Cyber-Physical System for Environmental Monitoring Based on Deep Learning

Monedero, Íñigo; Barbancho, Julio; Márquez, Rafael; Beltrán, Juan F.

doi:10.3390/s21113655

Cited by 8 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the abnormal data appeared, alarm would be on in the server side. And, the current GPS data were recorded and sent to the environment management monitoring center and mobile phone terminals (community staff) [ 20 ]. The Web server of the system was the overall monitoring center of the environment monitoring system, mainly being responsible for the display of historical data, view of user records, alarm in emergencies, and task distribution in abnormal situations [ 21 ].…”

Section: Methodsmentioning

confidence: 99%

Residential Environment Pollution Monitoring System Based on Cloud Computing and Internet of Things

Sun

Zhang

et al. 2022

International Journal of Analytical Chemistry

View full text Add to dashboard Cite

In order to solve the problems of single monitoring factor, weak comprehensive analysis ability, and poor real time performance in traditional environmental monitoring systems, a research method of residential environment pollution monitoring system based on cloud computing and Internet of Things is proposed. The method mainly includes two parts: an environmental monitoring terminal and an environmental pollution monitoring and management platform. Through the Wi-Fi module, the data is sent to the environmental pollution monitoring and management platform in real time. The environmental monitoring management platform is mainly composed of environmental pollution monitoring server, web server, and mobile terminal. The results are as follows. The data measured by the system is close to the data measured by the instrument, and the overall error is small. The measurement error of harmful gases is about 6%. PM 2.5 is about 6.5%. Noise is about 1%. The average time for sensor data update is 0.762 s. The average alarm response time is 2 s. The average data transfer time is 2 s. Practice has proved that the environmental pollution monitoring and alarm system operates stably and can realize real-time collection and transmission of data such as noise, PM 2.5, harmful gas concentration, illumination, GPS, and video images, providing a reliable guarantee for timely environmental pollution control.

show abstract

Section: Methodsmentioning

confidence: 99%

Residential Environment Pollution Monitoring System Based on Cloud Computing and Internet of Things

Sun

Zhang

et al. 2022

International Journal of Analytical Chemistry

View full text Add to dashboard Cite

show abstract

“…A CNN-LSTM was trained initially for classifying model in 4 sound categories created in prior work [1], as described previously in the data preprocessing part. Afterward, a secondary CNN-LSTM was developed to add the other five classes in Table 1 to the classification method.…”

Section: Classification Using Cnn-lstmmentioning

confidence: 99%

“…On their routes from Europe to Africa, multiple species of birds pause in the DNP, an important ecosystem. These characteristics give this area an exceptional setting for exploring various facets of the relationships between people and the natural world [1].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep CNN-LSTM-Based Feature Extraction for Cyber-Physical System Monitoring

Omran Almagrabi

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

A potential concept that could be effective for multiple applications is a "cyber-physical system" (CPS). The Internet of Things (IoT) has evolved as a research area, presenting new challenges in obtaining valuable data through environmental monitoring. The existing work solely focuses on classifying the audio system of CPS without utilizing feature extraction. This study employs a deep learning method, CNN-LSTM, and two-way feature extraction to classify audio systems within CPS. The primary objective of this system, which is built upon a convolutional neural network (CNN) with Long Short Term Memory (LSTM), is to analyze the vocalization patterns of two different species of anurans. It has been demonstrated that CNNs, when combined with mel-spectrograms for sound analysis, are suitable for classifying ambient noises. Initially, the data is augmented and preprocessed. Next, the mel spectrogram features are extracted through two-way feature extraction. First, Principal Component Analysis (PCA) is utilized for dimensionality reduction, followed by Transfer learning for audio feature extraction. Finally, the classification is performed using the CNN-LSTM process. This methodology can potentially be employed for categorizing various biological acoustic objects and analyzing biodiversity indexes in natural environments, resulting in high classification accuracy. The study highlights that this CNN-LSTM approach enables cost-effective and resource-efficient monitoring of large natural regions. The dissemination of updated CNN-LSTM models across distant IoT nodes is facilitated flexibly and dynamically through the utilization of CPS.

show abstract

“…A recent publication has pointed out that the SONYC acoustic sensor network for urban noise monitoring is also a CPS in the sense that machine listening software and microphone hardware constitute its “cyber” and “physical” components respectively [23]. The term CPS has also been employed in the context of acoustic communication between autonomous underwater vehicles [24] and in the SCENA-RBD project for terrestrial monitoring of amphibians [25].…”

Section: Introductionmentioning

confidence: 99%

BirdVox: Machine listening for bird migration monitoring

Lostanlen

Cramer

Farnsworth

et al. 2022

Preprint

View full text Add to dashboard Cite

The steady decline of avian populations worldwide urgently calls for a cyber-physical system to monitor bird migration at the continental scale. Compared to other sources of information (radar and crowdsourced observations), bioacoustic sensor networks combine low latency with a high taxonomic specificity. However, the scarcity of flight calls in bioacoustic monitoring scenes (below 0.1% of total recording time) requires the automation of audio content analysis. In this article, we address the problem of scaling up the detection and classification of flight calls to a full-season dataset: 6672 hours across nine sensors, yielding around 480 million neural network predictions. Our proposed pipeline, BirdVox, combines multiple machine learning modules to produce per-species flight call counts. We evaluate BirdVox on an annotated subset of the full season (296 hours) and discuss the main sources of estimation error which are inherent to a real-world deployment: mechanical sensor failures, sensitivity to background noise, misdetection, and taxonomic confusion. After developing dedicated solutions to mitigate these sources of error, we demonstrate the usability of BirdVox by reporting a species-specific temporal estimate of flight call activity for the Swainson's Thrush (Catharus ustulatus).

show abstract

Cyber-Physical System for Environmental Monitoring Based on Deep Learning

Cited by 8 publications

References 26 publications

Residential Environment Pollution Monitoring System Based on Cloud Computing and Internet of Things

Residential Environment Pollution Monitoring System Based on Cloud Computing and Internet of Things

A Deep CNN-LSTM-Based Feature Extraction for Cyber-Physical System Monitoring

BirdVox: Machine listening for bird migration monitoring

Contact Info

Product

Resources

About