{"title":"Design of High Efficiency Broadband Amplifier and Automatic Test System","authors":"Yang Yang, Shichang Zhong","doi":"10.1145/3514105.3514126","DOIUrl":"https://doi.org/10.1145/3514105.3514126","url":null,"abstract":"Based on the GaN technology platform developed by Nanjing Electronic Device Institute, an L-band high efficiency power amplifier is designed. In order to improve the test efficiency and reduce manual intervention, the implementation of automatic test system based on LabVIEW development platform is proposed. According to the actual needs, the signal source and power meter instrument are controlled through GPIB interface technology to realize the power test, data acquisition and analysis of power amplifier. The test results show that under the input continuous wave signal of 31dbm and 28V drain working voltage, the output power is 41dBm and the maximum efficiency is 83%, which shows the high-efficiency performance advantages of GaN broadband power amplifier. At the same time, the software is proved to be extensible and maintainable.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128345772","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 Network Architecture Design Based on Artificial Intelligence Application Technology","authors":"Jinge Guo","doi":"10.1145/3514105.3514124","DOIUrl":"https://doi.org/10.1145/3514105.3514124","url":null,"abstract":"Abstract: With the continuous development of AI technology, the training of massive data and the emergence of large-scale models have made stand-alone model training increasingly unable to meet the needs of AI applications. Distributed machine learning technologies (such as data parallelism and model parallelism) have appeared at historic moments and will have extreme large-scale application scenarios. At present, the training speed of distributed machine learning models is slow, and the scale of model parameters is still the main problem in this field. From the perspective of model parallelism, this article aims to design the optimal division method for different models under model parallelism by analyzing the structure of the existing AI application model. According to the framework structure of artificial intelligence application model, design the model optimization partition strategy and model based on parallelism. A network architecture suitable for accelerating AI application training, focusing on solving technical problems, such as network architecture design based on AI applications and model optimization and partitioning under model parallelization.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128071538","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":"Implementation of Smart Home Care System Based on Beidou/GPS","authors":"Qing An, Wenqun Fu, Bo Jiang, Shusen Wu","doi":"10.1145/3514105.3514119","DOIUrl":"https://doi.org/10.1145/3514105.3514119","url":null,"abstract":"Abstract: By using the Beidou / GPS positioning technology, integrating advanced technologies such as intelligent perception, wireless transmission, Internet of things, big data, cloud platform, and taking the Beidou / GPS smart watch with the functions of positioning, calling, and physical sign measurement as the terminal carrier, the mobile client app of health and safety monitoring system based on Android / IOS system is developed, and the smart home care service platform is built, so as to integrate the elderly with the society District, guardian, government and medical institutions are closely linked to provide comprehensive services for the elderly, such as health care, safety monitoring, spiritual comfort and emergency rescue, so as to realize the three major innovations of service mode, technical mode and management mode for the elderly.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134405983","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}
Xiaodong Liu, Yunhui Yi, Nan Chen, Shuo Yang, Yuanxinyu Luo, Wentao Kan
{"title":"Cooperative Sensing Task Assignment Algorithm for Heterogeneous Devices Based on Internet of Things","authors":"Xiaodong Liu, Yunhui Yi, Nan Chen, Shuo Yang, Yuanxinyu Luo, Wentao Kan","doi":"10.1145/3514105.3514121","DOIUrl":"https://doi.org/10.1145/3514105.3514121","url":null,"abstract":"Thanks to the rapid popularization of intelligent terminal device and the further development of wireless communication technology, mobile crowd sensing has become an effective means to collect massive data. Task assignment has always been an important part of the mobile crowd sensing (MCS) system. At present, there are many literatures on task assignment, but there are few researches on cooperative sensing task assignment for heterogeneous intelligent sensing devices. In order to solve the task assignment problem in this multiple heterogeneous sensing device scenario, this paper proposed a task assignment algorithm (TAGA) based on combinatorial double auction and elite-preserving genetic algorithm (EGA). Firstly, the pricing method based on combinatorial double auction is used to determine the offer price and asked price, and then the EGA algorithm is used to determine the final task assignment scheme. The simulation results show that the algorithm can effectively improve the overall utility of the whole system.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129076355","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":"A Novel Design of Concurrent Dual-Band RF Power Amplifier","authors":"Mingming Gao, Gaoyang Xu, Shao-jun Fang, J. Nan","doi":"10.1145/3514105.3514129","DOIUrl":"https://doi.org/10.1145/3514105.3514129","url":null,"abstract":"This paper proposed a novel design method of concurrent multi-band matching circuit in The concurrent dual-band matching circuit can realize arbitrary impedance matching in arbitrary frequency band. A Concurrent dual-band RF power amplifier operating at 2.4 G and 2.8 G is designed. The test results show that when the output power reaches 10W, at 2.4 G and 2.8G bands, the power added efficiency (PAE) is 57.2% and 56.5%. Therefore, the feasibility of the design method of the concurrent dual band matching structure is verified.