Time Series in Sensor Data Using State-of-the-Art Deep Learning Approaches: A Systematic Literature Review

Jácome-Galarza, Luis-Roberto; Realpe, Miguel; Corredores, Jonathan S. Paillacho; Maldonado, José Leonardo Benavides

doi:10.1007/978-981-16-4126-8_45

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms leverage the hierarchical structure of neural networks with multiple hidden layers to capture complex patterns and dependencies in the data. Examples of DNN algorithms suitable for time series forecasting include, among others, Recurrent Neural Networks (RNNs), like Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRU) networks, and Convolutional Neural Networks (CNNs); see, for instance, Lim and Zohren (2021) and Jacome et al (2022).…”

Section: Dnn Model Selection and Hyperparameter Optimizationmentioning

confidence: 99%

Revealing the structural behaviour of Brunelleschi’s Dome with machine learning techniques

Masini,

Bacci,

Cipollini

et al. 2024

Data Min Knowl Disc

View full text Add to dashboard Cite

The Brunelleschi’s Dome is one of the most iconic symbols of the Renaissance and is among the largest masonry domes ever constructed. Since the late 17th century, first masonry cracks appeared on the Dome, giving the start to a monitoring activity. In modern times, since 1988 a monitoring system comprised of 166 electronic sensors, including deformometers and thermometers, has been in operation, providing a valuable source of real-time data on the monument’s health status. With the deformometers taking measurements at least four times per day, a vast amount of data is now available to explore the potential of the latest Artificial Intelligence and Machine Learning techniques in the field of historical-architectural heritage conservation. The objective of this contribution is twofold. Firstly, for the first time ever, we aim to unveil the overall structural behaviour of the Dome as a whole, as well as that of its specific sections (known as webs). We achieve this by evaluating the effectiveness of certain dimensionality reduction techniques on the extensive daily detections generated by the monitoring system, while also accounting for fluctuations in temperature over time. Secondly, we estimate a number of recurrent and convolutional neural network models to verify their capability for medium- and long-term prediction of the structural evolution of the Dome. We believe this contribution is an important step forward in the protection and preservation of historical buildings, showing the utility of machine learning in a context in which these are still little used.

show abstract

Section: Dnn Model Selection and Hyperparameter Optimizationmentioning

confidence: 99%

Revealing the structural behaviour of Brunelleschi’s Dome with machine learning techniques

Masini,

Bacci,

Cipollini

et al. 2024

Data Min Knowl Disc

View full text Add to dashboard Cite

show abstract

“…Jácome-Galarza et al [44] review efficient deep learning architectures for time series data produced by IoT sensors, with applications in smart cities, industry 4.0, sustainable agriculture, and robotics. The paper highlights the capabilities of long short-term memory (LSTM), convolutional neural networks (CNN), recurrent neural networks (RNN), and stacked LSTM autoencoders in time series prediction.…”

Section: Artificial Intelligence and Machine Learningmentioning

confidence: 99%

Time Series Prediction in Industry 4.0: A Comprehensive Review and Prospects for Future Advancements

Kashpruk,

Piskor-Ignatowicz,

Baranowski

2023

Applied Sciences

View full text Add to dashboard Cite

Time series prediction stands at the forefront of the fourth industrial revolution (Industry 4.0), offering a crucial analytical tool for the vast data streams generated by modern industrial processes. This literature review systematically consolidates existing research on the predictive analysis of time series within the framework of Industry 4.0, illustrating its critical role in enhancing operational foresight and strategic planning. Tracing the evolution from the first to the fourth industrial revolution, the paper delineates how each phase has incrementally set the stage for today’s data-centric manufacturing paradigms. It critically examines how emergent technologies such as the Internet of things (IoT), artificial intelligence (AI), cloud computing, and big data analytics converge in the context of Industry 4.0 to transform time series data into actionable insights. Specifically, the review explores applications in predictive maintenance, production optimization, sales forecasting, and anomaly detection, underscoring the transformative impact of accurate time series forecasting on industrial operations. The paper culminates in a call to action for the strategic dissemination and management of these technologies, proposing a pathway for leveraging time series prediction to drive societal and economic advancement. Serving as a foundational compendium, this article aims to inform and guide ongoing research and practice at the intersection of time series prediction and Industry 4.0.

show abstract

“…In 2021, Jácome‐Galarza and Realpe‐Robalino 54 presented a comprehensive review of time series in sensor data using state‐of‐the‐art deep learning approaches. Key features of the proposed work are IoT, deep learning, convolutional neural networks (CNN), recurrent neural networks (RNN), time‐series data prediction and son.…”

Section: Literature Review Of the Current Status Of The Survey In Wsnmentioning

confidence: 99%

Data transmission reduction techniques for improving network lifetime in wireless sensor networks: An up‐to‐date survey from 2017 to 2022

Jain

Kumar

Singh

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) have now become a substantial part of our life as it provides an incredible setup for monitoring environmental conditions such as glaciers melting, earthquakes, climate change, volcanic eruption, agriculture, and other natural calamities. One of the most important challenges in data gathering and examining accurate data is "energy consumption." However, continuously changing environmental conditions, mobility in devices and extreme resource usage, such as battery capacity in WSNs collectively contribute to a high possibility of redundant data transmission thus making it tremendously hard to achieve a satisfactory network lifetime. Additionally, these environmental monitoring applications periodically senses and aggregate data which usually exhibits high temporal and spatial redundancies. As a result, exploiting these redundancies is essential for both resource utilization, as well as accurate data transmission. Since a huge amount of energy is exhausted in transmitting the redundant data, which has become a bottleneck in scaling such applications. In this context, this article provides a thorough examination of existing energy-efficient redundant data transmission reduction techniques, as well as their strengths and drawbacks. The idea of redundant data transmission reduction concept is divided into three stages: the sensor nodes (SN) at the first stage, the cluster heads (CHs) at the second stage, and the base station (BS) at the third stage. Furthermore, this survey focuses on the current issues and challenges, as well as the future directions in reducing redundant data transmission for future investigation.

show abstract

Time Series in Sensor Data Using State-of-the-Art Deep Learning Approaches: A Systematic Literature Review

Cited by 6 publications

References 21 publications

Revealing the structural behaviour of Brunelleschi’s Dome with machine learning techniques

Revealing the structural behaviour of Brunelleschi’s Dome with machine learning techniques

Time Series Prediction in Industry 4.0: A Comprehensive Review and Prospects for Future Advancements

Data transmission reduction techniques for improving network lifetime in wireless sensor networks: An up‐to‐date survey from 2017 to 2022

Contact Info

Product

Resources

About