Electronics

19 pages, 2511 KiB

Open AccessArticle

TS-GRU: A Stock Gated Recurrent Unit Model Driven via Neuro-Inspired Computation

by Yuanfang Zhang and Heinz D. Fill

Electronics 2024, 13(23), 4659; https://doi.org/10.3390/electronics13234659 (registering DOI) - 26 Nov 2024

Existing risk measurement methods often fail to fully consider the impact of climatic conditions on stock market risk, making it difficult to capture dynamic patterns and long-term dependencies. To address these issues, we propose the TS-GRU method: this approach utilizes a temporal convolutional [...] Read more.

Existing risk measurement methods often fail to fully consider the impact of climatic conditions on stock market risk, making it difficult to capture dynamic patterns and long-term dependencies. To address these issues, we propose the TS-GRU method: this approach utilizes a temporal convolutional network (TCN) to extract underlying features from historical data, capturing key characteristics of time series data. Subsequently, a gated recurrent unit (GRU) model is employed to capture dynamic patterns and long-term dependencies within the stock market. Finally, the TS-GRU model is optimized using the Sparrow algorithm based on collective behavior, iteratively evaluating and refining model parameters to obtain improved solutions. Experimental results demonstrate the effectiveness of the TS-GRU method in providing accurate risk assessment and forecasting. This comprehensive approach takes into account carbon finance, climate change, and environmental factors, offering valuable insights to investors to help them to understand and manage investment risks in the ever-changing stock market. Full article

► Show Figures

Figure 1

13 pages, 3796 KiB

Open AccessArticle

Lightweight Segmentation Method for Wood Panel Images Based on Improved DeepLabV3+

by Xiangwei Mou, Hongyang Chen, Xinye Yu, Lintao Chen, Zhujing Peng and Rijun Wang

Electronics 2024, 13(23), 4658; https://doi.org/10.3390/electronics13234658 (registering DOI) - 26 Nov 2024

Abstract

Accurate and efficient pixel-wise segmentation of wood panels is crucial for enabling machine vision technologies to optimize the sawing process. Traditional image segmentation algorithms often struggle with robustness and accuracy in complex industrial environments. To address these challenges, this paper proposes an improved [...] Read more.

Accurate and efficient pixel-wise segmentation of wood panels is crucial for enabling machine vision technologies to optimize the sawing process. Traditional image segmentation algorithms often struggle with robustness and accuracy in complex industrial environments. To address these challenges, this paper proposes an improved DeepLabV3+-based segmentation algorithm for wood panel images. The model incorporates a lightweight MobileNetV3 backbone to enhance feature extraction, reducing the number of parameters and computational complexity while minimizing any trade-off in segmentation accuracy, thereby increasing the model’s processing speed. Additionally, the introduction of a coordinate attention (CA) mechanism allows the model to better capture fine details and local features of the wood panels while suppressing interference from complex backgrounds. A novel feature fusion mechanism is also employed, combining shallow and deep network features to enhance the model’s ability to capture edges and textures, leading to improved feature fusion across scales and boosting segmentation accuracy. The experimental results demonstrate that the improved DeepLabV3+ model not only achieves superior segmentation performance across various wood panel types but also significantly increases segmentation speed. Specifically, the model improves the mean intersection over union (MIoU) by 1.05% and boosts the processing speed by 59.2%, achieving a processing time of 0.184 s per image. Full article

► Show Figures

Figure 1

17 pages, 10360 KiB

Open AccessArticle

A Novel Analysis of the Influence of Zero-Axis Control on Neutral-Point Potential Self-Balancing of Three-Level Converters

by Haiguo Tang, Lingchao Kong and Yong Wang

Electronics 2024, 13(23), 4657; https://doi.org/10.3390/electronics13234657 (registering DOI) - 26 Nov 2024

Abstract

The neutral-point potential balance issues in three-level converters have obtained great attention. The popular view thinks that the neutral-point voltage deviation can be suppressed by regulating the injected zero-sequence component, whether via carrier modulation or space vector modulation techniques. However, this paper presents [...] Read more.

The neutral-point potential balance issues in three-level converters have obtained great attention. The popular view thinks that the neutral-point voltage deviation can be suppressed by regulating the injected zero-sequence component, whether via carrier modulation or space vector modulation techniques. However, this paper presents a novel finding: the efficacy of different frame controllers on the self-balancing of neutral-point potential in three-level converters differs when a comprehensive analysis of zero-sequence dynamics, including neutral-point current and PWM modulation, is conducted. That is, the proportional-resonant (PR) controller in the abc frame effectively introduces a zero-axis PR control of the zero-sequence component, which subsequently degrades the stability of neutral-point potential self-balancing. In contrast, the PI control in the dq frame does not incorporate any additional control of the zero-sequence component, thereby enhancing the self-balancing capability of the neutral-point potential. To substantiate this novel finding, a series of simulations and experimental validations were performed. Full article

(This article belongs to the Special Issue Power Electronics in Smart Grids)

► Show Figures

Figure 1

24 pages, 1660 KiB

Open AccessArticle

Performance Study of FSO/THz Dual-Hop System Based on Cognitive Radio and Energy Harvesting System

by Jingwei Lu, Rongpeng Liu, Yawei Wang, Ziyang Wang and Hongzhan Liu

Electronics 2024, 13(23), 4656; https://doi.org/10.3390/electronics13234656 (registering DOI) - 26 Nov 2024

Abstract

In order to address the problems of low spectrum efficiency in current communication systems and extend the lifetime of energy-constrained relay devices, this paper proposes a novel dual-hop free-space optical (FSO) system that integrates cognitive radio (CR) and energy harvesting (EH). In this [...] Read more.

In order to address the problems of low spectrum efficiency in current communication systems and extend the lifetime of energy-constrained relay devices, this paper proposes a novel dual-hop free-space optical (FSO) system that integrates cognitive radio (CR) and energy harvesting (EH). In this system, the source node communicates with two users at the terminal via FSO and terahertz (THz) hard-switching links, as well as a multi-antenna relay for non-orthogonal multiple access (NOMA). There is another link whose relay acts as both the power beacon (PB) in the EH system and the primary network (PN) in the CR system, achieving the double function of auxiliary transmission. In addition, based on the three possible practical working scenarios of the system, three different transmit powers of the relay are distinguished, thus enabling three different working modes of the system. Closed-form expressions are derived for the interruption outage probability per user for these three operating scenarios, considering the Gamma–Gamma distribution for the FSO link, the

α - μ

distribution for the THz link, and the Rayleigh fading distribution for the radio frequency (RF) link. Finally, the numerical results show that this novel system can be adapted to various real-world scenarios and possesses unique advantages. Full article

(This article belongs to the Section Microwave and Wireless Communications)

► Show Figures

Figure 1

20 pages, 7361 KiB

Open AccessArticle

An Optimization Method for Design Solutions to Active Reflective Surface Control Systems Based on Axiomatic Design and Multi-Criteria Decision Making

by Qinghai Zhang, Xiaoqian Zhang, Qingjian Zhao, Shuang Zhao, Yanan Zhao, Yang Guo and Zhengxu Zhao

Electronics 2024, 13(23), 4655; https://doi.org/10.3390/electronics13234655 - 25 Nov 2024

Abstract

The design of an Active Reflective Surface Control System (ARCS) is a complex engineering task involving multidimensional and multi-criteria constraints. This paper proposes a novel methodological approach for ARCS design and optimization by integrating Axiomatic Design (AD) and Multi-Criteria Decision Making (MCDM) techniques. [...] Read more.

