您的检索：
学者姓名：于乃功
精炼检索结果：
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 ：
Recognition of wafer map defect patterns is essential for evaluating the reliability of micro-electronic manufacturing. Due to the difficulty of labeling, the available large-scale wafer maps are raw data without labeling. The scarcity of labeled samples reduces the defect pattern recognition accuracy of popular deep convolutional neural networks. To overcome this problem, we propose a wafer map deep clustering (WMDC) model. It learns generic representations from unlabeled datasets in an unsupervised manner. A prototype metric loss during training helps to learn the semantic features of the categories. We improve the recognition accuracy of the model when trained using scarce labeled data by transferring the weights of unsupervised pretraining. Experiments on WM811K and MixedWM38 wafer datasets demonstrate that the WMDC model is capable of obtaining robust prior representations from the unlabeled wafer maps. Accuracies of 97.43% and 98.74% are obtained when fine-tuning using scarce labeled data from both datasets, respectively.
关键词 ：
unsupervised representation learning unsupervised representation learning deep clustering deep clustering convolutional neural network convolutional neural network scarce labeled data scarce labeled data Wafer map defect pattern recognition Wafer map defect pattern recognition Labeling Labeling Data models Data models Pattern recognition Pattern recognition Semiconductor device modeling Semiconductor device modeling Manuals Manuals Task analysis Task analysis Training Training
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Xu, Qiao , Yu, Naigong , Yu, Hejie . Unsupervised Representation Learning for Large-Scale Wafer Maps in Micro-Electronic Manufacturing [J]. | IEEE TRANSACTIONS ON CONSUMER ELECTRONICS , 2024 , 70 (1) : 1226-1235 . |
| MLA | Xu, Qiao 等. "Unsupervised Representation Learning for Large-Scale Wafer Maps in Micro-Electronic Manufacturing" . | IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 70 . 1 (2024) : 1226-1235 . |
| APA | Xu, Qiao , Yu, Naigong , Yu, Hejie . Unsupervised Representation Learning for Large-Scale Wafer Maps in Micro-Electronic Manufacturing . | IEEE TRANSACTIONS ON CONSUMER ELECTRONICS , 2024 , 70 (1) , 1226-1235 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Detecting wafer map anomalies is crucial for preventing yield loss in semiconductor fabrication, although intricate patterns and resource-intensive labeled data prerequisites hinder precise deep-learning segmentation. This paper presents an innovative, unsupervised method for detecting pixel-level anomalies in wafer maps. It utilizes an efficient dual attention module with a knowledge distillation network to learn defect distributions without anomalies. Knowledge transfer is achieved by distilling information from a pre-trained teacher into a student network with similar architecture, except an efficient dual attention module is incorporated atop the teacher network's feature pyramid hierarchies, which enhances feature representation and segmentation across pyramid hierarchies that selectively emphasize relevant and discard irrelevant features by capturing contextual associations in positional and channel dimensions. Furthermore, it enables student networks to acquire an improved knowledge of hierarchical features to identify anomalies across different scales accurately. The dissimilarity in feature pyramids acts as a discriminatory function, predicting the likelihood of an abnormality, resulting in highly accurate pixel-level anomaly detection. Consequently, our proposed method excelled on the WM-811K and MixedWM38 datasets, achieving AUROC, AUPR, AUPRO, and F1-Scores of (99.65%, 99.35%), (97.31%, 92.13%), (90.76%, 84.66%) respectively, alongside an inference speed of 3.204 FPS, showcasing its high precision and efficiency.
