Electronics

Zhang, Liumei;Xia, Bowen;Wang, Yichuan;Zhang, Wei;Han, Yu

doi: 10.3390/electronics12234717pmid: N/A

Emotion recognition, as an important part of human-computer interaction, is of great research significance and has already played a role in the fields of artificial intelligence, healthcare, and distance education. In recent times, there has been a growing trend in using deep learning techniques for EEG emotion recognition. These methods have shown higher accuracy in recognizing emotions when compared with traditional machine learning methods. However, most of the current EEG emotion recognition performs multi-category single-label prediction, and is a binary classification problem based on the dimensional model. This simplifies the fact that human emotions are mixed and complex. In order to adapt to real-world applications, fine-grained emotion recognition is necessary. We propose a new method for building emotion classification labels using linguistic resource and density-based spatial clustering of applications with noise (DBSCAN). Additionally, we integrate the frequency domain and spatial features of emotional EEG signals and feed these features into a serial network that combines a convolutional neural network (CNN) and a long short-term memory (LSTM) recurrent neural network (RNN) for EEG emotion feature learning and classification. We conduct emotion classification experiments on the DEAP dataset, and the results show that our method has an average emotion classification accuracy of 92.98% per subject, validating the effectiveness of the improvements we have made to our emotion classification method. Our method for emotion classification holds potential for future use in the domain of affective computing, such as mental health care, education, social media, and so on. By constructing an automatic emotion analysis system using our method to enable the machine to understand the emotional implications conveyed by the subjects’ EEG signals, it can provide healthcare professionals with valuable information for effective treatment outcomes.

Lozano Domínguez, José Manuel;Redondo González, Manuel Joaquín;Davila Martin, Jose Miguel;Mateo Sanguino, Tomás de J.

doi: 10.3390/electronics12234718pmid: N/A

Pedestrian safety is a major concern in urban areas, and crosswalks are one of the most critical locations where accidents can occur. This research introduces an intelligent crosswalk, employing sensor fusion and machine learning techniques to distinguish the presence of pedestrians and drivers. Upon detecting a pedestrian, the system proactively activates a warning light signal. This approach aims to quickly alert nearby people and mitigate potential dangers, thereby strengthening pedestrian safety. The system integrates data from radio detection and ranging sensors and a magnetic field sensor, using a hierarchical classifier. The One-Class support vector machine algorithm is used to classify objects in the radio detection and ranging data, while fuzzy logic is used to filter out targets from the magnetic field sensor. Additionally, this work presents a novel method for the manufacture of the road signaling system, using mixtures of resins, aggregates, and reinforcing fibers that are cold-injected into an aluminum mold. The mechanical, optical, and electrical characteristics were subjected to standardized tests, validating its autonomous operation in real-world conditions. The results revealed the system’s effectiveness in detecting pedestrians with a 99.11% accuracy and a 0.0% false-positive rate, marking a substantial improvement over the previous fuzzy logic-based system with an 81.33% accuracy. Attitude testing revealed a significant 33.33% reduction in pedestrian erratic behavior and a substantial decrease in driver speed (32.83% during the day and 70.6% during the night) compared to conventional crossings. Consequently, this comprehensive work offers a unique solution to pedestrian safety at crosswalks by showcasing the potential of machine learning techniques, particularly the One-Class support vector machine algorithm, in advancing road safety through precise and reliable pattern recognition.

Azurmendi, Iker;Zulueta, Ekaitz;Lopez-Guede, Jose Manuel;González, Manuel

doi: 10.3390/electronics12234719pmid: N/A

Object detection is an essential and impactful technology in various fields due to its ability to automatically locate and identify objects in images or videos. In addition, object-distance estimation is a fundamental problem in 3D vision and scene perception. In this paper, we propose a simultaneous object-detection and distance-estimation algorithm based on YOLOv5 for obstacle detection in indoor autonomous vehicles. This method estimates the distances to the desired obstacles using a single monocular camera that does not require calibration. On the one hand, we train the algorithm with the KITTI dataset, which is an autonomous driving vision dataset that provides labels for object detection and distance prediction. On the other hand, we collect and label 100 images from a custom environment. Then, we apply data augmentation and transfer learning to generate a fast, accurate, and cost-effective model for the custom environment. The results show a performance of mAP0.5:0.95 of more than 75% for object detection and 0.71 m of mean absolute error in distance prediction, which are easily scalable with the labeling of a larger amount of data. Finally, we compare our method with other similar state-of-the-art approaches.

Zhang, Peng;Jing, Qingyang;Zhao, Xinlei;Dong, Lijia;Lei, Weimin;Zhang, Wei;Lin, Zhaonan

doi: 10.3390/electronics12234720pmid: N/A

Aiming to solve the problem of the identity switching of objects with similar appearances in real scenarios, a multi-object tracking approach combining contextual features and trajectory prediction is proposed. This approach integrates the motion and appearance features of objects. The motion features are mainly used for trajectory prediction, and the appearance features are divided into contextual features and individual features, which are mainly used for trajectory matching. In order to accurately distinguish the identities of objects with similar appearances, a context graph is constructed by taking the specified object as the master node and its neighboring objects as the branch nodes. A preprocessing module is applied to exclude unnecessary connections in the graph model based on the speed of the historical trajectory of the object, and to distinguish the features of objects with similar appearances. Feature matching is performed using the Hungarian algorithm, based on the similarity matrix obtained from the features. Post-processing is performed for the temporarily unmatched frames to obtain the final object matching results. The experimental results show that the approach proposed in this paper can achieve the highest MOTA.

Leszczuk, Mikołaj;Janowski, Lucjan;Nawała, Jakub;Zhu, Jingwen;Wang, Yuding;Boev, Atanas

doi: 10.3390/electronics12234721pmid: N/A

In the realm of modern video processing systems, traditional metrics such as the Peak Signal-to-Noise Ratio and Structural Similarity are often insufficient for evaluating videos intended for recognition tasks, like object or license plate recognition. Recognizing the need for specialized assessment in this domain, this study introduces a novel approach tailored to Automatic License Plate Recognition (ALPR). We developed a robust evaluation framework using a dataset with ground truth coordinates for ALPR. This dataset includes video frames captured under various conditions, including occlusions, to facilitate comprehensive model training, testing, and validation. Our methodology simulates quality degradation using a digital camera image acquisition model, representing how luminous flux is transformed into digital images. The model’s performance was evaluated using Video Quality Indicators within an OpenALPR library context. Our findings show that the model achieves a high F-measure score of 0.777, reflecting its effectiveness in assessing video quality for recognition tasks. The proposed model presents a promising avenue for accurate video quality assessment in ALPR tasks, outperforming traditional metrics in typical recognition application scenarios. This underscores the potential of the methodology for broader adoption in video quality analysis for recognition purposes.

Zheng, Yuanbing;Wang, Jizhe;Wang, Jian;Chen, Lu;Wu, Chongchong;Li, Xue;Liao, Yong;Lu, Peng;Wan, Shaohua

doi: 10.3390/electronics12234722pmid: N/A

Vehicle to everything (V2X) is widely regarded as a critical application for future wireless communication networks. In V2X, large relative speeds between vehicles may severely deteriorate the performance of communication between vehicles. Orthogonal time frequency space (OTFS) modulation, which converts time- and frequency-selective channels into non-selective channels in the delay-Doppler (DD) domain, provides a solution for establishing reliable wireless communications in V2X scenarios. However, in the complex multi-scattering scenarios, the channel also suffers from a serious inter-Doppler interference (IDI) problem, which poses a great challenge to the accurate demodulation of OTFS receiver signals. To address the above problems, this paper considers the variation of Doppler sampling points within one symbol when deriving the channel model, which effectively overcomes the IDI problem, and employs a basis expansion model (BEM) to convert the channel estimation into a sparse recovery problem for the basis coefficients. In addition, to better utilize the sparse nature of the OTFS channel, a generalized approximate message passing-sparse Bayesian learning (GAMP-SBL)-based algorithm is employed to estimate the basis coefficients of the channel. The complexity of this algorithm is greatly reduced compared to the conventional SBL algorithm. Finally, system simulation results are reported to verify the superiority of the proposed scheme.

Chen, Xuehao;Zhou, Jin;Chen, Yuehui;Han, Shiyuan;Wang, Yingxu;Du, Tao;Yang, Cheng;Liu, Bowen

doi: 10.3390/electronics12234723pmid: N/A

Contrastive-based clustering models usually rely on a large number of negative pairs to capture uniform representations, which requires a large batch size and high computational complexity. In contrast, some self-supervised methods perform non-contrastive learning to capture discriminative representations only with positive pairs, but suffer from the collapse of clustering. To solve these issues, a novel end-to-end self-supervised clustering model is proposed in this paper. The basic self-supervised learning network is first modified, followed by the incorporation of a Softmax layer to obtain cluster assignments as data representation. Then, adversarial learning on the cluster assignments is integrated into the methods to further enhance discrimination across different clusters and mitigate the collapse between clusters. To further encourage clustering-oriented guidance, a new cluster-level discrimination is assembled to promote clustering performance by measuring the self-correlation between the learned cluster assignments. Experimental results on real-world datasets exhibit better performance of the proposed model compared with the existing deep clustering methods.

Ma, Chong;Lu, Baoli

doi: 10.3390/electronics12234724pmid: N/A

The protection of heritage building communities is of important historical significance, the occurrence of a landslide is related to the safety and stability of the heritage building, and ground monitoring and forecasting are the key steps for the early warning and timely restoration of the heritage building. This study utilizes remote sensing technology to monitor the ground of a cultural heritage building, and employs a Long Short-Term Memory (LSTM) network for prediction. Firstly, we conducted ground subsidence monitoring within a specific time series of the study area using heritage remote sensing images and SBAS-InSAR technology. Following the subsidence monitoring, and incorporating an attention mechanism, we effectively localized and extracted features of heritage building clusters within the region. This approach efficiently addresses the challenge of feature identification resulting from the dense distribution of buildings and the similarity between various objects. The results indicate that the maximum subsidence rate in the research area reached −60 mm/year, reached a maximum uplift rate of 45 mm/year, and that the maximum cumulative subsidence reached −65 mm. Secondly, for the multi-level, multi-scale, and class-specific objects in remote sensing images, the LSTM network enables adaptive contextual information during deep and shallow feature extraction. This allows for better contextual modeling and the correlation between predicted and actual results reaches a 0.95 correlation, demonstrating the accurate predictive performance of the LSTM network. In conclusion, both LSTM and SBAS technologies play a crucial role in decision-making for heritage buildings, facilitating effective early warning and disaster mitigation.

Nkembi, Armel Asongu;Santoro, Danilo;Cova, Paolo;Delmonte, Nicola

doi: 10.3390/electronics12234725pmid: N/A

Distributed energy resources (DERs), such as photovoltaic (PV) sources, together with storage systems, such as battery energy storage systems (BESS), are increasingly present and necessary in our electricity distribution networks. Furthermore, the need for efficient use of energy from DERs, especially in developing countries and remote communities, must be addressed with the development of nanogrids (NGs), particularly DC NGs, and standalone PV systems with adequate control strategies. This paper investigates the control and dynamic operation of a standalone PV system. It consists mainly of three DC–DC power converters for the PV source interface, battery management, and load voltage control. A two-level modulation scheme is applied to each of these converters to switch them ON and OFF. A maximum power point tracking (MPPT) closed-loop voltage control system is implemented to make sure that the PV operates at optimum power regardless of the irradiance level or temperature, while battery voltage and load-side voltage control are also implemented to indirectly provide the required load power. The control of each of the converters is achieved by deriving their small-signal models using a state-space approach from which various control objectives are implemented. The DC-link is clamped by a BESS which acts as a backup source to provide power to the DC load in the absence of sufficient power from the PV panel. The dynamic operation of the whole system is enhanced by proposing a robust feedforward scheme that improves the response of the system in the presence of disturbances. The models are analyzed and implemented using PLECS, and numerical simulations are performed to validate the developed models and control schemes.

Yang, Chenyu;Liu, Kai;Hu, Mingjin;Hua, Wei

doi: 10.3390/electronics12234726pmid: N/A

The conventional finite control set model predictive current control (FCS-MPCC) suffers from suboptimal steady-state performance, primarily due to the limited selection of only eight basic voltage vectors in each control cycle. To overcome this limitation, the proposed extended control set MPCC (ECS-MPCC) utilizes an control set consisting of 818 selectable vectors, enabling a more refined voltage output and achieving a deadbeat response for current control by minimizing the cost function. To mitigate the computational burden resulting from the substantial increase in voltage vectors, a simplified search strategy is devised, which can be extended to other multi-objective cost functions. Remarkably, based on the inherent parallelism of the algorithm, the ECS-MPCC is implemented on an FPGA, further reducing the overall control time of the current loop to an impressive 0.61 μs. Through simulation and experimental tests on a laboratory PMSM driver, the effectiveness of the proposed ECS-MPCC strategy is validated. The experimental results demonstrate a significant reduction of 79% in the total harmonic distortion of phase currents compared to the conventional FCS-MPCC approach. This improvement underscores the superiority of the ECS-MPCC in enhancing the performance of PMSM drives, thereby illustrating its potential for practical implementation in real-world applications.