{"title":"Appliance Recognition Using V-I Trajectories based on Deep Learning","authors":"Peng Zhang, Bowen Gao, Hong Chen, Zhi-Qiang Yu","doi":"10.1109/ICPICS55264.2022.9873552","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873552","url":null,"abstract":"One aim of the non-intrusive load monitoring is disaggregate the total power consumption to the power consumption of a single device by analyzing the change in voltage and current measured in order to realize recognition of appliance loads. The appliance identification is the core of the non-intrusive load monitoring (NILM). In this paper, a methodology for characterizing appliances and identifying appliances in a 2-dimensional V-I trajectory is proposed for actual measured appliances data. And a method is proposed to filter the sampled data using Empirical Mode Decomposition (EMD). A deep learning method is applied to automatically extract features from the built V-I trajectory maps. After experiments, the accuracy of load identification is relatively high.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132317794","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}
Yandan Kong, Kai Liu, Zhihong Liang, Tianchen Liu, Yuxiang Huang, Mingming Qin
{"title":"Research on small object detection methods based on deep learning","authors":"Yandan Kong, Kai Liu, Zhihong Liang, Tianchen Liu, Yuxiang Huang, Mingming Qin","doi":"10.1109/ICPICS55264.2022.9873614","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873614","url":null,"abstract":"The efficiency and accuracy of object detection are steadily improving due to the development and widespread application of deep learning. However, small object detection remains a challenge. When employing mainstream object detection algorithms, small objects have low resolution, little feature information, and weak expressiveness, which leads to missed false detection and poor detection accuracy. This paper systematically describes on small object detection methods based on deep learning, divides them into four categories based on small object detection optimization methods, such as data augmentation, multi-scale feature fusion, contextual features, and optimized backbone networks, and analyzes the benefits and drawbacks of each method, and offers a forecast on future research directions.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"281 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113972305","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}
{"title":"Insulation State Assessment of Cable Intermediate Joint based on Fuzzy Comprehensive Evaluation with Variable Weight","authors":"Yijun Liu, Xiaomei Ou, Shaohui Liu, Guowei Guo, Jia-yue Chen, Haorong Qiu","doi":"10.1109/ICPICS55264.2022.9873733","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873733","url":null,"abstract":"Based on the close relationship between partial discharge(PD) and cable immediate joint insulation, a method based on variable weight and fuzzy comprehensive evaluation is proposed, and the cable joint insulation evaluation model is established. Firstly, this model selects the representative PD characteristic parameters as the quantitative index of cable joint insulation state, and uses the analytic hierarchy process to determine the constant weight of each index. Considering the imbalance of indicators, the variable weight theory is introduced to optimize the constant weight. Furthermore, the ridge membership function of PD parameters corresponding to different state levels is established. Finally, the insulation state evaluation of cable intermediate joints is realized based on the fuzzy comprehensive evaluation method. The case analysis shows that the variable weights can better reflect the data characteristics of the indexes. Therefore, the variable weight fuzzy comprehensive evaluation method can more accurately and effectively evaluate the insulation status of cable intermediate joints.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":" 31","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114051458","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}
{"title":"Representation based Few-Shot Learning for Brand-logo Detection","authors":"Zhixiong Yang, Huaizhang Liao, Haoyu Zhang, Weijie Li, Jingyuan Xia","doi":"10.1109/ICPICS55264.2022.9873791","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873791","url":null,"abstract":"In this paper, we propose an attention-net based few-shot object detection (AN-FSOD) model for brand-logo detection and recognition. With the fact that brand-logo detection has many distinct properties: tiny objects, similar brands, and adversarial images, most of the current FSOD approaches, motivated by meta-learning, metric-learning and transfer learning techniques, typically perform less-effective due to the difficulties on target region allocation. The proposed AN-FSOD aims to locate the region of the brand-logo targets, achieved by a well- trained attention-net, therefore providing an explicit feature maps for detection and classification. An end-to-end feature extractor and target detector model is established, implementing with a simultaneous parameter fine-tuning with respect to the few-shot dataset. Extensive simulations have confirmed that the proposed AN-FSOD gains significantly better performance than the vanilla FSOD model and the majority of the feature extractor aligned model on a public brand-logo dataset.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115330819","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}
{"title":"Design of The Humanoid Biped Robot based on Luby Controller","authors":"Yang Zheng, Ping Jin, Yunfei Xia","doi":"10.1109/ICPICS55264.2022.9873553","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873553","url":null,"abstract":"This article introduces the hardware and software design of a humanoid biped robot based on Luby controller with “robot competition in Anhui province” humanoid sprint project as the background. Design a humanoid biped robot. The Luby controller is implemented by the STM32 chip, which was adopted to realize process control, through the pace planning, speed adjustment, sensor detection to complete the robot’s humanoid sprint action task. After the actual competition, it was verified that the biped robot has certain practicability and stability.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126798785","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}
Dan Liu, Nianzhang Liu, Tian Dong, D. Ke, Jian Xu, Yuhui Wu
{"title":"Short-Term Load Forecasting Considering the Separation and Identification of Generalized Load","authors":"Dan Liu, Nianzhang Liu, Tian Dong, D. Ke, Jian Xu, Yuhui Wu","doi":"10.1109/ICPICS55264.2022.9873547","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873547","url":null,"abstract":"Affected by the distributed generation (DG), traditional load forecasting models have been difficult to forecast generalized load (GL). In this paper, a short-term load forecasting method considering the separation and identification of GL is proposed. First, the key influencing factors of GL are obtained by grey relational analysis, which are mainly temperature and DG. Secondly, the proposed improved back propagation (BP) neural network is used to realize the separation and identification of temperature-sensitive load (TSL) and DG in GL. Finally, long short-term memory (LSTM) network is used for TSL and DG output forecasting, Autoregressive Integrated Moving Average (ARIMA) model is used for normal load forecasting. The short-term GL forecasting results are obtained by summing. The practical example shows the effectiveness of the proposed method.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126217257","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}
Chengyu Luo, Y. Xue, Jun Peng, Heng Liu, Yuxi Wang
{"title":"Application of Satellite Image in Substation Location","authors":"Chengyu Luo, Y. Xue, Jun Peng, Heng Liu, Yuxi Wang","doi":"10.1109/ICPICS55264.2022.9873638","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873638","url":null,"abstract":"The selection of substation sites is an important part of power grid planning. The reasonable locations of substations not only affect the investment in the construction in the early stage, but also play a vital role in the operation of power grid in the later stage. A method of substation location based on satellite images is proposed in this paper. With the rapid development of technology, it has become possible to obtain high-definition satellite images. Satellite images are converted into corresponding data, and a wide-area geographic information database is established to build actual three-dimensional geographic models, which can save manpower, material resources and time consumption of on-site inspections. In the 3D model, a large amount of attribute data can be directly reflected, and the visualization degree is stronger. The basic process and advantages of this method are analyzed and summarized, and the feasibility is verified by a case.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126006079","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}
{"title":"Research on Dynamic Decoupling Algorithm of Six-axis Force Sensor based on Space Partition","authors":"Changjun Chen, Chen Xiliang","doi":"10.1109/ICPICS55264.2022.9873786","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873786","url":null,"abstract":"Aiming at the decoupling problem of the calibration of the six-axis force sensor, the coupling relationship is established according to the calibration experiment results of the six- axis force sensor. The basic principle of least square method and space partition decoupling algorithm is introduced. According to the algorithm principle, the calibration matrix is calculated by calibration data. The decoupling algorithm is used to decouple the calibration matrix, and finally the decoupling calibration matrix is obtained and verified. The results demonstrate the effectiveness of the proposed decoupling algorithm.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124840419","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}
{"title":"High Performance Crypto for 5G Wireless on x86 Platform","authors":"Liheng Zhang, Yao Dong","doi":"10.1109/ICPICS55264.2022.9873766","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873766","url":null,"abstract":"The crypto, including ciphering and integrity protection, is a high cycle consumption job inside PDCP in 5G. When 5G RAN is deployed on Cloud and Edge based on general x86 platform, there are two common ways to implement the crypto functions, namely software lib based or hardware acceleration QAT based. The former occupies computing resource, but is quick for small packets, while the latter saves computing resource, but has longer processing latency. Both of them may meet the performance scaling issue, as the packet size varies, especially when eMBB slice and uRLLC slice are both enabled. This paper provides an efficient way to have both high computation performance and low processing latency for crypto functions with Intel Architecture technologies.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122824313","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}
Lim Guowei, Liang Nianbai, Deng Jiayi, Guo Guowei, Liu Shaohui, Bei Chun
{"title":"A high sensitivity high-frequency current sensor design","authors":"Lim Guowei, Liang Nianbai, Deng Jiayi, Guo Guowei, Liu Shaohui, Bei Chun","doi":"10.1109/ICPICS55264.2022.9873581","DOIUrl":"https://doi.org/10.1109/ICPICS55264.2022.9873581","url":null,"abstract":"In this paper, based on the analysis of the working principle of high-frequency current transformer (HFCT), a high sensitivity small HFCT is designed for partial discharge (PD) detection of cable intermediate joints, and the factors affecting the sensitivity of the sensor are analyzed. The results of simulation analysis and experiments show that the sensor has good linearity in the passband, and the gain in the frequency range of 1MHz~5MHz can reach more than 44dB (150mV/mA), with high sensitivity, and can couple out the small partial discharge current, which has strong practical application value.","PeriodicalId":257180,"journal":{"name":"2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125593604","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}