2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)最新文献_第10页

A Low-power Bandgap Reference Voltage Source for Smart Grid Sensor System on Chip 芯片上智能电网传感器系统的低功耗带隙参考电压源

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135246

Changbao Xu, Mingyong Xin, Yulei Wang, Junfei Tang, Dehong Liu, Xiaowen Jiang

{"title":"A Low-power Bandgap Reference Voltage Source for Smart Grid Sensor System on Chip","authors":"Changbao Xu, Mingyong Xin, Yulei Wang, Junfei Tang, Dehong Liu, Xiaowen Jiang","doi":"10.1109/ICCECE58074.2023.10135246","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135246","url":null,"abstract":"For smart grid sensor system-on-chips, traditional bandgap reference circuits have high power consumption, so low-power bandgap reference circuits must be designed that can meet their complex operating environments. This work designs a low-power bandgap reference voltage source for smart grid sensor system chips. Compared to traditional bandgap reference voltage sources, this design combines the high stability of the traditional BJT bandgap reference and the low power consumption characteristics of the sub-threshold bandgap reference, and they are controlled by a digital signal. In normal mode, only conventional BJT bandgap reference (main bandgap) works, and only the sub-threshold low-power bandgap reference (auxiliary bandgap) works in sleep mode. Realized in UMC 55nm ULP CMOS process, the normal mode power consumption is 65 µ W, the temperature coefficient (TC) is 7.7ppm/°C, and the PSRR is - 78dB; After switching to the sleep mode, the power consumption is 2.38 µ W with a TC 1.45ppm/°C. It provides a stable 1.2V reference voltage when the power supply voltage is 1.6V to meet the demand for stable power supply of the on-chip smart grid sensor system under complex working conditions.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124350816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Cross-layer Self-attention Learning Network for Fine-grained Classification 面向细粒度分类的跨层自关注学习网络

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135230

Jianhua Chen, Songsen Yu, Junle Liang

{"title":"A Cross-layer Self-attention Learning Network for Fine-grained Classification","authors":"Jianhua Chen, Songsen Yu, Junle Liang","doi":"10.1109/ICCECE58074.2023.10135230","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135230","url":null,"abstract":"Fine-grained image classification refers to the more fine-grained sub-categories division based on the basic categories that have been divided. It has become a very challenging research task, due to the characteristics of data with large inter-class differences and small intra-class differences. This paper proposes a cross-layer self-attention (CS) network for learning refined discriminative image features across layers. The network consists of a backbone and a cross-layer self-attention module including three submodules, i.e., cross-layer channel attention, cross-layer space attention and feature fusion submodules. Cross-layer channel attention module can bring a channel self-attention by interacting information between low-layer and high-layer in convolutional networks and then load the channel self-attention into low-level to obtain finer low-level features. Cross-layer spatial attention module has similar effect and can obtain finer low level features in the spatial dimension. The feature fusion module fuses low-level features with high-level features where low-level features can be obtained through combining channel and spatial features. The experiments on three benchmark datasets show that the network based on backbone ResNet101 outperform the most mainstream models on the classification accuracy.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129820048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Real-time Monitoring of the Technical Status of General Equipment Based on Integrated Learning 基于集成学习的通用设备技术状态实时监控

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135358

Wei Zhang, Xiaowei Zhang, Wen Dong, Wenshi Wang, Yucai Dong

引用次数: 0

Research on Dynamic Site Selection of Flexible Transit Considering Passenger Source Competition 考虑客源竞争的柔性交通动态选址研究

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135373

Qi Wang, Wen-hong Lv, Ge Gao, Guimin Gong

{"title":"Research on Dynamic Site Selection of Flexible Transit Considering Passenger Source Competition","authors":"Qi Wang, Wen-hong Lv, Ge Gao, Guimin Gong","doi":"10.1109/ICCECE58074.2023.10135373","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135373","url":null,"abstract":"In order to reduce the travel of taxis and private cars and meet the personalized travel needs of passengers, a site selection method is proposed to avoid the conventional bus service area and compete for taxi customers. Flexible bus site selection includes fixed site selection and dynamic site selection. Firstly, 1000 points in the morning and evening peak periods of Shenzhen taxi track data were selected, and the theoretical fixed stations were obtained by using the clustering algorithm combined with DBSCAN and K-means. The service areas of conventional bus stations were marked to avoid the conventional bus passenger sources, and the location optimization from theoretical stations to actual stations was realized. Secondly, a dynamic site selection model aiming at minimizing the total cost of the system was constructed and solved by genetic algorithm. Finally, it is verified by an example. The results show that this method has good usability in avoiding the regular bus passenger source and competing with the taxi passenger source by taking the taxi data as the demand point and avoiding the service area of the regular station.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121391208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fine-grained Recognition Algorithm For Transformer Based On Part Features 基于零件特征的变压器细粒度识别算法

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135351

Zhuangzhuang Feng, Wei Wu

{"title":"Fine-grained Recognition Algorithm For Transformer Based On Part Features","authors":"Zhuangzhuang Feng, Wei Wu","doi":"10.1109/ICCECE58074.2023.10135351","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135351","url":null,"abstract":"Fine-grained image recognition is a challenging task. Due to the small differences between the categories of fine-grained images and the large differences within the categories, traditional networks based on CNN or Transformer have their own shortcomings in feature extraction. This paper gives full consideration to the characteristics of CNN and Transformer, and proposes a fine-grained recognition algorithm combining WS-DAN (Weakly Supervised Data Augmentation Network) and ViT (Vision Transformer). Firstly, the image patch is obtained by WS-DAN to eliminate the incomplete semantic information of image patch caused by traditional ViT. Then, the image patch is encoded based on Transformer framework and global token is introduced for topological relationship constraints among components, which overcomes the locality of features extracted from traditional CNN network. Finally, the training based on the combination of cross entropy and contrast loss function further improves the recognition ability of the network. The proposed algorithm has achieved satisfactory results on the CUB-200-2011, FGVC-Aircraft and Stanford Cars datasets.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126266021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on clustering algorithm based on spark 基于spark的聚类算法研究

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135496

Kun Lang, Xiaoli Chai

引用次数: 0

Bayesian Filter Pruning for Deep Convolutional Neural Network Compression 深度卷积神经网络压缩的贝叶斯滤波剪枝

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135208

Haomin Lin, Tianyou Yu

引用次数: 0

Vibration prediction analysis of 3000TEU container ship 3000TEU集装箱船振动预测分析

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135277

J. Ren, Anxi Cao, Yongxing Jin, Ye Jiang

引用次数: 0

Fair Machine Learning-An Analytical Study Based on CiteSpace 公平机器学习——基于CiteSpace的分析研究

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135360

Xiang Luo, Jianfeng Cui, Shuai Ma

引用次数: 0

Instance Segmentation Combined CMT and Swin Transformer in Driving Scenes 基于CMT和Swin变压器的驾驶场景实例分割

2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2023-01-06 DOI: 10.1109/ICCECE58074.2023.10135453

Zhengyi Zha

引用次数: 0