of VIIRS fire counts. Agricultural activities, including paddy residue burning and harvesting operations, contributed less than 40% to the overall PM loading, even in the peak burning period at Nadampur. We show that the increased residential heating emissions in the winter season have a profound and currently neglected impact on ambient air quality. A dip in the daily average temperature by 1 ºC increased the daily emission of PM<sub>10</sub> by 6.3 tonnes and that of PM<sub>2.5</sub> by 5.8 tonnes. Overall, paddy harvest, local and regional paddy residue burning, residential heating emissions, ventilation, and wet scavenging could explain 79% of the variations in PM<sub>10</sub> and 85% of the variations in PM<sub>2.5</sub>. Day to day variations in PM emissions from residential heating in response to the ambient temperature must be incorporated into emission inventories and models for accurate air quality forecasts.</p>

scholarly journals Low-Cost IoT Remote Sensor Mesh for Large-Scale Orchard Monitorization

2020 ◽  
Vol 9 (3) ◽  
pp. 44
Author(s):  
Leonor Varandas ◽  
João Faria ◽  
Pedro Gaspar ◽  
Martim Aguiar
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Low Cost ◽  
Experimental Tests ◽  
Remote Measurement ◽  
Land Protection ◽  
Remote Monitoring System ◽  
Solar Powered ◽  
The Individual ◽  
System Nodes

Population growth and climate change lead agricultural cultures to face environmental degradation and rising of resistant diseases and pests. These conditions result in reduced product quality and increasing risk of harmful toxicity to human health. Thus, the prediction of the occurrence of diseases and pests and the consequent avoidance of the erroneous use of phytosanitary products will contribute to improving food quality and safety and environmental land protection. This study presents the design and construction of a low-cost IoT sensor mesh that enables the remote measurement of parameters of large-scale orchards. The developed remote monitoring system transmits all monitored data to a central node via LoRaWAN technology. To make the system nodes fully autonomous, the individual nodes were designed to be solar-powered and to require low energy consumption. To improve the user experience, a web interface and a mobile application were developed, which allow the monitored information to be viewed in real-time. Several experimental tests were performed in an olive orchard under different environmental conditions. The results indicate an adequate precision and reliability of the system and show that the system is fully adequate to be placed in remote orchards located at a considerable distance from networks, being able to provide real-time parameters monitoring of both tree and the surrounding environment.

scholarly journals A deep learning view of the census of galaxy clusters in IllustrisTNG

2020 ◽  
Vol 498 (4) ◽  
pp. 5620-5628
Author(s):  
Y Su ◽  
Y Zhang ◽  
G Liang ◽  
J A ZuHone ◽  
D J Barnes ◽  
...  
Keyword(s):  
Deep Learning ◽  
Galaxy Clusters ◽  
Large Scale ◽  
Learning Algorithm ◽  
X Ray ◽  
Deep Learning Algorithm ◽  
Cluster Evolution ◽  
Novel Method ◽  
Massive Clusters ◽  
Activation Mapping

ABSTRACT The origin of the diverse population of galaxy clusters remains an unexplained aspect of large-scale structure formation and cluster evolution. We present a novel method of using X-ray images to identify cool core (CC), weak cool core (WCC), and non-cool core (NCC) clusters of galaxies that are defined by their central cooling times. We employ a convolutional neural network, ResNet-18, which is commonly used for image analysis, to classify clusters. We produce mock Chandra X-ray observations for a sample of 318 massive clusters drawn from the IllustrisTNG simulations. The network is trained and tested with low-resolution mock Chandra images covering a central 1 Mpc square for the clusters in our sample. Without any spectral information, the deep learning algorithm is able to identify CC, WCC, and NCC clusters, achieving balanced accuracies (BAcc) of 92 per cent, 81 per cent, and 83 per cent, respectively. The performance is superior to classification by conventional methods using central gas densities, with an average ${\rm BAcc}=81{{\ \rm per\ cent}}$, or surface brightness concentrations, giving ${\rm BAcc}=73{{\ \rm per\ cent}}$. We use class activation mapping to localize discriminative regions for the classification decision. From this analysis, we observe that the network has utilized regions from cluster centres out to r ≈ 300 kpc and r ≈ 500 kpc to identify CC and NCC clusters, respectively. It may have recognized features in the intracluster medium that are associated with AGN feedback and disruptive major mergers.

Sign in / Sign up

Export Citation Format

Share Document