Sensors

Research

27 pages, 4071 KiB

Open AccessArticle

Deep Learning-Based River Flow Forecasting with MLPs: Comparative Exploratory Analysis Applied to the Tejo and the Mondego Rivers

by Gonçalo Jesus, Zahra Mardani, Elsa Alves and Anabela Oliveira

Sensors 2025, 25(7), 2154; https://doi.org/10.3390/s25072154 - 28 Mar 2025

Viewed by 184

Abstract

This paper presents an innovative service for river flow forecasting and its demonstration in two dam-controlled rivers in Portugal, Tejo, and Mondego rivers, based on using Multilayer Perceptron (MLP) models to predict and forecast river flow. The main goal is to create and [...] Read more.

This paper presents an innovative service for river flow forecasting and its demonstration in two dam-controlled rivers in Portugal, Tejo, and Mondego rivers, based on using Multilayer Perceptron (MLP) models to predict and forecast river flow. The main goal is to create and improve AI models that operate as remote services, providing precise and timely river flow predictions for the next 3 days. This paper examines the use of MLP architectures to predict river discharge using comprehensive hydrological data from Portugal’s National Water Resources Information System (Sistema Nacional de Informação de Recursos Hídricos, SNIRH), demonstrated for the Tejo and Mondego river basins. The methodology is described in detail, including data preparation, model training, and forecasting processes, and provides a comparative study of the MLP model’s performance in both case studies. The analysis shows that MLP models attain acceptable accuracy in short-term river flow forecasts for the selected scenarios and datasets, adeptly reflecting discharge patterns and peak occurrences. These models seek to enhance water resources management and decision-making by amalgamating modern data-driven methodologies with established hydrological and meteorological data sources, facilitating better flood mitigation and sustainable water resource planning as well as accurate boundary conditions for downstream forecast systems. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

21 pages, 4728 KiB

Open AccessFeature PaperArticle

Improvement of Wireless Localization Precision Using Chirp Signals

by Ki-Tae Kim, Kwang-Yul Kim and Yoan Shin

Sensors 2025, 25(6), 1844; https://doi.org/10.3390/s25061844 - 16 Mar 2025

Viewed by 454

Abstract

This study presents a novel localization framework that leverages the unique properties of chirp signals combined with a time division multiple access (TDMA)-based tactical data link to achieve high-precision positioning. Chirp signals, with their wide bandwidth and high temporal resolution, enable an oversampling-like [...] Read more.

This study presents a novel localization framework that leverages the unique properties of chirp signals combined with a time division multiple access (TDMA)-based tactical data link to achieve high-precision positioning. Chirp signals, with their wide bandwidth and high temporal resolution, enable an oversampling-like effect, significantly enhancing distance estimation accuracy without the need for additional sampling rates. The proposed framework integrates chirp-based ranging and localization algorithms, incorporating raised cosine interpolation and circular shift techniques to improve temporal resolution and ensure precise peak detection. By utilizing the time differential of arrival (TDoA) and Fang’s algorithm, the system demonstrates robust performance, effectively mitigating challenges posed by multipath interference and jamming. The TDMA system provides synchronized time slots, allowing the seamless integration of communication and localization functionalities while ensuring stable and efficient operation. Experimental evaluations under various environmental conditions, including dense multipath and high-jamming scenarios, confirm the framework’s superiority over conventional localization methods in terms of accuracy, reliability, and resilience. These results highlight the framework’s potential applications in diverse fields, such as Internet of Things (IoT) networks, smart city infrastructure, and tactical communication systems, where high precision and robust localization are critical. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

18 pages, 1946 KiB

Open AccessArticle

Minimizing Delay and Power Consumption at the Edge

by Erol Gelenbe

Sensors 2025, 25(2), 502; https://doi.org/10.3390/s25020502 - 16 Jan 2025

Viewed by 853

Abstract

Edge computing systems must offer low latency at low cost and low power consumption for sensors and other applications, including the IoT, smart vehicles, smart homes, and 6G. Thus, substantial research has been conducted to identify optimum task allocation schemes in this context [...] Read more.

