Search

Copyright of Zhejiang Electric Power is the property of Zhejiang Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Southern Energy Construction is the property of Southern Energy Construction Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Zhejiang Electric Power is the property of Zhejiang Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Automobile Technology is the property of Automobile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Xi'an Polytechnic University is the property of Editorial Department of Journal of Xi'an Polytechnic University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To solve the large proportion of small targets and complex background in UAV (unmanned aerial vehicle) aerial image, the current object detection model has the problems of low accuracy and missed detection of small targets. Based on the YOLOv8s model, this paper proposes a 3D multi-layer feature collaboration UAV remote sensing object detection algorithm. Firstly, based on the coordinate attention, this paper proposes 3D multi-branch coordinate attention (MBCA), which improves the global feature extraction ability of the model and reduces the computation of spatial dimension by increasing the information interaction of channel dimension and the splitting and fusion of extended branches. Secondly, SPD-Conv is used to replace part of the standard convolution, which effectively retains more feature information and speeds up inference during downsampling. Then, a more efficient FastDBB_Bottleneck module is used in the C2f module, combining PConv and DBB structure reparameterization superposition to further reduce the calculation of the model. Finally, PG-Detect detection head is introduced to significantly reduce the calculation and effectively reduce the missed detection rate of small targets. Experimental results on the VisDrone2019 dataset show that the mAP50 value of the proposed method reaches 44.5%, which is 5.7 percentage points higher than that of the YOLOv8s baseline model. Simultaneously, the crack detection verification experiment is carried out on the self-built dam crack dataset, and the mAP50 value of the improved method is 3.3 percentage points higher than that of YOLOv8s, the FPS reaches 289 frames. Experimental results show that the proposed method improves the accuracy and real- time performance of the detection model in complex scene object detection, and has good adaptability and robustness. [ABSTRACT FROM AUTHOR]

In recent years, deep learning-based object detection algorithms have been a hot topic in computer vision research, with the YOLO (you only look once) algorithm standing out as an excellent object detection algorithm. The evolution of its network architecture has played a crucial role in improving detection speed and accuracy. This paper conducts a comprehensive horizontal analysis of the overall frameworks of YOLOv1 to YOLOv9, comparing the network architecture (backbone network, neck layers and head layers) and loss functions. The strengths and limitations of different improvement methods are thoroughly discussed, with a specific evaluation of the impact of these improvements on model accuracy. This paper also delves into discussions on dataset selection and construction methods, the rationale behind choosing different evaluation metrics, and their applicability and limitations in various application scenarios. It further explores specific improvement methods for YOLO algorithm in five application domains (industrial, transportation, remote sensing, agriculture, biology), and discusses the balance among detection speed, accuracy, and complexity in these application domains. Finally, this paper analyzes the current development status of YOLO in various fields, summarizes existing issues in YOLO algorithm research through specific examples, and in conjunction with the trends in application domains, provides an outlook on the future of the YOLO algorithm. It also offers detailed explanations for four future research directions of YOLO (multi-task learning, edge computing, multimodal integration, virtual and augmented reality technology).

[Introduction] In the low-voltage distribution network, the residual current protection device, as an important guarantee of electricity safety, can reduce the harm caused by the leakage fault of electrical appliances and prevent human electrocution accidents. The current residual current protection device relies on the residual current signal size as the basis for the action of the protection mechanism, but has no function to identify the electrocution characteristics. To address this problem, this paper proposes a method for electrocution signal feature extraction and electrocution diagnosis in low-voltage distribution networks based on wavelet decomposition and denoising, as well as GRU. [Method] In this paper, the residual currents collected from electrocution experiments were pre-processed by downsampling and discrete wavelet denoising; The time and frequency domain electrocution characteristic parameters of the residual currents were extracted by the sliding window method, and the Fourier transform was used to extract the characteristic parameters of residual currents to the second harmonic amplitude. All the extracted feature parameters were used to form a high-dimensional feature space vector; which was subject to dimensionality reduction using the method of principal component analysis to obtain a new set of three-dimensional feature vectors. A diagnostic model for electrocution was established, and the three-dimensional feature vectors representing electrocution features were input into the model. Comparison experiments were conducted on electrocution signals using five different electrocution diagnostic models, such as recurrent gated network (GRU). [Result] The experimental results show that the convergence of the GRU-based electrocution diagnosis model is good, and the recognition rate reaches 98.33%. [Conclusion] The method provides new insights for the research and development of a new generation of residual current protection devices and offers an effective guarantee for electrical safety.

In recent years, deep learning has been widely applied to various classification tasks due to its capability in automatically extracting features and superior classification performance. Research on the classification of lung nodules has gradually shifted from traditional methods that involve manual feature extraction to deep learning-based classification approaches. To better investigate the benign-malignant classification of lung nodules in CT images, the current status of deep learning methods based on convolutional neural network (CNN) in the research of benign and malignant classification of lung nodules is summarized. Firstly, this paper introduces commonly used publicly available datasets for lung nodule classification, including their contents, limitations, and download sources. Secondly, it outlines commonly used performance evaluation metrics. It then highlights the recent research work on deep learning methods for lung nodule classification: current methods for lung nodule classification are categorized as using only CNN, introducing an attention mechanism in CNN, multi-view learning, multi-modal learning, and using migration learning, adversarial neural networks, and other methods, repectively, from the level of network structure and data. Meanwhile, this paper further summarizes the network structures, advantages and disadvantages of these classification methods. A comparative analysis is conducted on the benign-malignant classification performance of lung nodule classification methods based on these aspects over the past three years using publicly available nodule datasets. Finally, this paper discusses current challenges and explores further research directions in the field of lung nodule classification.

Large power texts contain numerous abbreviations of technical terms， alternative names， and irregular expressions. Existing word segmentation tools often fail to identify specialized vocabulary in the electrical engineering field， significantly hindering the analysis and utilization of unstructured texts. To address this challenge， this paper proposes a set of indexing rules tailored to the characteristics of unstructured texts in electrical engineering. Segmentation based on these rules can significantly enhance segmentation accuracy， laying a solid foundation for feature extraction of power texts. Furthermore， by employing effective long-text segmentation algorithms to preserve the semantic information of the original text， the paper integrates and embeds text feature information extracted by the BERT model with vocabulary feature information extracted by Word2Vec. This combined approach enables the extraction of precise features from large unstructured power texts. Finally， experimental results have demonstrated the effectiveness of the proposed method for extracting features from large unstructured power texts.

Copyright of Jordanian Journal of Computers & Information Technology is the property of Jordanian Journal of Computers & Information Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The paper proposes a novel fault diagnosis method for hydroelectric units to address the challenge of achieving high-precision fault diagnosis due to the non-stationarity and non-linearity of vibration signals, which makes it difficult to extract single features. The method utilizes convolutional neural networks to extract vibration signal features, and employs empirical mode decomposition and approximate entropy to construct signal feature vectors, which are used to create a fusion feature vector. Furthermore, a BP neural network is trained with the fusion feature vector as input and the fault category as output to obtain a hydroelectric unit fault recognizer that can identify the unit's operating state as normal or with a specific fault type. The validity of the proposed method in signal feature mining and its high fault diagnosis accuracy are verified through rotor experimental data. [ABSTRACT FROM AUTHOR]

The surface cracks caused by mining have a significant impact on the safety production of coal mines. Utilizing unmanned aerial vehicle (UAV) image recognition to identify the development characteristics of cracks in coal mining subsidence areas holds practical value. In this paper, an improved YOLOv7 model for intelligent recognition of mining-induced cracks is proposed. It incorporates the GAM global attention mechanism into the backbone network of the model to reduce the loss of feature information during the image convolution process. Additionally, depth-wise separable convolutions are introduced to replace the ordinary convolutions in the backbone network, which reduces the size of the image feature map without causing feature loss during the convolution process. Furthermore, GIOU_Loss is further used to improve the network boundary frame loss function, which improves the small target identification ability of the model. For the experiments, a training dataset for mining-induced crack recognition was created using the LabelImg image annotation software, containing 2 143 images with a resolution of 5 472×3 648 pixels. After initial preprocessing of the UAV images in the subsidence area to construct a digital orthophoto model (DOM), the DOM was further cropped using a sliding window of size 640×640 for feature recognition. The experimental results demonstrate that the improved YOLOv7 model exhibits significant improvements in the recognition performance and missed detections of dense, small-sized, and vegetation-covered crack images. The average precision (mAP) reaches 0.84.