关键词 ：
Image segmentation Image segmentation Feature extraction Feature extraction Semiconductor device modeling Semiconductor device modeling Knowledge engineering Knowledge engineering Training Training attention network attention network Fabrication Fabrication knowledge distillation knowledge distillation Wafer map anomaly detection Wafer map anomaly detection Anomaly detection Anomaly detection
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Hasan, Mohammad Mehedi , Yu, Naigong , Mirani, Imran Khan . Efficient Dual-Attention-Based Knowledge Distillation Network for Unsupervised Wafer Map Anomaly Detection [J]. | IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING , 2024 , 37 (3) : 293-303 . |
| MLA | Hasan, Mohammad Mehedi 等. "Efficient Dual-Attention-Based Knowledge Distillation Network for Unsupervised Wafer Map Anomaly Detection" . | IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING 37 . 3 (2024) : 293-303 . |
| APA | Hasan, Mohammad Mehedi , Yu, Naigong , Mirani, Imran Khan . Efficient Dual-Attention-Based Knowledge Distillation Network for Unsupervised Wafer Map Anomaly Detection . | IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING , 2024 , 37 (3) , 293-303 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
The photovoltaic curtain wall is a combination of an outer photovoltaic module plate and inner vacuum glass, which forms a narrow cavity with obstacles such as beams and junction boxes inside. After the cavity of the photovoltaic curtain wall is contaminated, it is impossible to enter manually. For the problem of cavity cleaning, a cross-frame barrier-crossing and wall-climbing cleaning robot is developed. The robot body mechanism is designed as a cross-frame motion mechanism to achieve flexible movement in narrow cavities; its adsorption device is designed as a liftable 3*5 vacuum suction cup set to achieve stable adsorption on the vacuum glass surface and the function of crossing obstacles; its cleaning structure is designed as a foldable brush cleaning structure to achieve the cleaning function on the photovoltaic module surface. Based on the kinematic model, the robot motion simulation analysis was completed; the robot prototype was developed, and the adsorption and movement experiments of the robot were carried out. The experimental results show that the robot can achieve stable adsorption and autonomous movement on the vertical wall surface.
关键词 ：
Cleaning robot Cleaning robot Photovoltaic curtain wall cavity Photovoltaic curtain wall cavity Crossing obstacles Crossing obstacles Cross frame Cross frame
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yu, Naigong , Feng, Wanhu , Zhang, Fan et al. Design of a cross-frame barrier-crossing and wall-climbing cleaning robot [J]. | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 : 4941-4947 . |
| MLA | Yu, Naigong et al. "Design of a cross-frame barrier-crossing and wall-climbing cleaning robot" . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC (2023) : 4941-4947 . |
| APA | Yu, Naigong , Feng, Wanhu , Zhang, Fan , Yu, Hejie . Design of a cross-frame barrier-crossing and wall-climbing cleaning robot . | 2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC , 2023 , 4941-4947 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
In neuromorphic computing, the coding method of spiking neurons serves as the foundation and is crucial for various aspects of network operation. Existing mainstream coding methods, such as rate coding and temporal coding, have different focuses, and each has its own advantages and limitations. This paper proposes a novel coding scheme called activeness coding that integrates the strengths of both rate and temporal coding methods. It encompasses precise timing information of the most recent neuronal spike as well as the historical firing rate information. The results of basic characteristic tests demonstrate that this encoding method accurately expresses input information and exhibits robustness. Furthermore, an unsupervised learning method based on activeness-coding triplet spike-timing dependent plasticity (STDP) is introduced, with the MNIST classification task used as an example to assess the performance of this encoding method in solving cognitive tasks. Test results show an improvement in accuracy of approximately 4.5%. Additionally, activeness coding also exhibits potential advantages in terms of resource conservation. Overall, activeness offers a promising approach for spiking neural network encoding with implications for various applications in the field of neural computation.
关键词 ：
temporal coding temporal coding spiking neural network spiking neural network MNIST MNIST neural coding neural coding rate coding rate coding activeness activeness
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wang, Zongxia , Yu, Naigong , Liao, Yishen . Activeness: A Novel Neural Coding Scheme Integrating the Spike Rate and Temporal Information in the Spiking Neural Network [J]. | ELECTRONICS , 2023 , 12 (19) . |
| MLA | Wang, Zongxia et al. "Activeness: A Novel Neural Coding Scheme Integrating the Spike Rate and Temporal Information in the Spiking Neural Network" . | ELECTRONICS 12 . 19 (2023) . |
| APA | Wang, Zongxia , Yu, Naigong , Liao, Yishen . Activeness: A Novel Neural Coding Scheme Integrating the Spike Rate and Temporal Information in the Spiking Neural Network . | ELECTRONICS , 2023 , 12 (19) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Physiological studies have shown that rats in a dark environment rely on the limbs and vestibule for their self-motion information, which can maintain the specific firing patterns of grid cells and hippocampal CA3 place cells. In the development stage of rats, grid cells are considered to come from place cells, and place cells can be encoded by hippocampal theta cells. Based on these, the quadruped robot is used as a platform in this paper. Firstly, the sensing information of the robot's limbs and inertial measurement unit is obtained to solve its position in the environment. Then the position information is encoded by theta cells and mapped to place cells through a neural network. After obtaining the place cells with single-peak firing fields, Hebb learning is used to adjust the connection weight of the neural network between place cells and grid cells. In order to verify the model, 3-D simulation experiments are designed in this paper. The experiment results show that with the robot exploring in space, the spatial cells firing effects obtained by the model are consistent with the physiological research facts, which lay the foundation for the bionic environmental cognition model.
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yu, Naigong , Liao, Yishen , Yu, Hejie et al. Construction of the rat brain spatial cell firing model on a quadruped robot [J]. | CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY , 2022 , 7 (4) : 732-743 . |
| MLA | Yu, Naigong et al. "Construction of the rat brain spatial cell firing model on a quadruped robot" . | CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY 7 . 4 (2022) : 732-743 . |
| APA | Yu, Naigong , Liao, Yishen , Yu, Hejie , Sie, Ouattara . Construction of the rat brain spatial cell firing model on a quadruped robot . | CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY , 2022 , 7 (4) , 732-743 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
How rats achieve goal-oriented navigation is a hot research topic in neuroscience. Inspired by neurophysiological research, this paper proposes a brain-like navigation method inspired by the spatial cells' cognitive mechanism. Firstly, a neural computational model of the entorhinalhippocampal structure is constructed for path integration. Subsequently, a visual pathway computational model is constructed to correct the accumulated errors. Finally, a self-organizing computational model of hippocampal CA1 place cells is constructed to optimize the navigation path. In order to verify the model, this paper designs the 2-D simulation experiment, and the proposed model is also compared with other models. The experimental results show that the proposed model cannot only make the navigation process more robust by using visual information. Moreover, it can gradually optimize the navigation path through the self-organized activity of hippocampal CA1 place cells, thus improving the efficiency of navigation.
关键词 ：
Goal -oriented navigation Goal -oriented navigation Visual pathway Visual pathway Entorhinal-Hippocampal Entorhinal-Hippocampal Path integration Path integration
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Liao, Yishen , Yu, Hejie , Yu, Naigong . A brain-like navigation method inspired by the spatial cells' cognitive mechanism [J]. | COMPUTERS & ELECTRICAL ENGINEERING , 2022 , 103 . |
| MLA | Liao, Yishen et al. "A brain-like navigation method inspired by the spatial cells' cognitive mechanism" . | COMPUTERS & ELECTRICAL ENGINEERING 103 (2022) . |
| APA | Liao, Yishen , Yu, Hejie , Yu, Naigong . A brain-like navigation method inspired by the spatial cells' cognitive mechanism . | COMPUTERS & ELECTRICAL ENGINEERING , 2022 , 103 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
在灾后危险的环境下,含人员位置信息的情景地图是实现救援、提供补给的重要保障。本文提出了一种含受害人员的灾后情景地图构建方法,主要应用于灾后探测机器人上,完成灾后危险环境地图构建任务及在地图上标定需要营救或补给人员的位置信息等任务。首先以搭载激光雷达,里程计,陀螺仪及深度摄像头的自主移动机器人为主体。通过先验地图设定环境探索路径,实现机器人自主地在环境中进行激光建图与搜索任务。建图过程中,对采集到的图像进行人员检测,根据检测结果得到对应检测目标的像素中心。并结合对应的深度信息和当前机器人的位置,通过三维定位模型推算目标人员在世界坐标系中的位置,并标定在地图上。本文所提的方法可为救援和医疗人员提供...
关键词 ：
位置信息 位置信息 情景地图 情景地图 导航 导航 人员检测 人员检测 激光建图 激光建图
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 于乃功 , 郑相国 , 廖诣深 et al. 含受害人员的灾后危险环境情景地图构建方法 [C] //2020中国自动化大会(CAC2020)论文集 . 2021 . |
| MLA | 于乃功 et al. "含受害人员的灾后危险环境情景地图构建方法" 2020中国自动化大会(CAC2020)论文集 . (2021) . |
| APA | 于乃功 , 郑相国 , 廖诣深 , 冯慧 . 含受害人员的灾后危险环境情景地图构建方法 2020中国自动化大会(CAC2020)论文集 . (2021) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明公开了一种光伏幕墙空腔清洁机器人，由机器人本体装置、清洁装置、运动控制系统、远程遥控系统四部分组成。机器人本体采用两组导轨搭建十字框架型结构，包括移动机构、伸缩气缸等，能够实现机器人在光伏幕墙空腔狭小的空间内自主移动、清洁、避障等功能。清洁装置分为吸附面清洁和非吸附面清洁，吸附面和非吸附面的清洁方式都采用直流吸尘装置清洁，能够实现光伏幕墙空腔双侧全方位清洁的功能。在机器人本体结构上，安装了测距传感器等多种传感器，控制器能够对采集的光伏幕墙空腔环境信息进行分析和处理，进而控制清洁机器人完成自主移动、清洁、避障等工作。清洁机器人包括无线传输模块，能够实现机器人的远程监督和控制。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 于乃功 , 冯万虎 , 张帆 et al. 一种光伏幕墙空腔清洁机器人 : CN202110059472.4[P]. | 2021-01-15 . |
| MLA | 于乃功 et al. "一种光伏幕墙空腔清洁机器人" : CN202110059472.4. | 2021-01-15 . |
| APA | 于乃功 , 冯万虎 , 张帆 , 闫金涵 , 于贺捷 , 甘孟哲 et al. 一种光伏幕墙空腔清洁机器人 : CN202110059472.4. | 2021-01-15 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明涉及机器人领域，具体涉及一种光伏幕墙空腔清洁机器人的清洁吸附装置，包括第一部件，第二部件，第三部件和密封空腔，所述第一部件通过固定支架连接于机器人本体，通过活塞端盖安装于密封空腔上方；所述第二部件与所述第三部件共同安装于所述密封空腔内部；所述第三部件通过过滤网与第二部件隔开；所述密封空腔为清洁吸附装置外壳，另设有缓冲装置和橡胶密封圈。本发明光伏幕墙空腔清洁机器人的清洁吸附装置，通过第一、第二和第三部件的协同工作，实现多位一体的清洁、吸附和越障功能，极大地降低了光伏幕墙空腔清洁机器人的高度和重量，增加了其在狭窄空腔内运动、越障和清洁的灵活性，提升了光伏幕墙空腔清洁工作的清洁效率。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 于乃功 , 张帆 , 冯万虎 et al. 一种光伏幕墙空腔清洁机器人的清洁吸附装置 : CN202110059666.4[P]. | 2021-01-15 . |
| MLA | 于乃功 et al. "一种光伏幕墙空腔清洁机器人的清洁吸附装置" : CN202110059666.4. | 2021-01-15 . |
| APA | 于乃功 , 张帆 , 冯万虎 , 闫金涵 , 于贺捷 , 甘孟哲 et al. 一种光伏幕墙空腔清洁机器人的清洁吸附装置 : CN202110059666.4. | 2021-01-15 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Wafer bin map (WBM) inspection is a critical approach for evaluating the semiconductor manufacturing process. An excellent inspection algorithm can improve the production efficiency and yield. This paper proposes a WBM defect pattern inspection strategy based on the DenseNet deep learning model, the structure and training loss function are improved according to the characteristics of the WBM. In addition, a constrained mean filtering algorithm is proposed to filter the noise grains. In model prediction, an entropy-based Monte Carlo dropout algorithm is employed to quantify the uncertainty of the model decision. The experimental results show that the recognition ability of the improved DenseNet is better than that of traditional algorithms in terms of typical WBM defect patterns. Analyzing the model uncertainty can not only effectively reduce the miss or false detection rate but also help to identify new patterns.
关键词 ：
DenseNet DenseNet convolutional neural network convolutional neural network model uncertainty model uncertainty wafer defect inspection wafer defect inspection
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Yu Nai-gong , Xu Qiao , Wang Hong-lu et al. Wafer bin map inspection based on DenseNet [J]. | JOURNAL OF CENTRAL SOUTH UNIVERSITY , 2021 , 28 (8) : 2436-2450 . |
| MLA | Yu Nai-gong et al. "Wafer bin map inspection based on DenseNet" . | JOURNAL OF CENTRAL SOUTH UNIVERSITY 28 . 8 (2021) : 2436-2450 . |
| APA | Yu Nai-gong , Xu Qiao , Wang Hong-lu , Lin Jia . Wafer bin map inspection based on DenseNet . | JOURNAL OF CENTRAL SOUTH UNIVERSITY , 2021 , 28 (8) , 2436-2450 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