Edge computing systems must offer low latency at low cost and low power consumption for sensors and other applications, including the IoT, smart vehicles, smart homes, and 6G. Thus, substantial research has been conducted to identify optimum task allocation schemes in this context using non-linear optimization, machine learning, and market-based algorithms. Prior work has mainly focused on two methodologies: (i) formulating non-linear optimizations that lead to NP-hard problems, which are processed via heuristics, and (ii) using AI-based formulations, such as reinforcement learning, that are then tested with simulations. These prior approaches have two shortcomings: (a) there is no guarantee that optimum solutions are achieved, and (b) they do not provide an explicit formula for the fraction of tasks that are allocated to the different servers to achieve a specified optimum. This paper offers a radically different and mathematically based principled method that explicitly computes the optimum fraction of jobs that should be allocated to the different servers to (1) minimize the average latency (delay) of the jobs that are allocated to the edge servers and (2) minimize the average energy consumption of these jobs at the set of edge servers. These results are obtained with a mathematical model of a multiple-server edge system that is managed by a task distribution platform, whose equations are derived and solved using methods from stochastic processes. This approach has low computational cost and provides simple linear complexity formulas to compute the fraction of tasks that should be assigned to the different servers to achieve minimum latency and minimum energy consumption. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

13 pages, 1317 KiB

Open AccessArticle

Channel-Hopping Sequence and Searching Algorithm for Rendezvous of Spectrum Sensing

by Young-June Choi, Young-Sik Kim and Ji-Woong Jang

Sensors 2025, 25(1), 62; https://doi.org/10.3390/s25010062 - 25 Dec 2024

Viewed by 493

Abstract

In this paper, we propose a method for applying the p-ary m-sequence as a channel-searching pattern for rendezvous in the asymmetric channel model of cognitive radio. We mathematically analyzed and calculated the ETTR when the m-sequence is applied to the conventional scheme, [...] Read more.

In this paper, we propose a method for applying the p-ary m-sequence as a channel-searching pattern for rendezvous in the asymmetric channel model of cognitive radio. We mathematically analyzed and calculated the ETTR when the m-sequence is applied to the conventional scheme, and our simulation results demonstrated that the ETTR performance is significantly better than that of the JS algorithm. Furthermore, we introduced a new channel-searching scheme that maximizes the benefits of the m-sequence and proposed a method to adapt the generation of the m-sequence for use in the newly proposed scheme. We also derived the ETTR mathematically for the new scheme with the m-sequence and showed through simulations that the performance of the new scheme with the m-sequence is superior to that of the conventional scheme with the m-sequence. Notably, when there is only one common channel, the new scheme with the m-sequence achieved approximately four times the improvement in the ETTR compared to the conventional scheme. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

25 pages, 6464 KiB

Open AccessArticle

A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models

by Athanasios Donas, Ioannis Kordatos, Alex Alexandridis, George Galanis and Ioannis Th. Famelis

Sensors 2024, 24(24), 8006; https://doi.org/10.3390/s24248006 - 15 Dec 2024

Viewed by 756

Abstract

The aim of this study is to introduce and evaluate a dual filter that combines Radial Basis Function neural networks and Kalman filters to enhance the accuracy of numerical wave prediction models. Unlike the existing methods, which focus solely on systematic errors, the [...] Read more.

