In this article, a new hybrid deep learning (DL) algorithm is developed to make a computer-assisted forecasting energy management (EM) system. Applying the Copula function, the Hankel matrix is created for processing gathered automatic metering infrastructure (AMI) load information in the smart network. This processing of the data results in model optimization through the suggested new pooling-based deep neural network (PDNN). Through increased size and variation of AMI data, the suggested PDNN reduces overfitting issues during testing and training. The real-time AMI southern grid data of Tamil Nadu electricity is used as the benchmark. The suggested DL model performs better than the traditional EM forecasting techniques in both mean absolute error and accuracy by 12.7% and 9.5%, respectively.
Deceit often occurs in questionnaire surveys, which leads to the misreporting of data and poor reliability. The purpose of this study is to explore whether eye-tracking could contribute to the detection of deception in questionnaire surveys, and whether the eye behaviors that appeared in instructed lying still exist in spontaneous lying. Two studies were conducted to explore eye movement behaviors in instructed and spontaneous lying conditions. The results showed that pupil size and fixation behaviors are both reliable indicators to detect lies in questionnaire surveys. Blink and saccade behaviors do not seem to predict deception. Deception resulted in increased pupil size, fixation count and duration. Meanwhile, respondents focused on different areas of the questionnaire when lying versus telling the truth. Furthermore, in the actual deception situation, the linear support vector machine (SVM) deception classifier achieved an accuracy of 74.09%. In sum, this study indicates the eye-tracking signatures of lying are not restricted to instructed deception, demonstrates the potential of using eye-tracking to detect deception in questionnaire surveys, and contributes to the questionnaire surveys of sensitive issues.
Corrosion defects will increase the risk of power equipment failure, which will directly affect the stable operation of power systems. Although existing methods can detect the corrosion of equipment, these methods are often poor in real-time. This study presents a two-stage detection approach that combines YOLOv8 and DDRNet to achieve real-time and precise corrosion area localization. In the first stage, the YOLOv8 network is used to identify and locate substation equipment, and the detected ROI areas are passed to the DDRNet network in the second stage for semantic segmentation. To enhance the performance of both YOLOv8 and DDRNet, a multi-head attention block is integrated into their algorithms. Additionally, to address the challenge posed by the scarcity of corrosion defect samples, this study augmented the dataset using the cut-copy-paste method. Experimental results indicate that the improved YOLOv8 and DDRNet, incorporating the multi-head attention block, boost the mAP and mIoU by 5.8 and 9.7, respectively, when compared to the original method on our self-built dataset. These findings also validate the effectiveness of our data augmentation technique in enhancing the model’s detection accuracy for corrosion categories. Ultimately, the effectiveness of the proposed two-stage detection method in the real-time detection of substation equipment corrosion defects is verified, and it is 48.7% faster than the one-stage method.
Dynamic emojis are a form of nonverbal communication used in social programs to express emotions during conversations. Studies have shown that different dynamic effects can influence users’ emotional perceptions. Previous studies have focused on the emotional responses elicited by static emojis, while the emotional responses to dynamic emojis have not been thoroughly explored. In this study, we examined the impact of 128 different dynamic effects, categorized into emotional types (HAHV, LAHV, HALV, and LALV), on users’ arousal and valence, and conducted semi-structured interviews to identify users’ preferred dynamic effects. The results revealed significant and positive correlations between the arousal levels of all dynamic emojis and the effects of rhythms. However, the impact of rhythms on the valence of dynamic emojis varied depending on the emotion types of emojis. Specifically, the effects of motion on the valence of dynamic high-valence emojis were found to be significant, whereas they were not significant for dynamic low-valence emojis. Based on these findings, we recommend considering following factors in the design of dynamic emojis, including rhythms, motion effects, motion range, emotional metaphors, and the creation of contrast.
Efficient localization algorithm is a research focus in the field of wireless sensor network (WSN). Nowadays, localization for wireless sensor network based on support vector regression(SVR) algorithm is one of the most important localization algorithms. In this paper, we analyse localization model based on support vector regression and propose a novel extraction method of training data for localization model. By simulations, the results show the proposed algorithm gives better accuracy than the original programming localization.
5 June 2023 in IEEE Transactions on Instrumentation and Measurement
As a core procedure in an increasingly automated industrial environment, defect detection is important for producing micro armatures. However, there are still some difficulties in using general deep learning detection methods, the spatial feature loss problem for small targets of solder surface defects and the difficulty in tuning the reference of sample selection strategy. Therefore, this paper proposes an adaptive label assignment detection framework. The detector uses an anchor free object detection network as the backbone. A feature compensation method is proposed to complement the spatial information for solving the feature disappearance problem of small objects. For addressing the label matching tuning problem of anchor-free network, an adaptive central region sample selection strategy is proposed at the base of the feature selective anchor-free (FSAF) module. To further improve the performance of the detection head, the dynamic head and soft non-maximum suppression (Soft-NMS) are introduced. The detection framework in this paper is evaluated on the Micro-Armature Solder Surface Defect Detection (MASS-DET) dataset, and the experimental results show that our framework can achieve 87.7 % mAP50 and 65.5% mAR, making it superior to common object detection methods. Moreover, the method presented in this paper can be applied in most industrial environments to improve the accuracy and efficiency of defect detection of non-standard micro workpiece. The dataset of this paper is open source and available on https://github.com/scuzw/Micro-Armature-Solder-Surface-Defect-Detection.