2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)最新文献_第2页

Design for Low Latency and High Reliability: OPC-UA Based Production Line for Product Traceability and Customized Service 低延迟和高可靠性设计:基于OPC-UA的生产线，用于产品可追溯性和定制服务

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637063

Kaiqiang Cao, Li Zhang, Chengwei Zhou

{"title":"Design for Low Latency and High Reliability: OPC-UA Based Production Line for Product Traceability and Customized Service","authors":"Kaiqiang Cao, Li Zhang, Chengwei Zhou","doi":"10.1109/ICITES53477.2021.9637063","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637063","url":null,"abstract":"With the growing popularity of edge computing and Industry 4.0, the Industrial Internet-of-Things (IIoT) has emerged as a promising alternative to improve the production efficiency of the manufacturing system. Among various intelligent manufacturing features, product traceability and customized service are highly desired, which not only enables the tracking of the end to end inventory to ensure high reliability, but also provides personalized characteristics to meet different customer demands. However, in tradition, such traceability or customized service are achieved at the cost additional time-consuming steps and hence incur more manufacturing cost. To address the aforementioned issues, we propose a low latency OPC-UA based IIoT system and apply that to the production line for product traceability and customized service. The designed OPC-UA is deployed at the edge gateway to effectively solve the data heterogeneity, support centralized control of network resources, and ensure low latency and high reliability of data transmission. In addition, the inter-communication mechanism among multiple devices on the same production line is improved to enable both flexibility and robustness. Experimental results on a demo production line show that the proposed architecture can help achieve both low latency and high reliability.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133686623","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

On Pareto-frontier Approximate Computing for Many-core Systems 多核系统的pareto边界近似计算

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637071

Xinyue Hou, Xiaohang Wang, M. Palesi, A. Singh, Yingtao Jiang, Mei Yang, Letian Huang, Junying Chen

{"title":"On Pareto-frontier Approximate Computing for Many-core Systems","authors":"Xinyue Hou, Xiaohang Wang, M. Palesi, A. Singh, Yingtao Jiang, Mei Yang, Letian Huang, Junying Chen","doi":"10.1109/ICITES53477.2021.9637071","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637071","url":null,"abstract":"Approximate computing is an emerging paradigm that aggressively improves performance or reduces energy consumption by sacrificing computation quality for error forgiving applications. Various approximate techniques, including loop truncation, approximate communication, etc. have been proposed. Previous works focus on optimization using only one approximation knob. However, we have observed that simultaneously optimizing with multiple approximation knobs leads to a large search space and is more likely to find better solutions. Therefore, in this paper, we first develop application models for performance, error, and power, followed by formulation of an optimization problem to maximize system performance under error and power constraints, using three approximation knobs, which are loop truncation, data dropping, and computational precision scaling. In order to solve the problem efficiently, a lightweight algorithm based on interior point algorithm is proposed. Experimental results show that, compared to state-of-the-art approximate approaches, the proposed scheme can reduce the execution time by as much as 33.1%. The overhead of the proposed method is low, making it a suitable approximate scheme for future many-core systems.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"601 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132756326","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

Emotion Recognition from ECG Signals Contaminated by Motion Artifacts 基于运动伪影污染的心电信号的情绪识别

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637072

Wenwen He, Yalan Ye, Tongjie Pan, Qianhe Meng, Yunxia Li

引用次数: 1

Leveraging Relational Database for Fast Construction of OPC UA Information Model 利用关系数据库快速构建OPC UA信息模型

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637064

Rongkai Wang, Shibo He, Yang Liu, Chengwei Zhou, Zhiguo Shi, Jiming Chen

{"title":"Leveraging Relational Database for Fast Construction of OPC UA Information Model","authors":"Rongkai Wang, Shibo He, Yang Liu, Chengwei Zhou, Zhiguo Shi, Jiming Chen","doi":"10.1109/ICITES53477.2021.9637064","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637064","url":null,"abstract":"With the development of manufacturing factory, massive devices are being deployed in production lines for performance monitoring and optimization, which raises the challenge of interconnectivity and interoperability among devices. OPC UA is widely recognized as one of the effective technologies to address such an issue. Traditional ways of constructing OPC UA information model need to manually add and define different nodes describing the devices and their attributes (e.g., names, ID, data types, etc.), which is costly and time-consuming when a huge number of devices is involved. Some works defined mapping rules between existing data model/structure/exchange format and OPC UA information model to reduce the workloads. However, they ignored the construction process of OPC UA information model and assumed that the existing referenced data structure/exchange format was created before the transformation of information model. Also, the mapping rules do not provide detailed implementation of mapping method. In this paper, we take the first attempt on the fast construction process of OPC UA information model. The raw data of field devices represented as structured data in rational database is fully utilized to extract the information, even though there are no existing data model for reference. The challenge of transforming structured data in database to OPC UA address space is discussed, based on which we propose a specific fast construction method for OPC UA information model. The method is deployed in the built industrial discrete manufacturing production line platform to evaluate the applicability of fast information model construction.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123216021","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

Robust Optimization in Enabling Optimal Economic Dispatch of IES Based on Information Interaction 基于信息交互的电力系统最优经济调度鲁棒优化

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637087

Zengjie Sun, Xuefei Liu, Guozhen Ma, Ren Liu, Zhenwei Li

{"title":"Robust Optimization in Enabling Optimal Economic Dispatch of IES Based on Information Interaction","authors":"Zengjie Sun, Xuefei Liu, Guozhen Ma, Ren Liu, Zhenwei Li","doi":"10.1109/ICITES53477.2021.9637087","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637087","url":null,"abstract":"At present, The Internet of Things is an important support for the construction of the energy Internet, and it is of great significance to realize the intelligent coordination, promote the transformation of the country's energy structure. On this basis, small-scale wind and solar power are increasingly integrated into modern power system through integrated energy system. Taking into account the uncertainty of wind-solar power, this paper establishes a two-stage robust optimization model to achieve the minimum operating cost. Before the uncertainty is realized, the day-ahead stage as the first stage determines operating strategy that can withstand the worst-case uncertainty. As long as the uncertainty is observed, the operating units will be adjusted in the real-time stage to compensate for errors caused by the operating strategy. Due to the difficulties of solving the model, this paper further adopts the duality theory, Big-M method, and column-and-constraint generation (C&CG) decomposition to transform the model into two tractable mixed integer linear programming problems. In addition, C&CG iterative algorithm is also used to solve MILP, which ultimately provides the optimal economic day-ahead scheduling strategy. The experimental results demonstrate the effectiveness of the proposed method.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126611531","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

A Siamese Network for Face Verification with Depth Images 深度图像人脸验证的暹罗网络

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637086

Qi Wang, Hang Lei, Xupeng Wang

引用次数: 0

Network Strengthening Strategy for Fault Disposal of High-Voltage Power Grid 高压电网故障处置的网络强化策略

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637104

Chenxiao Ma, Yuchun Luo, Xiaocong Zhang, Jinghu Zhao, Xiang Ma, Xin Shan, Shuxi Xu, Yi Wang

{"title":"Network Strengthening Strategy for Fault Disposal of High-Voltage Power Grid","authors":"Chenxiao Ma, Yuchun Luo, Xiaocong Zhang, Jinghu Zhao, Xiang Ma, Xin Shan, Shuxi Xu, Yi Wang","doi":"10.1109/ICITES53477.2021.9637104","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637104","url":null,"abstract":"The application of the Internet of Things and embedded technologies in the power grid is in a period of rapid development, and the structure and data of the high-voltage power grid are becoming increasingly complex. However extreme natural disasters such as typhoons will have a serious impact on the high-voltage AC power grid, destroying operating equipment and leading to large-scale failures of the power grid and power outages, which not only causing economic losses, but also bringing difficulties to the fault handling methods of grid dispatch. In this paper, the current coordinated control technology of generation-grid-load three sides after the failure of the high-voltage grid is introduced. In addition, to prevent grid fault and rapidly recover power supply, the resilient power grid construction technology, which include two network strengthening strategies for the hot spare lines operation and the bus tie switches closing with their technical implementation methods are proposed in detail. Finally, the effectiveness of the strategy is proved through case studies on the high-voltage grid model of Zhejiang Power Grid.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130306887","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

TransTracking for UAV: An Autonomous Real-time Target Tracking System for UAV via Transformer Tracking 一种基于变压器跟踪的无人机自主实时目标跟踪系统

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637088

Xiaolou Sun, Fei Xie, Qi Wang, Yuncon Yao, Hao Wang, Wei Wang, Wankou Yang

{"title":"TransTracking for UAV: An Autonomous Real-time Target Tracking System for UAV via Transformer Tracking","authors":"Xiaolou Sun, Fei Xie, Qi Wang, Yuncon Yao, Hao Wang, Wei Wang, Wankou Yang","doi":"10.1109/ICITES53477.2021.9637088","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637088","url":null,"abstract":"Most of the existing Siamese-type trackers usually adopt pre-defined anchor boxes or anchor-free schemes to accurately estimate the bounding box of targets. Unfortunately, they suffer from complicated hand-designed components and tedious post-processings. It is not easy to adjust parameters for unique scenes in real applications. So, we propose a new scheme by formulating visual tracking as a direct set prediction problem to alleviate this issue. The main component is a transformer attached to the Siamese-type feature extraction networks. Thus, our new framework can be summarized as Siamese Network with Transformers (SiamTFR). With a fixed small set of learned object queries, we force the final set of predictions via bipartite matching, significantly reducing hyper-parameters associated with the candidate boxes. Due to the unique predictions of this framework, we significantly ease the heavy burden of hyper-parameters search of post-processings in visual tracking. Extensive experiments on visual tracking benchmarks, including GOT-10K, demonstrate that SiamTFR achieves competitive performance and runs at 50 FPS. Specifically, SiamTFR outperforms leading anchor-based tracker SiamRPN++ in the GOT-10K benchmark, confirming its effectiveness and efficiency. Furthermore, SiamTFR is deployed on the embedded device in which the algorithm can be run at 30FPS or 54FPS with TensorRT meeting the real-time requirements. In addition, we design the complete tracking system demo that can work in the real road to narrow the gap between the academic models and industrial deployments.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124559377","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

Fault Diagnosis on Imbalanced Data Using an Adaptive Cost-sensitive Multiscale Attention Network 基于自适应代价敏感多尺度关注网络的不平衡数据故障诊断

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637101

Jie Xu, Yuxiang Li, Fanjun Meng, Dashun Zhang, Yalan Ye, Li Lu

{"title":"Fault Diagnosis on Imbalanced Data Using an Adaptive Cost-sensitive Multiscale Attention Network","authors":"Jie Xu, Yuxiang Li, Fanjun Meng, Dashun Zhang, Yalan Ye, Li Lu","doi":"10.1109/ICITES53477.2021.9637101","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637101","url":null,"abstract":"Mechanical fault diagnosis using vibration signals is a difficult problem in real-world applications, since few equipments in an abnormal state making abnormal data difficult to obtain, so that original samples are usually highly imbalanced. Imbalanced data make fault diagnostic models' classifier be biased toward normal samples, resulting in misdiagnosis of abnormal samples. To decrease the influence of imbalanced data on fault diagnosis, most methods based on oversampling have high computational burden due to the generation of many redundant samples, and the generated samples can also bring new noise to the diagnostic model leading to the decrease of diagnostic accuracy. In this paper, an adaptive cost-sensitive multiscale attention network, termed CS-MAN, is proposed, which consists of a Multiscale Convolutional Attention Network (MAN) for 1-D vibration signals and an Imbalanced Cross-Entropy (ICE) loss function. Specifically, MAN, as a feature extractor, constructs a broader feature space to obtain more discriminative features. The ICE considers the contribution of the imbalanced proportion of each sample and the characteristics of Difficult Samples Mining (DSM) to the overall misclassification cost. In this way, ICE can adaptively assign more suitable misclassification cost to decrease the influence of imbalanced data. Compared with oversampling-based methods, our method has lower computational burden and higher diagnostic accuracy. Experimental results on an imbalanced bearing dataset verify that our method outperforms the state-of-the-art methods based on over-sampling.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"25 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133937923","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: 2

Energy-efficient Ternary Content Addressable Memory Using Ferroelectric FET 利用铁电场效应晶体管的高能效三元内容可寻址存储器

2021 International Conference on Intelligent Technology and Embedded Systems (ICITES) Pub Date : 2021-10-31 DOI: 10.1109/ICITES53477.2021.9637079

Luo Xudong, Yin Xunzhao

{"title":"Energy-efficient Ternary Content Addressable Memory Using Ferroelectric FET","authors":"Luo Xudong, Yin Xunzhao","doi":"10.1109/ICITES53477.2021.9637079","DOIUrl":"https://doi.org/10.1109/ICITES53477.2021.9637079","url":null,"abstract":"To overcome the Memory Wall problem in the traditional von Neumann machines, computing in-memory (CiM) circuits where computational tasks are performed within the memory blocks are widely investigated. Ternary content addressable memory (TCAM) is a commonly used circuit for CiM, which performs parallel searches across the entire memory against a given query. TCAM has a wide range of application scenarios, such as IP routers, associative memories and advanced machine learning models, etc. Currently some non-volatile devices, for example, resistive random access memories (ReRAMs), ferroelectric transistors (FeFETs), are employed in TCAM designs for improved area efficiency. However, since TCAM often works in parallel with the computational unit, its energy consumption is one of the aspects that we are more concerned about. In this paper, we design two energy-efficient FeFET-based TCAM designs by either reducing the matching line capacitance or eliminating the pre-charging phase to reduce the search energy, and then use Spectre to validate the circuit functionality, and compare the proposed two FeFET TCAMs with several existing representative TCAMs in terms of cell size, energy consumption and delay.","PeriodicalId":370828,"journal":{"name":"2021 International Conference on Intelligent Technology and Embedded Systems (ICITES)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115048185","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