The aim of this study is to introduce and evaluate a dual filter that combines Radial Basis Function neural networks and Kalman filters to enhance the accuracy of numerical wave prediction models. Unlike the existing methods, which focus solely on systematic errors, the proposed framework concurrently targets both systematic and non-systematic parts of forecast errors, significantly reducing the bias and variability in significant wave height predictions. The produced filter is self-adaptive, identifying optimal Radial Basis Function network configurations through an automated process involving various network parameters tuning. The produced computational system is assessed using a time-window procedure applied across divergent time periods and regions in the Aegean Sea and the Pacific Ocean. The results reveal a consistent performance, outperforming classic Kalman filters with an average reduction of 53% in bias and 28% in RMSE, underlining the dual filter’s potential as a robust post-processing tool for environmental simulations. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

15 pages, 8532 KiB

Open AccessArticle

Data-Aided Maximum Likelihood Joint Angle and Delay Estimator Over Orthogonal Frequency Division Multiplex Single-Input Multiple-Output Channels Based on New Gray Wolf Optimization Embedding Importance Sampling

by Maha Abdelkhalek, Souheib Ben Amor and Sofiène Affes

Sensors 2024, 24(17), 5821; https://doi.org/10.3390/s24175821 - 7 Sep 2024

Viewed by 1097

Abstract

In this paper, we propose a new data-aided (DA) joint angle and delay (JADE) maximum likelihood (ML) estimator. The latter consists of a substantially modified and, hence, significantly improved gray wolf optimization (GWO) technique by fully integrating and embedding within it the powerful [...] Read more.

In this paper, we propose a new data-aided (DA) joint angle and delay (JADE) maximum likelihood (ML) estimator. The latter consists of a substantially modified and, hence, significantly improved gray wolf optimization (GWO) technique by fully integrating and embedding within it the powerful importance sampling (IS) concept. This new approach, referred to hereafter as GWOEIS (for “GWO embedding IS”), guarantees global optimality, and offers higher resolution capabilities over orthogonal frequency division multiplex (OFDM) (i.e., multi-carrier and multi-path) single-input multiple-output (SIMO) channels. The traditional GWO randomly initializes the wolfs’ positions (angles and delays) and, hence, requires larger packs and longer hunting (iterations) to catch the prey, i.e., find the correct angles of arrival (AoAs) and time delays (TDs), thereby affecting its search efficiency, whereas GWOEIS ensures faster convergence by providing reliable initial estimates based on a simplified importance function. More importantly, and beyond simple initialization of GWO with IS (coined as IS-GWO hereafter), we modify and dynamically update the conventional simple expression for the convergence factor of the GWO algorithm that entirely drives its hunting and tracking mechanisms by accounting for new cumulative distribution functions (CDFs) derived from the IS technique. Simulations unequivocally confirm these significant benefits in terms of increased accuracy and speed Moreover, GWOEIS reaches the Cramér–Rao lower bound (CRLB), even at low SNR levels. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

23 pages, 2085 KiB

Open AccessArticle

Energy Performance of LR-FHSS: Analysis and Evaluation

by Roger Sanchez-Vital, Lluís Casals, Bartomeu Heer-Salva, Rafael Vidal, Carles Gomez and Eduard Garcia-Villegas

Sensors 2024, 24(17), 5770; https://doi.org/10.3390/s24175770 - 5 Sep 2024

Cited by 1 | Viewed by 2066

Abstract

Long-range frequency hopping spread spectrum (LR-FHSS) is a pivotal advancement in the LoRaWAN protocol that is designed to enhance the network’s capacity and robustness, particularly in densely populated environments. Although energy consumption is paramount in LoRaWAN-based end devices, this is the first study [...] Read more.

Long-range frequency hopping spread spectrum (LR-FHSS) is a pivotal advancement in the LoRaWAN protocol that is designed to enhance the network’s capacity and robustness, particularly in densely populated environments. Although energy consumption is paramount in LoRaWAN-based end devices, this is the first study in the literature, to our knowledge, that models the impact of this novel mechanism on energy consumption. In this article, we provide a comprehensive energy consumption analytical model of LR-FHSS, focusing on three critical metrics: average current consumption, battery lifetime, and energy efficiency of data transmission. The model is based on measurements performed on real hardware in a fully operational LR-FHSS network. While in our evaluation, LR-FHSS can show worse consumption figures than LoRa, we find that with optimal configuration, the battery lifetime of LR-FHSS end devices can reach 2.5 years for a 50 min notification period. For the most energy-efficient payload size, this lifespan can be extended to a theoretical maximum of up to 16 years with a one-day notification interval using a cell-coin battery. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

20 pages, 5930 KiB

Open AccessArticle

Asynchronous Code Division Multiplexing-Based Visible Light Positioning and Communication Network Using Successive Interference Cancellation Decoding

by Zhongxu Liu, Xiaodi You and Changyuan Yu

Sensors 2024, 24(17), 5609; https://doi.org/10.3390/s24175609 - 29 Aug 2024

Viewed by 1086

Abstract

In the evolving landscape of sixth-generation wireless communication, the integration of visible light communication (VLC) and visible light positioning (VLP), known as visible light positioning and communication (VLPC), emerges as a pivotal technology. This study addresses the challenges of asynchronous code division multiplexing [...] Read more.

In the evolving landscape of sixth-generation wireless communication, the integration of visible light communication (VLC) and visible light positioning (VLP), known as visible light positioning and communication (VLPC), emerges as a pivotal technology. This study addresses the challenges of asynchronous code division multiplexing (ACDM) in VLPC networks, focusing on the enhancement of data transmission quality and positioning accuracy. Firstly, we propose an orthogonal pseudo-random code (OPRC) for ACDM-based VLP systems. Leveraging its excellent correlation properties, VLP signals preserve orthogonality even amidst asynchronous transmissions, achieving sub-centimeter average positioning errors. Next, by combining OPRC with successive interference cancellation decoding (SICD), we propose an enhanced ACDM-based VLPC system that utilizes OPRC for improved signal orthogonality and SICD for progressive elimination of multiple access interference (MAI) among VLPC signals. The results show substantial improvements in bit-error rate (BER) and positioning error (PE), approaching the performance levels observed in synchronized VLPC systems. Specifically, the SICD-OPRC scheme reduces average BER to 4.3 × 10⁻⁴ and average PE to 2.7 cm, demonstrating its robustness and superiority in complex asynchronous scenarios. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

24 pages, 1955 KiB

Open AccessArticle

Energy Consumption Minimization with SNR Constraint for Wireless Powered Communication Networks

by Kuei-Ping Shih, Yu-Sheng Tsai, Yen-Da Chen and San-Yuan Wang

Sensors 2024, 24(17), 5535; https://doi.org/10.3390/s24175535 - 27 Aug 2024

Viewed by 949

Abstract

The article addresses the energy consumption minimization problem in wireless powered communication networks (WPCNs) and proposes a time allocation scheme, named DaTA, which is based on the Different Target Simultaneous Wireless Information and Power Transfer (DT-SWIPT) scheme such that the wireless station can [...] Read more.

The article addresses the energy consumption minimization problem in wireless powered communication networks (WPCNs) and proposes a time allocation scheme, named DaTA, which is based on the Different Target Simultaneous Wireless Information and Power Transfer (DT-SWIPT) scheme such that the wireless station can share the remaining energy after transmission to the Hybrid Access Point (HAP) to those who have not transmitted to the HAP to minimize the energy consumption of the WPCN. In addition to proposing a new frame structure, the article also considers the Signal-to-Noise (SNR) constraint to guarantee that the HAP can successfully receive data from wireless stations. In the article, the problem of minimization of energy consumption is formulated as a nonlinear programming model. We employ the SQP (Sequential Quadratic Programming) algorithm to figure out the optimal solution. Moreover, a heuristic method is proposed as well to obtain a near-optimal solution in a shorter time. The simulation results showed that the proposed scheme outperforms the related work in terms of energy consumption and energy efficiency. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

18 pages, 4816 KiB

Open AccessArticle

Prototyping a Secure and Usable User Authentication Mechanism for Mobile Passenger ID Devices for Land/Sea Border Control

by Maria Papaioannou, Georgios Zachos, Georgios Mantas, Emmanouil Panaousis and Jonathan Rodriguez

Sensors 2024, 24(16), 5193; https://doi.org/10.3390/s24165193 - 11 Aug 2024

Viewed by 1119

Abstract

As the number of European Union (EU) visitors grows, implementing novel border control solutions, such as mobile devices for passenger identification for land and sea border control, becomes paramount to ensure the convenience and safety of passengers and officers. However, these devices, handling [...] Read more.

