Next Issue
Volume 10, September-1
Previous Issue
Volume 10, August-1
 
 

Electronics, Volume 10, Issue 16 (August-2 2021) – 174 articles

Cover Story (view full-size image): The expansion of electric vehicles in urban areas has paved the way toward the era of autonomous vehicles. This field of research opens immediate applications in the tourism areas, airports or business centres. This project shows the problems derived from autonomous driving such as vehicle localization, low coverage of 4G/5G and GPS, detection of the road and navigable zones, detection of static and dynamic obstacles, longitudinal and lateral control and cybersecurity aspects. The approaches proposed in this article are sufficient to solve the problems related to autonomous vehicle application in special locations on unstructured roads. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
22 pages, 8285 KiB  
Article
Application of Mineral Compounds for a High-Voltage Portable Grounding System: An Experimental Study
by Rizwan Ahmad, Mahmoud Kassas, Chokri B. Ahmed, Faisal Khan, Sikandar Khan, Arshad Jamal and Irshad Ullah
Electronics 2021, 10(16), 2043; https://doi.org/10.3390/electronics10162043 - 23 Aug 2021
Cited by 8 | Viewed by 2322
Abstract
Electrical grounding is an indispensable part of the power system network. The grounding system is mainly affected by grounding resistance and the nature of the soil. High ground resistance produces the phenomenon of soil ionization, surface arching, and back flashover. A conventional grounding [...] Read more.
Electrical grounding is an indispensable part of the power system network. The grounding system is mainly affected by grounding resistance and the nature of the soil. High ground resistance produces the phenomenon of soil ionization, surface arching, and back flashover. A conventional grounding system requires the deep digging of electrodes, thus creating maintenance difficulties. This research work focuses on the safe operation of an electric power system from external and internal impulses arising due to lightning strikes or short circuits. The study proposes an application of mineral samples as grounding materials, and bentonite is used as backfilling material in portable grounding systems. A detailed experimental analysis was conducted under controlled conditions to evaluate the performance of selected materials in high-resistance soil. The problem of a deeply driven electrode is addressed by designing the portable grounding system. The study results demonstrate that the proposed portable grounding system could be installed in troubled environments such as forests, deserts, and rocky terrains. To measure the breakdown voltages of the proposed samples, X-ray Diffraction (XRD) analysis and other laboratory tests were conducted. The electric field intensities are extracted through Finite Element Analysis (FEA). The experimental and simulation findings show the expected performance of mineral samples under various operating conditions. The findings of this study can guide the practitioners for safe and efficient operations of portable electrical grounding systems. Full article
(This article belongs to the Section Power Electronics)
Show Figures

Figure 1

35 pages, 1007 KiB  
Systematic Review
Data Transformation Schemes for CNN-Based Network Traffic Analysis: A Survey
by Jacek Krupski, Waldemar Graniszewski and Marcin Iwanowski
Electronics 2021, 10(16), 2042; https://doi.org/10.3390/electronics10162042 - 23 Aug 2021
Cited by 19 | Viewed by 5267
Abstract
The enormous growth of services and data transmitted over the internet, the bloodstream of modern civilization, has caused a remarkable increase in cyber attack threats. This fact has forced the development of methods of preventing attacks. Among them, an important and constantly growing [...] Read more.
The enormous growth of services and data transmitted over the internet, the bloodstream of modern civilization, has caused a remarkable increase in cyber attack threats. This fact has forced the development of methods of preventing attacks. Among them, an important and constantly growing role is that of machine learning (ML) approaches. Convolutional neural networks (CNN) belong to the hottest ML techniques that have gained popularity, thanks to the rapid growth of computing power available. Thus, it is no wonder that these techniques have started to also be applied in the network traffic classification domain. This has resulted in a constant increase in the number of scientific papers describing various approaches to CNN-based traffic analysis. This paper is a survey of them, prepared with particular emphasis on a crucial but often disregarded aspect of this topic—the data transformation schemes. Their importance is a consequence of the fact that network traffic data and machine learning data have totally different structures. The former is a time series of values—consecutive bytes of the datastream. The latter, in turn, are one-, two- or even three-dimensional data samples of fixed lengths/sizes. In this paper, we introduce a taxonomy of data transformation schemes. Next, we use this categorization to describe various CNN-based analytical approaches found in the literature. Full article
(This article belongs to the Special Issue Cybersecurity and Data Science)
Show Figures

Graphical abstract

14 pages, 1174 KiB  
Article
Specifying Power Filter Insertion Loss Values in Terms of Electromagnetic Safety of IT Equipment
by Leszek Nowosielski, Bartosz Dudziński, Rafał Przesmycki and Marek Bugaj
Electronics 2021, 10(16), 2041; https://doi.org/10.3390/electronics10162041 - 23 Aug 2021
Cited by 1 | Viewed by 1997
Abstract
At present, one of the main methods of minimizing risk resulting from electromagnetic information leakage is to attenuate the undesired levels of radiated and conducted disturbances generated by IT equipment, as these disturbances can carry information processed by said equipment. Attenuation of conducted [...] Read more.
At present, one of the main methods of minimizing risk resulting from electromagnetic information leakage is to attenuate the undesired levels of radiated and conducted disturbances generated by IT equipment, as these disturbances can carry information processed by said equipment. Attenuation of conducted compromising emissions is most commonly handled with filters with a sufficiently high insertion loss. This article defines an original analytical relation specifying insertion loss value requirements for mains filters and estimates values of parameters included in the defined relation. Furthermore, this defined relation was used to define requirements for insertion loss provided by the mains filters, above which the ratio value of potentially compromising conducted emission levels to the environmental noise level at the infiltrating system input S/N < 0 dB. As a consequence, electromagnetic infiltration is significantly impeded. Full article
(This article belongs to the Special Issue Electromagnetic Interference and Compatibility, Volume II)
Show Figures

Figure 1

31 pages, 4291 KiB  
Review
Security Impacts Assessment of Active Distribution Network on the Modern Grid Operation—A Review
by Ifedayo Oladeji, Peter Makolo, Muhammad Abdillah, Jian Shi and Ramon Zamora
Electronics 2021, 10(16), 2040; https://doi.org/10.3390/electronics10162040 - 23 Aug 2021
Cited by 8 | Viewed by 3002
Abstract
The future grid will include a high penetration of distributed generation, which will have an impact on its security. This paper discusses the latest trends, components, tools, and frameworks aimed at 100% renewable energy generation for the emerging grid. The technical and economic [...] Read more.
The future grid will include a high penetration of distributed generation, which will have an impact on its security. This paper discusses the latest trends, components, tools, and frameworks aimed at 100% renewable energy generation for the emerging grid. The technical and economic impacts of renewable energy sources (RES)-based distributed generation (DG) on the emerging grid security are also discussed. Moreover, the latest approaches and techniques for allocating RES-DG into the distribution networks using specific performance indices based on recent literature were reviewed. Most of the methods in recent literature are based on metaheuristic optimization algorithms that can optimally allocate the RES-DGs based on the identified network variables. However, there is a need to extend these methods in terms of parameters considered, objectives, and possible ancillary support to the upstream network. The limitations of existing methods in recent literature aimed at ensuring the security of the integrated transmission-active distribution network under high RES-DG penetration were identified. Lastly, the existing coordination methods for voltage and frequency control at the transmission and active distribution system interface were also investigated. Relevant future research areas with a focus on ensuring the security of the emerging grid with high RES-DG penetration into the distribution networks are also recommended. Full article
Show Figures

Figure 1

15 pages, 88423 KiB  
Article
Wideband Frequency Invariant Array Synthesis Based on Matrix Singular Value Decomposition
by Le Xu, Rui Li, Xiaoqun Chen, Feng Wei and Xiaowei Shi
Electronics 2021, 10(16), 2039; https://doi.org/10.3390/electronics10162039 - 23 Aug 2021
Cited by 2 | Viewed by 1844
Abstract
In this paper, an analytic method for frequency invariant (FI) array synthesis is proposed based on matrix singular value decomposition. By grouping the elements of FI array into a few subarrays, the FI pattern in the whole frequency band is realized. Using this [...] Read more.
In this paper, an analytic method for frequency invariant (FI) array synthesis is proposed based on matrix singular value decomposition. By grouping the elements of FI array into a few subarrays, the FI pattern in the whole frequency band is realized. Using this algorithm, the number of sub arrays is reduced. Simulation results show that the proposed algorithm can synthesize the 64-element broadband FI array in 0.52 s. For the 18-element linear array, the half power beam width (HPBW) changes less than 0.6 degrees in the bandwidth. Moreover, the range of HPBW variation decreases rapidly along with the increase in the number of elements. Furthermore, the effectiveness of the algorithm is verified by synthesizing FI array with low side lobe level (SLL), beam scanning, and notch requirements. The examples in this paper show that the proposed algorithm can achieve better pattern characteristics with fewer elements. Finally, a broadband antenna with 2:1 bandwidth is improved, and two FI arrays of 23 elements and 64 elements are formed by using the antenna. The active pattern of the array element is introduced into the proposed algorithm, and two FI arrays synthesized by the algorithm are simulated by full wave software. Full article
(This article belongs to the Special Issue Novel Microwave/Millimeter-Wave Devices and Antennas)
Show Figures

Figure 1

15 pages, 1420 KiB  
Article
Accurate and Lightweight RailNet for Real-Time Rail Line Detection
by Zhen Tao, Shiwei Ren, Yueting Shi, Xiaohua Wang and Weijiang Wang
Electronics 2021, 10(16), 2038; https://doi.org/10.3390/electronics10162038 - 23 Aug 2021
Cited by 2 | Viewed by 2723
Abstract
Railway transportation has always occupied an important position in daily life and social progress. In recent years, computer vision has made promising breakthroughs in intelligent transportation, providing new ideas for detecting rail lines. Yet the majority of rail line detection algorithms use traditional [...] Read more.
Railway transportation has always occupied an important position in daily life and social progress. In recent years, computer vision has made promising breakthroughs in intelligent transportation, providing new ideas for detecting rail lines. Yet the majority of rail line detection algorithms use traditional image processing to extract features, and their detection accuracy and instantaneity remain to be improved. This paper goes beyond the aforementioned limitations and proposes a rail line detection algorithm based on deep learning. First, an accurate and lightweight RailNet is designed, which takes full advantage of the powerful advanced semantic information extraction capabilities of deep convolutional neural networks to obtain high-level features of rail lines. The Segmentation Soul (SS) module is creatively added to the RailNet structure, which improves segmentation performance without any additional inference time. The Depth Wise Convolution (DWconv) is introduced in the RailNet to reduce the number of network parameters and eventually ensure real-time detection. Afterward, according to the binary segmentation maps of RailNet output, we propose the rail line fitting algorithm based on sliding window detection and apply the inverse perspective transformation. Thus the polynomial functions and curvature of the rail lines are calculated, and rail lines are identified in the original images. Furthermore, we collect a real-world rail lines dataset, named RAWRail. The proposed algorithm has been fully validated on the RAWRail dataset, running at 74 FPS, and the accuracy reaches 98.6%, which is superior to the current rail line detection algorithms and shows powerful potential in real applications. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

16 pages, 1322 KiB  
Article
Comprehensive Survey of Various Energy Storage Technology Used in Hybrid Energy
by Ahmed Riyaz, Pradip Kumar Sadhu, Atif Iqbal and Basem Alamri
Electronics 2021, 10(16), 2037; https://doi.org/10.3390/electronics10162037 - 23 Aug 2021
Cited by 6 | Viewed by 2370
Abstract
Various power generation technologies, such as wind turbines and solar power plants, have been increasingly installed in renewable energy projects as a result of rising demand and ongoing efforts by global researchers to mitigate environmental effects. The sole source of energy for such [...] Read more.
Various power generation technologies, such as wind turbines and solar power plants, have been increasingly installed in renewable energy projects as a result of rising demand and ongoing efforts by global researchers to mitigate environmental effects. The sole source of energy for such generation is nature. The incorporation of the green unit into the power grid also results in volatility. The stabilization of frequencies is critical and depends on the balance of supply and demand. An efficient monitoring scheme called Load Frequency Monitoring (LFM) is introduced to reduce the frequency deviation from its natural state. Specific energy storage systems may be considered to improve the efficiency of the control system. The storage system contributes to the load rate, peak rushing, black start support, etc., in addition to high energy and rapid responsive features. A detailed study of different power storage systems, their current business scenario, and the application of LFM facilities, as well as their analysis and disturbance, is presented in this paper. According to the literature analysis, the current approaches can be divided into two categories: grid and load scale structures. This article also distinguishes between the organized aggregate system and the uncoordinated system control scheme, both of which have advantages and disadvantages in terms of technology. Full article
Show Figures

Figure 1

9 pages, 7135 KiB  
Article
Analytical Study and Comparison of Electromagnetic Characteristics of 8-Pole 9-Slot and 8-Pole 12-Slot Permanent Magnet Synchronous Machines Considering Rotor Eccentricity
by Hoon-Ki Lee, Tae-Kyoung Bang, Jeong-In Lee, Jong-Hyeon Woo, Hyo-Seob Shin, Ick-Jae Yoon and Jang-Young Choi
Electronics 2021, 10(16), 2036; https://doi.org/10.3390/electronics10162036 - 23 Aug 2021
Cited by 3 | Viewed by 2362
Abstract
In this study, a magnetic field is analyzed using an analytical method and compared with the electromagnetic characteristics of 8-pole 9-slot and 8-pole 12-slot permanent magnet synchronous machines considering rotor eccentricity. The magnetic flux density and back electromotive force (EMF) are derived using [...] Read more.
In this study, a magnetic field is analyzed using an analytical method and compared with the electromagnetic characteristics of 8-pole 9-slot and 8-pole 12-slot permanent magnet synchronous machines considering rotor eccentricity. The magnetic flux density and back electromotive force (EMF) are derived using perturbation theory and electromagnetic theory. First, the Fourier modeling of a permanent magnet is performed through magnetization modeling, and two analysis regions are set based on several assumptions for applying the analytical method. Accordingly, the governing equations of the analysis regions are derived in the form of Poisson and Laplace equations. In addition, the undefined coefficients of the general solutions are calculated through general solutions and appropriate boundary conditions, and the magnetic flux density and back EMF of the air gap region are derived based on the definition of the magnetic vector potential. The results obtained using the analytical method are compared with the finite element method and experimental results. In addition, we perform a torque analysis considering rotor eccentricity and analyze the torque ripple based on rotor eccentricity for two cases involving the pole/slot combination. Full article
(This article belongs to the Special Issue Robust Design Optimization of Electrical Machines and Devices)
Show Figures

Figure 1

18 pages, 1540 KiB  
Article
Wearable IoTs and Geo-Fencing Based Framework for COVID-19 Remote Patient Health Monitoring and Quarantine Management to Control the Pandemic
by Farman Ullah, Hassan Ul Haq, Jebran Khan, Arslan Ali Safeer, Usman Asif and Sungchang Lee
Electronics 2021, 10(16), 2035; https://doi.org/10.3390/electronics10162035 - 23 Aug 2021
Cited by 21 | Viewed by 4532
Abstract
The epidemic disease of Severe Acute Respiratory Syndrome (SARS) called COVID-19 has become a more frequently active disease. Managing and monitoring COVID-19 patients is still a challenging issue for advanced technologies. The first and foremost critical issue in COVID-19 is to diagnose it [...] Read more.
The epidemic disease of Severe Acute Respiratory Syndrome (SARS) called COVID-19 has become a more frequently active disease. Managing and monitoring COVID-19 patients is still a challenging issue for advanced technologies. The first and foremost critical issue in COVID-19 is to diagnose it timely and cut off the chain of transmission by isolating the susceptible and patients. COVID-19 spreads through close interaction and contact with an infected person. It has affected the entire world, and every country is facing the challenges of having adequate medical facilities along with the availability of medical staff in rural and urban areas that have a high number of patients due to the pandemic. Due to the invasive method of treatment, SARS-COVID is spreading swiftly. In this paper, we propose an intelligent health monitoring framework using wearable Internet of Things (IoT) and Geo-fencing for COVID-19 susceptible and patient monitoring, and isolation and quarantine management to control the pandemic. The proposed system consists of four layers, and each layer has different functionality: a wearable sensors layer, IoT gateway layer, cloud server layer, and client application layer for visualization and analysis. The wearable sensors layer consists of wearable biomedical and GPS sensors for physiological parameters, and GPS and Wi-Fi Received Signal Strength Indicator acquisition for health monitoring and user Geo-fencing. The IoT gateway layer provides a Bluetooth and Wi-Fi based wireless body area network and IoT environment for data transmission anytime and anywhere. Cloud servers use Raspberry Pi and ThingSpeak cloud for data analysis and web-based application layers for remote monitoring based on user consent. The susceptible and patient conditions, real-time sensor’s data, and Geo-fencing enables minimizing the spread through close interaction. The results show the effectiveness of the proposed framework. Full article
(This article belongs to the Special Issue Applications for Smart Cyber Physical Systems)
Show Figures

Figure 1

27 pages, 1591 KiB  
Article
Security, Privacy, and Reliability in Digital Healthcare Systems Using Blockchain
by Aitizaz Ali, Hasliza A. Rahim, Muhammad Fermi Pasha, Rafael Dowsley, Mehedi Masud, Jehad Ali and Mohammed Baz
Electronics 2021, 10(16), 2034; https://doi.org/10.3390/electronics10162034 - 23 Aug 2021
Cited by 50 | Viewed by 6955
Abstract
According to the security breach level index, millions of records are stolen worldwide on every single day. Personal health records are the most targeted records on the internet, and they are considered sensitive, and valuable. Security and privacy are the most important parameters [...] Read more.
According to the security breach level index, millions of records are stolen worldwide on every single day. Personal health records are the most targeted records on the internet, and they are considered sensitive, and valuable. Security and privacy are the most important parameters of cryptography and encryption. They reduce the availability of data on patients and healthcare to the appropriate personnel and ultimately lead to a barrier in the transfer of healthcare into a digital health system. Using a permission blockchain to share healthcare data can reduce security and privacy issues. According to the literature, most healthcare systems rely on a centralized system, which is more prone to security vulnerabilities. The existing blockchain-based healthcare schemes provide only a data-sharing framework, but they lack security and privacy. To cope with these kinds of security issues, we have designed a novel security algorithm that provides security as well as privacy with much better efficiency and a lower cost. Hence, in this research, we have proposed a patient healthcare framework that provides greater security, reliability, and authentication compared to existing blockchain-based access control. Full article
(This article belongs to the Special Issue Blockchain Based Electronic Healthcare Solution and Security)
Show Figures

Figure 1

12 pages, 2052 KiB  
Article
Spatial Jitter Influence on the Average BLER Performance of SIMO FSO Links over Atmospheric Turbulence Channels
by Nikolaos A. Androutsos, Hector E. Nistazakis, Efstratios V. Chatzikontis, Argyris N. Stassinakis and George S. Tombras
Electronics 2021, 10(16), 2033; https://doi.org/10.3390/electronics10162033 - 22 Aug 2021
Cited by 1 | Viewed by 1683
Abstract
In the recent years, Free Space Optics (FSO) technology has attracted significant research and commercial interest mostly because of its many advantages in comparison with other radio systems used for point-to-point connections. However, the reliable operation of these systems significantly depends on the [...] Read more.
In the recent years, Free Space Optics (FSO) technology has attracted significant research and commercial interest mostly because of its many advantages in comparison with other radio systems used for point-to-point connections. However, the reliable operation of these systems significantly depends on the conditions of the atmosphere in the area in which the optical beam propagates. The most important of these conditions are atmospheric turbulence and the misalignment between the optical beam and the receiver, which is also known as the pointing errors effect. In this work, in order to obviate the performance mitigation caused by these phenomena, we examined the most widely accepted and one of the most effective techniques, i.e., the implementation of receivers’ diversity. Various metrics have been investigated to evaluate the performance of such systems, but most of them do not take into account that the ultra-fast modern optical communication systems use blocks of bits for the transmission and codes for the detection and/or correction of erroneous bits. Thus, by taking these aspects into account, in this work, we investigated the combined impact of spatial jitter and atmospheric turbulence on the total average block error rate of an optical wireless system with receivers’ diversity. Novel closed-form analytical formulas were derived. Full article
Show Figures

Figure 1

22 pages, 1743 KiB  
Article
Analysis of Cooperative Skills Development through Relational Coordination in a Gamified Online Learning Environment
by Rosa Estriegana, Jose-Amelio Medina-Merodio, Rafael Robina-Ramírez and Roberto Barchino
Electronics 2021, 10(16), 2032; https://doi.org/10.3390/electronics10162032 - 22 Aug 2021
Cited by 11 | Viewed by 3398
Abstract
One of the main problems of the sudden digital transition to online education due to the COVID-19 pandemic is the increased isolation of students. On the other hand, one of the main goals of higher education is to develop students’ cooperative competence. This [...] Read more.
One of the main problems of the sudden digital transition to online education due to the COVID-19 pandemic is the increased isolation of students. On the other hand, one of the main goals of higher education is to develop students’ cooperative competence. This experimental study presents an online learning environment, consisting of a set of web-based resources such as virtual laboratories, interactive activities, educational videos and a game-based learning methodology. The study also examines the influence of the combination of such resources with active and collaborative learning on the improvement of students’ relationships and the development of cooperative competence. To this end, an analysis was conducted based on the data collected from a core subject of the Computer Engineering and Computer Science Engineering degree courses. The answers of an online survey (n = 289) were examined by using the structural equation modeling technique (SEM). The results suggest that the proposed learning environment has a significant and positive impact on the two dimensions of relational coordination; communication and relationships, and plays a key role in the acquisition and development of cooperative competence. Findings also indicate that effective, accurate, frequent and timely communication, positively influences on students’ relationships. Additionally, this study addresses other important issues with significant theoretical and practical implications for higher education. Full article
Show Figures

Figure 1

19 pages, 3074 KiB  
Article
A Cross-Mode Universal Digital Pre-Distortion Technology for Low-Sidelobe Active Antenna Arrays in 5G and Satellite Communications
by Yunfeng Li, Yonghui Huang, Martin Hedegaard Nielsen, Feridoon Jalili, Wei Wei, Jian Ren, Yingzeng Yin, Ming Shen and Gert Frølund Pedersen
Electronics 2021, 10(16), 2031; https://doi.org/10.3390/electronics10162031 - 22 Aug 2021
Cited by 2 | Viewed by 2245
Abstract
A cross-mode universal digital pre-distortion (CMUDPD) technology is proposed here to linearize low-sidelobe active antenna arrays with non-uniform fixed power levels for each branch, which are desired in satellite communications with stringent requirements to minimize interference. In low-sidelobe arrays formed by nonuniform amplitude [...] Read more.
A cross-mode universal digital pre-distortion (CMUDPD) technology is proposed here to linearize low-sidelobe active antenna arrays with non-uniform fixed power levels for each branch, which are desired in satellite communications with stringent requirements to minimize interference. In low-sidelobe arrays formed by nonuniform amplitude excitation, conventional digital pre-distortion (DPD) techniques require multiple feedback paths for either one-to-one or average linearization of the PAs, which increases system complexity and is infeasible for large-scale arrays. This is because the power amplifiers (PAs) usually operate in different modes where the supply voltages, bias voltages, and input power levels are different. The proposed CMUDPD method aims at solving this issue by intentionally arranging the PAs to work in different modes but with shared nonlinear characteristics. Based on the nonlinear correlation established among the PAs’ different operating modes, a single feedback path is sufficient to capture the common nonlinearity of all the PAs and determine the parameters of the CMUDPD module. The concept is explained in theory and validated by simulations and experiments using GaN PAs operating with three significantly different output power levels and two orthogonal frequency division multiplexing (OFDM) signal bandwidths. Full article
(This article belongs to the Special Issue 5G Front-End Transceivers)
Show Figures

Figure 1

16 pages, 2067 KiB  
Article
Rain Attenuation Scaling in South Korea: Experimental Results and Artificial Neural Network
by Md Abdus Samad, Feyisa Debo Diba and Dong-You Choi
Electronics 2021, 10(16), 2030; https://doi.org/10.3390/electronics10162030 - 22 Aug 2021
Cited by 3 | Viewed by 2792
Abstract
Scaling rain attenuation parameters will significantly benefit the quick monitoring of rain attenuation in a particular channel with previously known results or in situ setup attenuation measurements. Most of the rain attenuation scaling techniques have been derived for slant links. In this study, [...] Read more.
Scaling rain attenuation parameters will significantly benefit the quick monitoring of rain attenuation in a particular channel with previously known results or in situ setup attenuation measurements. Most of the rain attenuation scaling techniques have been derived for slant links. In this study, we also applied frequency and polarization scaling techniques for terrestrial link applications. We collected real measured datasets from research paper publications and examined those datasets using International Telecommunication Union-Radiocommunication sector (ITU-R) models (P.530-17, P.618-13). Our analyzed results show that existing long-term frequency and polarization scaling rain attenuation models (ITU-R P.618-13 for slant links and ITU-R P.530-17 for terrestrial links) show reduced performance for frequency and polarization scaling measured locations in South Korea. Hence, we proposed a new scaling technique using artificial neural networks from the measured rain attenuation data of slant and terrestrial links in South Korea. The experimental results confirm that the proposed Artificial Neural Network (ANN)-based scaling model shows satisfactory performance to predict attenuation for frequency and vertical polarization scaling. Full article
(This article belongs to the Section Microwave and Wireless Communications)
Show Figures

Figure 1

12 pages, 3466 KiB  
Article
Learning-Rate Annealing Methods for Deep Neural Networks
by Kensuke Nakamura, Bilel Derbel, Kyoung-Jae Won and Byung-Woo Hong
Electronics 2021, 10(16), 2029; https://doi.org/10.3390/electronics10162029 - 22 Aug 2021
Cited by 18 | Viewed by 12344
Abstract
Deep neural networks (DNNs) have achieved great success in the last decades. DNN is optimized using the stochastic gradient descent (SGD) with learning rate annealing that overtakes the adaptive methods in many tasks. However, there is no common choice regarding the scheduled-annealing for [...] Read more.
Deep neural networks (DNNs) have achieved great success in the last decades. DNN is optimized using the stochastic gradient descent (SGD) with learning rate annealing that overtakes the adaptive methods in many tasks. However, there is no common choice regarding the scheduled-annealing for SGD. This paper aims to present empirical analysis of learning rate annealing based on the experimental results using the major data-sets on the image classification that is one of the key applications of the DNNs. Our experiment involves recent deep neural network models in combination with a variety of learning rate annealing methods. We also propose an annealing combining the sigmoid function with warmup that is shown to overtake both the adaptive methods and the other existing schedules in accuracy in most cases with DNNs. Full article
Show Figures

Figure 1

16 pages, 7923 KiB  
Article
WSN Deployment Strategy for Real 3D Terrain Coverage Based on Greedy Algorithm with DEM Probability Coverage Model
by Wendi Fu, Yan Yang, Guoqi Hong and Jing Hou
Electronics 2021, 10(16), 2028; https://doi.org/10.3390/electronics10162028 - 21 Aug 2021
Cited by 8 | Viewed by 2241
Abstract
The key to the study of node deployment in Wireless Sensor Networks (WSN) is to find the appropriate location of the WSN nodes and reduce the cost of network deployment while meeting the monitoring requirements in the covered area. This paper proposes a [...] Read more.
The key to the study of node deployment in Wireless Sensor Networks (WSN) is to find the appropriate location of the WSN nodes and reduce the cost of network deployment while meeting the monitoring requirements in the covered area. This paper proposes a WSN node deployment algorithm based on real 3D terrain, which provides an effective solution to the surface-covering problem. First of all, actual geographic elevation data is adopted to conduct surface modeling. The model can vividly reflect the real terrain characteristics of the area to be deployed and make the deployment plan more visible and easy to adjust. Secondly, a probabilistic coverage model based on DEM (Digital Elevation Model) data is proposed. Based on the traditional spherical coverage model, the influence of signal attenuation and terrain occlusion on the coverage model is added to make the deployment model closer to reality. Finally, the Greedy algorithm based on grid scanning is used to deploy nodes. Simulation results show that the proposed algorithm can effectively improve the coverage rate, reduce the deployment cost, and reduce the time and space complexity in solving the WSN node deployment problem under the complex 3D land surface model, which verifies the effectiveness of the proposed algorithm. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Figure 1

16 pages, 1996 KiB  
Communication
Utility DERMS for Active Management of Emerging Distribution Grids with High Penetration of Renewable DERs
by Luka Strezoski and Izabela Stefani
Electronics 2021, 10(16), 2027; https://doi.org/10.3390/electronics10162027 - 21 Aug 2021
Cited by 14 | Viewed by 5557
Abstract
Operational and planning challenges caused by ever-increasing integration of electronically coupled renewable distributed energy resources (DERs) have become a reality all over the globe. These challenges range from technical constraint violations to malfunctional setting and coordination of the protective equipment and inaccurate operational [...] Read more.
Operational and planning challenges caused by ever-increasing integration of electronically coupled renewable distributed energy resources (DERs) have become a reality all over the globe. These challenges range from technical constraint violations to malfunctional setting and coordination of the protective equipment and inaccurate operational planning. Moreover, to enable the preconditions for the integration of high penetration of renewable DERs, utilities are faced with potentially huge investment requirements in strengthening the grid assets. However, recent advances in specialized software solutions for integration and active management of high penetration of DERs could turn these challenges into operational and monetary benefits. Hence, if planned, managed, and operated in an optimal way, the high penetration of DERs could be a valuable resource for increasing the efficiency of the overall management of distribution grids. Utility distributed energy resource management systems (utility DERMSs) aim to provide all of these capabilities integrated into a single software solution. In this paper, a utility DERMS concept is introduced, and the capabilities of state-of-the-art utility DERMS solutions for helping the key stakeholders to pave the way towards stable, optimal, and secure emerging distribution systems with high penetration of electronically coupled renewable DERs are explored. Full article
Show Figures

Figure 1

21 pages, 6600 KiB  
Article
Theoretical Computational Model for Cylindrical Permanent Magnet Coupling
by Ke Sun, Jianwen Shi, Wei Cui and Guoying Meng
Electronics 2021, 10(16), 2026; https://doi.org/10.3390/electronics10162026 - 21 Aug 2021
Cited by 5 | Viewed by 3713
Abstract
Permanent magnet coupling is extensively studied owing to its economic efficiency and stability. In this study, a computational model for cylindrical permanent magnet coupling (CPMC) was designed using the magnetic field division method to divide an air gap magnetic field. An equivalent magnetic [...] Read more.
Permanent magnet coupling is extensively studied owing to its economic efficiency and stability. In this study, a computational model for cylindrical permanent magnet coupling (CPMC) was designed using the magnetic field division method to divide an air gap magnetic field. An equivalent magnetic circuit model was also designed based on the equivalent magnetic circuit method. The novelty of this study is that both the skin effect and the working point of the permanent magnet are taken into consideration to obtain the magnetic circuit and induce eddy current characteristics of permanent magnet coupling. Furthermore, a computational model was obtained for the transmission torque of the CPMC based on the principles of Faraday’s and Ampere’s laws. Additionally, the accuracy of the model was verified using a finite element simulation model and a test bench. Full article
(This article belongs to the Section Power Electronics)
Show Figures

Figure 1

15 pages, 471 KiB  
Article
An Efficient Distributed Elliptic Positioning for Underground Remote Sensing
by Sanaa S. Al-Samahi, Huda Ansaf and Bahaa I. K. Ansaf
Electronics 2021, 10(16), 2025; https://doi.org/10.3390/electronics10162025 - 21 Aug 2021
Viewed by 1506
Abstract
Remote surveying of unknown bound geometries, such as the mapping of underground water supplies and tunnels, remains a challenging task. The obstacles and absorption in media make the long-distance telecommunication and localization process inefficient due to mobile sensors’ power limitations. This work develops [...] Read more.
Remote surveying of unknown bound geometries, such as the mapping of underground water supplies and tunnels, remains a challenging task. The obstacles and absorption in media make the long-distance telecommunication and localization process inefficient due to mobile sensors’ power limitations. This work develops a new short-range sequential localization approach to reduce the required amount of signal transmission power. The developed algorithm is based on a sequential localization process that can utilize a multitude of randomly distributed wireless sensors while only employing several anchors in the process. Time delay elliptic and frequency range techniques are employed in developing the proposed algebraic closed-form solution. The proposed method is highly effective as it reaches the Cramer–Rao Lower Bound performance level. The estimated positions can act as initializations for the iterative Maximum Likelihood Estimator (MLE) via the Taylor series linearization to acquire even higher positioning accuracy as needed. By reducing the need for high power at the transmit modules in the sensors, the developed localization approach can be used to design a compact sensor with low power consumption and greater longevity that can be utilized to explore unknown bounded geometries for life-long efficient observation mapping. Full article
(This article belongs to the Special Issue Application of Wireless Sensor Networks in Accredited Monitoring)
Show Figures

Figure 1

11 pages, 2330 KiB  
Communication
High PSRR Wide Supply Range Dual-Voltage Reference Circuit for Bio-Implantable Applications
by Ruhaifi Bin Abdullah Zawawi, Hojong Choi and Jungsuk Kim
Electronics 2021, 10(16), 2024; https://doi.org/10.3390/electronics10162024 - 21 Aug 2021
Cited by 3 | Viewed by 2013
Abstract
On-chip systems are challenging owing to the limited size of the components, such as the capacitor bank in the rectifier. With a small on-chip capacitor, the output voltage of the rectifier might ring if the circuit experiences significant changes in current. The reference [...] Read more.
On-chip systems are challenging owing to the limited size of the components, such as the capacitor bank in the rectifier. With a small on-chip capacitor, the output voltage of the rectifier might ring if the circuit experiences significant changes in current. The reference circuit is the first block after the rectifier, and the entire system relies on its robustness. A fully integrated dual-voltage reference circuit for bio-implantable applications is presented. The proposed circuit utilizes nonlinear current compensation techniques that significantly decrease supply variations and reject high-supply ripples for various frequencies. The reference circuit was verified using a 0.35 µm complementary metal-oxide semiconductor (CMOS) process. Maximum PSRR values of −112 dB and −128 dB were obtained. With a supply range from 2.8 to 12 V, the proposed design achieves 0.916 and 1.5 mV/V line regulation for the positive and negative reference circuits, respectively. Full article
(This article belongs to the Special Issue New Technologies for Biomedical Circuits and Systems)
Show Figures

Figure 1

22 pages, 3707 KiB  
Article
A Low Area High Speed FPGA Implementation of AES Architecture for Cryptography Application
by Thanikodi Manoj Kumar, Kasarla Satish Reddy, Stefano Rinaldi, Bidare Divakarachari Parameshachari and Kavitha Arunachalam
Electronics 2021, 10(16), 2023; https://doi.org/10.3390/electronics10162023 - 21 Aug 2021
Cited by 59 | Viewed by 6268
Abstract
Nowadays, a huge amount of digital data is frequently changed among different embedded devices over wireless communication technologies. Data security is considered an important parameter for avoiding information loss and preventing cyber-crimes. This research article details the low power high-speed hardware architectures for [...] Read more.
Nowadays, a huge amount of digital data is frequently changed among different embedded devices over wireless communication technologies. Data security is considered an important parameter for avoiding information loss and preventing cyber-crimes. This research article details the low power high-speed hardware architectures for the efficient field programmable gate array (FPGA) implementation of the advanced encryption standard (AES) algorithm to provide data security. This work does not depend on the Look-Up Table (LUTs) for the implementation the SubBytes and InvSubBytes stages of transformations of the AES encryption and decryption; this new architecture uses combinational logical circuits for implementing SubBytes and InvSubBytes transformation. Due to the elimination of LUTs, unwanted delays are eliminated in this architecture and a subpipelining structure is introduced for improving the speed of the AES algorithm. Here, modified positive polarity reed muller (MPPRM) architecture is inserted to reduce the total hardware requirements, and comparisons are made with different implementations. With MPPRM architecture introduced in SubBytes stages, an efficient mixcolumn and invmixcolumn architecture that is suited to subpipelined round units is added. The performances of the proposed AES-MPPRM architecture is analyzed in terms of number of slice registers, flip flops, number of slice LUTs, number of logical elements, slices, bonded IOB, operating frequency and delay. There are five different AES architectures including LAES, AES-CTR, AES-CFA, AES-BSRD, and AES-EMCBE. The LUT of the AES-MPPRM architecture designed in the Spartan 6 is reduced up to 15.45% when compared to the AES-BSRD. Full article
(This article belongs to the Section Networks)
Show Figures

Figure 1

16 pages, 763 KiB  
Article
Motor Unit Discharges from Multi-Kernel Deconvolution of Single Channel Surface Electromyogram
by Luca Mesin
Electronics 2021, 10(16), 2022; https://doi.org/10.3390/electronics10162022 - 21 Aug 2021
Cited by 2 | Viewed by 1584
Abstract
Surface electromyogram (EMG) finds many applications in the non-invasive characterization of muscles. Extracting information on the control of motor units (MU) is difficult when using single channels, e.g., due to the low selectivity and large phase cancellations of MU action potentials (MUAPs). In [...] Read more.
Surface electromyogram (EMG) finds many applications in the non-invasive characterization of muscles. Extracting information on the control of motor units (MU) is difficult when using single channels, e.g., due to the low selectivity and large phase cancellations of MU action potentials (MUAPs). In this paper, we propose a new method to face this problem in the case of a single differential channel. The signal is approximated as a sum of convolutions of different kernels (adapted to the signal) and firing patterns, whose sum is the estimation of the cumulative MU firings. Three simulators were used for testing: muscles of parallel fibres with either two innervation zones (IZs, thus, with MUAPs of different phases) or one IZ and a model with fibres inclined with respect to the skin. Simulations were prepared for different fat thicknesses, distributions of conduction velocity, maximal firing rates, synchronizations of MU discharges, and variability of the inter-spike interval. The performances were measured in terms of cross-correlations of the estimated and simulated cumulative MU firings in the range of 0–50 Hz and compared with those of a state-of-the-art single-kernel algorithm. The median cross-correlations for multi-kernel/single-kernel approaches were 92.2%/82.4%, 98.1%/97.6%, and 95.0%/91.0% for the models with two IZs, one IZ (parallel fibres), and inclined fibres, respectively (all statistically significant differences, which were larger when the MUAP shapes were of greater difference). Full article
Show Figures

Figure 1

14 pages, 1833 KiB  
Article
Derogation of Physical Layer Security Breaches in Maturing Heterogeneous Optical Networks
by Ammar Armghan
Electronics 2021, 10(16), 2021; https://doi.org/10.3390/electronics10162021 - 21 Aug 2021
Viewed by 1805
Abstract
The evolution journey of optical network (ON) towards heterogeneous and flexible frameworks with high order of applications is continued from the last decade. Furthermore, the prominence of optical security, amount of transmitted data, bandwidth, and dependable presentation are heightened. The performance of ON [...] Read more.
The evolution journey of optical network (ON) towards heterogeneous and flexible frameworks with high order of applications is continued from the last decade. Furthermore, the prominence of optical security, amount of transmitted data, bandwidth, and dependable presentation are heightened. The performance of ON is degraded in view of various natures of attacks at the physical layer, such as service disrupting and access to carrier data. In order to deal with such security breaches, new and efficient ON must be identified. So, this paper elaborates a detailed structure on physical layer security for heterogeneous ON. Possible mechanisms, such as Elliptic-curve Diffie–Hellman (ECDH), are used to treat a physical layer attack, and an efficient framework is proposed in this paper for 64 quadrature amplitude modulation-based orthogonal frequency division multiplex (64QAM-OFDM) ONs. Finally, theoretical and simulation validations are presented, and the effective results of the proposed method and viewpoint are concluded. Full article
(This article belongs to the Special Issue New Advances and Challenges in Communication Networks)
Show Figures

Figure 1

29 pages, 2920 KiB  
Article
FO-Sketch: A Fast Oblivious Sketch for Secure Network Measurement Service in the Cloud
by Lingtong Liu, Yulong Shen, Shuiguang Zeng and Zhiwei Zhang
Electronics 2021, 10(16), 2020; https://doi.org/10.3390/electronics10162020 - 20 Aug 2021
Cited by 1 | Viewed by 1692
Abstract
Network measurements are the foundation for network applications. The metrics generated by those measurements help applications improve their performance of the monitored network and harden their security. As severe network attacks using leaked information from a public cloud exist, it raises privacy and [...] Read more.
Network measurements are the foundation for network applications. The metrics generated by those measurements help applications improve their performance of the monitored network and harden their security. As severe network attacks using leaked information from a public cloud exist, it raises privacy and security concerns if directly deployed in network measurement services in a third-party public cloud infrastructure. Recent studies, most notably OblivSketch, demonstrated the feasibility of alleviating those concerns by using trusted hardware and Oblivious RAM (ORAM). As their performance is not good enough, and there are certain limitations, they are not suitable for broad deployment. In this paper, we propose FO-Sketch, a more efficient and general network measurement service that meets the most stringent security requirements, especially for a large-scale network with heavy traffic volume and burst traffic. Let a mergeable sketch update the local flow statistics in each local switch; FO-Sketch merges (in an Intel SGX-created enclave) these sketches obliviously to form a global “one big sketch” in the cloud. With the help of Oblivious Shuffle, Divide and Conquer, and SIMD speedup, we optimize all of the critical routines in our FO-Sketch to make it 17.3x faster than a trivial oblivious solution. While keeping the same level of accuracy and packet processing throughput as non-oblivious Elastic Sketch, our FO-Sketch needs only ∼4.5 MB enclave memory space in total to record metrics and for PORAM to store the global sketch in the cloud. Extensive experiments demonstrate that, for the recommended setting, it takes only ∼ 0.6 s in total to rebuild those data during each measurement interval. Full article
(This article belongs to the Special Issue Advanced Security, Trust and Privacy Solutions for Wireless Networks)
Show Figures

Figure 1

15 pages, 7604 KiB  
Article
The Three-Carrier Quasi Switched Boost Inverter Control Technique
by Thanh-Hai Quach, Xuan-Vinh Le and Viet-Anh Truong
Electronics 2021, 10(16), 2019; https://doi.org/10.3390/electronics10162019 - 20 Aug 2021
Viewed by 1547
Abstract
This paper presents a carrier modulation technique to control the three-phase, two-level quasi switched boost inverter. This PWM algorithm uses three carrier waves, the first of which is for the inverter while the others are for the booster. The boost factor depends on [...] Read more.
This paper presents a carrier modulation technique to control the three-phase, two-level quasi switched boost inverter. This PWM algorithm uses three carrier waves, the first of which is for the inverter while the others are for the booster. The boost factor depends on the short circuit interval on the DC/DC booster and the inverter. When the short circuit interval on the DC boost is twice that on the inverter, the modulation index can be enlarged. The new algorithm is analyzed, calculated, simulated, and tested. The analysis and calculation results show that the proposed technique can reduce the voltage on the DC link capacitor compared to a conventional approach. It can reach 22.16% when the ratio of the DC source voltage to the effective reference voltage is 0.5. The modulation index can extend to 29% under these conditions and the current ripple in the boost inductor can be reduced by 4.8%. The simulation and experimental results also show similarities, thereby confirming the analysis and calculation. Full article
(This article belongs to the Section Power Electronics)
Show Figures

Figure 1

21 pages, 519 KiB  
Article
A Metaheuristic Based Approach for the Customer-Centric Perishable Food Distribution Problem
by Hanane El Raoui, Mustapha Oudani, David A. Pelta and Ahmed El Hilali Alaoui
Electronics 2021, 10(16), 2018; https://doi.org/10.3390/electronics10162018 - 20 Aug 2021
Cited by 4 | Viewed by 1740
Abstract
High transportation costs and poor quality of service are common vulnerabilities in various logistics networks, especially in food distribution. Here we propose a many-objective Customer-centric Perishable Food Distribution Problem that focuses on the cost, the quality of the product, and the service level [...] Read more.
High transportation costs and poor quality of service are common vulnerabilities in various logistics networks, especially in food distribution. Here we propose a many-objective Customer-centric Perishable Food Distribution Problem that focuses on the cost, the quality of the product, and the service level improvement by considering not only time windows but also the customers’ target time and their priority. Recognizing the difficulty of solving such model, we propose a General Variable Neighborhood Search (GVNS) metaheuristic based approach that allows to efficiently solve a subproblem while allowing us to obtain a set of solutions. These solutions are evaluated over some non-optimized criteria and then ranked using an a posteriori approach that requires minimal information about decision maker preferences. The computational results show (a) GVNS achieved same quality solutions as an exact solver (CPLEX) in the subproblem; (b) GVNS can generate a wide number of candidate solutions, and (c) the use of the a posteriori approach makes easy to generate different decision maker profiles which in turn allows to obtain different rankings of the solutions. Full article
Show Figures

Figure 1

15 pages, 4384 KiB  
Article
Detection and Classification of Defective Hard Candies Based on Image Processing and Convolutional Neural Networks
by Jinya Wang, Zhenye Li, Qihang Chen, Kun Ding, Tingting Zhu and Chao Ni
Electronics 2021, 10(16), 2017; https://doi.org/10.3390/electronics10162017 - 20 Aug 2021
Cited by 7 | Viewed by 2964
Abstract
Defective hard candies are usually produced due to inadequate feeding or insufficient cooling during the candy production process. The human-based inspection strategy needs to be brought up to date with the rapid developments in the confectionery industry. In this paper, a detection and [...] Read more.
Defective hard candies are usually produced due to inadequate feeding or insufficient cooling during the candy production process. The human-based inspection strategy needs to be brought up to date with the rapid developments in the confectionery industry. In this paper, a detection and classification method for defective hard candies based on convolutional neural networks (CNNs) is proposed. First, the threshold_li method is used to distinguish between hard candy and background. Second, a segmentation algorithm based on concave point detection and ellipse fitting is used to split the adhesive hard candies. Finally, a classification model based on CNNs is constructed for defective hard candies. According to the types of defective hard candies, 2552 hard candies samples were collected; 70% were used for model training, 15% were used for validation, and 15% were used for testing. Defective hard candy classification models based on CNNs (Alexnet, Googlenet, VGG16, Resnet-18, Resnet34, Resnet50, MobileNetV2, and MnasNet0_5) were constructed and tested. The results show that the classification performances of these deep learning models are similar except MnasNet0_5 with the classification accuracy of 84.28%, and the Resnet50-based classification model is the best (98.71%). This research has certain theoretical reference significance for the intelligent classification of granular products. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Figure 1

17 pages, 4026 KiB  
Review
A Fuzzy Based Handover Decision Scheme for Mobile Devices Using Predictive Model
by Amit Kumar Gupta, Vikas Goel, Ruchi Rani Garg, Dasarada Rajagopalan Thirupurasundari, Ankit Verma and Mangal Sain
Electronics 2021, 10(16), 2016; https://doi.org/10.3390/electronics10162016 - 20 Aug 2021
Cited by 9 | Viewed by 2738
Abstract
Handover usually deals with the mobility of the end users in a mobile network to assure about the ongoing session of a user. It is observed that frequent handover results in call dropping due to latency. In order to overcome this issue, a [...] Read more.
Handover usually deals with the mobility of the end users in a mobile network to assure about the ongoing session of a user. It is observed that frequent handover results in call dropping due to latency. In order to overcome this issue, a fuzzy based handover decision scheme for mobile devices using a predictive model is proposed. First, an MFNN (Multi-layer Feed Forward Network) is used to determine the next cell of the user along with best hand off time. To obtain the best access network, multiple-attribute Access Network Selection Function (ANSF) is used. The fuzzy rule is applied by considering the parameter data rate, reliability, signal strength, battery power and mobility as input and the output obtained is the optimal network. The proposed scheme selects the best access network and enhances the quality of services. Full article
Show Figures

Figure 1

19 pages, 794 KiB  
Article
Estimating the Memory Consumption of a Hardware IP Defragmentation Block
by Maciej Czekaj, Ernest Jamro and Kazimierz Wiatr
Electronics 2021, 10(16), 2015; https://doi.org/10.3390/electronics10162015 - 20 Aug 2021
Viewed by 2390
Abstract
IP fragmentation is still prevalent on the Internet. Defragmented traffic is a prerequisite for many network processing algorithms. This work focuses on the size and organization of a flow table, which is an essential ingredient of the hardware IP defragmentation block. Previous research [...] Read more.
IP fragmentation is still prevalent on the Internet. Defragmented traffic is a prerequisite for many network processing algorithms. This work focuses on the size and organization of a flow table, which is an essential ingredient of the hardware IP defragmentation block. Previous research suggests that fragmented IP traffic is highly local, and a relatively small flow table (on the order of a thousand entries) can process most of the traffic. Samples of IP traffic were obtained from public data sources and used for a statistical analysis, revealing the key factors in achieving design goals. The findings were backed by an extensive design space exploration of the software defragmentation model, which resulted in the efficiency estimates. To provide a robust score of the simulation model, a new validation technique is employed that helps to overcome the limitations of the samples. Full article
(This article belongs to the Section Computer Science & Engineering)
Show Figures

Graphical abstract

15 pages, 41453 KiB  
Article
Deep Image Prior for Super Resolution of Noisy Image
by Sujy Han, Tae Bok Lee and Yong Seok Heo
Electronics 2021, 10(16), 2014; https://doi.org/10.3390/electronics10162014 - 20 Aug 2021
Cited by 5 | Viewed by 4395
Abstract
Single image super-resolution task aims to reconstruct a high-resolution image from a low-resolution image. Recently, it has been shown that by using deep image prior (DIP), a single neural network is sufficient to capture low-level image statistics using only a single image without [...] Read more.
Single image super-resolution task aims to reconstruct a high-resolution image from a low-resolution image. Recently, it has been shown that by using deep image prior (DIP), a single neural network is sufficient to capture low-level image statistics using only a single image without data-driven training such that it can be used for various image restoration problems. However, super-resolution tasks are difficult to perform with DIP when the target image is noisy. The super-resolved image becomes noisy because the reconstruction loss of DIP does not consider the noise in the target image. Furthermore, when the target image contains noise, the optimization process of DIP becomes unstable and sensitive to noise. In this paper, we propose a noise-robust and stable framework based on DIP. To this end, we propose a noise-estimation method using the generative adversarial network (GAN) and self-supervision loss (SSL). We show that a generator of DIP can learn the distribution of noise in the target image with the proposed framework. Moreover, we argue that the optimization process of DIP is stabilized when the proposed self-supervision loss is incorporated. The experiments show that the proposed method quantitatively and qualitatively outperforms existing single image super-resolution methods for noisy images. Full article
Show Figures

Figure 1

Previous Issue
Back to TopTop