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"29 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122859137","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":"KL-Mat: Fair Recommender System via Information Geometry","authors":"Hao Wang","doi":"10.1145/3514105.3514107","DOIUrl":"https://doi.org/10.1145/3514105.3514107","url":null,"abstract":"Recommender system has intrinsic problems such as sparsity and fairness. Although it has been widely adopted for the past decades, research on fairness of recommendation algorithms has been largely neglected until recently. One important paradigm for resolving the issue is regularization. However, researchers have not been able to come up with a consensusly agreed regularization term like regularization framework in other fields such as Lasso or Ridge Regression. In this paper, we borrow concepts from information geometry and propose a new regularization-based fair algorithm called KL-Mat. The algorithmic technique leads to a more robust performance in accuracy performance such as MAE. More importantly, the algorithm produces much fairer results than vanilla matrix factorization approach. KL-Mat is fast, easy-to-implement and explainable.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121202580","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":"456Gbps High-speed Ceramic Package Applied to Optical Communication","authors":"Huizeng Yan, Huanbei Chen, Hao Zhou, Qiushi Liang","doi":"10.1145/3514105.3514131","DOIUrl":"https://doi.org/10.1145/3514105.3514131","url":null,"abstract":"A high-speed ceramic package based on High-temperature cofired ceramics (HTCC) process is presented in this paper. The traditional differential vias structure is replaced by face via structure at the signal transmission port. By analyzing its equivalent circuit model and simulating in frequency domain, the port can realize single channel high-speed signal transmission with 40GHz bandwidth on the premise of ensuring signal integrity. The cylinder via structure and face via structure under the same conditions are analyzed in frequency domain and time domain. It is verified that the face via structure has better transmission characteristics and can more effectively ensure the signal integrity. Finally, the structure is applied to the four-channel package of Optical module, which can support high-speed signal transmission above 4 × 56Gbps.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122590962","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":"VTuckeR: Multimodal Tucker Fusion for Scene Graph Generation","authors":"Geng Jia, Yunhui Yi, Wentao Kan","doi":"10.1145/3514105.3514111","DOIUrl":"https://doi.org/10.1145/3514105.3514111","url":null,"abstract":"Originated from object segmentation and word vector representations, Scene Graph Generation (SGG) became a complex task built on enumerous research results. Today's scene graph generation (SGG) task is still far from practical, we believe that it's due to unfair matching strategies between images and object regions. Inspired by Tucker decomposition's success in VQA area, in this paper, we propose VTuckeR, a relatively straightforward but powerful linear model based on Tucker decomposition of the tensor representation of images and object features. In VTuckeR, we control the complexity of the merging scheme while keeping itself good interpretability. We show our model is able to enforce multiple types of Scene Graph Generation models in Visual Genome dataset in the PredCls mode. What's more, a more accurate scene graph may aid prediction of wireless channel dynamics in the future, which is called V2C.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126320909","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}
Tianxing Zhou, Tianxin Li, Chunyu Wen, Haoming Shi
{"title":"Design of A Positioning and Navigation System for Intelligent Inspection Robots in Oil and Gas Stations","authors":"Tianxing Zhou, Tianxin Li, Chunyu Wen, Haoming Shi","doi":"10.1145/3514105.3514122","DOIUrl":"https://doi.org/10.1145/3514105.3514122","url":null,"abstract":"In order to solve the problem of difficult inspections in oil and gas stations and prone to product accidents, this project designed an intelligent inspection vehicle for oil and gas stations based on sensor fusion algorithms. This project uses the Kalman filter algorithm to fuse the data collected by GNSS and IMU. Through simulation experiments, it is concluded that the algorithm can obtain high-precision positioning data under low-cost conditions, which can be effectively used in industrial production and is conducive to the promotion of self-driving inspection vehicles.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125531514","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":"Batch gradient neuro-fuzzy learning method with smoothing L0 regularization for the first-order Takagi-Sugeno system","authors":"Qingqing Ma, Chunmei Qi, Huisheng Zhang","doi":"10.1145/3514105.3514108","DOIUrl":"https://doi.org/10.1145/3514105.3514108","url":null,"abstract":"In this paper, we propose a batch gradient neuro-fuzzy learning algorithm with smoothing regularization (BGNFSL0) for the first-order Takagi-Sugeno system. The regularization method usually tends to produce the sparsest solution, however, its solving is an NP-hard problem, and it cannot be directly used in designing the regularized gradient neuro-fuzzy learning method. By exploiting a series of smoothing functions to approximate the regularizer, the proposed BGNFSL0 successfully avoids the NP-hard nature of the original regularization method, while inheriting the advantage in producing the sparsest solution. In this way, BGNFSL0 can prune the network efficiently during the learning procedure and thus improve the generalization capability of the networks. By conducting simulations to compare it with several other popular regularization learning methods, it is found that BGNFSL0 exhibits the best performance in generating the parsimonious network as well as the generalization capability.","PeriodicalId":360718,"journal":{"name":"Proceedings of the 2022 9th International Conference on Wireless Communication and Sensor Networks","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123508811","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}