As the number of European Union (EU) visitors grows, implementing novel border control solutions, such as mobile devices for passenger identification for land and sea border control, becomes paramount to ensure the convenience and safety of passengers and officers. However, these devices, handling sensitive personal data, become attractive targets for malicious actors seeking to misuse or steal such data. Therefore, to increase the level of security of such devices without interrupting border control activities, robust user authentication mechanisms are essential. Toward this direction, we propose a risk-based adaptive user authentication mechanism for mobile passenger identification devices for land and sea border control, aiming to enhance device security without hindering usability. In this work, we present a comprehensive assessment of novelty and outlier detection algorithms and discern OneClassSVM, Local Outlier Factor (LOF), and Bayesian_GaussianMixtureModel (B_GMM) novelty detection algorithms as the most effective ones for risk estimation in the proposed mechanism. Furthermore, in this work, we develop the proposed risk-based adaptive user authentication mechanism as an application on a Raspberry Pi 4 Model B device (i.e., playing the role of the mobile device for passenger identification), where we evaluate the detection performance of the three best performing novelty detection algorithms (i.e., OneClassSVM, LOF, and B_GMM), with B_GMM surpassing the others in performance when deployed on the Raspberry Pi 4 device. Finally, we evaluate the risk estimation overhead of the proposed mechanism when the best performing B_GMM novelty detection algorithm is used for risk estimation, indicating efficient operation with minimal additional latency. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

23 pages, 1335 KiB

Open AccessArticle

Leveraging Edge Computing for Video Data Streaming in UAV-Based Emergency Response Systems

by Mekhla Sarkar and Prasan Kumar Sahoo

Sensors 2024, 24(15), 5076; https://doi.org/10.3390/s24155076 - 5 Aug 2024

Cited by 1 | Viewed by 1404

Abstract

The rapid advancement of technology has greatly expanded the capabilities of unmanned aerial vehicles (UAVs) in wireless communication and edge computing domains. The primary objective of UAVs is the seamless transfer of video data streams to emergency responders. However, live video data streaming [...] Read more.

The rapid advancement of technology has greatly expanded the capabilities of unmanned aerial vehicles (UAVs) in wireless communication and edge computing domains. The primary objective of UAVs is the seamless transfer of video data streams to emergency responders. However, live video data streaming is inherently latency dependent, wherein the value of the video frames diminishes with any delay in the stream. This becomes particularly critical during emergencies, where live video streaming provides vital information about the current conditions. Edge computing seeks to address this latency issue in live video streaming by bringing computing resources closer to users. Nonetheless, the mobile nature of UAVs necessitates additional trajectory supervision alongside the management of computation and networking resources. Consequently, efficient system optimization is required to maximize the overall effectiveness of the collaborative system with limited UAV resources. This study explores a scenario where multiple UAVs collaborate with end users and edge servers to establish an emergency response system. The proposed idea takes a comprehensive approach by considering the entire emergency response system from the incident site to video distribution at the user level. It includes an adaptive resource management strategy, leveraging deep reinforcement learning by simultaneously addressing video streaming latency, UAV and user mobility factors, and varied bandwidth resources. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

14 pages, 3208 KiB

Open AccessArticle

Smart Industrial Internet of Things Framework for Composites Manufacturing

by Boon Xian Chai, Maheshi Gunaratne, Mohammad Ravandi, Jinze Wang, Tharun Dharmawickrema, Adriano Di Pietro, Jiong Jin and Dimitrios Georgakopoulos

Sensors 2024, 24(15), 4852; https://doi.org/10.3390/s24154852 - 26 Jul 2024

Cited by 7 | Viewed by 1904

Abstract

Composite materials are increasingly important in making high-performance products. However, contemporary composites manufacturing processes still encounter significant challenges that range from inherent material stochasticity to manufacturing process variabilities. This paper proposes a novel smart Industrial Internet of Things framework, which is also referred [...] Read more.

Composite materials are increasingly important in making high-performance products. However, contemporary composites manufacturing processes still encounter significant challenges that range from inherent material stochasticity to manufacturing process variabilities. This paper proposes a novel smart Industrial Internet of Things framework, which is also referred to as an Artificial Intelligence of Things (AIoT) framework for composites manufacturing. This framework improves production performance through real-time process monitoring and AI-based forecasting. It comprises three main components: (i) an array of temperature, heat flux, dielectric, and flow sensors for data acquisition from production machines and products being made, (ii) an IoT-based platform for instantaneous sensor data integration and visualisation, and (iii) an AI-based model for production process forecasting. Via these components, the framework performs real-time production process monitoring, visualisation, and prediction of future process states. This paper also presents a proof-of-concept implementation of the framework and a real-world composites manufacturing case study that showcases its benefits. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

16 pages, 8759 KiB

Open AccessArticle

Normal-Incidence Germanium Photodetectors Integrated with Polymer Microlenses for Optical Fiber Communication Applications

by Yu-Hsuan Liu, Chia-Peng Lin, Po-Wei Chen, Chia-Tai Tsao, Chun-Chi Lin, Tsung-Ting Wu, Likarn Wang and Neil Na

Sensors 2024, 24(13), 4221; https://doi.org/10.3390/s24134221 - 29 Jun 2024

Viewed by 1311

Abstract

We present a novel photon-acid diffusion method to integrate polymer microlenses (MLs) on a four-channel, high-speed photo-receiver consisting of normal-incidence germanium (Ge) p-i-n photodiodes (PDs) fabricated on a 200 mm Si substrate. For a 29 µm diameter PD capped with a 54 µm [...] Read more.

We present a novel photon-acid diffusion method to integrate polymer microlenses (MLs) on a four-channel, high-speed photo-receiver consisting of normal-incidence germanium (Ge) p-i-n photodiodes (PDs) fabricated on a 200 mm Si substrate. For a 29 µm diameter PD capped with a 54 µm diameter ML, its dark current, responsivity, 3 dB bandwidth (BW), and effective aperture size at −3 V bias and 850 nm wavelength are measured to be 138 nA, 0.6 A/W, 21.4 GHz, and 54 µm, respectively. The enlarged aperture size significantly decouples the tradeoff between aperture size and BW and enhances the optical fiber misalignment tolerance from ±5 µm to ±15 µm to ease the module packaging precision. The sensitivity of the photo-receiver is measured to be −9.2 dBm at 25.78 Gb/s with a bit error rate of 10⁻¹² using non-return-to-zero (NRZ) transmission. Reliability tests are performed, and the results show that the fabricated Ge PDs integrated with polymer MLs pass the GR-468 reliability assurance standard. The demonstrated photo-receiver, a first of its kind to the best of our knowledge, features decent performance, high yield, high throughput, low cost, and compatibility with complementary metal-oxide-semiconductor (CMOS) fabrication processes, and may be further applied to 400 Gb/s pulse-amplitude modulation four-level (PAM4) communication. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

16 pages, 667 KiB

Open AccessArticle

BiLSTM-MLAM: A Multi-Scale Time Series Prediction Model for Sensor Data Based on Bi-LSTM and Local Attention Mechanisms

by Yongxin Fan, Qian Tang, Yangming Guo and Yifei Wei

Sensors 2024, 24(12), 3962; https://doi.org/10.3390/s24123962 - 19 Jun 2024

Cited by 7 | Viewed by 3320

Abstract

This paper introduces BiLSTM-MLAM, a novel multi-scale time series prediction model. Initially, the approach utilizes bidirectional long short-term memory to capture information from both forward and backward directions in time series data. Subsequently, a multi-scale patch segmentation module generates various long sequences composed [...] Read more.

This paper introduces BiLSTM-MLAM, a novel multi-scale time series prediction model. Initially, the approach utilizes bidirectional long short-term memory to capture information from both forward and backward directions in time series data. Subsequently, a multi-scale patch segmentation module generates various long sequences composed of equal-length segments, enabling the model to capture data patterns across multiple time scales by adjusting segment lengths. Finally, the local attention mechanism enhances feature extraction by accurately identifying and weighting important time segments, thereby strengthening the model’s understanding of the local features of the time series, followed by feature fusion. The model demonstrates outstanding performance in time series prediction tasks by effectively capturing sequence information across various time scales. Experimental validation illustrates the superior performance of BiLSTM-MLAM compared to six baseline methods across multiple datasets. When predicting the remaining life of aircraft engines, BiLSTM-MLAM outperforms the best baseline model by 6.66% in RMSE and 11.50% in MAE. In the LTE dataset, it achieves RMSE improvements of 12.77% and MAE enhancements of 3.06%, while in the load dataset, it demonstrates RMSE enhancements of 17.96% and MAE improvements of 30.39%. Additionally, ablation experiments confirm the positive impact of each module on prediction accuracy. Through segment length parameter tuning experiments, combining different segment lengths has resulted in lower prediction errors, affirming the effectiveness of the multi-scale fusion strategy in enhancing prediction accuracy by integrating information from multiple time scales. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

15 pages, 3882 KiB

Open AccessArticle

A Dual-Stream Cross AGFormer-GPT Network for Traffic Flow Prediction Based on Large-Scale Road Sensor Data

by Yu Sun, Yajing Shi, Kaining Jia, Zhiyuan Zhang and Li Qin

Sensors 2024, 24(12), 3905; https://doi.org/10.3390/s24123905 - 17 Jun 2024

Viewed by 1153

Abstract

Traffic flow prediction can provide important reference data for managers to maintain traffic order, and can also be based on personal travel plans for optimal route selection. On account of the development of sensors and data collection technology, large-scale road network historical data [...] Read more.

Traffic flow prediction can provide important reference data for managers to maintain traffic order, and can also be based on personal travel plans for optimal route selection. On account of the development of sensors and data collection technology, large-scale road network historical data can be effectively used, but their high non-linearity makes it meaningful to establish effective prediction models. In this regard, this paper proposes a dual-stream cross AGFormer-GPT network with prompt engineering for traffic flow prediction, which integrates traffic occupancy and speed as two prompts into traffic flow in the form of cross-attention, and uniquely mines spatial correlation and temporal correlation information through the dual-stream cross structure, effectively combining the advantages of the adaptive graph neural network and large language model to improve prediction accuracy. The experimental results on two PeMS road network data sets have verified that the model has improved by about 1.2% in traffic prediction accuracy under different road networks. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

20 pages, 1613 KiB

Open AccessArticle

Energy-Efficient Edge and Cloud Image Classification with Multi-Reservoir Echo State Network and Data Processing Units

by E. J. López-Ortiz, M. Perea-Trigo, L. M. Soria-Morillo, J. A. Álvarez-García and J. J. Vegas-Olmos

Sensors 2024, 24(11), 3640; https://doi.org/10.3390/s24113640 - 4 Jun 2024

Cited by 2 | Viewed by 1102

Abstract

In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning [...] Read more.

In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State Networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms. Full article

(This article belongs to the Special Issue Feature Papers in the 'Sensor Networks' Section 2024)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Feature Papers in the 'Sensor Networks' Section 2024

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Related Special Issues

Published Papers (16 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI