With the world moving towards low-carbon and environmentally friendly development, the rapid growth of new-energy vehicles is evident. The utilization of deep-learning-based license-plate-recognition ...(LPR) algorithms has become widespread. However, existing LPR systems have difficulty achieving timely, effective, and energy-saving recognition due to their inherent limitations such as high latency and energy consumption. An innovative Edge–LPR system that leverages edge computing and lightweight network models is proposed in this paper. With the help of this technology, the excessive reliance on the computational capacity and the uneven implementation of resources of cloud computing can be successfully mitigated. The system is specifically a simple LPR. Channel pruning was used to reconstruct the backbone layer, reduce the network model parameters, and effectively reduce the GPU resource consumption. By utilizing the computing resources of the Intel second-generation computing stick, the network models were deployed on edge gateways to detect license plates directly. The reliability and effectiveness of the Edge–LPR system were validated through the experimental analysis of the CCPD standard dataset and real-time monitoring dataset from charging stations. The experimental results from the CCPD common dataset demonstrated that the network’s total number of parameters was only 0.606 MB, with an impressive accuracy rate of 97%.
Transformer network is widely emphasized and studied relying on its excellent performance. The self-attention mechanism finds a good solution for feature coding among multiple channels of ...electroencephalography (EEG) signals. However, using the self-attention mechanism to construct models on EEG data suffers from the problem of the large amount of data required and the complexity of the algorithm.
We propose a Transformer neural network combined with the addition of Mixture of Experts (MoE) layer and ProbSparse Self-attention mechanism for decoding the time-frequency-spatial domain features from motor imagery (MI) EEG of spinal cord injury patients. The model is named as EEG MoE-Prob-Transformer (EMPT). The common spatial pattern and the modified s-transform method are employed for achieving the time-frequency-spatial features, which are used as feature embeddings to input the improved transformer neural network for feature reconstruction, and then rely on the expert model in the MoE layer for sparsity mapping, and finally output the results through the fully connected layer.
EMPT achieves an accuracy of 95.24% on the MI EEG dataset for patients with spinal cord injury. EMPT has also achieved excellent results in comparative experiments with other state-of-the-art methods.
The MoE layer and ProbSparse Self-attention inside the EMPT are subjected to visualisation experiments. The experiments prove that sparsity can be introduced to the Transformer neural network by introducing MoE and kullback-leibler divergence attention pooling mechanism, thereby enhancing its applicability on EEG datasets. A novel deep learning approach is presented for decoding EEG data based on MI.
As a medium for developing brain-computer interface systems, EEG signals are complex and difficult to identify due to their complexity, weakness, and differences between subjects. At present, most of ...the current research on sleep EEG signals are single-channel and dual-channel, ignoring the research on the relationship between different brain regions. Brain functional connectivity is considered to be closely related to brain activity and can be used to study the interaction relationship between brain areas.
Phase-locked value (PLV) is used to construct a functional connection network. The connection network is used to analyze the connection mechanism and brain interaction in different sleep stages. Firstly, the entire EEG signal is divided into multiple sub-periods. Secondly, Phase-locked value is used for feature extraction on the sub-periods. Thirdly, the PLV of multiple sub-periods is used for feature fusion. Fourthly, the classification performance optimization strategy is used to discuss the impact of different frequency bands on sleep stage classification performance and to find the optimal frequency band. Finally, the brain function network is constructed by using the average value of the fusion features to analyze the interaction of brain regions in different frequency bands during sleep stages.
The experimental results have shown that when the number of sub-periods is 30, the α (8-13 Hz) frequency band has the best classification effect, The classification result after 10-fold cross-validation reaches 92.59%.
The proposed algorithm has good sleep staging performance, which can effectively promote the development and application of an EEG sleep staging system.
Stroke, a sudden cerebrovascular ailment resulting from brain tissue damage, has prompted the use of motor imagery (MI)-based Brain-Computer Interface (BCI) systems in stroke rehabilitation. However, ...analyzing EEG signals from stroke patients is challenging because of their low signal-to-noise ratio and high variability. Therefore, we propose a novel approach that combines the modified S-transform (MST) and a dense graph convolutional network (DenseGCN) algorithm to enhance the MI-BCI performance across time, frequency, and space domains. MST is a time-frequency analysis method that efficiently concentrates energy in EEG signals, while DenseGCN is a deep learning model that uses EEG feature maps from each layer as inputs for subsequent layers, facilitating feature reuse and hyper-parameters optimization. Our approach outperforms conventional networks, achieving a peak classification accuracy of 90.22% and an average information transfer rate (ITR) of 68.52 bits per minute. Moreover, we conduct an in-depth analysis of the event-related desynchronization/event-related synchronization (ERD/ERS) phenomenon in the deep-level EEG features of stroke patients. Our experimental results confirm the feasibility and efficacy of the proposed approach for MI-BCI rehabilitation systems.
From strengthening the construction of an innovation system, adhering to the green development model of the industry, advancing the rural revitalization strategy, strengthening the protection and ...inheritance of cultural heritage, accelerating the development of social undertakings, and expanding the space for regional cooperation, this paper discusses the strategies for the construction of sustainable development experimental zone in Fumian District, Yulin City. It is intended to build Fumian District into a vibrant, economically prosperous, urban and rural integrated, characteristic cultural, safe and harmonious, inclusive and open district.
This paper first analyzes the main opportunities for sustainable development of Fumian District, Yulin City, and then discusses the challenges faced by Fumian District in its sustainable development. ...Finally, it proposes safeguard measures for sustainable development of Fumian District: (i) strengthening leadership and implementing responsibilities; (ii) enhancing cooperation and gathering forces; (iii) reinforcing supervision and ensuring implementation; (iv) increasing input and integrating resources; (v) strengthening publicity and creating an atmosphere.
Currently, it is still a significant challenge to simultaneously boost various reactions by one electrocatalyst with high activity, excellent durability, as well as low cost. Herein, hybrid ...trifunctional electrocatalysts are explored via a facile one‐pot strategy toward an efficient oxygen reduction reaction (ORR), oxygen evolution reaction (OER), and hydrogen evolution reaction (HER). The catalysts are rationally designed to be composed by FeCo nanoparticles encapsuled in graphitic carbon films, Co2P nanoparticles, and N,P‐codoped carbon nanofiber networks. The FeCo nanoparticles and the synergistic effect from Co2P and FeCo nanoparticles make the dominant contributions to the ORR, OER, and HER activities, respectively. Their bifunctional activity parameter (∆E) for ORR and OER is low to 0.77 V, which is much smaller than those of most nonprecious metal catalysts ever reported, and comparable with state‐of‐the‐art Pt/C and RuO2 (0.78 V). Accordingly, the as‐assembled Zn–air battery exhibits a high power density of 154 mW cm−2 with a low charge–discharge voltage gap of 0.83 V (at 10 mA cm−2) and excellent stability. The as‐constructed overall water‐splitting cell achieves a current density of 10 mA cm−2 (at 1.68 V), which is comparable to the best reported trifunctional catalysts.
Trifunctional electrocatalysts based on FeCo/Co2P hybrid nanoparticles are reported, which have excellent activities and stabilities toward the oxygen reduction reaction, oxygen evolution reaction, and hydrogen evolution reaction. The as‐assembled Zn–air battery exhibits charge–discharge voltage gap of 0.83 V at 10 mA cm−2, and an as‐constructed overall water‐splitting cell achieves a current density of 10 mA cm−2 at 1.68 V.
The exploration of cheap, efficient, and durable bifunctional electrocatalysts for oxygen reduction reaction (ORR) and oxygen evolution reaction (OER) is highly desired to push forward the ...commercialization of rechargeable metal–air batteries. Here, bifunctional ORR/OER electrocatalysts based on CoxP (0 < x < 2, i.e., Co2P, Co2P/CoP mixture, and CoP) nanoparticles (NPs) anchored on N,P‐doped carbon framework (CoxP@NPC) are developed via one‐step carbonization of the mixture of as‐synthesized ZIF‐67 and melamine–phytic acid supermolecular aggregate (MPSA). The stoichiometric ratio of resultant CoxP NPs can be rationally designed by adjusting the introduced ratio of ZIF‐67 to MPSA, enabling their fabrication in a controlled manner. It is found that the as‐synthesized Co2P@NPC exhibits the best bifunctional ORR/OER activity among the CoxP@NPC analogues, with a reversible oxygen electrode index (ΔE = Ej10 − E1/2) down to ~0.75 V. The constructed Zn–air battery based on Co2P@NPC delivers a peak power density of 157 mW cm−2 and an excellent charge‐discharge stability with negligible voltage decay for 140 h at 10 mA cm−2, superior to those based on Pt/C+RuO2 and most CoxP‐based electrodes ever reported.
Controllable construction of CoxP (0 < x < 2) nanoparticles anchored on N,P‐doped carbon frameworks is reported for efficient and durable oxygen reduction reaction and oxygen evolution reaction.