The design of an Active Reflective Surface Control System (ARCS) is a complex engineering task involving multidimensional and multi-criteria constraints. This paper proposes a novel methodological approach for ARCS design and optimization by integrating Axiomatic Design (AD) and Multi-Criteria Decision Making (MCDM) techniques. Initially, a structured design plan is formulated within the axiomatic design framework. Subsequently, four MCDM methods—Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), Entropy Weight Method (EWM), Multi-Criteria Optimization and Compromise Solution (VIKOR), and the integrated TOPSIS–Grey Relational Analysis (GRA) approach—are used to evaluate and compare the alternative solutions. Additionally, fuzzy information axioms are used to calculate the total information content for each alternative to identify the optimal design. A case study is conducted, selecting the optimal actuator for a 5 m diameter scaled model of the Five-hundred-meter Aperture Spherical radio Telescope (FAST), followed by digital control experiments on the chosen actuator. Based on the optimal design scheme, an ARCS prototype is constructed, which accelerates project completion and substantially reduces trial-and-error costs. Full article

17 pages, 1714 KiB

Open AccessArticle

Mechanism and Control Strategies for Current Sharing in Multi-Chip Parallel Automotive Power Modules

by Yuqi Jiang, Xuehan Li and Kun Ma

Electronics 2024, 13(23), 4654; https://doi.org/10.3390/electronics13234654 - 25 Nov 2024

Abstract

Multi-chip parallel power modules are highly favored in applications requiring high capacity and high switching frequency. However, the dynamic current imbalance between parallel chips caused by asymmetric layouts limits the available capacity. This paper presents a method to optimize dynamic current distribution by [...] Read more.

Multi-chip parallel power modules are highly favored in applications requiring high capacity and high switching frequency. However, the dynamic current imbalance between parallel chips caused by asymmetric layouts limits the available capacity. This paper presents a method to optimize dynamic current distribution by adjusting the lengths and connection points of bond wires. For the first time, a response surface model and nonlinear constraint optimization algorithm are introduced, along with parameter analysis based on finite element methods, to establish the response surface models for the parasitic inductance of bond wires and DBC (direct bonded copper). By leveraging the optimization goals for parasitic inductance and the analytical expressions of all response surfaces, the dynamic current sharing issue was transformed into a nonlinear constrained optimization problem. The solution to this optimization problem identified the optimal connection points for the bond wires, enhancing dynamic current sharing performance. Simulations and experiments were conducted, revealing that the optimized automotive-grade module exhibited a significant reduction in current differences between parallel branches, from 41.7% to 5.03% compared with the original design. This indicated that the proposed optimization scheme for adjusting bond wire connection points could significantly mitigate current disparities, thereby markedly improving current distribution uniformity. Full article

17 pages, 1370 KiB

Open AccessArticle

FL-YOLOv8: Lightweight Object Detector Based on Feature Fusion

by Ying Xue, Qijin Wang, Yating Hu, Yu Qian, Long Cheng and Hongqiang Wang

Electronics 2024, 13(23), 4653; https://doi.org/10.3390/electronics13234653 - 25 Nov 2024

Abstract

In recent years, anchor-free object detectors have become predominant in deep learning, the YOLOv8 model as a real-time object detector based on anchor-free frames is universal and influential, it efficiently detects objects across multiple scales. However, the generalization performance of the model is [...] Read more.

In recent years, anchor-free object detectors have become predominant in deep learning, the YOLOv8 model as a real-time object detector based on anchor-free frames is universal and influential, it efficiently detects objects across multiple scales. However, the generalization performance of the model is lacking, and the feature fusion within the neck module overly relies on its structural design and dataset size, and it is particularly difficult to localize and detect small objects. To address these issues, we propose the FL-YOLOv8 object detector, which is improved based on YOLOv8s. Firstly, we introduce the FSDI module in the neck, enhancing semantic information across all layers and incorporating rich detailed features through straightforward layer-hopping connections. This module integrates both high-level and low-level information to enhance the accuracy and efficiency of image detection. Meanwhile, the structure of the model was optimized and designed, and the LSCD module is constructed in the detection head; adopting a lightweight shared convolutional detection head reduces the number of parameters and computation of the model by 19% and 10%, respectively. Our model achieves a comprehensive performance of 45.5% on the COCO generalized dataset, surpassing the benchmark by 0.8 percentage points. To further validate the effectiveness of the method, experiments were also performed on specific domain urine sediment data (FCUS22), and the results on category detection also better justify the FL-YOLOv8 object detection algorithm. Full article

34 pages, 3226 KiB

Open AccessArticle

A Hyper-Parameter Optimizer Algorithm Based on Conditional Opposition Local-Based Learning Forbidden Redundant Indexes Adaptive Artificial Bee Colony Applied to Regularized Extreme Learning Machine

by Philip Vasquez-Iglesias, Amelia E. Pizarro, David Zabala-Blanco, Juan Fuentes-Concha, Roberto Ahumada-Garcia, David Laroze and Paulo Gonzalez

Electronics 2024, 13(23), 4652; https://doi.org/10.3390/electronics13234652 - 25 Nov 2024

Abstract

Finding the best configuration of a neural network’s hyper-parameters may take too long to be feasible using an exhaustive search, especially when the cardinality of the search space has a big combinatorial number of possible solutions with various hyper-parameters. This problem is aggravated [...] Read more.

Finding the best configuration of a neural network’s hyper-parameters may take too long to be feasible using an exhaustive search, especially when the cardinality of the search space has a big combinatorial number of possible solutions with various hyper-parameters. This problem is aggravated when we also need to optimize the parameters of the neural network, such as the weight of the hidden neurons and biases. Extreme learning machines (ELMs) are part of the random weights neural network family, in which parameters are randomly initialized, and the solution, unlike gradient-descent-based algorithms, can be found analytically. This ability is especially useful for metaheuristic analysis due to its reduced training times allowing a faster optimization process, but the problem of finding the best hyper-parameter configuration is still remaining. In this paper, we propose a modification of the artificial bee colony (ABC) metaheuristic to act as parameterizers for a regularized ELM, incorporating three methods: an adaptive mechanism for ABC to balance exploration (global search) and exploitation (local search), an adaptation of the opposition-based learning technique called opposition local-based learning (OLBL) to strengthen exploitation, and a record of access to the search space called forbidden redundant indexes (FRI) that allow us to avoid redundant calculations and track the explored percentage of the search space. We set ten parameterizations applying different combinations of the proposed methods, limiting them to explore up to approximately 10% of the search space, with results over 98% compared to the maximum performance obtained in the exhaustive search in binary and multiclass datasets. The results demonstrate a promising use of these parameterizations to optimize the hyper-parameters of the R-ELM in datasets with different characteristics in cases where computational efficiency is required, with the possibility of extending its use to other problems with similar characteristics with minor modifications, such as the parameterization of support vector machines, digital image filters, and other neural networks, among others. Full article

(This article belongs to the Section Computer Science & Engineering)

15 pages, 1639 KiB

Open AccessArticle

Energy Management in a Renewable-Based Microgrid Using a Model Predictive Control Method for Electrical Energy Storage Devices

by Ibrahima Toure, Alireza Payman, Mamadou-Baïlo Camara and Brayima Dakyo

Electronics 2024, 13(23), 4651; https://doi.org/10.3390/electronics13234651 - 25 Nov 2024

Abstract

In this paper, an energy management strategy is developed in a renewable energy-based microgrid composed of a wind farm, a battery energy storage system, and an electolyzer unit. The main objective of energy management in the studied microgrid is to guarantee a stable [...] Read more.

In this paper, an energy management strategy is developed in a renewable energy-based microgrid composed of a wind farm, a battery energy storage system, and an electolyzer unit. The main objective of energy management in the studied microgrid is to guarantee a stable supply of electrical energy to local consumers. In addition, it encompasses hydrogen gas production by using part of the available excess energy in the system, which has some economic benefits. Also, energy management can protect the battery bank from damage by preventing the possibility of it being overcharged. These objectives should be achieved by developing a robust and effective control technique for DC-DC converters that are connected to energy storage devices. For this purpose, an advanced control technique based on Model Predictive Control, which is recognized as a popular control technique for industrial and process applications, is developed. This technique has a fast dynamic response and good tracking features and is simple to implement. The simulation results prove the effectiveness of the proposed control strategy and control technique for energy management in the studied renewable energy-based microgrid. Full article

(This article belongs to the Special Issue Recent Advances in Modeling, Optimization and Control of the Distributed Energy Resources)

20 pages, 1386 KiB

Open AccessArticle

Privacy-Enhanced Sentiment Analysis in Mental Health: Federated Learning with Data Obfuscation and Bidirectional Encoder Representations from Transformers

by Shakil Ibne Ahsan, Djamel Djenouri and Rakibul Haider

Electronics 2024, 13(23), 4650; https://doi.org/10.3390/electronics13234650 - 25 Nov 2024

Abstract

This research aims to find an optimal balance between privacy and performance in forecasting mental health sentiment. This paper investigates federated learning (FL) augmented with a novel data obfuscation (DO) technique, where synthetic data is used to "mask" real data points. Bidirectional Encoder [...] Read more.

This research aims to find an optimal balance between privacy and performance in forecasting mental health sentiment. This paper investigates federated learning (FL) augmented with a novel data obfuscation (DO) technique, where synthetic data is used to "mask" real data points. Bidirectional Encoder Representations from Transformer (BERT) is used for sentiment analysis, forming a new framework, FL-BERT+DO, that addresses the privacy-performance trade-off. With FL, data remains decentralized, ensuring that user-sensitive information is retained on local devices rather than being shared with the FL server. The integration of BERT gives our system an enhanced feature of context sense-making from text conduct, and our model is extremely proficient in emotion categorization tasks. The experiments were performed on combined (real and replica synthetic) datasets containing emotions and showed significant enhancements compared to baseline methods. The proposed FL-BERT+DO framework shows the following metrics: prediction accuracy,

82.74 %

; precision,

83.30 %

; recall,

82.74 %

; F1-score,

82.80 %

. Further, we assessed its performance in the adversarial setup using membership inference and linkage attacks to ensure the privacy-preserved performance did not suffer deeply. It demonstrates that, even for large datasets, providing privacy-preserving prediction is possible and can significantly improve existing methods of addressing personal issues, like mental health support. Based on the results of our work, we can propose the development of secure decentralized learning systems that are capable of providing high accuracy of sentiment analysis and meeting strict privacy constraints. Full article

(This article belongs to the Section Networks)

26 pages, 2063 KiB

Open AccessArticle

Dynamic Characteristic Analysis of Multi-Virtual Synchronous Generator Systems Considering Line Impedance in Multi-Node Microgrid

by Wei Xie, Liangzi Li, Weihao Kong, Zheng Peng, Xiaogang Li, Dandan Jiao, Chenyi Xu and Zebin Yang

Electronics 2024, 13(23), 4649; https://doi.org/10.3390/electronics13234649 - 25 Nov 2024

Abstract

With the increasing integration of distributed energy resources into modern power systems, virtual synchronous generators (VSGs) have been a promising approach to imitate the inertial response of synchronous generators, thereby enhancing microgrid stability in a dynamic state. When many VSGs are integrated into [...] Read more.

With the increasing integration of distributed energy resources into modern power systems, virtual synchronous generators (VSGs) have been a promising approach to imitate the inertial response of synchronous generators, thereby enhancing microgrid stability in a dynamic state. When many VSGs are integrated into microgrids, the dynamic characteristics of the system become increasingly complex. Current studies typically assume that different VSGs are connected to a common coupling point, focusing on analyzing the interaction characteristics, which may overlook the widely distributed line impedances in microgrids with distance between different facilities. This may lead to incomplete understanding of the interaction dynamics when VSGs are distributed over long feeder lines. Therefore, this paper proposes and investigates a multi-node, multi-VSG model incorporating line impedances among different nodes, establishing transfer function models for multi-node load disturbances and the frequency responses of individual VSGs. The study explores the dynamic response characteristics of VSGs under varying parameter influences and proposes principles for designing VSG port impedance and inertia parameters to optimize system dynamic frequency characteristics. The findings, validated through simulations in PSCAD v46, provide insights for enhancing the flexibility and reliability of grids incorporating VSGs. Full article

(This article belongs to the Special Issue Innovations in Intelligent Microgrid Operation and Control)

22 pages, 1195 KiB

Open AccessArticle

Optimized Profit Allocation Model for Service Alliance Transactions Considering Risk

by Wei Liu, Mengxing Huang and Wenlong Feng

Electronics 2024, 13(23), 4648; https://doi.org/10.3390/electronics13234648 - 25 Nov 2024

Abstract

In service alliances, where multiple service providers collaborate to complete service transactions, the equitable allocation of profits based on their respective contributions and risk-bearing capacities is paramount. This paper introduces an optimized profit allocation game model that integrates risk considerations into the Nash [...] Read more.

In service alliances, where multiple service providers collaborate to complete service transactions, the equitable allocation of profits based on their respective contributions and risk-bearing capacities is paramount. This paper introduces an optimized profit allocation game model that integrates risk considerations into the Nash bargaining framework. Initially, the study established a service alliance transaction model that considered the interactions among multiple participants, providing a robust theoretical foundation for cooperation. Subsequently, the concept of marginal risk was introduced, and a unique calculation method based on the Shapley value was devised to quantify risk contributions. Finally, an improved Nash bargaining model was proposed, which introduced a risk adjustment factor, explicitly addressing the impact of each participant’s risk on profit allocation. Through computational cases and result analyses, this model demonstrated its ability to balance profit and risk and to optimize outcomes for all participants, and it validated the fairness and rationality of the proposed allocation method. Full article

► Show Figures

Figure 1

24 pages, 8579 KiB

Open AccessArticle

Research on Directional Elements of Two-Terminal Weak-Feed AC Systems with a Negative Sequence Control Strategy

by Yan Li, Wentao Yang, Xiaofang Wu, Runbin Cao, Weihuang Huang, Faxi Peng and Junjie Hou

Electronics 2024, 13(23), 4647; https://doi.org/10.3390/electronics13234647 - 25 Nov 2024

Abstract

It has become a typical scenario in power systems that renewable energy power supply is connected to an AC system through flexible DC transmission. However, since both sides of the AC line are power electronic converters, the negative sequence suppression strategy will be [...] Read more.

It has become a typical scenario in power systems that renewable energy power supply is connected to an AC system through flexible DC transmission. However, since both sides of the AC line are power electronic converters, the negative sequence suppression strategy will be put into the converters at both ends during the asymmetric fault, which causes fundamental changes in the fault characteristics of the system, which is reflected in the two-terminal weak-feed characteristics, leading to the decline of traditional protection performance and affecting the safe operation of the system. Therefore, this paper presents a directional element of a double-ended weakly fed AC system with a negative sequence control strategy. Firstly, the characteristics of the negative sequence impedance under the negative sequence suppression strategy are analyzed when the AC line has asymmetric faults. Secondly, the difference in negative sequence impedance amplitude is analyzed. Finally, the direction element is constructed by the method of de-wave trend analysis The proposed scheme can realize the rapid identification of fault directions at both ends. The simulation results show that the proposed scheme is suitable for a two-terminal weak-feed AC system and can operate reliably under 300 Ω transition resistance and 20 dB noise interference. Full article

(This article belongs to the Special Issue Advanced Online Monitoring and Fault Diagnosis of Power Equipment)

► Show Figures

Figure 1

16 pages, 255 KiB

Open AccessArticle

Fuzzy Neural Network for Detecting Anomalies in Blockchain Transactions

by Łukasz Apiecionek and Paweł Karbowski

Electronics 2024, 13(23), 4646; https://doi.org/10.3390/electronics13234646 - 25 Nov 2024

Abstract

This publication focuses on the use of the artificial intelligence for detecting anomalies, especially in the blockchain network. The research methodology includes the selection of anomalies to be detected and the processing of blockchain data. Various artificial intelligence methods were implemented for anomaly [...] Read more.

This publication focuses on the use of the artificial intelligence for detecting anomalies, especially in the blockchain network. The research methodology includes the selection of anomalies to be detected and the processing of blockchain data. Various artificial intelligence methods were implemented for anomaly detection as part of the tests, and one new solution—a Fuzzy Neural Network—was presented. The findings indicate the possibility of detecting selected anomalies in the blockchain using artificial intelligence, which is of significant importance for the security of this technology. The conclusions present a discussion on limitations, future research prospects, and guidelines for future work. Full article

(This article belongs to the Special Issue Advances in Intelligent and Adaptive Decision Support Systems)

17 pages, 5933 KiB

Open AccessArticle

A Lightweight Transmission Line Foreign Object Detection Algorithm Incorporating Adaptive Weight Pooling

by Junbo Hao, Guangying Yan, Lidong Wang, Honglan Pei, Xu Xiao and Baifu Zhang

Electronics 2024, 13(23), 4645; https://doi.org/10.3390/electronics13234645 - 25 Nov 2024

Abstract

Aerial photography using unmanned aerial vehicles (UAVs) to detect foreign objects is an important method to ensure the safety of transmission lines. However, existing detection algorithms often encounter challenges in complex environments, including limited recognition capability and high computational demands. To address these [...] Read more.

Aerial photography using unmanned aerial vehicles (UAVs) to detect foreign objects is an important method to ensure the safety of transmission lines. However, existing detection algorithms often encounter challenges in complex environments, including limited recognition capability and high computational demands. To address these issues, this paper proposes YOLO-LAF, a lightweight foreign object detection algorithm that is based on YOLOv8n and incorporates an innovative adaptive weight pooling technique. The proposed method introduces a novel adaptive weight pooling module within the backbone network to enhance feature extraction for detecting foreign objects on transmission lines. Additionally, a multi-scale detection strategy is designed to integrate the FasterBlock and EMA modules. This combination enables the model to effectively capture both global and local image features through cross-channel interactions, thereby reducing misdetection and omission rates. Furthermore, a C2f-SCConv module is introduced in the neck network to streamline the model by eliminating redundant features, thus improving computational efficiency. Experimental results demonstrate that YOLO-LAF achieves average accuracies of 91.2% and 85.3% on the Southern Power Grid and RailFOD23 datasets, respectively, outperforming the original YOLOv8n algorithm by 2.6% and 1.8%. Moreover, YOLO-LAF reduces the number of parameters by 23.5% and 14.8% and the computational costs by 19.9% and 24.8%, respectively. These improvements demonstrate the superior detection performance of YOLO-LAF compared to other mainstream detection algorithms. Full article

► Show Figures

Figure 1

30 pages, 4423 KiB

Open AccessArticle

Watermarking Tiny MLCommons Image Applications Without Extra Deployability Costs

by Alessandro Carra, Dilan Ece Durmuskaya, Beatrice Di Giulio, Laura Falaschetti, Claudio Turchetti and Danilo Pietro Pau

Electronics 2024, 13(23), 4644; https://doi.org/10.3390/electronics13234644 - 25 Nov 2024

Viewed by 32

Abstract

The tasks assigned to neural network (NN) models are increasingly challenging due to the growing demand for their applicability across domains. Advanced machine learning programming skills, development time, and expensive assets are required to achieve accurate models, and they represent important assets, particularly [...] Read more.

The tasks assigned to neural network (NN) models are increasingly challenging due to the growing demand for their applicability across domains. Advanced machine learning programming skills, development time, and expensive assets are required to achieve accurate models, and they represent important assets, particularly for small and medium enterprises. Whether they are deployed in the Cloud or on Edge devices, i.e., resource-constrained devices that require the design of tiny NNs, it is of paramount importance to protect the associated intellectual properties (IP). Neural networks watermarking (NNW) can help the owner to claim the origin of an NN model that is suspected to have been attacked or copied, thus illegally infringing the IP. Adapting two state-of-the-art NNW methods, this paper aims to define watermarking procedures to securely protect tiny NNs’ IP in order to prevent unauthorized copies of these networks; specifically, embedded applications running on low-power devices, such as the image classification use cases developed for MLCommons benchmarks. These methodologies inject into a model a unique and secret parameter pattern or force an incoherent behavior when trigger inputs are used, helping the owner to prove the origin of the tested NN model. The obtained results demonstrate the effectiveness of these techniques using AI frameworks both on computers and MCUs, showing that the watermark was successfully recognized in both cases, even if adversarial attacks were simulated, and, in the second case, if accuracy values, required resources, and inference times remained unchanged. Full article

(This article belongs to the Special Issue Towards Efficient and Reliable AI at the Edge)

► Show Figures

Figure 1

13 pages, 347 KiB

Open AccessArticle

Adaptive Control of Retrieval-Augmented Generation for Large Language Models Through Reflective Tags

by Chengyuan Yao and Satoshi Fujita

Electronics 2024, 13(23), 4643; https://doi.org/10.3390/electronics13234643 - 25 Nov 2024

Abstract

While retrieval-augmented generation (RAG) enhances large language models (LLMs), it also introduces challenges that can impact accuracy and performance. In practice, RAG can obscure the intrinsic strengths of LLMs. Firstly, LLMs may become too reliant on external retrieval, underutilizing their own knowledge and [...] Read more.

While retrieval-augmented generation (RAG) enhances large language models (LLMs), it also introduces challenges that can impact accuracy and performance. In practice, RAG can obscure the intrinsic strengths of LLMs. Firstly, LLMs may become too reliant on external retrieval, underutilizing their own knowledge and reasoning, which can diminish responsiveness. Secondly, RAG may introduce irrelevant or low-quality data, adding noise that disrupts generation, especially with complex tasks. This paper proposes an RAG framework that uses reflective tags to manage retrieval, evaluating documents in parallel and applying the chain-of-thought (CoT) technique for step-by-step generation. The model selects the highest quality content for final output. The key contributions are as follows: (1) reducing hallucinations by focusing on high-scoring documents; (2) improving real-time performance through efficient retrieval; and (3) mitigating negative effects by filtering out irrelevant information using parallel generation and reflective tagging. These innovations aim to optimize RAG for more reliable, high-quality results. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

17 pages, 4297 KiB

Open AccessArticle

Multi-Scale Frequency-Spatial Domain Attention Fusion Network for Building Extraction in Remote Sensing Images

by Jia Liu, Hao Chen, Zuhe Li and Hang Gu

Electronics 2024, 13(23), 4642; https://doi.org/10.3390/electronics13234642 - 25 Nov 2024

Viewed by 80

Abstract

Building extraction from remote sensing images holds significant importance in the fields of land resource management, urban planning, and disaster assessment. Encoder-decoder deep learning models are increasingly favored due to their advanced feature representation capabilities in image analysis. However, because of the diversity [...] Read more.

Building extraction from remote sensing images holds significant importance in the fields of land resource management, urban planning, and disaster assessment. Encoder-decoder deep learning models are increasingly favored due to their advanced feature representation capabilities in image analysis. However, because of the diversity of architectural styles and issues such as tree occlusion, traditional methods often result in building omissions and blurred boundaries when extracting building footprints. Given these limitations, this paper proposes a cutting-edge Multi-Scale Frequency-Spatial Domain Attention Fusion Network (MFSANet), which consists of two principal modules, named Frequency-Spatial Domain Attention Fusion Module (FSAFM) and Attention-Guided Multi-scale Fusion Upsampling Module (AGMUM). FSAFM introduces frequency domain attention and spatial attention separately to enhance the feature maps, thereby strengthening the model’s boundary-detection capabilities and ultimately improving the accuracy of building extraction. AGMUM first resizes and concatenates attention enhancement maps to enhance contextual understanding and applies attention guidance to further improve prediction accuracy. Our model demonstrates superior performance compared to existing semantic segmentation methods on both the WHU building data set and the Inria aerial image data set. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

13 pages, 1984 KiB

Open AccessArticle

CTDNets: A High-Precision Hybrid Deep Learning Model for Modulation Recognition with Early-Stage Layer Fusion

by Zhiyuan Zhao, Yi Qu, Xin Zhou, Yiyong Zhu, Li Zhang, Jirui Lin and Haohui Jiang

Electronics 2024, 13(23), 4641; https://doi.org/10.3390/electronics13234641 - 25 Nov 2024

Viewed by 66

Abstract

To further enhance the recognition accuracy of automatic modulation recognition, improve communication efficiency, strengthen security, and optimize resource management, this paper designs a high-precision hybrid deep learning model featuring early-stage layer fusion. This model combines with Convolutional Neural Networks (CNN), Transformers, and Deep [...] Read more.

To further enhance the recognition accuracy of automatic modulation recognition, improve communication efficiency, strengthen security, and optimize resource management, this paper designs a high-precision hybrid deep learning model featuring early-stage layer fusion. This model combines with Convolutional Neural Networks (CNN), Transformers, and Deep Neural Networks (DNN) to enhance the model’s feature extraction capabilities, thereby improving modulation recognition accuracy. Experiments are performed on RadioML2016.10a and RadioML2018.01a, and the results show that this architecture can effectively combine the advantages of different types of models, making the overall performance more robust and suitable for complex automatic modulation recognition problems. Full article

► Show Figures

Figure 1

14 pages, 2922 KiB

Open AccessArticle

Enhancing Security of Automotive OTA Firmware Updates via Decentralized Identifiers and Distributed Ledger Technology

by Ana Kovacevic and Nenad Gligoric

Electronics 2024, 13(23), 4640; https://doi.org/10.3390/electronics13234640 - 25 Nov 2024

Viewed by 135

Abstract

The increasing connectivity and complexity of automotive systems require enhanced mechanisms for firmware updates to ensure security and integrity. Traditional methods are insufficient for modern vehicles that require seamless over-the-air (OTA) updates. Current OTA mechanisms often lack robust security measures, leaving vehicles vulnerable [...] Read more.

The increasing connectivity and complexity of automotive systems require enhanced mechanisms for firmware updates to ensure security and integrity. Traditional methods are insufficient for modern vehicles that require seamless over-the-air (OTA) updates. Current OTA mechanisms often lack robust security measures, leaving vehicles vulnerable to attacks. This paper proposes an innovative approach based on the use of decentralized identifiers (DIDs) and distributed ledger technology (DLT) for secure OTA firmware updates of on-vehicle software. By utilizing DIDs for unique vehicle identification, as well as verifiable credentials (VCs) and verifiable presentations (VPs) for secure information exchange and verification, the solution ensures the integrity and authenticity of software updates. It also allows for the revocation of specific updates, if necessary, thereby improving overall security. The security analysis applied the STRIDE methodology, which enabled the identification of potential threats, including spoofing, tampering, and privilege escalation. The results showed that our solution effectively mitigates these threats, while a performance evaluation indicated low latency during operations. Full article

(This article belongs to the Special Issue Advanced Industry 4.0/5.0: Intelligence and Automation)

► Show Figures

Figure 1

23 pages, 8982 KiB

Open AccessArticle

Heat Transfer Simulation and Structural Optimization of Spiral Fin-and-Tube Heat Exchanger

by Huaquan Jiang, Tingting Jiang, Hongyang Tian, Qiang Wu, Congying Deng and Renliang Zhang

Electronics 2024, 13(23), 4639; https://doi.org/10.3390/electronics13234639 - 25 Nov 2024

Viewed by 154

Abstract

The spiral fin-and-tube heat exchanger is a widely used heat transfer device in heating and cooling applications, and its performance is influenced by multiple structural parameters, including the pitch, thickness, and height of the fins, the diameter and thickness of the base tube, [...] Read more.

The spiral fin-and-tube heat exchanger is a widely used heat transfer device in heating and cooling applications, and its performance is influenced by multiple structural parameters, including the pitch, thickness, and height of the fins, the diameter and thickness of the base tube, and the transverse and longitudinal tube spacings. This study comprehensively explores how these factors affect the heat transfer performance of the spiral fin-and-tube heat exchanger and aims to determine its optimal configuration of structural parameters. First, orthogonal experiments are arranged based on these factors to conduct the corresponding finite element numerical simulations and to determine the effects of these factors on the heat transfer and resistance performance of the spiral fin-and-tube heat exchanger. Subsequently, support vector regression (SVR) is introduced to predict the heat transfer factor and the resistance factor, with the aim of benefiting the construction of a multi-objective optimization model for optimizing the two factors simultaneously. Then, a comprehensive performance indicator is used to transform the multi-optimization problem to a single optimization problem, and the genetic algorithm is adopted to solve an optimal configuration of the heat exchanger structural parameters. Ultimately, the finite element numerical simulation is utilized to validate the accuracy of the optimization. Case studies are conducted on a specific spiral fin-and-tube heat exchanger. After the optimization, the heat transfer factor is improved by 44.44%, and the resistance factor is increased by 14.19%. However, the comprehensive performance indicator is increased by 38.79%. Full article

(This article belongs to the Special Issue Digital Twins of Complex Systems: Data, Modeling, Algorithm and Application)

► Show Figures

Figure 1

17 pages, 2856 KiB

Open AccessArticle

Improved Deep Learning for Parkinson’s Diagnosis Based on Wearable Sensors

by Jintao Yu, Ke Meng, Tingwei Liang, He Liu and Xiaowen Wang

Electronics 2024, 13(23), 4638; https://doi.org/10.3390/electronics13234638 - 25 Nov 2024

Viewed by 161

Abstract

Parkinson’s disease is a neurodegenerative disease that seriously affects the quality of life of patients. In this study, we propose a new Parkinson’s diagnosis method using deep learning techniques. The method takes multi-channel sensor signals as inputs, and the full convolutional and LSTM [...] Read more.

Parkinson’s disease is a neurodegenerative disease that seriously affects the quality of life of patients. In this study, we propose a new Parkinson’s diagnosis method using deep learning techniques. The method takes multi-channel sensor signals as inputs, and the full convolutional and LSTM blocks of the model perceive the same time-series inputs from two different views, and connect the extracted spatial features with temporal features. In order to improve the detection performance, a channel attention mechanism was incorporated into the model, and a data augmentation approach was used to eliminate the effect of unbalanced datasets on model training. The pd vs. hc and pd vs. dd classification tasks were performed, which improved accuracy by 4.25% and 8.03%, respectively, compared to the previous best results. Both improvements were higher than the previous methods using machine learning combined with feature extraction. To utilize the available data resources more effectively, this study conducted the pd vs. hc vs. dd triple classification task for the first time, which improved the model’s ability to identify disease features. In that task, the accuracy rate reached 78.23%. The experimental results fully demonstrated the effectiveness of the proposed deep learning method for Parkinson’s diagnosis. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

► Show Figures

Figure 1

19 pages, 5074 KiB

Open AccessArticle

Effects of Industrial Maintenance Task Complexity on Neck and Shoulder Muscle Activity During Augmented Reality Interactions

by Mohammed H. Alhaag, Faisal M. Alessa, Ibrahim M. Al-harkan, Mustafa M. Nasr, Mohamed Z. Ramadan and Saleem S. AlSaleem

Electronics 2024, 13(23), 4637; https://doi.org/10.3390/electronics13234637 - 25 Nov 2024

Viewed by 174

Abstract

Extensive studies have demonstrated the advantages of augmented reality (AR) in improving efficiency, thereby fulfilling a quality role in industry. Yet, the corresponding physical strain on individuals poses a significant challenge. This study explores the effects of task difficulty (complex versus simple maintenance [...] Read more.

Extensive studies have demonstrated the advantages of augmented reality (AR) in improving efficiency, thereby fulfilling a quality role in industry. Yet, the corresponding physical strain on individuals poses a significant challenge. This study explores the effects of task difficulty (complex versus simple maintenance activities) and multimedia guidance (e.g., paper-based versus AR via HoloLens) on physical strain, body discomfort ratings, perceived exertion, and mental effort. A 2 × 2 mixed design was employed, involving a total of 28 participants with an average age of 32.12 ± 2.45 years. Physical strain was evaluated by measuring the normalized root mean square (RMS) of electromyography (EMG) indicators, expressed as a percentage of maximum voluntary contraction (%MVC) from six muscles (i.e., right flexor carpi radialis (RFCR), right middle deltoid (RMD), right upper trapezius (RUT), right cervical extensor (RCE), and right and left splenius (RSPL and LSPL) muscles. The results indicated that AR instruction, particularly in complex tasks, led to higher physical strain in the neck and shoulder muscles (RCE and RUT) compared with paper-based methods. However, AR significantly reduced strain in the RSPL, LSPL, RMD, and RFCR muscles during both simple and complex tasks. This study highlights that while AR can lower physical strain in certain muscle groups, it also introduces increased strain in the neck and shoulders, particularly during more demanding tasks. This study highlights the need for ergonomic considerations when designing and implementing AR technologies, especially for complex tasks that inherently demand more from the user, both physically and cognitively. Full article

(This article belongs to the Special Issue Applications of Virtual, Augmented and Mixed Reality)

► Show Figures

Figure 1

15 pages, 3512 KiB

Open AccessArticle

MMAformer: Multiscale Modality-Aware Transformer for Medical Image Segmentation

by Hao Ding, Xiangfen Zhang, Wenhao Lu, Feiniu Yuan and Haixia Luo

Electronics 2024, 13(23), 4636; https://doi.org/10.3390/electronics13234636 - 25 Nov 2024

Viewed by 115

Abstract

The segmentation of medical images, particularly for brain tumors, is essential for clinical diagnosis and treatment planning. In this study, we proposed MMAformer, a Multiscale Modality-Aware Transformer model, which is designed for segmenting brain tumors by utilizing multimodality magnetic resonance imaging (MRI). Complementary [...] Read more.

The segmentation of medical images, particularly for brain tumors, is essential for clinical diagnosis and treatment planning. In this study, we proposed MMAformer, a Multiscale Modality-Aware Transformer model, which is designed for segmenting brain tumors by utilizing multimodality magnetic resonance imaging (MRI). Complementary information between different sequences helps the model delineate tumor boundaries and distinguish different tumor tissues. To enable the model to acquire the complementary information between related sequences, MMAformer employs a multistage encoder, which uses a cross-modal downsampling (CMD) block for learning and integrating the complementary information between sequences at different scales. In order to effectively fuse the various information extracted by the encoder, the Multimodal Gated Aggregation (MGA) block combines the dual attention mechanism and multi-gated clustering to effectively fuse the spatial, channel, and modal features of different MRI sequences. In the comparison experiments on the BraTS2020 and BraTS2021 datasets, the average Dice score of MMAformer reached 86.3% and 91.53%, respectively, indicating that MMAformer surpasses the current state-of-the-art approaches. MMAformer’s innovative architecture, which effectively captures and integrates multimodal information at various scales, offers a promising solution for tackling complex medical image segmentation challenges. Full article

(This article belongs to the Special Issue Machine Learning and Deep Learning Based Pattern Recognition)

► Show Figures

Figure 1

8 pages, 3626 KiB

Open AccessCommunication

Analysis and Design of Low-Noise Radio-Frequency Power Amplifier Supply Modulator for Frequency Division Duplex Cellular Systems

by Ji-Seon Paek

Electronics 2024, 13(23), 4635; https://doi.org/10.3390/electronics13234635 - 25 Nov 2024

Viewed by 160

Abstract

This paper describes an analysis of power supply rejection and noise improvement techniques for an envelope-tracking power amplifier. Although the envelope-tracking technique improves efficiency, its power supply rejection ratio is much lower than that of average power tracking or a fixed-supply power amplifier. [...] Read more.

This paper describes an analysis of power supply rejection and noise improvement techniques for an envelope-tracking power amplifier. Although the envelope-tracking technique improves efficiency, its power supply rejection ratio is much lower than that of average power tracking or a fixed-supply power amplifier. In FDD systems with the envelope-tracking technique, the low power supply rejection ratio generates much output noise in the RX band and degrades the receiver’s sensitivity. An SM is designed by using a 130 nm CMOS process, and the chip die area is 2 × 2 mm² with a 25-pin wafer-level chip-scale package. The designed SM achieved peak efficiencies of 78–83% for LTE signals with a 5.8 dB PAPR and various channel bandwidths. For the low-output-noise-supply modulator, noise reduction techniques using resonant-frequency tuning and a notch filter are employed, and the measured results show maximum 1.8/5/5.3/3.8/3 dB noise reduction in LTE bands B17/B5/B2/B3/B7, respectively. Full article

(This article belongs to the Special Issue Millimeter-Wave/Terahertz Integrated Circuit Design)

► Show Figures

Figure 1

13 pages, 4672 KiB

Open AccessArticle

A Four-Point Orientation Method for Scene-to-Model Point Cloud Registration of Engine Blades

by Duanjiao Li, Ying Zhang, Ziran Jia, Zhiyu Wang, Qiu Fang and Xiaogang Zhang

Electronics 2024, 13(23), 4634; https://doi.org/10.3390/electronics13234634 - 25 Nov 2024

Viewed by 171

Abstract

The use of 3D optical equipment for multi-view scanning is a promising approach to assessing the processing errors of engine blades. However, incomplete scanned point cloud data may impact the accuracy of point cloud registration (PCR). This paper proposes a four-point orientation point [...] Read more.

The use of 3D optical equipment for multi-view scanning is a promising approach to assessing the processing errors of engine blades. However, incomplete scanned point cloud data may impact the accuracy of point cloud registration (PCR). This paper proposes a four-point orientation point cloud registration method to improve the efficiency and accuracy of the coarse registration of turbine blades and prevent PCR failure. First, the point cloud is divided into four labeling blocks based on a principal component analysis. Second, keypoints are detected in each block based on their distance from the plane formed by the principal axes and described with a location-label descriptor based on their position. Third, a keypoint pair set is chosen based on the descriptor, and a suitable keypoint base is selected through singular value decomposition to obtain the final rigid transformation. To verify the effectiveness of the method, experiments are conducted on different blades. The results demonstrate the improved performance and efficiency of the proposed method of coarse registration for turbine blades. Full article

(This article belongs to the Special Issue Advanced Machine Learning Technologies and Their Applications in Intelligent Imaging and Image Processing)

► Show Figures

Figure 1

19 pages, 715 KiB

Open AccessArticle

Applying Large Language Model to User Experience Testing

by Nien-Lin Hsueh, Hsuen-Jen Lin and Lien-Chi Lai

Electronics 2024, 13(23), 4633; https://doi.org/10.3390/electronics13234633 - 24 Nov 2024

Viewed by 184

Abstract

The maturation of internet usage environments has elevated User Experience (UX) to a critical factor in system success. However, traditional manual UX testing methods are hampered by subjectivity and lack of standardization, resulting in time-consuming and costly processes. This study explores the potential [...] Read more.

The maturation of internet usage environments has elevated User Experience (UX) to a critical factor in system success. However, traditional manual UX testing methods are hampered by subjectivity and lack of standardization, resulting in time-consuming and costly processes. This study explores the potential of Large Language Models (LLMs) to address these challenges by developing an automated UX testing tool. Our innovative approach integrates the Rapi web recording tool to capture user interaction data with the analytical capabilities of LLMs, utilizing Nielsen’s usability heuristics as evaluation criteria. This methodology aims to significantly reduce the initial costs associated with UX testing while maintaining assessment quality. To validate the tool’s efficacy, we conducted a case study featuring a tennis-themed course reservation system. The system incorporated multiple scenarios per page, allowing users to perform tasks based on predefined goals. We employed our automated UX testing tool to evaluate screenshots and interaction logs from user sessions. Concurrently, we invited participants to test the system and complete UX questionnaires based on their experiences. Comparative analysis revealed that varying prompts in the automated UX testing tool yielded different outcomes, particularly in detecting interface elements. Notably, our tool demonstrated superior capability in identifying issues aligned with Nielsen’s usability principles compared to participant evaluations. This research contributes to the field of UX evaluation by leveraging advanced language models and established usability heuristics. Our findings suggest that LLM-based automated UX testing tools can offer more consistent and comprehensive assessments. Full article

(This article belongs to the Special Issue Recent Advances of Software Engineering)

14 pages, 483 KiB

Open AccessArticle

Enhanced In-Network Caching for Deep Learning in Edge Networks

by Jiaqi Zhang, Wenjing Liu, Li Zhang and Jie Tian

Electronics 2024, 13(23), 4632; https://doi.org/10.3390/electronics13234632 - 24 Nov 2024

Viewed by 150

Abstract

With the deep integration of communication technology and Internet of Things technology, the edge network structure is becoming increasingly dense and heterogeneous. At the same time, in the edge network environment, characteristics such as wide-area differentiated services, decentralized deployment of computing and network [...] Read more.

With the deep integration of communication technology and Internet of Things technology, the edge network structure is becoming increasingly dense and heterogeneous. At the same time, in the edge network environment, characteristics such as wide-area differentiated services, decentralized deployment of computing and network resources, and highly dynamic network environment lead to the deployment of redundant or insufficient edge cache nodes, which restricts the efficiency of network service caching and resource allocation. In response to the above problems, research on the joint optimization of service caching and resources in the decentralized edge network scenario is carried out. Therefore, we have conducted research on the collaborative caching of training data among multiple edge nodes and optimized the number of collaborative caching nodes. Firstly, we use a multi-queue model to model the collaborative caching process. This model can be used to simulate the in-network cache replacement process on collaborative caching nodes. In this way, we can describe the data flow and storage changes during the caching process more clearly. Secondly, considering the limitation of storage space of edge nodes and the demand for training data within a training epoch, we propose a stochastic gradient descent algorithm to obtain the optimal number of caching nodes. This algorithm entirely takes into account the resource constraints in practical applications and provides an effective way to optimize the number of caching nodes. Finally, the simulation results clearly show that the optimized number of caching nodes can significantly improve the adequacy rate and hit rate of the training data, with the adequacy rate reaching 84% and the hit rate reaching 100%. Full article

(This article belongs to the Special Issue New Advances in Distributed Computing and Its Applications)

13 pages, 1520 KiB

Open AccessArticle

A Mobile Application to Facilitate Meal Box Sharing in Corporate Environments Using Cloud Infrastructure

by Priya Tushar Mohod, Richard I. Otuka, Nemitari Ajienka, Isibor Kennedy Ihianle and Augustine O. Nwajana

Electronics 2024, 13(23), 4631; https://doi.org/10.3390/electronics13234631 - 24 Nov 2024

Viewed by 213

Abstract

Food waste is a pressing global issue, particularly in urban settings, where substantial amounts of surplus food go unused. In corporate environments, this challenge is compounded by the lack of dedicated platforms to facilitate food sharing and reduce waste effectively. This paper examines [...] Read more.

Food waste is a pressing global issue, particularly in urban settings, where substantial amounts of surplus food go unused. In corporate environments, this challenge is compounded by the lack of dedicated platforms to facilitate food sharing and reduce waste effectively. This paper examines the current landscape of food waste, existing solutions, and the need for a specialised platform aimed at corporate employees. The proposed solution is the creation of a user-friendly application that enables the sharing of untouched homemade meals. Suppliers can post their meal boxes with details such as location, type of food, and availability status, while consumers can search for and select meal boxes based on their preferences. This paper addresses the gap in solutions for reducing food waste within corporate environments. The meal-box-sharing app provides a practical and sustainable method for minimising food waste and promoting productivity, health, and safety in the workplace. Full article

(This article belongs to the Special Issue Advances in AI, IoT and Smart Sensors for Digital Healthcare Applications)

16 pages, 3503 KiB

Open AccessArticle

Wireless Remote-Monitoring Technology for Wind-Induced Galloping and Vibration of Transmission Lines

by Peng Wang, Yuanchang Zhong, Yu Chen and Dalin Li

Electronics 2024, 13(23), 4630; https://doi.org/10.3390/electronics13234630 - 24 Nov 2024

Viewed by 242

Abstract

In order to achieve wireless remote monitoring of wind-induced vibrations in power-transmission lines based on MEMS sensors, it is necessary to devise a method for reconstructing the wind swing curve, enabling the device’s real-time performance to promptly acquire, restore, and analyze data. Based [...] Read more.

In order to achieve wireless remote monitoring of wind-induced vibrations in power-transmission lines based on MEMS sensors, it is necessary to devise a method for reconstructing the wind swing curve, enabling the device’s real-time performance to promptly acquire, restore, and analyze data. Based on existing single-axis vibration-sensitive components, a measurement array using self-powered MEMS sensors and spacers has been designed. The Orthogonal Matching Pursuit (OMP) algorithm is selected to obtain displacement data collected by sensors installed on the transmission-line spacers. Leveraging the inherent sparsity of the data, a Gaussian white noise regularization matrix is chosen to establish the observation matrix. Through the algorithm, wind data curve reconstruction is achieved, enabling the reconstruction of large-span wind-induced vibration information without distortion. The experimental results demonstrate that when applying the orthogonal tracking algorithm in transmission-line curve reconstruction, sparsity is selected based on the sampling length, that is, the number of sensors installed on the spacers is determined by the span length; a portion of the observation values are selected to generate the observation matrix; and the wind galloping data curve of the transmission line is well restored. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 13, Issue 23 (December-1 2024) – 83 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI