Electronics

24 pages, 2796 KiB

Open AccessArticle

Performance and Latency Efficiency Evaluation of Kubernetes Container Network Interfaces for Built-In and Custom Tuned Profiles

by Vedran Dakić, Jasmin Redžepagić, Matej Bašić and Luka Žgrablić

Electronics 2024, 13(19), 3972; https://doi.org/10.3390/electronics13193972 - 9 Oct 2024

Viewed by 1041

Abstract

In the era of DevOps, developing new toolsets and frameworks that leverage DevOps principles is crucial. This paper demonstrates how Ansible’s powerful automation capabilities can be harnessed to manage the complexity of Kubernetes environments. This paper evaluates efficiency across various CNI (Container Network [...] Read more.

In the era of DevOps, developing new toolsets and frameworks that leverage DevOps principles is crucial. This paper demonstrates how Ansible’s powerful automation capabilities can be harnessed to manage the complexity of Kubernetes environments. This paper evaluates efficiency across various CNI (Container Network Interface) plugins by orchestrating performance analysis tools across multiple power profiles. Our performance evaluations across network interfaces with different theoretical bandwidths gave us a comprehensive understanding of CNI performance and overall efficiency, with performance efficiency coming well below expectations. Our research confirms that certain CNIs are better suited for specific use cases, mainly when tuning our environment for smaller or larger network packets and workload types, but also that there are configuration changes we can make to mitigate that. This paper also provides research into how to use performance tuning to optimize the performance and efficiency of our CNI infrastructure, with practical implications for improving the performance of Kubernetes environments in real-world scenarios, particularly in more demanding scenarios such as High-Performance Computing (HPC) and Artificial Intelligence (AI). Full article

(This article belongs to the Special Issue Software-Defined Cloud Computing: Latest Advances and Prospects)

► Show Figures

Figure 1

17 pages, 4841 KiB

Open AccessArticle

Research on Multi-Objective Optimization Methods of Urban Rail Train Automatic Driving Based on NSGA-II

by Xiaoqiang Chen, Jianjun Meng, Ruxun Xu, Decang Li and Haobo Yang

Electronics 2024, 13(19), 3971; https://doi.org/10.3390/electronics13193971 - 9 Oct 2024

Viewed by 913

Abstract

In order to improve the control performance of automatic train operation (ATO) in urban rail trains, five typical operating sequences of urban rail trains were studied. Under the condition of meeting the safety and comfort principles of train operation, a train dynamics model [...] Read more.

In order to improve the control performance of automatic train operation (ATO) in urban rail trains, five typical operating sequences of urban rail trains were studied. Under the condition of meeting the safety and comfort principles of train operation, a train dynamics model was established to achieve the goals of low energy consumption, short running time, and high stopping accuracy in urban rail transit trains. In the process of finding a multi-objective solution to this problem, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was used with an elite retention strategy, and the optimal Pareto multi-objective solution set was sought. In the process of optimal solution weight assignment, the hierarchical analysis Mahalanobis distance method, which combines subjective and objective analysis, was used. Finally, taking the Beijing Yizhuang subway line as the background design example, the simulation verified the effectiveness and feasibility of the algorithm and obtained high-quality automatic train driving curves under various working conditions. This research has important reference significance for the actual operation of automatic driving in urban rail trains. Full article

► Show Figures

Figure 1

22 pages, 4062 KiB

Open AccessArticle

A Distributed Non-Intrusive Load Monitoring Method Using Karhunen–Loeve Feature Extraction and an Improved Deep Dictionary

by Siqi Liu, Zhiyuan Xie and Zhengwei Hu

Electronics 2024, 13(19), 3970; https://doi.org/10.3390/electronics13193970 - 9 Oct 2024

Viewed by 621

Abstract

In recent years, the non-invasive load monitoring (NILM) method based on sparse coding has shown promising research prospects. This type of method learns a sparse dictionary for each monitoring target device, and it expresses load decomposition as a problem of signal reconstruction using [...] Read more.

In recent years, the non-invasive load monitoring (NILM) method based on sparse coding has shown promising research prospects. This type of method learns a sparse dictionary for each monitoring target device, and it expresses load decomposition as a problem of signal reconstruction using dictionaries and sparse vectors. The existing NILM methods based on sparse coding have problems such as inability to be applied to multi-state and time-varying devices, single-load characteristics, and poor recognition ability for similar devices in distributed manners. Using the analysis above, this paper focuses on devices with similar features in households and proposes a distributed non-invasive load monitoring method using Karhunen–Loeve (KL) feature extraction and an improved deep dictionary. Firstly, Karhunen–Loeve expansion (KLE) is used to perform subspace expansion on the power waveform of the target device, and a new load feature is extracted by combining singular value decomposition (SVD) dimensionality reduction. Afterwards, the states of all the target devices are modeled as super states, and an improved deep dictionary based on the distance separability measure function (DSM-DDL) is learned for each super state. Among them, the state transition probability matrix and observation probability matrix in the hidden Markov model (HMM) are introduced as the basis for selecting the dictionary order during load decomposition. The KL feature matrix of power observation values and improved depth dictionary are used to discriminate the current super state based on the minimum reconstruction error criterion. The test results based on the UK-DALE dataset show that the KL feature matrix can effectively reduce the load similarity of devices. Combined with DSM-DDL, KL has a certain information acquisition ability and acceptable computational complexity, which can effectively improve the load decomposition accuracy of similar devices, quickly and accurately estimating the working status and power demand of household appliances. Full article

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

► Show Figures

Figure 1

21 pages, 6252 KiB

Open AccessArticle

HCTC: Hybrid Convolutional Transformer Classifier for Automatic Modulation Recognition

by Jayesh Deorao Ruikar, Do-Hyun Park, Soon-Young Kwon and Hyoung-Nam Kim

Electronics 2024, 13(19), 3969; https://doi.org/10.3390/electronics13193969 - 9 Oct 2024

Viewed by 643

Abstract

Automatic modulation recognition (AMR) methods used in advanced wireless communications systems can identify unknown signals without requiring reference information. However, the acceptance of these methods depends on the accuracy, number of parameters, and computational complexity. This study proposes a hybrid convolutional transformer classifier [...] Read more.

Automatic modulation recognition (AMR) methods used in advanced wireless communications systems can identify unknown signals without requiring reference information. However, the acceptance of these methods depends on the accuracy, number of parameters, and computational complexity. This study proposes a hybrid convolutional transformer classifier (HCTC) for the classification of unknown signals. The proposed method utilizes a three-stage framework to extract features from in-phase/quadrature (I/Q) signals. In the first stage, spatial features are extracted using a convolutional layer. In the second stage, temporal features are extracted using a transformer encoder. In the final stage, the features are mapped using a deep-learning network. The proposed HCTC method is investigated using the benchmark RadioML database and compared with state-of-the-art methods. The experimental results demonstrate that the proposed method achieves a better performance in modulation signal classification. Additionally, the performance of the proposed method is evaluated when applied to different batch sizes and model configurations. Finally, open issues in modulation recognition research are addressed, and future research perspectives are discussed. Full article

(This article belongs to the Special Issue Artificial Intelligence and Machine Learning Techniques for Microwave Technologies)

► Show Figures

Figure 1

20 pages, 19118 KiB

Open AccessArticle

Visual Anomaly Detection via CNN-BiLSTM Network with Knit Feature Sequence for Floating-Yarn Stacking during the High-Speed Sweater Knitting Process

by Jing Li, Yixiao Wang, Weisheng Liang, Chao Xiong, Wenbo Cai, Lijun Li and Yi Liu

Electronics 2024, 13(19), 3968; https://doi.org/10.3390/electronics13193968 - 9 Oct 2024

Viewed by 748

Abstract

In order to meet the current expanding market demand for knitwear, high-speed automatic knitting machines with “one-line knit to shape” capability are widely used. However, the frequent emergence of floating-yarn stacking anomalies during the high-speed knitting process will seriously hinder the normal reciprocating [...] Read more.

In order to meet the current expanding market demand for knitwear, high-speed automatic knitting machines with “one-line knit to shape” capability are widely used. However, the frequent emergence of floating-yarn stacking anomalies during the high-speed knitting process will seriously hinder the normal reciprocating motion of the needles and cause a catastrophic fracture of the whole machine needle plate, greatly affecting the efficiency of the knitting machines. To overcome the limitations of the existing physical-probe detection method, in this work, we propose a visual floating-yarn anomaly recognition framework based on a CNN-BiLSTM network with the knit feature sequence (CNN-BiLSTM-KFS), which is a unique sequence of knitting yarn positions depending on the knitting status. The sequence of knitting characteristics contains the head speed, the number of rows, and the head movements of the automatic knitting machine, enabling the model to achieve more accurate and efficient floating-yarn identification in complex knitting structures by utilizing contextual information from knitting programs. Compared to the traditional probe inspection method, the framework is highly versatile as it does not need to be adjusted to the specifics of the automatic knitting machine during the production process. The recognition model is trained at the design and sampling stages, and the resulting model can be applied to different automatic knitting machines to recognize floating yarns occurring in various knitting structures. The experimental results show that the improved network spends 75% less time than the probe-based detection, has a higher overall average detection accuracy of 93% compared to the original network, and responds faster to floating yarn anomalies. The as-proposed CNN-BiLSTM-KFS floating-yarn visual detection method not only enhances the reliability of floating-yarn anomaly detection, but also reduces the time and cost required for production adjustments. The results of this study will bring significant improvements in the field of automatic floating-yarn detection and have the potential to promote the application of smart technologies in the knitting industry. Full article

► Show Figures

Figure 1

18 pages, 16340 KiB

Open AccessArticle

Real-Time Embedded Control of Vehicle Dynamics Using ESP32: A Discrete Nonlinear Approach

by Antonio Navarrete Guzmán, Cuauhtémoc Acosta Lúa, J. A. García-Rodríguez, Carlos Vidrios-Serrano and Marco A. Meza-Aguilar

Electronics 2024, 13(19), 3967; https://doi.org/10.3390/electronics13193967 - 9 Oct 2024

Viewed by 1113

Abstract

This article explores the application of the Espressif ESP32 System-On-Chip (SoC) for managing vehicle dynamics through real-time digital proportional–integral (PI-like) control. We present the development of advanced driving assistance algorithms for Active Front Steering (AFS) and Rear Torque Vectoring (RTV) on this cost-effective, [...] Read more.

This article explores the application of the Espressif ESP32 System-On-Chip (SoC) for managing vehicle dynamics through real-time digital proportional–integral (PI-like) control. We present the development of advanced driving assistance algorithms for Active Front Steering (AFS) and Rear Torque Vectoring (RTV) on this cost-effective, commercially available embedded system. Using digital PI-like control algorithms designed for AFS and RTV, the primary ESP32 board receives and processes steering signals, executing a discrete-time control model of the vehicle dynamic to enable dynamic adjustments to steering and torque. To enhance simulation realism, a secondary ESP32 is employed to generate the steering signal, effectively mimicking a steer-by-wire system via its analog output ports. This configuration facilitates the simulation and evaluation of control algorithms in a realistic test environment, ensuring enhanced vehicle dynamic stability and maneuverability under various conditions. Additionally, simulations are conducted using MATLAB 2023a and CarSim 2017.1 to compare the efficacy and benefits of the implementation. Our objective is to establish a platform for evaluating discrete controllers capable of real-time vehicle operation. This methodology accelerates and reduces the cost of improving vehicle system stability and responsiveness, enabling the immediate verification and fine-tuning of control parameters as needed. Full article

(This article belongs to the Special Issue Embedded Systems: Fundamentals, Design and Practical Applications)

► Show Figures

Figure 1

23 pages, 2789 KiB

Open AccessArticle

TCα-PIA: A Personalized Social Network Anonymity Scheme via Tree Clustering and α-Partial Isomorphism

by Mingmeng Zhang, Liang Chang, Yuanjing Hao, Pengao Lu and Long Li

Electronics 2024, 13(19), 3966; https://doi.org/10.3390/electronics13193966 - 9 Oct 2024

Viewed by 518

Abstract

Social networks have become integral to daily life, allowing users to connect and share information. The efficient analysis of social networks benefits fields such as epidemiology, information dissemination, marketing, and sentiment analysis. However, the direct publishing of social networks is vulnerable to privacy [...] Read more.

Social networks have become integral to daily life, allowing users to connect and share information. The efficient analysis of social networks benefits fields such as epidemiology, information dissemination, marketing, and sentiment analysis. However, the direct publishing of social networks is vulnerable to privacy attacks such as typical 1-neighborhood attacks. This attack can infer the sensitive information of private users using users’ relationships and identities. To defend against these attacks, the k-anonymity scheme is a widely used method for protecting user privacy by ensuring that each user is indistinguishable from at least

k - 1

other users. However, this approach requires extensive modifications that compromise the utility of the anonymized graph. In addition, it applies uniform privacy protection, ignoring users’ different privacy preferences. To address the above challenges, this paper proposes an anonymity scheme called TC

α

-PIA (Tree Clustering and

α

-Partial Isomorphism Anonymization). Specifically, TC

α

-PIA first constructs a similarity tree to capture subgraph feature information at different levels using a novel clustering method. Then, it extracts the different privacy requirements of each user based on the node cluster. Using the privacy requirements, it employs an

α

-partial isomorphism-based graph structure anonymization method to achieve personalized privacy requirements for each user. Extensive experiments on four public datasets show that TC

α

-PIA outperforms other alternatives in balancing graph privacy and utility. Full article

► Show Figures

Figure 1

27 pages, 3375 KiB

Open AccessReview

Power Converter Topologies for Heat Pumps Powered by Renewable Energy Sources: A Literature Review

by Joyce Assaf, Joselyn Stephane Menye, Mamadou Baïlo Camara, Damien Guilbert and Brayima Dakyo

Electronics 2024, 13(19), 3965; https://doi.org/10.3390/electronics13193965 - 9 Oct 2024

Viewed by 1164

Abstract

Heat pumps (HPs) have become pivotal for heating and cooling applications, serving as sustainable energy solutions. Coupled with renewable energy sources (RES) to run the compressor, which is the major energy-consuming component, they contribute to eco-conscious practices. Notably, their adaptability to be supplied [...] Read more.

Heat pumps (HPs) have become pivotal for heating and cooling applications, serving as sustainable energy solutions. Coupled with renewable energy sources (RES) to run the compressor, which is the major energy-consuming component, they contribute to eco-conscious practices. Notably, their adaptability to be supplied by either alternating (AC) or direct (DC) currents, facilitated through converters, makes them more flexible for versatile renewable energy (RE) applications. This paper presents a comprehensive review of converter topologies employed in various HP applications. The review begins by exploring previous applied photovoltaic (PV)-HP projects, focusing on the gaps in the literature concerning the employed converter topologies. Additionally, the review extends to include a broader examination of the converter topologies that could be employed on the source and load sides of a system powered by a mix of renewable energy sources, such as photovoltaics (PV), wind turbines (WTs), and energy storage systems (ESS), and analyzes their strengths and weaknesses. Special emphasis is given to understanding the various topologies of the power electronics converters in the context of HP applications. Finally, the paper concludes with a summary of the literature gaps, challenges, and directions for future research. Full article

(This article belongs to the Special Issue Efficient and Reliable DC–DC Converters and Related Industrial Electronics)

► Show Figures

Figure 1

19 pages, 3589 KiB

Open AccessArticle

Investigation of Bird Sound Transformer Modeling and Recognition

by Darui Yi and Xizhong Shen

Electronics 2024, 13(19), 3964; https://doi.org/10.3390/electronics13193964 - 9 Oct 2024

Viewed by 567

Abstract

Birds play a pivotal role in ecosystem and biodiversity research, and accurate bird identification contributes to the monitoring of biodiversity, understanding of ecosystem functionality, and development of effective conservation strategies. Current methods for bird sound recognition often involve processing bird songs into various [...] Read more.

Birds play a pivotal role in ecosystem and biodiversity research, and accurate bird identification contributes to the monitoring of biodiversity, understanding of ecosystem functionality, and development of effective conservation strategies. Current methods for bird sound recognition often involve processing bird songs into various acoustic features or fusion features for identification, which can result in information loss and complicate the recognition process. At the same time, the recognition method based on raw bird audio has not received widespread attention. Therefore, this study proposes a bird sound recognition method that utilizes multiple one-dimensional convolutional neural networks to directly learn feature representations from raw audio data, simplifying the feature extraction process. We also apply positional embedding convolution and multiple Transformer modules to enhance feature processing and improve accuracy. Additionally, we introduce a trainable weight array to control the importance of each Transformer module for better generalization of the model. Experimental results demonstrate our model’s effectiveness, with an accuracy rate of 99.58% for the public dataset Birds_data, as well as 98.77% for the Birdsonund1 dataset, and 99.03% for the UrbanSound8K environment sound dataset. Full article

► Show Figures

Figure 1

16 pages, 2345 KiB

Open AccessArticle

Performance Evaluation of Routing Algorithm in Satellite Self-Organizing Network on OMNeT++ Platform

by Guoquan Wang, Jiaxin Zhang, Yilong Zhang, Chang Liu and Zhaoyang Chang

Electronics 2024, 13(19), 3963; https://doi.org/10.3390/electronics13193963 - 9 Oct 2024

Viewed by 607

Abstract

Self-organizing networks of small satellites have gradually gained attention in recent years. However, self-organizing networks of small satellites have high topological change frequency, large transmission delay, and complex communication environments, which require appropriate networking and routing methods. Therefore, this paper, considering the characteristics [...] Read more.

Self-organizing networks of small satellites have gradually gained attention in recent years. However, self-organizing networks of small satellites have high topological change frequency, large transmission delay, and complex communication environments, which require appropriate networking and routing methods. Therefore, this paper, considering the characteristics of satellite networks, proposes the shortest queue length-cluster-based routing protocol (SQL-CBRP) and has built a satellite self-organizing network simulation platform based on OMNeT++. In this platform, functions such as the initial establishment of satellite self-organizing networks and cluster maintenance have been implemented. The platform was used to verify the latency and packet loss rate of SQL-CBRP and to compare it with Dijkstra and Greedy Perimeter Stateless Routing (GPSR). The results show that under high load conditions, the delay of SQL-CBRP is reduced by up to 4.1%, and the packet loss rate is reduced by up to 7.1% compared to GPSR. When the communication load is imbalanced among clusters, the delay of SQL-CBRP is reduced by up to 12.7%, and the packet loss rate is reduced by up to 16.7% compared to GPSR. Therefore, SQL-CBRP performs better in networks with high loads and imbalance loads. Full article

(This article belongs to the Special Issue Satellite Terrestrial Networks: Technologies, Security and Applications)

► Show Figures

Figure 1

17 pages, 3242 KiB

Open AccessArticle

Analysis of Handwriting for Recognition of Parkinson’s Disease: Current State and New Study

by Kamila Białek, Anna Potulska-Chromik, Jacek Jakubowski, Monika Nojszewska and Anna Kostera-Pruszczyk

Electronics 2024, 13(19), 3962; https://doi.org/10.3390/electronics13193962 - 9 Oct 2024

Viewed by 773

Abstract

One of the symptoms of Parkinson’s disease (PD) is abnormal handwriting caused by motor dysfunction. The development of tablet technology opens up opportunities for an effective analysis of the writing process of people suffering from Parkinson’s disease, aimed at supporting medical diagnosis using [...] Read more.

One of the symptoms of Parkinson’s disease (PD) is abnormal handwriting caused by motor dysfunction. The development of tablet technology opens up opportunities for an effective analysis of the writing process of people suffering from Parkinson’s disease, aimed at supporting medical diagnosis using machine learning methods. Several approaches have been used and presented in the literature that discuss the analysis and understanding of images created during the writing of single words or sentences. In this study, we propose an analysis based on a sequence of sentences, which allows us to assess the evolution of writing over time. The study material consisted of handwriting image samples acquired in a group of 24 patients with PD and 24 healthy controls. The parameterization of the handwriting image samples was carried out using domain knowledge. Using the exhaustive search method, we selected the relevant features for the SVM algorithm performing binary classification. The results obtained were assessed using quality measures, including overall accuracy, which was 91.67%. The results were compared with competitive works on the same subject and seem to be better (a higher level of accuracy with a much smaller number of features than those presented by others). Full article

(This article belongs to the Collection Image and Video Analysis and Understanding)

► Show Figures

Figure 1

9 pages, 1212 KiB

Open AccessArticle

Doherty Power Amplifier Design via Differential Combining

by Jorge Julian Moreno Rubio and Abdolhamid Noori

Electronics 2024, 13(19), 3961; https://doi.org/10.3390/electronics13193961 - 8 Oct 2024

Viewed by 792

Abstract

This paper introduces a novel differential combiner designed to effectively address parasitic capacitances of transistors used in power amplifier (PA) designs with precise compensation at a specified frequency. The combiner consists of a

λ / 4

transmission line with an integrated capacitor of [...] Read more.

This paper introduces a novel differential combiner designed to effectively address parasitic capacitances of transistors used in power amplifier (PA) designs with precise compensation at a specified frequency. The combiner consists of a

λ / 4

transmission line with an integrated capacitor of value

2 C_{O U T}

at its midpoint, which ensures accurate cancellation of parasitic effects. This design connects the drain pins of two transistors, which are considered identical in this configuration. By eliminating the need for complex parasitic compensation techniques, this method significantly simplifies the design process of Doherty Power Amplifiers (DPAs). Extensive simulations validate the effectiveness of this approach, highlighting its potential as a versatile and straightforward solution for next-generation communication systems. Full article

► Show Figures

Figure 1

18 pages, 3905 KiB

Open AccessArticle

Photovoltaic Maximum Power Point Tracking Technology Based on Improved Perturbation Observation Method and Backstepping Algorithm

by Yulin Wang and Liying Sun

Electronics 2024, 13(19), 3960; https://doi.org/10.3390/electronics13193960 - 8 Oct 2024

Viewed by 735

Abstract

Photovoltaic power generation systems mainly use the maximum power tracking (MPPT) controller to adjust the voltage and current of the solar cells in the photovoltaic array, so that the photovoltaic array runs at the maximum power point (MPP) to achieve the purpose of [...] Read more.

Photovoltaic power generation systems mainly use the maximum power tracking (MPPT) controller to adjust the voltage and current of the solar cells in the photovoltaic array, so that the photovoltaic array runs at the maximum power point (MPP) to achieve the purpose of maximum power output. At present, photovoltaic power stations mainly adopt the traditional method to track the maximum power point, but this fixed step method easily causes output power oscillation of the photovoltaic array when tracking the maximum power point, and it easily falls into the local extreme point under partial shadow conditions. In order to solve these problems, this paper proposes an improved perturbation observation method and backstepping method (IP&O-backstepping) to replace the traditional method applied to the MPPT controller to optimize the operating state of the solar cell, thereby improving the output power point of the photovoltaic array and increasing the output power of the photovoltaic array. The algorithm first uses the improved perturbation and observation (IP&O) method to search the maximum power point of the photovoltaic array and output the reference voltage. Secondly, the reference voltage is input into the backstepping algorithm for voltage tracking. Finally, the algorithm tracks the reference voltage and makes the photovoltaic array operate at the maximum power point. The simulation is carried out by using MATLAB/Simulink. The IP&O-backstepping algorithm is compared with the intelligent algorithm and the traditional method, and the results show that compared to the above algorithm, the IP&O-backstepping algorithm can not only track the maximum power point of the photovoltaic array, but also has a faster tracking speed, and the output power has almost no oscillation when the photovoltaic array runs at the maximum power point. Full article

► Show Figures

Figure 1

34 pages, 40732 KiB

Open AccessArticle

AWDP-FL: An Adaptive Differential Privacy Federated Learning Framework

by Zhiyan Chen, Hong Zheng and Gang Liu

Electronics 2024, 13(19), 3959; https://doi.org/10.3390/electronics13193959 - 8 Oct 2024

Viewed by 714

Abstract

Data security and user privacy concerns are receiving increasing attention. Federated learning models based on differential privacy offer a distributed machine learning framework that protects data privacy. However, the noise introduced by the differential privacy mechanism may affect the model’s usability, especially when [...] Read more.

Data security and user privacy concerns are receiving increasing attention. Federated learning models based on differential privacy offer a distributed machine learning framework that protects data privacy. However, the noise introduced by the differential privacy mechanism may affect the model’s usability, especially when reasonable gradient clipping is absent. Fluctuations in the gradients can lead to issues like gradient explosion, compromising training stability and potentially leaking privacy. Therefore, gradient clipping has become a crucial method for protecting both model performance and data privacy. To balance privacy protection and model performance, we propose the Adaptive Weight-Based Differential Privacy Federated Learning (AWDP-FL) framework, which processes model gradient parameters at the neural network layer level. First, by designing and recording the change trends of two-layer historical gradient sequences, we analyze and predict gradient variations in the current iteration and calculate the corresponding weight values. Then, based on these weights, we perform adaptive gradient clipping for each data point in each training batch, which is followed by gradient momentum updates based on the third moment. Before uploading the parameters, Gaussian noise is added to protect privacy while maintaining model accuracy. Theoretical analysis and experimental results validate the effectiveness of this framework under strong privacy constraints. Full article

(This article belongs to the Special Issue AI for Edge Computing)

► Show Figures

Figure 1

15 pages, 22303 KiB

Open AccessArticle

Innovation Adaptive UKF Train Location Method Based on Kinematic Constraints

by Xiaoping Li and Jianbin Zhang

Electronics 2024, 13(19), 3958; https://doi.org/10.3390/electronics13193958 - 8 Oct 2024

Viewed by 549

Abstract

To address the issue of reduced positioning accuracy caused by satellite signal interruptions when trains pass through long tunnels, a novel train positioning method based on an innovative adaptive unscented Kalman filter (UKF) under kinematic constraints is proposed. This method aims to improve [...] Read more.

To address the issue of reduced positioning accuracy caused by satellite signal interruptions when trains pass through long tunnels, a novel train positioning method based on an innovative adaptive unscented Kalman filter (UKF) under kinematic constraints is proposed. This method aims to improve the accuracy of the location of trains during operation. By considering the dynamic characteristics of the train, a dynamic kinematic-constrained inertial navigation system (INS)/odometer (ODO) combination positioning system is established. This system utilizes kinematic constraints to correct the accumulated errors of the INS. Additionally, the algorithm incorporates real-time estimation of the measurement noise covariance using innovation sequences. The updated adaptive estimation algorithm is applied within the UKF framework for nonlinear filtering, forming the innovative adaptive UKF algorithm. At each time step, the difference between the ODO sensor data and the INS output is used as the measurement input for the innovative adaptive UKF algorithm, enabling global estimation. This process ultimately yields the actual positioning result for the train. Simulation results demonstrate that the innovative adaptive UKF train positioning method, incorporating kinematic constraints, effectively mitigates the impact of satellite signal interruptions. Compared with the traditional INS/ODO positioning method, the innovative adaptive UKF method reduces position errors by 34.35% and speed errors by 36.33%. Overall, this method enhances navigation accuracy, minimizes train positioning errors, and meets the requirements of modern train positioning systems. Full article

► Show Figures

Figure 1

25 pages, 16110 KiB

Open AccessArticle

Optimizing Routing Protocol Design for Long-Range Distributed Multi-Hop Networks

by Shengli Pang, Jing Lu, Ruoyu Pan, Honggang Wang, Xute Wang, Zhifan Ye and Jingyi Feng

Electronics 2024, 13(19), 3957; https://doi.org/10.3390/electronics13193957 - 8 Oct 2024

Viewed by 820

Abstract

The advancement of communication technologies has facilitated the deployment of numerous sensors, terminal human–machine interfaces, and smart devices in various complex environments for data collection and analysis, providing automated and intelligent services. The increasing urgency of monitoring demands in complex environments necessitates low-cost [...] Read more.

The advancement of communication technologies has facilitated the deployment of numerous sensors, terminal human–machine interfaces, and smart devices in various complex environments for data collection and analysis, providing automated and intelligent services. The increasing urgency of monitoring demands in complex environments necessitates low-cost and efficient network deployment solutions to support various monitoring tasks. Distributed networks offer high stability, reliability, and economic feasibility. Among various Low-Power Wide-Area Network (LPWAN) technologies, Long Range (LoRa) has emerged as the preferred choice due to its openness and flexibility. However, traditional LoRa networks face challenges such as limited coverage range and poor scalability, emphasizing the need for research into distributed routing strategies tailored for LoRa networks. This paper proposes the Optimizing Link-State Routing Based on Load Balancing (LB-OLSR) protocol as an ideal approach for constructing LoRa distributed multi-hop networks. The protocol considers the selection of Multipoint Relay (MPR) nodes to reduce unnecessary network overhead. In addition, route planning integrates factors such as business communication latency, link reliability, node occupancy rate, and node load rate to construct an optimization model and optimize the route establishment decision criteria through a load-balancing approach. The simulation results demonstrate that the improved routing protocol exhibits superior performance in node load balancing, average node load duration, and average business latency. Full article

► Show Figures

Figure 1

20 pages, 2054 KiB

Open AccessReview

Using Social Robotics to Identify Educational Behavior: A Survey

by Antonio J. Romero-C. de Vaca, Roberto Angel Melendez-Armenta and Hiram Ponce

Electronics 2024, 13(19), 3956; https://doi.org/10.3390/electronics13193956 - 8 Oct 2024

Viewed by 1439

Abstract

The advancement of social robots in recent years has opened a promising avenue for providing users with more accessible and personalized attention. These robots have been integrated into various aspects of human life, particularly in activities geared toward students, such as entertainment, education, [...] Read more.

The advancement of social robots in recent years has opened a promising avenue for providing users with more accessible and personalized attention. These robots have been integrated into various aspects of human life, particularly in activities geared toward students, such as entertainment, education, and companionship, with the assistance of artificial intelligence (AI). AI plays a crucial role in enhancing these experiences by enabling social and educational robots to interact and adapt intelligently to their environment. In social robotics, AI is used to develop systems capable of understanding human emotions and responding to them, thereby facilitating interaction and collaboration between humans and robots in social settings. This article aims to present a survey of the use of robots in education, highlighting the degree of integration of social robots in this field worldwide. It also explores the robotic technologies applied according to the students’ educational level. This study provides an overview of the technical literature in social robotics and behavior recognition systems applied to education at various educational levels, especially in recent years. Additionally, it reviews the range of social robots in the market involved in these activities. The objects of study, techniques, and tools used, as well as the resources and results, are described to offer a view of the current state of the reviewed areas and to contribute to future research. Full article

(This article belongs to the Special Issue New Advances in Human-Robot Collaboration)

► Show Figures

Figure 1

31 pages, 1965 KiB

Open AccessArticle

Holistic Information Security Management and Compliance Framework

by Šarūnas Grigaliūnas, Michael Schmidt, Rasa Brūzgienė, Panayiota Smyrli, Stephanos Andreou and Audrius Lopata

Electronics 2024, 13(19), 3955; https://doi.org/10.3390/electronics13193955 - 7 Oct 2024

Viewed by 845

Abstract

The growing complexity of cybersecurity threats demands a robust framework that integrates various security domains, addressing the issue of disjointed security practices that fail to comply with evolving regulations. This paper introduces a novel information security management and compliance framework that integrates operational, [...] Read more.

The growing complexity of cybersecurity threats demands a robust framework that integrates various security domains, addressing the issue of disjointed security practices that fail to comply with evolving regulations. This paper introduces a novel information security management and compliance framework that integrates operational, technical, human, and physical security domains. The aim of this framework is to enable organizations to identify the requisite information security controls and legislative compliance needs effectively. Unlike traditional approaches, this framework systematically aligns with both current and emerging security legislation, including GDPR, NIS2 Directive, and the Artificial Intelligence Act, offering a unified approach to comprehensive security management. The experimental methodology involves evaluating the framework against five distinct risk scenarios to test its effectiveness and adaptability. Each scenario assesses the framework’s capability to manage and ensure compliance with specific security controls and regulations. The results demonstrate that the proposed framework not only meets compliance requirements across multiple security domains but also provides a scalable solution for adapting to new threats and regulations efficiently. These findings represent a significant step forward in holistic security management, indicating that organizations can enhance their security posture and legislative compliance simultaneously through this integrated framework. Full article

(This article belongs to the Special Issue New Challenges in Information Security and Privacy and Cyber Resilience)

► Show Figures

Figure 1

18 pages, 3553 KiB

Open AccessArticle

Personal Identity Proofing for E-Commerce: A Case Study of Online Service Users in the Republic of Korea

by Jongbae Kim

Electronics 2024, 13(19), 3954; https://doi.org/10.3390/electronics13193954 - 7 Oct 2024

Viewed by 594

Abstract

The rapid expansion of non-face-to-face e-commerce services in the Korea has significantly increased the importance of personal identity proofing (PIP) for verifying users in online transactions, such as payments, refunds, membership registrations, and access to age-restricted products. Currently, personal identity proofing agencies (PIPAs) [...] Read more.

The rapid expansion of non-face-to-face e-commerce services in the Korea has significantly increased the importance of personal identity proofing (PIP) for verifying users in online transactions, such as payments, refunds, membership registrations, and access to age-restricted products. Currently, personal identity proofing agencies (PIPAs) indiscriminately provide all of a user’s personal information to internet service providers (ISPs), leading to substantial privacy concerns and preventing users from selectively disclosing only the necessary information. The objective of this paper is to enhance the safety, convenience, and security of PIP services by proposing a method that empowers users to control the personal information they disclose while enabling digital identity integration for both online and offline applications. To achieve this, an extensive overview and analysis of the current PIP systems in Korea is presented, including methods. The strengths and weaknesses of these systems are critically examined, revealing limitations in privacy protection, user convenience, and security. Based on this analysis, a new method is proposed that introduces differentiated levels of PIP means according to authentication strength, allowing for the minimal necessary disclosure of personal information. The proposed method aims to improve the stability and reliability of the PIP service environment by addressing current privacy concerns and enhancing user control over personal information. This approach can be applied to e-commerce services in Korea and other countries facing similar challenges, contributing to the development of safer and more reliable online services. Full article

► Show Figures

Figure 1

29 pages, 420 KiB

Open AccessArticle

Predictive Modeling of Customer Response to Marketing Campaigns

by Mohammed El-Hajj and Miglena Pavlova

Electronics 2024, 13(19), 3953; https://doi.org/10.3390/electronics13193953 - 7 Oct 2024

Viewed by 756

Abstract

In today’s data-driven marketing landscape, predicting customer responses to marketing campaigns is essential for optimizing both engagement and Return On Investment (ROI). This study aims to develop a predictive model using a Decision Tree (DT) to identify key factors influencing customer behavior and [...] Read more.

In today’s data-driven marketing landscape, predicting customer responses to marketing campaigns is essential for optimizing both engagement and Return On Investment (ROI). This study aims to develop a predictive model using a Decision Tree (DT) to identify key factors influencing customer behavior and improve campaign targeting. The methodology involves building the DT model, initially achieving an accuracy of 87.3%. However, the model faced challenges with precision and recall due to class imbalance. To address this, a resampling technique was applied, which significantly improved model performance, increasing recall from 44% to 83.1% and the F1-score from 49% to 74.2%. Key influential features identified include the recency of a customer’s purchase, their duration as a customer, and their response history to previous campaigns. This study demonstrates the practicality and interpretability of the DT model, offering actionable insights for marketing professionals seeking to enhance campaign effectiveness and customer targeting. Full article

(This article belongs to the Special Issue Intelligent Data and Information Processing Application in the Digital Economy)

► Show Figures

Figure 1

21 pages, 10416 KiB

Open AccessReview

Examining the Role of Augmented Reality and Virtual Reality in Safety Training

by Georgios Lampropoulos, Pablo Fernández-Arias, Álvaro Antón-Sancho and Diego Vergara

Electronics 2024, 13(19), 3952; https://doi.org/10.3390/electronics13193952 - 7 Oct 2024

Viewed by 1073

Abstract

This study aims to provide a review of the existing literature regarding the use of extended reality technologies and the metaverse focusing on virtual reality (VR), augmented reality (AR), and mixed reality (MR) in safety training. Based on the outcomes, VR was predominantly [...] Read more.

This study aims to provide a review of the existing literature regarding the use of extended reality technologies and the metaverse focusing on virtual reality (VR), augmented reality (AR), and mixed reality (MR) in safety training. Based on the outcomes, VR was predominantly used in the context of safety training with immersive VR yielding the best outcomes. In comparison, only recently has AR been introduced in safety training but with positive outcomes. Both AR and VR can be effectively adopted and integrated in safety training and render the learning experiences and environments more realistic, secure, intense, interactive, and personalized, which are crucial aspects to ensure high-quality safety training. Their ability to provide safe virtual learning environments in which individuals can practice and develop their skills and knowledge in real-life simulated working settings that do not involve any risks emerged as one of the main benefits. Their ability to support social and collaborative learning and offer experiential learning significantly contributed to the learning outcomes. Therefore, it was concluded that VR and AR emerged as effective tools that can support and enrich safety training and, in turn, increase occupational health and safety. Full article

► Show Figures

Figure 1

13 pages, 352 KiB

Open AccessArticle

Research on Pattern Classification Based on Double Pseudo-Inverse Extreme Learning Machine

by Yumin Yin, Bolin Liao, Shuai Li and Jieyang Zhou

Electronics 2024, 13(19), 3951; https://doi.org/10.3390/electronics13193951 - 7 Oct 2024

Viewed by 674

Abstract

This research aims to address the limitations inherent in the traditional Extreme Learning Machine (ELM) algorithm, particularly the stochastic determination of input-layer weights and hidden-layer biases, which frequently leads to an excessive number of hidden-layer neurons and inconsistent performance. To augment the neural [...] Read more.

This research aims to address the limitations inherent in the traditional Extreme Learning Machine (ELM) algorithm, particularly the stochastic determination of input-layer weights and hidden-layer biases, which frequently leads to an excessive number of hidden-layer neurons and inconsistent performance. To augment the neural network’s efficacy in pattern classification, Principal Component Analysis (PCA) is employed to reduce the dimensionality of the input matrix and alleviate multicollinearity issues during the computation of the input weight matrix. This paper introduces an enhanced ELM methodology, designated the PCA-DP-ELM algorithm, which integrates PCA with Double Pseudo-Inverse Weight Determination (DP). The PCA-DP-ELM algorithm proposed in this study consistently achieves superior average classification accuracy across various datasets, irrespective of whether assessed through longitudinal or cross-sectional experiments. The results from both experimental paradigms indicate that the optimized algorithm not only enhances accuracy but also improves stability. These findings substantiate that the proposed methodology exerts a positive influence on pattern classification. Full article

► Show Figures

Figure 1

14 pages, 526 KiB

Open AccessArticle

Assessment of Ensemble-Based Machine Learning Algorithms for Exoplanet Identification

by Thiago S. F. Luz, Rodrigo A. S. Braga and Enio R. Ribeiro

Electronics 2024, 13(19), 3950; https://doi.org/10.3390/electronics13193950 - 7 Oct 2024

Viewed by 873

Abstract

This paper presents a comprehensive assessment procedure for evaluating Ensemble-based Machine Learning algorithms in the context of exoplanet classification. Each of the algorithm hyperparameter values were tuned. Deployments were carried out using the cross-validation method. Performance metrics, including accuracy, sensitivity, specificity, precision, and [...] Read more.

This paper presents a comprehensive assessment procedure for evaluating Ensemble-based Machine Learning algorithms in the context of exoplanet classification. Each of the algorithm hyperparameter values were tuned. Deployments were carried out using the cross-validation method. Performance metrics, including accuracy, sensitivity, specificity, precision, and F1 score, were evaluated using confusion matrices generated from each implementation. Machine Learning (ML) algorithms were trained and used to identify exoplanet data. Most of the current research deals with traditional ML algorithms for this purpose. The Ensemble algorithm is another type of ML technique that combines the prediction performance of two or more algorithms to obtain an improved final prediction. Few studies have applied Ensemble algorithms to predict exoplanets. To the best of our knowledge, no paper that has exclusively assessed Ensemble algorithms exists, highlighting a significant gap in the literature about the potential of Ensemble methods. Five Ensemble algorithms were evaluated in this paper: Adaboost, Random Forest, Stacking, Random Subspace Method, and Extremely Randomized Trees. They achieved an average performance of more than 80% in all metrics. The results underscore the substantial benefits of fine tuning hyperparameters to enhance predictive performance. The Stacking algorithm achieved a higher performance than the other algorithms. This aspect is discussed in this paper. The results of this work show that it is worth increasing the use of Ensemble algorithms to improve exoplanet identification. Full article

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

► Show Figures

Figure 1

21 pages, 10847 KiB

Open AccessArticle

DLCH-YOLO: An Object Detection Algorithm for Monitoring the Operation Status of Circuit Breakers in Power Scenarios

by Riben Shu, Lihua Chen, Lumei Su, Tianyou Li and Fan Yin

Electronics 2024, 13(19), 3949; https://doi.org/10.3390/electronics13193949 - 7 Oct 2024

Viewed by 665

Abstract

In the scenario of power system monitoring, detecting the operating status of circuit breakers is often inaccurate due to variable object scales and background interference. This paper introduces DLCH-YOLO, an object detection algorithm aimed at identifying the operating status of circuit breakers. Firstly, [...] Read more.

In the scenario of power system monitoring, detecting the operating status of circuit breakers is often inaccurate due to variable object scales and background interference. This paper introduces DLCH-YOLO, an object detection algorithm aimed at identifying the operating status of circuit breakers. Firstly, we propose a novel C2f_DLKA module based on Deformable Large Kernel Attention. This module adapts to objects of varying scales within a large receptive field, thereby more effectively extracting multi-scale features. Secondly, we propose a Semantic Screening Feature Pyramid Network designed to fuse multi-scale features. By filtering low-level semantic information, it effectively suppresses background interference to enhance localization accuracy. Finally, the feature extraction network incorporates Generalized-Sparse Convolution, which combines depth-wise separable convolution and channel mixing operations, reducing computational load. The DLCH-YOLO algorithm achieved a 91.8% mAP on our self-built power equipment dataset, representing a 4.7% improvement over the baseline network Yolov8. With its superior detection accuracy and real-time performance, DLCH-YOLO outperforms mainstream detection algorithms. This algorithm provides an efficient and viable solution for circuit breaker status detection. Full article

► Show Figures

Figure 1

16 pages, 503 KiB

Open AccessArticle

Leveraging Incremental Learning for Dynamic Modulation Recognition

by Song Ma, Lin Zhang, Zhangli Song, Wei Yu and Tian Liu

Electronics 2024, 13(19), 3948; https://doi.org/10.3390/electronics13193948 - 7 Oct 2024

Viewed by 503

Abstract

Modulation recognition is an important technology used to correctly identify the modulation modes of wireless signals and is widely used in cooperative and confrontational scenarios. Traditional modulation-recognition algorithms require the assistance of expert experiences, which constrains their applications. With the rapid development of [...] Read more.

Modulation recognition is an important technology used to correctly identify the modulation modes of wireless signals and is widely used in cooperative and confrontational scenarios. Traditional modulation-recognition algorithms require the assistance of expert experiences, which constrains their applications. With the rapid development of artificial intelligence in recent years, deep learning (DL) is widely advocated for intelligent modulation recognition. Typically, DL-based modulation-recognition algorithms implicitly assume a relatively static scenario in which the signal samples of all the modulation modes can be completely collected in advance. In practical situations, the radio environment is quite dynamic and the signal samples with new modulation modes may appear sequentially, in which the current DL-based modulation-recognition algorithms may require unacceptable time and computing resource consumption to re-train the optimal model from scratch. In this study, we leveraged incremental learning (IL) and designed a novel IL-based modulation-recognition algorithm that consists of an initial stage and multiple incremental stages. The main novelty of the proposed algorithm lies in the new loss function design in each incremental stage, which combines the distillation loss of recognizing old modulation modes and the cross-entropy loss of recognizing new modulation modes. With the proposed algorithm, the knowledge of the signal samples with new modulation modes can be efficiently learned in the current stage without forgetting the knowledge learned in the previous stages. The simulation results demonstrate that the proposed algorithm could achieve a recognition accuracy close to the upper bound with a much lower computing time and it outperformed the existing IL-based benchmarks. Full article

(This article belongs to the Section Electrical and Autonomous Vehicles)

► Show Figures

Figure 1

24 pages, 73490 KiB

Open AccessFeature PaperArticle

A Design Review for Biomedical Wireless Power Transfer Systems with a Three-Coil Inductive Link through a Case Study for NICU Applications

by Amin Hazrati Marangalou, Miguel Gonzalez, Nathaniel Reppucci and Ulkuhan Guler

Electronics 2024, 13(19), 3947; https://doi.org/10.3390/electronics13193947 - 7 Oct 2024

Viewed by 867

Abstract

This paper outlines a design approach for biomedical wireless power transfer systems with a focus on three-coil inductive links for neonatal intensive care unit applications. The relevant literature has been explored to support the design approach, equations, simulation results, and the process of [...] Read more.

This paper outlines a design approach for biomedical wireless power transfer systems with a focus on three-coil inductive links for neonatal intensive care unit applications. The relevant literature has been explored to support the design approach, equations, simulation results, and the process of experimental analysis. The paper begins with a brief overview of various power amplifier classes, followed by an in-depth examination of the most common power amplifiers used in biomedical wireless power transfer systems. Among the traditional linear and switching amplifier classes, class-D and class-E switching amplifiers are highlighted for their enhanced efficiency and straightforward implementation in biomedical contexts. The impact of load variation on these systems is also discussed. This paper then explores the basic concepts and essential equations governing inductive links, comparing two-coil and multi-coil configurations. In the following, the paper discusses foundational coil parameters and provides theoretical and experimental analysis of both two-coil and multi-coil inductive links through step-by-step measurement techniques using lab equipment and addressing the relevant challenges. Finally, a case study for neonatal intensive care unit applications is presented, showcasing a wireless power transfer system operating at 13.56 MHz for powering a wearable device on a patient lying on a mattress. An inductive link with a transmitter coil embedded in a mattress is designed to supply power to a load at distances ranging from 4 cm to 12 cm, simulating the mattress-to-chest distance of an infant. the experimental results of a three-coil inductive link equipped with a Class-E power amplifier are reported, demonstrating power transfer efficiency ranging from 75% to 25% and power delivery to a 500

Ω

-load varying from 340 mW to 25 mW over various distances. Full article

(This article belongs to the Special Issue Wireless Power Transfer Technology and Its Applications)

► Show Figures

Figure 1

29 pages, 12522 KiB

Open AccessArticle

Motor Fault Diagnosis and Detection with Convolutional Autoencoder (CAE) Based on Analysis of Electrical Energy Data

by YuRim Choi and Inwhee Joe

Electronics 2024, 13(19), 3946; https://doi.org/10.3390/electronics13193946 - 7 Oct 2024

Viewed by 931

Abstract

This study develops a Convolutional Autoencoder (CAE) and deep neural network (DNN)-based model optimized for real-time signal processing and high accuracy in motor fault diagnosis. This model learns complex patterns from voltage and current data and precisely analyzes them in combination with DNN [...] Read more.

This study develops a Convolutional Autoencoder (CAE) and deep neural network (DNN)-based model optimized for real-time signal processing and high accuracy in motor fault diagnosis. This model learns complex patterns from voltage and current data and precisely analyzes them in combination with DNN through latent space representation. Traditional diagnostic methods relied on vibration and current sensors, empirical knowledge, or harmonic and threshold-based monitoring, but they had limitations in recognizing complex patterns and providing accurate diagnoses. Our model significantly enhances the accuracy of power data analysis and fault diagnosis by mapping each phase (R, S, and T) of the electrical system to the red, green, and blue (RGB) channels of image processing and applying various signal processing techniques. Optimized for real-time data streaming, this model demonstrated high practicality and effectiveness in an actual industrial environment, achieving 99.9% accuracy, 99.8% recall, and 99.9% precision. Specifically, it was able to more accurately diagnose motor efficiency and fault risks by utilizing power system analysis indicators such as phase voltage, total harmonic distortion (THD), and voltage unbalance. This integrated approach significantly enhances the real-time applicability of electric motor fault diagnosis and is expected to provide a crucial foundation for various industrial applications in the future. Full article

► Show Figures

Figure 1

17 pages, 4291 KiB

Open AccessArticle

Deep-Unfolded Tikhonov-Regularized Conjugate Gradient Algorithm for MIMO Detection

by Sümeye Nur Karahan and Aykut Kalaycıoğlu

Electronics 2024, 13(19), 3945; https://doi.org/10.3390/electronics13193945 - 7 Oct 2024

Viewed by 680

Abstract

In addressing the multifaceted problem of multiple-input multiple-output (MIMO) detection in wireless communication systems, this work highlights the pressing need for enhanced detection reliability under variable channel conditions and MIMO antenna configurations. We propose a novel method that sets a new standard for [...] Read more.

In addressing the multifaceted problem of multiple-input multiple-output (MIMO) detection in wireless communication systems, this work highlights the pressing need for enhanced detection reliability under variable channel conditions and MIMO antenna configurations. We propose a novel method that sets a new standard for deep unfolding in MIMO detection by integrating the iterative conjugate gradient method with Tikhonov regularization, combining the adaptability of modern deep learning techniques with the robustness of classical regularization. Unlike conventional techniques, our strategy treats the Tikhonov regularization parameter, as well as the step size and search direction coefficients of the conjugate gradient (CG) method, as trainable parameters within the deep learning framework. This enables dynamic adjustments based on varying channel conditions and MIMO antenna configurations. Detection performance is significantly improved by the proposed approach across a range of MIMO configurations and channel conditions, consistently achieving lower bit error rate (BER) and normalized minimum mean square error (NMSE) compared to well-known techniques like DetNet and CG. The proposed method has superior performance over CG and other model-based methods, especially with a small number of iterations. Consequently, the simulation results demonstrate the flexibility of the proposed approach, making it a viable choice for MIMO systems with a range of antenna configurations, modulation orders, and different channel conditions. Full article

(This article belongs to the Special Issue Advances in Deep Learning-Based Wireless Communication Systems)

► Show Figures

Figure 1

27 pages, 544 KiB

Open AccessArticle

Unsupervised Learning for Lateral-Movement-Based Threat Mitigation in Active Directory Attack Graphs

by David Herranz-Oliveros, Marino Tejedor-Romero, Jose Manuel Gimenez-Guzman and Luis Cruz-Piris

Electronics 2024, 13(19), 3944; https://doi.org/10.3390/electronics13193944 - 6 Oct 2024

Viewed by 807

Abstract

Cybersecurity threats, particularly those involving lateral movement within networks, pose significant risks to critical infrastructures such as Microsoft Active Directory. This study addresses the need for effective defense mechanisms that minimize network disruption while preventing attackers from reaching key assets. Modeling Active Directory [...] Read more.

Cybersecurity threats, particularly those involving lateral movement within networks, pose significant risks to critical infrastructures such as Microsoft Active Directory. This study addresses the need for effective defense mechanisms that minimize network disruption while preventing attackers from reaching key assets. Modeling Active Directory networks as a graph in which the nodes represent the network components and the edges represent the logical interactions between them, we use centrality metrics to derive the impact of hardening nodes in terms of constraining the progression of attacks. We propose using Unsupervised Learning techniques, specifically density-based clustering algorithms, to identify those nodes given the information provided by their metrics. Our approach includes simulating attack paths using a snowball model, enabling us to analytically evaluate the impact of hardening on delaying Domain Administration compromise. We tested our methodology on both real and synthetic Active Directory graphs, demonstrating that it can significantly slow down the propagation of threats from reaching the Domain Administration across the studied scenarios. Additionally, we explore the potential of these techniques to enable flexible selection of the number of nodes to secure. Our findings suggest that the proposed methods significantly enhance the resilience of Active Directory environments against targeted cyber-attacks. Full article

(This article belongs to the Special Issue Machine Learning for Cybersecurity: Threat Detection and Mitigation)

► Show Figures

Figure 1

16 pages, 5857 KiB

Open AccessArticle

A Scaled Monocular 3D Reconstruction Based on Structure from Motion and Multi-View Stereo

by Zhiwen Zhan, Fan Yang, Jixin Jiang, Jialin Du, Fanxing Li, Si Sun and Yan Wei

Electronics 2024, 13(19), 3943; https://doi.org/10.3390/electronics13193943 - 6 Oct 2024

Viewed by 573

Abstract

Three-dimensional digital modeling at actual scales is essential for digitally preserving cultural relics. While 3D reconstruction using a monocular camera offers a cost-effective solution, the lack of scale information in the resulting models limits their suitability for geometric measurements. Objects with monotonous textures, [...] Read more.

Three-dimensional digital modeling at actual scales is essential for digitally preserving cultural relics. While 3D reconstruction using a monocular camera offers a cost-effective solution, the lack of scale information in the resulting models limits their suitability for geometric measurements. Objects with monotonous textures, such as batteries, pose additional challenges due to insufficient feature points, increasing positional uncertainty. This article proposes a method incorporating point and line features to address the scale ambiguity in multi-view 3D reconstruction using monocular cameras. By pre-measuring the lengths of multiple sets of real line segments, building a lookup table, and associating the line features in different images, the table was input into the improved reconstruction algorithm to further optimize the scale information. Experimental results on real datasets showed that the proposed method outperformed the COLMAP method by 70.82% in reconstruction accuracy, with a scale recovery reaching millimeter-level accuracy. This method is highly generalizable, cost-effective, and supports lightweight computation, making it suitable for real-time operation on a CPU. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 13, Issue 19 (October-1 2024) – 185 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI