Electronics

16 pages, 48311 KiB

Open AccessArticle

An Efficient and High-Quality Mesh Reconstruction Method with Adaptive Visibility and Dynamic Refinement

by Qingsong Yan, Teng Xiao, Yingjie Qu, Junxing Yang and Fei Deng

Electronics 2023, 12(22), 4716; https://doi.org/10.3390/electronics12224716 - 20 Nov 2023

Cited by 1 | Viewed by 787

Image-based 3D reconstruction generates 3D mesh models from images and plays an important role in all walks of life. However, existing methods suffer from poor reconstruction quality and low reconstruction efficiency. To address this issue, we propose an improved optimization-based mesh reconstruction method [...] Read more.

Image-based 3D reconstruction generates 3D mesh models from images and plays an important role in all walks of life. However, existing methods suffer from poor reconstruction quality and low reconstruction efficiency. To address this issue, we propose an improved optimization-based mesh reconstruction method with adaptive visibility reconstruction and dynamic photo-metric refinement. The adaptive visibility reconstruction adjusts soft visibility based on the observation and geometry structure of points to reconstruct details while suppressing noise in the rough mesh. The dynamic photo-metric refinement tunes the learning rate using historical gradients and stops to optimize converged triangles to speed up the mesh refinement. Experiments on BlendedMVS and real datasets showed that our method found a good balance between reconstruction quality and reconstruction efficiency. Compared with the state-of-the-art methods, OpenMVS and TDR, our method achieved higher reconstruction quality than OpenMVS and obtained competitive reconstruction quality with TDR, but required only one-third of the reconstruction time of OpenMVS and one-tenth of the reconstruction time of TDR. Our method balances reconstruction efficiency and reconstruction quality and can meet real-world application requirements. Full article

► Show Figures

Figure 1

24 pages, 2161 KiB

Open AccessArticle

The Influence of Augmented Reality (AR) on the Motivation of High School Students

by Antonio Amores-Valencia, Daniel Burgos and John W. Branch-Bedoya

Electronics 2023, 12(22), 4715; https://doi.org/10.3390/electronics12224715 - 20 Nov 2023

Cited by 1 | Viewed by 1021

Abstract

Augmented reality (AR) is a technology whose presence has increased in the field of education in recent years. However, its role in secondary education has not been thoroughly explored. Therefore, this research aims to analyse the influence of AR on the motivation of [...] Read more.

Augmented reality (AR) is a technology whose presence has increased in the field of education in recent years. However, its role in secondary education has not been thoroughly explored. Therefore, this research aims to analyse the influence of AR on the motivation of students at this stage while considering gender and previous information and communication technology (ICT) experience. This research uses a quantitative methodology that follows Keller’s Attention, Relevance, Confidence and Satisfaction (ARCS) motivational model. We implemented this instructional design model for a sample of 321 students from the same educational centre. They were divided into two categories: an experimental group (n = 159) and a control group (n = 162). The control group were studied in a slide-based learning environment, while the experimental group worked with an AR mobile application. For data collection, we used the Instructional Materials Motivation Survey (IMMS). The results showed that the students who used AR displayed greater motivation, highlighting great interest in the integration of this technology into the learning process. However, no significant differences were obtained in the motivation of the students according to gender and previous experience with the use of ICT. In conclusion, this research shows that the use of AR improves motivation in secondary education. Full article

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

► Show Figures

Figure 1

28 pages, 7122 KiB

Open AccessReview

Emotion Recognition in Conversations: A Survey Focusing on Context, Speaker Dependencies, and Fusion Methods

by Yao Fu, Shaoyang Yuan, Chi Zhang and Juan Cao

Electronics 2023, 12(22), 4714; https://doi.org/10.3390/electronics12224714 - 20 Nov 2023

Cited by 1 | Viewed by 1749

Abstract

As a branch of sentiment analysis tasks, emotion recognition in conversation (ERC) aims to explore the hidden emotions of a speaker by analyzing the sentiments in utterance. In addition, emotion recognition in multimodal data from conversation includes the text of the utterance and [...] Read more.

As a branch of sentiment analysis tasks, emotion recognition in conversation (ERC) aims to explore the hidden emotions of a speaker by analyzing the sentiments in utterance. In addition, emotion recognition in multimodal data from conversation includes the text of the utterance and its corresponding acoustic and visual data. By integrating features from various modalities, the emotion of utterance can be more accurately predicted. ERC research faces challenges in context construction, speaker dependency design, and multimodal heterogeneous feature fusion. Therefore, this review starts by defining the ERC task, developing the research work, and introducing the utilized datasets in detail. Simultaneously, we analyzed context modeling in conversations, speaker dependency, and methods for fusing multimodal information concerning existing research work for evaluation purposes. Finally, this review also explores the research, application challenges, and opportunities of ERC. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 13132 KiB

Open AccessArticle

FPGA-Based CNN for Eye Detection in an Iris Recognition at a Distance System

by Camilo A. Ruiz-Beltrán, Adrián Romero-Garcés, Martín González-García, Rebeca Marfil and Antonio Bandera

Electronics 2023, 12(22), 4713; https://doi.org/10.3390/electronics12224713 - 20 Nov 2023

Cited by 1 | Viewed by 1350

Abstract

Neural networks are the state-of-the-art solution to image-processing tasks. Some of these neural networks are relatively simple, but the popular convolutional neural networks (CNNs) can consist of hundreds of layers. Unfortunately, the excellent recognition accuracy of CNNs comes at the cost of very [...] Read more.

Neural networks are the state-of-the-art solution to image-processing tasks. Some of these neural networks are relatively simple, but the popular convolutional neural networks (CNNs) can consist of hundreds of layers. Unfortunately, the excellent recognition accuracy of CNNs comes at the cost of very high computational complexity, and one of the current challenges is managing the power, delay and physical size limitations of hardware solutions dedicated to accelerating their inference process. In this paper, we describe the embedding of an eye detection system on a Zynq XCZU4EV UltraScale+ multiprocessor system-on-chip (MPSoC). This eye detector is used in the application framework of a remote iris recognition system, which requires high resolution images captured at high speed as input. Given the high rate of eye regions detected per second, it is also important that the detector only provides as output images eyes that are in focus, discarding all those seriously affected by defocus blur. In this proposal, the network will be trained only with correctly focused eye images to assess whether it can differentiate this pattern from that associated with the out-of-focus eye image. Exploiting the neural network’s advantage of being able to work with multi-channel input, the inputs to the CNN will be the grey level image and a high-pass filtered version, typically used to determine whether the iris is in focus or not. The complete system synthetises other cores and implements CNN using the so-called Deep Learning Processor Unit (DPU), the intellectual property (IP) block released by AMD/Xilinx. Compared to previous hardware designs for implementing FPGA-based CNNs, the DPU IP supports extensive deep learning core functions, and developers can leverage DPUs to conveniently accelerate CNN inference. Experimental validation has been successfully addressed in a real-world scenario working with walking subjects, demonstrating that it is possible to detect only eye images that are in focus. This prototype module includes a CMOS digital image sensor that provides 16 Mpixel images, and outputs a stream of detected eyes as 640 × 480 images. The module correctly discards up to 95% of the eyes present in the input images as not being correctly focused. Full article

(This article belongs to the Special Issue Convolutional Neural Networks and Vision Applications - Volume III)

► Show Figures

Figure 1

17 pages, 8323 KiB

Open AccessArticle

Post-Impact Stabilization during Lane Change Maneuver

by Yeayoung Park, Juhui Gim and Changsun Ahn

Electronics 2023, 12(22), 4712; https://doi.org/10.3390/electronics12224712 - 20 Nov 2023

Viewed by 629

Abstract

This study addresses challenges in vehicle collisions, especially in non-front or non-rear impacts, causing rapid state changes and a loss of control. Electronic Stability Control (ESC) can stabilize a vehicle in minor impact cases, but it cannot effectively handle major collision cases. To [...] Read more.

This study addresses challenges in vehicle collisions, especially in non-front or non-rear impacts, causing rapid state changes and a loss of control. Electronic Stability Control (ESC) can stabilize a vehicle in minor impact cases, but it cannot effectively handle major collision cases. To overcome this, our research focuses on Post-Impact Stabilization Control (PISC). Existing PISC methods face issues like misidentifying collisions during cornering maneuvers due to assumptions of straight driving, rendering them ineffective for lane change accidents. Our study aims to design PISC specifically for cornering and lane change maneuvers, predicting collision forces solely from the ego vehicle’s data, ensuring improved collision stability control. We employ the unscented Kalman filter to estimate collision forces and develop a sliding mode controller with an optimal force allocation algorithm to counter the disturbances caused by collisions and stabilize the vehicle. Rigorous validation through simulations and tests with a driving simulator demonstrates the feasibility of our proposed methodology in effectively stabilizing vehicles during collision accidents, particularly in lane change situations. Full article

(This article belongs to the Special Issue Advanced Technologies in Intelligent Transportation Systems)

► Show Figures

Figure 1

14 pages, 1891 KiB

Open AccessCommunication

A 55 nm CMOS RF Transmitter Front-End with an Active Mixer and a Class-E Power Amplifier for 433 MHz ISM Band Applications

by Huazhong Yuan, Ranran Zhou, Peng Wang, Hui Xu and Yong Wang

Electronics 2023, 12(22), 4711; https://doi.org/10.3390/electronics12224711 - 20 Nov 2023

Viewed by 748

Abstract

In order to meet the increasing demands of wireless communication for ISM bands, a 433 MHz transmitter RF front-end is designed using a 55 nm low-power CMOS technology. The circuits consist of an active mixer, a driver amplifier and a class-E power amplifier [...] Read more.

In order to meet the increasing demands of wireless communication for ISM bands, a 433 MHz transmitter RF front-end is designed using a 55 nm low-power CMOS technology. The circuits consist of an active mixer, a driver amplifier and a class-E power amplifier (PA). A double-balanced Gilbert active mixer is designed to realize binary phase-shift keying (BPSK) modulation. The driver is used to preamplify the modulated RF signals. The class-E PA adopts a parallel four-branch cascode structure to control the output power level. The load network of the PA is implemented through an off-chip circuit, in which a finite DC-feed inductance load network is selected to reduce the power loss. The mixer and driver are designed with a 1.2 V supply voltage, while the PA is operated at a 1.8 V supply voltage. The area of the chip is 0.206 mm × 0.089 mm, and the measured results show that it achieves a maximum output power of 2.7 dBm, with a total power consumption of 6.72 mW. At a drain efficiency (DE) of 34.5%, an

S_{22}

less than −10 dB over the frequency ranges from 393.79 MHz to 455.70 MHz can be measured for the PA. With 192 kbps BPSK data modulated at 433 MHz, the measured EVM is about 0.83% rms. Full article

(This article belongs to the Topic Advances in Microelectronics and Semiconductor Engineering)

► Show Figures

Figure 1

15 pages, 5756 KiB

Open AccessArticle

Design and Optimization of a Compact Super-Wideband MIMO Antenna with High Isolation and Gain for 5G Applications

by Bashar A. F. Esmail, Slawomir Koziel and Anna Pietrenko-Dabrowska

Electronics 2023, 12(22), 4710; https://doi.org/10.3390/electronics12224710 - 20 Nov 2023

Viewed by 918

Abstract

This paper presents a super-wideband multiple-input multiple-output (SWB MIMO) antenna with low profile, low mutual coupling, high gain, and compact size for microwave and millimeter-wave (mm-wave) fifth-generation (5G) applications. A single antenna is a simple elliptical-square shape with a small physical size of [...] Read more.

This paper presents a super-wideband multiple-input multiple-output (SWB MIMO) antenna with low profile, low mutual coupling, high gain, and compact size for microwave and millimeter-wave (mm-wave) fifth-generation (5G) applications. A single antenna is a simple elliptical-square shape with a small physical size of 20 × 20 × 0.787 mm³. The combination of both square and elliptical shapes results in an exceptionally broad impedance bandwidth spanning from 3.4 to 70 GHz. Antenna dimensions are optimized using the trust-region algorithm to enhance its impedance bandwidth and maintain the gain within a predefined limit across the entire band. For that purpose, regularized merit function is defined, which permits to control both the single antenna reflection response and gain. Subsequently, the SWB MIMO system is constructed with four radiators arranged orthogonally. This arrangement results in high isolation, better than 20 dB, over a frequency band from 3.4 to 70 GHz band. Further, the system achieves an average gain of approximately 7 dB below 45 GHz and a maximum gain equal to 12 dB for 70 GHz. The system exhibits excellent diversity performance throughout the entire bandwidth, as evidenced by the low envelope correlation coefficient (ECC) (<3 × 10⁻³), total active reflection coefficient (TARC) (≤−10 dB), and channel capacity loss (CCL) (<0.3 bit/s/Hz) metrics, as well as the high diversity gain (DG) of approximately 10 dB. Experimental validation of the developed SWB MIMO demonstrates a good matching between the measurements and simulations. Full article

► Show Figures

Figure 1

21 pages, 4152 KiB

Open AccessArticle

Full-Range Static Method of Calibration for Laser Tracker

by Chang’an Hu, Fei Lv, Liang Xue, Jiangang Li, Xiaoyin Zhong and Yue Xu

Electronics 2023, 12(22), 4709; https://doi.org/10.3390/electronics12224709 - 20 Nov 2023

Viewed by 602

Abstract

This paper focuses on the challenge of the inability to accurately calibrate the static measurement of a laser tracker across the full scale. To address this issue, this paper proposes to add a hollow corner cube prism on a 50 m high-precision composite [...] Read more.

This paper focuses on the challenge of the inability to accurately calibrate the static measurement of a laser tracker across the full scale. To address this issue, this paper proposes to add a hollow corner cube prism on a 50 m high-precision composite guide rail to achieve a double-range measurement of the laser tracker. Data analysis indicated that, in the 77 m identical-directional double-range measurement experiment, the maximum indication error of a single-beam laser interferometer was −29.5 μm, and that of a triple-beam laser interferometer was 14.6 μm, and the measurement indication error was obviously small when the Abbe error was eliminated. The single-point repeatability of the tracker was 0.9 μm. In the 50 m identical-directional verification experiment, the results of the direct measurement outperformed those of the double-range measurement, and the indication errors under standard conditions were −4.0 μm and −8.9 μm, respectively. Overall, the method used in the experiment satisfies the requirements of the laser tracker. In terms of the identical-directional measurement, the measurement uncertainty of the tracker indication error is U ≈ 1.0 μm + 0.2L (k = 2) L = (0~77 m). The proposed method also provides insights for length measurements using other high-precision measuring instruments. Full article

(This article belongs to the Special Issue Optoelectronic Materials, Heterostructures and Devices)

► Show Figures

Figure 1

15 pages, 3371 KiB

Open AccessArticle

ODCS: On-Demand Hierarchical Consistent Synchronization Approach for the IoT

by Safaa S. Saleh, Iman S. Alansari, Mounira Kezadri Hamiaz, Waleed Ead, Rana A. Tarabishi, Mohamed Farouk and Hatem A. Khater

Electronics 2023, 12(22), 4708; https://doi.org/10.3390/electronics12224708 - 20 Nov 2023

Viewed by 666

Abstract

An IoT data system is a time constraint in which some data needs to be serviced on or before its deadline. Distributed processing is one of the most latent sources in such systems and is considered a vital design concern. Many sources of [...] Read more.

An IoT data system is a time constraint in which some data needs to be serviced on or before its deadline. Distributed processing is one of the most latent sources in such systems and is considered a vital design concern. Many sources of delay in the IoT can affect the availability of data from different resources, which may cause missing data deadlines, resulting in a catastrophic effect. In fact, such systems are inherently distributed in nature and use distributed processing. The distributed processing permits different nodes to obtain the information from remote sites, which may take a long time to access the required data. Therefore, it is considered one of the most latent sources in such systems, which is considered a vital design concern. The typical recommended solution for this problem is to commit distributed transactions locally. Therefore, replication techniques are used to enhance the availability of data and consequently avoid the resulting latency. However, the use of local processing raises inconsistent periods. Therefore, this study proposes a new synchronization framework to minimize periods of temporal inconsistency. It permits several connected nodes to synchronize the shared data on demand concurrently without any need to use distributed synchronization, which consumes the system resource and raises its delay cost. The proposed framework aims to enhance the timely response of IoT real-time systems by minimizing the temporal inconsistency periods. The results indicate that the synchronization framework can be completed within a reasonable time period. They also depict improved consistency by minimizing the temporal inconsistency duration and increasing the chance of meeting critical time requirements. Full article

► Show Figures

Figure 1

24 pages, 5085 KiB

Open AccessArticle

Personalized Text-to-Image Model Enhancement Strategies: SOD Preprocessing and CNN Local Feature Integration

by Mujung Kim, Jisang Yoo and Soonchul Kwon

Electronics 2023, 12(22), 4707; https://doi.org/10.3390/electronics12224707 - 19 Nov 2023

Viewed by 1097

Abstract

Recent advancements in text-to-image models have been substantial, generating new images based on personalized datasets. However, even within a single category, such as furniture, where the structures vary and the patterns are not uniform, the ability of the generated images to preserve the [...] Read more.

Recent advancements in text-to-image models have been substantial, generating new images based on personalized datasets. However, even within a single category, such as furniture, where the structures vary and the patterns are not uniform, the ability of the generated images to preserve the detailed information of the input images remains unsatisfactory. This study introduces a novel method to enhance the quality of the results produced by text-image models. The method utilizes mask preprocessing with an image pyramid-based salient object detection model, incorporates visual information into input prompts using concept image embeddings and a CNN local feature extractor, and includes a filtering process based on similarity measures. When using this approach, we observed both visual and quantitative improvements in CLIP text alignment and DINO metrics, suggesting that the generated images more closely follow the text prompts and more accurately reflect the input image’s details. The significance of this research lies in addressing one of the prevailing challenges in the field of personalized image generation: enhancing the capability to consistently and accurately represent the detailed characteristics of input images in the output. This method enables more realistic visualizations through textual prompts enhanced with visual information, additional local features, and unnecessary area removal using a SOD mask; it can also be beneficial in fields that prioritize the accuracy of visual data. Full article

(This article belongs to the Special Issue Deep Learning-Based Computer Vision: Technologies and Applications)

► Show Figures

Figure 1

16 pages, 1170 KiB

Open AccessReview

On-Chip Bus Protection against Soft Errors

by Ján Mach, Lukáš Kohútka and Pavel Čičák

Electronics 2023, 12(22), 4706; https://doi.org/10.3390/electronics12224706 - 19 Nov 2023

Viewed by 929

Abstract

The increasing performance demands for processors leveraged in mission and safety-critical applications mean that the processors are implemented in smaller fabrication technologies, allowing a denser integration and higher operational frequency. Besides that, these applications require a high dependability and robustness level. The properties [...] Read more.

The increasing performance demands for processors leveraged in mission and safety-critical applications mean that the processors are implemented in smaller fabrication technologies, allowing a denser integration and higher operational frequency. Besides that, these applications require a high dependability and robustness level. The properties that provide higher performance also lead to higher susceptibility to transient faults caused by radiation. Many approaches exist for protecting individual processor cores, but the protection of interconnect buses is studied less. This paper describes the importance of protecting on-chip bus interconnects and reviews existing protection approaches used in processors for mission and safety-critical processors. The protection approaches are sorted into three groups: information, temporal, and spatial redundancy. Because the final selection of the protection approach depends on the use case and performance, power, and area demands, the three groups are compared according to their fundamental properties. For better context, the review also contains information about existing solutions for protecting the internal logic of the cores and external memories. This review should serve as an entry point to the domain of protecting the on-chip bus interconnect and interface of the core. Full article

(This article belongs to the Special Issue Progress and Future Development of Real-Time Systems on Chip)

► Show Figures

Figure 1

31 pages, 1853 KiB

Open AccessReview

Taxonomy and Survey of Current 3D Photorealistic Human Body Modelling and Reconstruction Techniques for Holographic-Type Communication

by Radostina Petkova, Ivaylo Bozhilov, Desislava Nikolova, Ivaylo Vladimirov and Agata Manolova

Electronics 2023, 12(22), 4705; https://doi.org/10.3390/electronics12224705 - 19 Nov 2023

Viewed by 985

Abstract

The continuous evolution of video technologies is now primarily focused on enhancing 3D video paradigms and consistently improving their quality, realism, and level of immersion. Both the research community and the industry work towards improving 3D content representation, compression, and transmission. Their collective [...] Read more.

The continuous evolution of video technologies is now primarily focused on enhancing 3D video paradigms and consistently improving their quality, realism, and level of immersion. Both the research community and the industry work towards improving 3D content representation, compression, and transmission. Their collective efforts culminate in the striving for real-time transfer of volumetric data between distant locations, laying the foundation for holographic-type communication (HTC). However, to truly enable a realistic holographic experience, the 3D representation of the HTC participants must accurately convey the real individuals’ appearance, emotions, and interactions by creating authentic and animatable 3D human models. In this regard, our paper aims to examine the most recent and widely acknowledged works in the realm of 3D human body modelling and reconstruction. In addition, we provide insights into the datasets and the 3D parametric body models utilized by the examined approaches, along with the employed evaluation metrics. Our contribution involves organizing the examined techniques, making comparisons based on various criteria, and creating a taxonomy rooted in the nature of the input data. Furthermore, we discuss the assessed approaches concerning different indicators and HTC. Full article

(This article belongs to the Special Issue Neural Networks and Deep Learning in Computer Vision)

► Show Figures

Figure 1

17 pages, 1270 KiB

Open AccessArticle

A Novel Secure Routing Design Based on Physical Layer Security in Millimeter-Wave VANET

by Mengqiu Chai, Shengjie Zhao and Yuan Liu

Electronics 2023, 12(22), 4704; https://doi.org/10.3390/electronics12224704 - 19 Nov 2023

Viewed by 643

Abstract

With the continuous development of millimeter-wave communication technology, new requirements such as ultra-reliability and higher data rates pose new challenges to the security issues of traditional cryptographic encryption in vehicular ad hoc networks (VANET). Physical layer security uses the characteristics of different wireless [...] Read more.

With the continuous development of millimeter-wave communication technology, new requirements such as ultra-reliability and higher data rates pose new challenges to the security issues of traditional cryptographic encryption in vehicular ad hoc networks (VANET). Physical layer security uses the characteristics of different wireless channels to protect the information security. In this paper, we propose a novel VANET routing mechanism that utilizes physical layer security to improve the secrecy performance, which is compatible with the millimeter-wave vehicular network. Specifically, we design a new secure routing selection factor, the utility function, that takes into account the effects of both secrecy rate and single-hop transmission distance to achieve the hop selection. In addition, we propose a novel routing mechanism and design a waiting mechanism based on the utility function. Compared with the traditional routing algorithms, the greedy perimeter stateless routing (GPSR) and Dijkstra simulation results illustrate that our design achieves superior performance in secrecy performance and dynamic adaptability. Full article

(This article belongs to the Special Issue Millimeter-Wave and Terahertz Technologies for Wireless Communications)

► Show Figures

Figure 1

15 pages, 5269 KiB

Open AccessArticle

Multimodal Emotion Recognition in Conversation Based on Hypergraphs

by Jiaze Li, Hongyan Mei, Liyun Jia and Xing Zhang

Electronics 2023, 12(22), 4703; https://doi.org/10.3390/electronics12224703 - 19 Nov 2023

Viewed by 890

Abstract

In recent years, sentiment analysis in conversation has garnered increasing attention due to its widespread applications in areas such as social media analytics, sentiment mining, and electronic healthcare. Existing research primarily focuses on sequence learning and graph-based approaches, yet they overlook the high-order [...] Read more.

In recent years, sentiment analysis in conversation has garnered increasing attention due to its widespread applications in areas such as social media analytics, sentiment mining, and electronic healthcare. Existing research primarily focuses on sequence learning and graph-based approaches, yet they overlook the high-order interactions between different modalities and the long-term dependencies within each modality. To address these problems, this paper proposes a novel hypergraph-based method for multimodal emotion recognition in conversation (MER-HGraph). MER-HGraph extracts features from three modalities: acoustic, text, and visual. It treats each modality utterance in a conversation as a node and constructs intra-modal hypergraphs (Intra-HGraph) and inter-modal hypergraphs (Inter-HGraph) using hyperedges. The hypergraphs are then updated using hypergraph convolutional networks. Additionally, to mitigate noise in acoustic data and mitigate the impact of fixed time scales, we introduce a dynamic time window module to capture local-global information from acoustic signals. Extensive experiments on the IEMOCAP and MELD datasets demonstrate that MER-HGraph outperforms existing models in multimodal emotion recognition tasks, leveraging high-order information from multimodal data to enhance recognition capabilities. Full article

(This article belongs to the Special Issue Applied AI in Emotion Recognition)

► Show Figures

Figure 1

14 pages, 5981 KiB

Open AccessFeature PaperArticle

Design of Power Supply Based on Inductive Power Transfer System for Medium Voltage Direct Current Sensor

by Seungjin Jo, Guangyao Li, Dong-Hee Kim and Jung-Hoon Ahn

Electronics 2023, 12(22), 4702; https://doi.org/10.3390/electronics12224702 - 19 Nov 2023

Viewed by 851

Abstract

This paper proposes a medium voltage direct current (MVDC) sensor power supply method based on inductive power transfer (IPT). Given that MVDC distribution networks transmit power at high voltages (several tens of kV), control through sensors is necessary to prevent exacerbating MVDC distribution [...] Read more.

This paper proposes a medium voltage direct current (MVDC) sensor power supply method based on inductive power transfer (IPT). Given that MVDC distribution networks transmit power at high voltages (several tens of kV), control through sensors is necessary to prevent exacerbating MVDC distribution network accidents. Moreover, these high voltages in MVDC distribution networks mean that high voltage insulation is required between the sensor and the distribution line and for any power supply device electrically connected to the sensor. Therefore, this paper proposes a safe and reliable power supply method using the principle of IPT to maintain a suitable insulation distance between the distribution network and the current sensor supply line. After proposing and designing a transmitter/receiver pad and IPT system by considering the current sensor specifications, a 50-W experimental prototype is developed. The experiments demonstrated that the proposed IPT system can resolve concerns about the breakdown of insulation between distribution networks and power supply lines. Full article

(This article belongs to the Special Issue Section Collection Series: New Horizons and Recent Advances in Power Electronics)

► Show Figures

Figure 1

21 pages, 3869 KiB

Open AccessArticle

Deep Learning-Based Small Target Detection for Satellite–Ground Free Space Optical Communications

by Nikesh Devkota and Byung Wook Kim

Electronics 2023, 12(22), 4701; https://doi.org/10.3390/electronics12224701 - 19 Nov 2023

Cited by 1 | Viewed by 1036

Abstract

Free space optical (FSO) channels between a low earth orbit (LEO) satellite and a ground station (GS) use a highly directional optical beam that necessitates a continuous line-of-sight (LOS) connection. In this paper, we propose a deep neural network (DNN)-based small target detection [...] Read more.

Free space optical (FSO) channels between a low earth orbit (LEO) satellite and a ground station (GS) use a highly directional optical beam that necessitates a continuous line-of-sight (LOS) connection. In this paper, we propose a deep neural network (DNN)-based small target detection method that detects the position of a LEO satellite in an infrared image, which can be used to determine the receiver alignment for establishing the LOS link. For the infrared small target detection task without excessive down-sampling, we design a target detection model using a modified ResNest-based feature extraction network (FEN), a custom feature pyramid network (FPN), and a target determination network (TDN). ResNest utilizes the feature map attention mechanism and multi-path propagation necessary for robust feature extraction of small infrared targets. The custom FPN combines multi-scale feature maps generated from the modified ResNest to obtain robust semantics across all scales. Finally, the semantically strong multi-scale feature maps are fed into the TDN to detect small infrared targets and determine their location in infrared images. Experimental results using two widely used point spread functions (PSFs) demonstrate that the proposed algorithm outperforms the conventional schemes and detects small targets with a true detection rate of 99.4% and 94.0%. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Future Wireless Communication Systems)

► Show Figures

Figure 1

11 pages, 554 KiB

Open AccessArticle

Improving Throughput of Mobile Sensors via Certificateless Signature Supporting Batch Verification

by Chuan He, Bo Zhang, Liang Zhang, Zesheng Xi, Yuan Fang and Yunfan Wang

Electronics 2023, 12(22), 4700; https://doi.org/10.3390/electronics12224700 - 19 Nov 2023

Viewed by 752

Abstract

Mobile sensors enjoy the advantages of easy installation and low consumption, which have been widely adopted in many information systems. In those systems where data are generated rapidly, the throughput of the sensors is one of the most fundamental factors that determine the [...] Read more.

Mobile sensors enjoy the advantages of easy installation and low consumption, which have been widely adopted in many information systems. In those systems where data are generated rapidly, the throughput of the sensors is one of the most fundamental factors that determine the system functionality. For example, to guarantee data integrity, digital signature techniques can be applied. In many practical scenarios, such as the smart grid system, data are generated rapidly and, hence, the signature together with the data must also be transmitted and verified in time. This requires the mobile sensors to support a high-throughput data processing ability. In this setting, how to achieve efficient signature schemes supporting batch verification must be considered. Many signatures, such as the original national cryptographic standard, namely, the SM2 algorithm, do not support batch verification and are in a public-key infrastructure setting. In this paper, we propose a SM2-based certificateless signature scheme with batch verification, which is suitable for the aforementioned environment. The scheme extends the Chinese cryptographic standard SM2 algorithm to the certificateless setting and multiple signatures can be verified simultaneously. Another advantage of this scheme is that its signing phase does not involve any pairing operation. The verification phase only requires a constant pairing operation, which is not related to the number of signatures to be verified. The construction is generic and can be instantiated using any traditional signature scheme. Full article

(This article belongs to the Special Issue Data Privacy and Cybersecurity in Mobile Crowdsensing)

► Show Figures

Figure 1

12 pages, 3607 KiB

Open AccessArticle

Improvement of Road Instance Segmentation Algorithm Based on the Modified Mask R-CNN

by Chenxia Wan, Xianing Chang and Qinghui Zhang

Electronics 2023, 12(22), 4699; https://doi.org/10.3390/electronics12224699 - 18 Nov 2023

Cited by 1 | Viewed by 846

Abstract

Although the Mask region-based convolutional neural network (R-CNN) model possessed a dominant position for complex and variable road scene segmentation, some problems still existed, including insufficient feature expressive ability and low segmentation accuracy. To address these problems, a novel road scene segmentation algorithm [...] Read more.

Although the Mask region-based convolutional neural network (R-CNN) model possessed a dominant position for complex and variable road scene segmentation, some problems still existed, including insufficient feature expressive ability and low segmentation accuracy. To address these problems, a novel road scene segmentation algorithm based on the modified Mask R-CNN was proposed. The multi-scale backbone network, Res2Net, was utilized to replace the ResNet network, and aimed to improve the feature extraction capability. The soft non-maximum suppression algorithm with attenuation function (soft-NMS) was adopted to improve detection efficiency in the case of a higher overlap rate. The comparison analyses of partition accuracy for various models were performed on the adopted Cityscapes dataset. The results demonstrated that the modified Mask R-CNN effectively increased the segmentation accuracy, especially for small and highly overlapping objects. The adopted Res2Net and soft-NMS can effectively enhance the feature extraction and improve segmentation performance. The average accuracy of the modified Mask R-CNN model reached up to 0.321, and was 0.054 higher than Mask R-CNN. This work provides important guidance to design a more efficient road scene instance segmentation algorithm for further promoting the actual application in automatic driving systems. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

28 pages, 453 KiB

Open AccessReview

Data-Driven Advancements in Lip Motion Analysis: A Review

by Shad Torrie, Andrew Sumsion, Dah-Jye Lee and Zheng Sun

Electronics 2023, 12(22), 4698; https://doi.org/10.3390/electronics12224698 - 18 Nov 2023

Viewed by 1167

Abstract

This work reviews the dataset-driven advancements that have occurred in the area of lip motion analysis, particularly visual lip-reading and visual lip motion authentication, in the deep learning era. We provide an analysis of datasets and their usage, creation, and associated challenges. Future [...] Read more.

This work reviews the dataset-driven advancements that have occurred in the area of lip motion analysis, particularly visual lip-reading and visual lip motion authentication, in the deep learning era. We provide an analysis of datasets and their usage, creation, and associated challenges. Future research can utilize this work as a guide for selecting appropriate datasets and as a source of insights for creating new and innovative datasets. Large and varied datasets are vital to a successful deep learning system. There have been many incredible advancements made in these fields due to larger datasets. There are indications that even larger, more varied datasets would result in further improvement upon existing systems. We highlight the datasets that brought about the progression in lip-reading systems from digit- to word-level lip-reading, and then from word- to sentence-level lip-reading. Through an in-depth analysis of lip-reading system results, we show that datasets with large amounts of diversity increase results immensely. We then discuss the next step for lip-reading systems to move from sentence- to dialogue-level lip-reading and emphasize that new datasets are required to make this transition possible. We then explore lip motion authentication datasets. While lip motion authentication has been well researched, it is not very unified on a particular implementation, and there is no benchmark dataset to compare the various methods. As was seen in the lip-reading analysis, large, diverse datasets are required to evaluate the robustness and accuracy of new methods attempted by researchers. These large datasets have pushed the work in the visual lip-reading realm. Due to the lack of large, diverse, and publicly accessible datasets, visual lip motion authentication research has struggled to validate results and real-world applications. A new benchmark dataset is required to unify the studies in this area such that they can be compared to previous methods as well as validate new methods more effectively. Full article

(This article belongs to the Special Issue Convolutional Neural Networks and Vision Applications - Volume III)

► Show Figures

Figure 1

17 pages, 5499 KiB

Open AccessArticle

A Decoding Method Using Riemannian Local Linear Feature Construction for a Lower-Limb Motor Imagery Brain–Computer Interface System

by Yao Hou, Rongnian Tang and Xiaofeng Xie

Electronics 2023, 12(22), 4697; https://doi.org/10.3390/electronics12224697 - 18 Nov 2023

Viewed by 746

Abstract

Recently, motor imagery brain–computer interfaces (BCIs) have been developed for use in motor function assistance and rehabilitation engineering. In particular, lower-limb motor imagery BCI systems are receiving increasing attention in the field of motor rehabilitation, because these systems could accurately and rapidly identify [...] Read more.

Recently, motor imagery brain–computer interfaces (BCIs) have been developed for use in motor function assistance and rehabilitation engineering. In particular, lower-limb motor imagery BCI systems are receiving increasing attention in the field of motor rehabilitation, because these systems could accurately and rapidly identify a patient’s lower-limb movement intention, which could improve the practicability of the motor rehabilitation. In this study, a novel lower-limb BCI system combining visual stimulation, auditory stimulation, functional electrical stimulation, and proprioceptive stimulation was designed to assist patients in lower-limb rehabilitation training. In addition, the Riemannian local linear feature construction (RLLFC) algorithm is proposed to improve the performance of decoding by using unsupervised basis learning and representation weight calculation in the motor imagery BCI system. Three in-house experiment were performed to demonstrate the effectiveness of the proposed system in comparison with other state-of-the-art methods. The experimental results indicate that the proposed system can learn low-dimensional features and correctly characterize the relationship between the testing trial and its k-nearest neighbors. Full article

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

► Show Figures

Figure 1

19 pages, 4986 KiB

Open AccessArticle

DanceTrend: An Integration Framework of Video-Based Body Action Recognition and Color Space Features for Dance Popularity Prediction

by Shiying Ding, Xingyu Hou, Yujia Liu, Wenxuan Zhu, Dong Fang, Yusi Fan, Kewei Li, Lan Huang and Fengfeng Zhou

Electronics 2023, 12(22), 4696; https://doi.org/10.3390/electronics12224696 - 18 Nov 2023

Viewed by 1026

Abstract

Background: With the rise of user-generated content (UGC) platforms, we are witnessing an unprecedented surge in data. Among various content types, dance videos have emerged as a potent medium for artistic and emotional expression in the Web 2.0 era. Such videos have increasingly [...] Read more.

Background: With the rise of user-generated content (UGC) platforms, we are witnessing an unprecedented surge in data. Among various content types, dance videos have emerged as a potent medium for artistic and emotional expression in the Web 2.0 era. Such videos have increasingly become a significant means for users to captivate audiences and amplify their online influence. Given this, predicting the popularity of dance videos on UGC platforms has drawn significant attention. Methods: This study postulates that body movement features play a pivotal role in determining the future popularity of dance videos. To test this hypothesis, we design a robust prediction framework DanceTrend to integrate the body movement features with color space information for dance popularity prediction. We utilize the jazz dance videos from the comprehensive AIST++ street dance dataset and segment each dance routine video into individual movements. AlphaPose was chosen as the human posture detection algorithm to help us obtain human motion features from the videos. Then, the ST-GCN (Spatial Temporal Graph Convolutional Network) is harnessed to train the movement classification models. These pre-trained ST-GCN models are applied to extract body movement features from our curated Bilibili dance video dataset. Alongside these body movement features, we integrate color space attributes and user metadata for the final dance popularity prediction task. Results: The experimental results endorse our initial hypothesis that the body movement features significantly influence the future popularity of dance videos. A comprehensive evaluation of various feature fusion strategies and diverse classifiers discern that a pre–post fusion hybrid strategy coupled with the XGBoost classifier yields the most optimal outcomes for our dataset. Full article

► Show Figures

Figure 1

15 pages, 488 KiB

Open AccessArticle

Guaranteeing Zero Secrecy Outage in Relaying Systems under Eavesdropper’s Arbitrary Location and Unlimited Number of Antennas

by Hien Q. Ta, Nga B. T. Nguyen, Khuong Ho-Van and Hoon Oh

Electronics 2023, 12(22), 4695; https://doi.org/10.3390/electronics12224695 - 18 Nov 2023

Viewed by 745

Abstract

This paper proposes a three-phase transmission scheme to ensure zero secrecy outage in decode-and-forward relay systems by using the strategies of artificial noise (AN) injection and channel state information (CSI) leakage avoidance. The zero-outage secrecy spectral efficiency (ZOSSE) and energy efficiency (ZOSEE) of [...] Read more.

This paper proposes a three-phase transmission scheme to ensure zero secrecy outage in decode-and-forward relay systems by using the strategies of artificial noise (AN) injection and channel state information (CSI) leakage avoidance. The zero-outage secrecy spectral efficiency (ZOSSE) and energy efficiency (ZOSEE) of the scheme are then analyzed. Finally, the paper demonstrates that the scheme can always achieve zero secrecy outage even when the eavesdropper has an unlimited number of antennas or is in an arbitrary location, which shows its practical applicability. The paper also shows that the ZOSSE increases with the transmit power and that both the ZOSSE and the ZOSEE are maximized when the relay is halfway between the transmitter and the receiver. This suggests that the placement of the helper node is important in securing the communication of two distant nodes. Full article

(This article belongs to the Special Issue Physical Layer Security in Future IoT Networks: Theories, Technologies, and Applications)

► Show Figures

Figure 1

14 pages, 1680 KiB

Open AccessEditor’s ChoiceArticle

AI to Train AI: Using ChatGPT to Improve the Accuracy of a Therapeutic Dialogue System

by Karolina Gabor-Siatkowska, Marcin Sowański, Rafał Rzatkiewicz, Izabela Stefaniak, Marek Kozłowski and Artur Janicki

Electronics 2023, 12(22), 4694; https://doi.org/10.3390/electronics12224694 - 18 Nov 2023

Cited by 1 | Viewed by 1590

Abstract

In this work, we present the use of one artificial intelligence (AI) application (ChatGPT) to train another AI-based application. As the latter one, we show a dialogue system named Terabot, which was used in the therapy of psychiatric patients. Our study was motivated [...] Read more.

In this work, we present the use of one artificial intelligence (AI) application (ChatGPT) to train another AI-based application. As the latter one, we show a dialogue system named Terabot, which was used in the therapy of psychiatric patients. Our study was motivated by the fact that for such a domain-specific system, it was difficult to acquire large real-life data samples to increase the training database: this would require recruiting more patients, which is both time-consuming and costly. To address this gap, we have employed a neural large language model: ChatGPT version 3.5, to generate data solely for training our dialogue system. During initial experiments, we identified intents that were most often misrecognized. Next, we fed ChatGPT with a series of prompts, which triggered the language model to generate numerous additional training entries, e.g., alternatives to the phrases that had been collected during initial experiments with healthy users. This way, we have enlarged the training dataset by 112%. In our case study, for testing, we used 2802 speech recordings originating from 32 psychiatric patients. As an evaluation metric, we used the accuracy of intent recognition. The speech samples were converted into text using automatic speech recognition (ASR). The analysis showed that the patients’ speech challenged the ASR module significantly, resulting in deteriorated speech recognition and, consequently, low accuracy of intent recognition. However, thanks to the augmentation of the training data with ChatGPT-generated data, the intent recognition accuracy increased by 13% relatively, reaching 86% in total. We also emulated the case of an error-free ASR and showed the impact of ASR misrecognitions on the intent recognition accuracy. Our study showcased the potential of using generative language models to develop other AI-based tools, such as dialogue systems. Full article

(This article belongs to the Special Issue Application of Machine Learning and Intelligent Systems)

► Show Figures

Figure 1

21 pages, 10741 KiB

Open AccessArticle

Design and Implementation of Omnidirectional Mobile Robot for Materials Handling among Multiple Workstations in Manufacturing Factories

by Hongfu Li, Jiang Liu, Changhuai Lyu, Daoxin Liu and Yinsen Liu

Electronics 2023, 12(22), 4693; https://doi.org/10.3390/electronics12224693 - 18 Nov 2023

Viewed by 1537

Abstract

This paper introduces the mechanical design and control system of a mobile robot for logistics transportation in manufacturing workshops. The robot is divided into a moving part and a grasping part. The moving part adopts the mecanum wheel four-wheel-drive chassis, which has omnidirectional [...] Read more.

This paper introduces the mechanical design and control system of a mobile robot for logistics transportation in manufacturing workshops. The robot is divided into a moving part and a grasping part. The moving part adopts the mecanum wheel four-wheel-drive chassis, which has omnidirectional moving ability. The mechanical system is based on four mechanical wheels, and a modular suspension mechanism is designed. The grasping part is composed of a depth camera, a cooperative manipulator, and an electric claw. Finally, the two are coordinated and controlled by computer. The controller hardware of the mobile platform is designed, and the functional modules of the mobile platform are designed based on the RT thread embedded system. For the navigation part of the mobile robot, a fuzzy PID deviation correction algorithm is designed and simulated. Using the Hough circular transform algorithm, the visual grasping of the manipulator is realized. Finally, the control mode of the computer-controlled manipulator and the manipulator-controlling mobile platform is adopted to realize the feeding function of the mobile robot, and the experimental verification is carried out. Full article

► Show Figures

Figure 1

18 pages, 5997 KiB

Open AccessArticle

Direct Torque Control for Series-Winding PMSM with Zero-Sequence Current Suppression Capability

by Zhicong Su, Yuefei Zuo and Xiaogang Lin

Electronics 2023, 12(22), 4692; https://doi.org/10.3390/electronics12224692 - 18 Nov 2023

Viewed by 781

Abstract

The series-winding permanent-magnet synchronous motor (SW-PMSM) has the merits of high output power and excellent control performance, as does the open-winding permanent-magnet synchronous motor (OW-PMSM). Meanwhile, it can greatly reduce the number of power devices. However, due to the existence of the zero-sequence [...] Read more.

The series-winding permanent-magnet synchronous motor (SW-PMSM) has the merits of high output power and excellent control performance, as does the open-winding permanent-magnet synchronous motor (OW-PMSM). Meanwhile, it can greatly reduce the number of power devices. However, due to the existence of the zero-sequence path, zero-sequence current occurs, which can cause additional losses and torque ripples. Thus, this paper proposes a novel direct torque-control strategy for the SW-PMSM with zero-sequence current suppression capability (ZSCS-DTC). First, the series-winding topology (SWT) and the voltage vector distribution in the SW-PMSM drives are analyzed. Secondly, the basic DTC (B-DTC) scheme for the SW-PMSM is investigated, and the defects of zero-sequence current open-loop control in the B-DTC scheme are revealed. Thirdly, a new voltage vector synthesis scheme is proposed for suppression of zero-sequence current while ensuring bus voltage utilization. A switching table is reconstructed with the newly synthesized voltage vectors. On this basis, a ZSCS-DTC scheme for the SW-PMSM is proposed based on zero-sequence current closed-loop control so that electromagnetic torque, stator flux linkage and zero-sequence current can be controlled simultaneously. Finally, the effectiveness of the proposed ZSCS-DTC scheme for the SW-PMSM drives is verified. Full article

(This article belongs to the Special Issue Advances in Control for Permanent Magnet Synchronous Motor (PMSM))

► Show Figures

Figure 1

18 pages, 2591 KiB

Open AccessArticle

Design of a 0.4 V, 8.43 ENOB, 5.29 nW, 2 kS/s SAR ADC for Implantable Devices

by Posani Vijaya Lakshmi, Sarada Musala, Avireni Srinivasulu and Cristian Ravariu

Electronics 2023, 12(22), 4691; https://doi.org/10.3390/electronics12224691 - 18 Nov 2023

Cited by 2 | Viewed by 1079

Abstract

This paper presents a 9-bit differential, minimum-powered, successive approximation register (SAR) ADC intended for implantable devices or sensors. Such applications demand nanowatt-range power consumption, which is achieved by designing the SAR ADC with a proposed bootstrap switch, bespoke split-capacitive DAC, customized comparator and [...] Read more.

This paper presents a 9-bit differential, minimum-powered, successive approximation register (SAR) ADC intended for implantable devices or sensors. Such applications demand nanowatt-range power consumption, which is achieved by designing the SAR ADC with a proposed bootstrap switch, bespoke split-capacitive DAC, customized comparator and a modified dynamic bit-slice unit for SAR logic. The linearity of the ADC is improved by introducing a bootstrap switch with a low clock feedthrough and threshold voltage variations along with the disseminated attenuation capacitor in the split-capacitive DAC. The dynamic comparator is customized to be simple in terms of the number of transistors to gain the advantage of low power and is also designed to have a low dynamic offset voltage. The stacking concept is embedded in the bit-slice unit of SAR logic to achieve reduced leakage power. This paper is concerned with how to contribute to low power consumption in all the aspects possible related to the implementation of the SAR ADC. With a 0.4 V supply and at 2 kS/s, the proposed ADC achieves an SNDR of 52.52 dB and a power consumption of 5.29 nW, resulting in a figure of merit (FOM) of 7.66 fJ/conversion-step. Full article

(This article belongs to the Special Issue CMOS Integrated Circuits Design)

► Show Figures

Figure 1

18 pages, 2315 KiB

Open AccessArticle

A Conceptual Framework for Developing Intelligent Services (a Platform) for Transport Enterprises: The Designation of Key Drivers for Action

by Maria Sartzetaki, Aristi Karagkouni and Dimitrios Dimitriou

Electronics 2023, 12(22), 4690; https://doi.org/10.3390/electronics12224690 - 18 Nov 2023

Viewed by 1137

Abstract

In the digital era, effective business management relies on dynamic risk analysis and real-time data integration, particularly amid the evolving landscape shaped by technological advancements and external factors such as climate change and global health crises. This study delves into the specific demands [...] Read more.

In the digital era, effective business management relies on dynamic risk analysis and real-time data integration, particularly amid the evolving landscape shaped by technological advancements and external factors such as climate change and global health crises. This study delves into the specific demands for digital services within the transportation sector, focusing on the crucial task of identifying an optimal data-driven management system (platform) to bolster transportation decision-making processes. The paper revolves around the formulation of a comprehensive conceptual framework for the development of intelligent services and platforms tailored explicitly to transport enterprises. Methodologically, a thorough analysis of critical infrastructure-related challenges was conducted, emphasizing the integration of a service-oriented approach to enhance overall functionality. Central to the paper’s approach is the careful navigation of conflicting user requirements, resource constraints, and the imperative of maintaining adaptability in service implementation. Additionally, a robust data flow analysis framework is presented, encompassing data collection, model building, and model extrapolation, which enables the generation of reliable outputs essential for informed decision-making. Notably, the study underscores the pivotal role played by the EN.I.R.I.S.S.T. research infrastructure in delivering essential services to the transportation domain, offering accessible data, user-friendly interfaces, and data analysis tools. The findings highlight the enthusiastic reception of the diverse services among potential users, indicating a strong willingness to engage and benefit from the proposed solutions. By emphasizing the integration of intelligent services, the paper seeks to present a systematic approach aimed at enhancing the efficiency, productivity, and competitive edge of transport enterprises through the strategic deployment of advanced technological solutions and proactive planning. This paper ultimately contributes cutting-edge research insights, empowering transportation managers, planners, and decision-makers with valuable resources for informed business intelligence and corporate strategy. Full article

(This article belongs to the Special Issue Emerging Technologies for Computer Architecture and Parallel Systems)

► Show Figures

Figure 1

14 pages, 1300 KiB

Open AccessArticle

GMIW-Pose: Camera Pose Estimation via Global Matching and Iterative Weighted Eight-Point Algorithm

by Fan Chen, Yuting Wu, Tianjian Liao, Huiquan Zeng, Sujian Ouyang and Jiansheng Guan

Electronics 2023, 12(22), 4689; https://doi.org/10.3390/electronics12224689 - 18 Nov 2023

Viewed by 1123

Abstract

We propose a novel approach, GMIW-Pose, to estimate the relative camera poses between two views. This method leverages a Transformer-based global matching module to obtain robust 2D–2D dense correspondences, followed by iterative refinement of matching weights using ConvGRU. Ultimately, the camera’s relative pose [...] Read more.

We propose a novel approach, GMIW-Pose, to estimate the relative camera poses between two views. This method leverages a Transformer-based global matching module to obtain robust 2D–2D dense correspondences, followed by iterative refinement of matching weights using ConvGRU. Ultimately, the camera’s relative pose is determined through the weighted eight-point algorithm. Compared with the previous best two-view pose estimation method, GMIW-Pose reduced the Absolute Trajectory Error (ATE) by 24% on the TartanAir dataset; it achieved the best or second-best performance in multiple scenarios of the TUM-RGBD and KITTI datasets without fine-tuning, among which ATE decreased by 22% on the TUM-RGBD dataset. Full article

(This article belongs to the Special Issue Recent Advances in Computer Vision: Technologies and Applications)

► Show Figures

Figure 1

14 pages, 2551 KiB

Open AccessArticle

Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings

by Qian Chen, Kehan Yang, Xin Guo, Suge Wang, Jian Liao and Jianxing Zheng

Electronics 2023, 12(22), 4688; https://doi.org/10.3390/electronics12224688 - 18 Nov 2023

Viewed by 789

Abstract

The objective of event extraction is to recognize event triggers and event categories within unstructured text and produce structured event arguments. However, there is a common phenomenon of triggers and arguments of different event types in a sentence that may be the same [...] Read more.

The objective of event extraction is to recognize event triggers and event categories within unstructured text and produce structured event arguments. However, there is a common phenomenon of triggers and arguments of different event types in a sentence that may be the same word elements, which poses new challenges to this task. In this article, a joint learning framework for overlapping event extraction (ROPEE) is proposed. In this framework, a role pre-judgment module is devised prior to argument extraction. It conducts role pre-judgment by leveraging the correlation between event types and roles, as well as trigger embeddings. Experiments on the FewFC show that the proposed model outperforms other baseline models in terms of Trigger Classification, Argument Identification, and Argument Classification by 0.4%, 0.9%, and 0.6%. In scenarios of trigger overlap and argument overlap, the proposed model outperforms the baseline models in terms of Argument Identification and Argument Classification by 0.9%, 1.2%, 0.7%, and 0.6%, respectively, indicating the effectiveness of ROPEE in solving overlapping events. Full article

(This article belongs to the Special Issue Advances in Intelligent Data Analysis and Its Applications, Volume II)

► Show Figures

Figure 1

22 pages, 6967 KiB

Open AccessArticle

Design and Implementation of a New Framework for Post-Synthesis Obfuscation with a Mixture of Multiple Cells with an Integrated Anti-SAT Block

by Hamidur Rahman, A. B. M. Harun-ur Rashid and Mahmudul Hasan

Electronics 2023, 12(22), 4687; https://doi.org/10.3390/electronics12224687 - 17 Nov 2023

Viewed by 859

Abstract

This paper proposes a new framework for post-synthesis obfuscation of digital circuits using a mixture of cells combined with an Anti-SAT block. Furthermore, a novel integrated framework has been established wherein obfuscation, along with Anti-SAT and validation of the benchmarks, progress through MATLAB [...] Read more.

This paper proposes a new framework for post-synthesis obfuscation of digital circuits using a mixture of cells combined with an Anti-SAT block. Furthermore, a novel integrated framework has been established wherein obfuscation, along with Anti-SAT and validation of the benchmarks, progress through MATLAB^®, Python, Cadence RTL Encounter^® and Cadence LEC^® to implement the proposed methodology. Area, delay, leakage power and total power are adopted as elements of the evaluation matrix. These parameters are compared between the original circuit, the circuit after obfuscation, the circuit after integration with Anti-SAT and the circuit after implementation of the proposed method of multiple-cell obfuscation with Anti-SAT. The probability of breaking a circuit is taken as the security criterion. It is mathematically proven that as the number of types of obfuscated cells used increases, then the probability of breaking the circuit decreases. The results obtained accord with the mathematical proof. The framework minimizes the delay by inserting obfuscation cells (OCs) in the non-critical paths, strengthens the security by using several types of OCs and allows the user to select a design based on justified area, leakage power and total power. However, against a Boolean SATisfiability (SAT) attack, obfuscation with multiple cells is not a sufficient defense. An Anti-SAT block performs better than obfuscation but has its own limitations. Thus, use of an Anti-SAT block in combination with multiple-cell obfuscation is proposed and implemented, giving better results against an efficient SAT attack. The number of iterations, as well as runtime to obtain the correct keys, increase significantly for the Anti-SAT block combined with multiple-cell obfuscation compared to the Anti-SAT or obfuscation block alone. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 12, Issue 22 (November-2 2023) – 163 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI