Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990171
M. Mallick, Steven L. Rubin, Yun Zhu
We discuss if track labels are needed in a tracker using physics-based reasoning. Using the concept of de Broglie wavelength, we show that it is possible to label macroscopic objects and their trajectories, whereas it is not possible to assign labels to microscopic objects. A number of cases are examined to show the difficulty of not using track labels in multitarget tracking. We analyze a simple case of two identical macroscopic and microscopic objects to show that indistinguishable macroscopic objects do not exist. Use of track labels in real-time and tracker evaluation is also discussed.
{"title":"Track Label and Classical and Quantum Probability Densities","authors":"M. Mallick, Steven L. Rubin, Yun Zhu","doi":"10.1109/ICCAIS56082.2022.9990171","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990171","url":null,"abstract":"We discuss if track labels are needed in a tracker using physics-based reasoning. Using the concept of de Broglie wavelength, we show that it is possible to label macroscopic objects and their trajectories, whereas it is not possible to assign labels to microscopic objects. A number of cases are examined to show the difficulty of not using track labels in multitarget tracking. We analyze a simple case of two identical macroscopic and microscopic objects to show that indistinguishable macroscopic objects do not exist. Use of track labels in real-time and tracker evaluation is also discussed.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116313592","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990157
Zonglin Hou, Linfeng Xu, Bingyang Fu
Most human activities and object motions in the real world are intention-driven. Taking advantage of the intention information (e.g., goals and destinations) can produce better motion models and more accurate trajectory prediction in general. Again, compared with the traditional state space models, Gaussian process (GP) based models have more capability to de-scribe complicated motions. This paper proposes a GP regression based approach to model learning and trajectory prediction for intention-driven motions. At first, the conditional kernels are devised by incorporating the known motion intent, from which it follows that the GP models of intention-driven motions are constructed. Then, the times at which the destination is reached, as key parameters for GP models with conditional kernels, are learned online based on the data stream. Finally, in the context of missile tracking, numerical simulations are provided to show the effectiveness of the proposed GP models and the self-learning ability of their hyper parameters for intention-driven motions.
{"title":"Spatio-Temporal GP Model Learning for Intention-Driven Motions","authors":"Zonglin Hou, Linfeng Xu, Bingyang Fu","doi":"10.1109/ICCAIS56082.2022.9990157","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990157","url":null,"abstract":"Most human activities and object motions in the real world are intention-driven. Taking advantage of the intention information (e.g., goals and destinations) can produce better motion models and more accurate trajectory prediction in general. Again, compared with the traditional state space models, Gaussian process (GP) based models have more capability to de-scribe complicated motions. This paper proposes a GP regression based approach to model learning and trajectory prediction for intention-driven motions. At first, the conditional kernels are devised by incorporating the known motion intent, from which it follows that the GP models of intention-driven motions are constructed. Then, the times at which the destination is reached, as key parameters for GP models with conditional kernels, are learned online based on the data stream. Finally, in the context of missile tracking, numerical simulations are provided to show the effectiveness of the proposed GP models and the self-learning ability of their hyper parameters for intention-driven motions.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131804835","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990087
Yue Xin, Yan Song, Tiancheng Li
Existing target trackers, as well as the corresponding evaluation metrics, are based on discrete-time point-state estimates. An emerging approach to target tracking is to estimate the continuous-time trajectories that are given by a state function of time and contain more information than discrete-time point estimates, for which a proper metric is still missing. In this study, a fundamental metric called the integral multi-target trajectory assignment (IMTA) distance that is suitable for evaluating the continuous-time curve trajectories is proposed. Based on optimal matching between the estimated and ground-truth trajectories, the localization distance consists of the integral for the time-consistent trajectory parts and the penalty for the trajectory time-inconsistent parts. Furthermore, the cardinality error is also defined to account for the false alarm and mis-detection in the level of a whole trajectory. Theoretical analysis and numerical examples are presented to demonstrate the performance of the proposed metric.
{"title":"A Metric for Multi-Target Continuous-Time Trajectory Evaluation","authors":"Yue Xin, Yan Song, Tiancheng Li","doi":"10.1109/ICCAIS56082.2022.9990087","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990087","url":null,"abstract":"Existing target trackers, as well as the corresponding evaluation metrics, are based on discrete-time point-state estimates. An emerging approach to target tracking is to estimate the continuous-time trajectories that are given by a state function of time and contain more information than discrete-time point estimates, for which a proper metric is still missing. In this study, a fundamental metric called the integral multi-target trajectory assignment (IMTA) distance that is suitable for evaluating the continuous-time curve trajectories is proposed. Based on optimal matching between the estimated and ground-truth trajectories, the localization distance consists of the integral for the time-consistent trajectory parts and the penalty for the trajectory time-inconsistent parts. Furthermore, the cardinality error is also defined to account for the false alarm and mis-detection in the level of a whole trajectory. Theoretical analysis and numerical examples are presented to demonstrate the performance of the proposed metric.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129843706","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990167
Changbeom Shim, Ji Youn Lee, D. Moratuwage, D. Kim, Y. Chung
Multi-Object Tracking (MOT) is concerned with estimating trajectories from sensor measurements. MOT using the Random Finite Set (RFS) framework has been gaining popularity due to its rigorous mathematical foundation and versatility in applications. Notably, large-scale trajectory estimation can be successfully achieved by the label-partitioned Generalized Labeled Multi-Bernoulli (GLMB) filter framework. In this work, we propose an efficient method for grouping object labels in scalable GLMB filtering. Specifically, the label grouping problem for parallel computation is generalized by considering the intersection of predicted measurements, i.e., uncertainty regions. The proposed approach provides a flexible criterion to construct label graphs, whereupon a large number of object labels can be rapidly determined whether to be grouped or not. We demonstrate the performance of our method via large-scale data sets.
{"title":"Generalized Label Grouping for Scalable Trajectory Estimation","authors":"Changbeom Shim, Ji Youn Lee, D. Moratuwage, D. Kim, Y. Chung","doi":"10.1109/ICCAIS56082.2022.9990167","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990167","url":null,"abstract":"Multi-Object Tracking (MOT) is concerned with estimating trajectories from sensor measurements. MOT using the Random Finite Set (RFS) framework has been gaining popularity due to its rigorous mathematical foundation and versatility in applications. Notably, large-scale trajectory estimation can be successfully achieved by the label-partitioned Generalized Labeled Multi-Bernoulli (GLMB) filter framework. In this work, we propose an efficient method for grouping object labels in scalable GLMB filtering. Specifically, the label grouping problem for parallel computation is generalized by considering the intersection of predicted measurements, i.e., uncertainty regions. The proposed approach provides a flexible criterion to construct label graphs, whereupon a large number of object labels can be rapidly determined whether to be grouped or not. We demonstrate the performance of our method via large-scale data sets.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134576025","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990410
D. Moratuwage, Yuthika Punchihewa, Ji Youn Lee
The recent multi-sensor Generalized Labeled Multi-Bernoulli (GLMB) is an efficient analytic implementation to the multi-sensor multi-object state estimation problem. The multi-sensor multi-object posterior is recursively propagated using the multi-sensor multi-object filtering density, by updating it with multi-sensor measurements at each time step. The measurement update step requires solving a series of NP-hard multidimensional assignment problems. In this paper, we introduce a faster implementation of this algorithm by an intuitive approximation, and combine that with the Gibbs sampler based truncation approach to produce an efficient multi-sensor multi-object estimation solution suitable for practical applications.
{"title":"A Faster implementation of Multi-sensor Generalized Labeled Multi-Bernoulli Filter","authors":"D. Moratuwage, Yuthika Punchihewa, Ji Youn Lee","doi":"10.1109/ICCAIS56082.2022.9990410","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990410","url":null,"abstract":"The recent multi-sensor Generalized Labeled Multi-Bernoulli (GLMB) is an efficient analytic implementation to the multi-sensor multi-object state estimation problem. The multi-sensor multi-object posterior is recursively propagated using the multi-sensor multi-object filtering density, by updating it with multi-sensor measurements at each time step. The measurement update step requires solving a series of NP-hard multidimensional assignment problems. In this paper, we introduce a faster implementation of this algorithm by an intuitive approximation, and combine that with the Gibbs sampler based truncation approach to produce an efficient multi-sensor multi-object estimation solution suitable for practical applications.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"269 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133577439","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990535
Wenbo Zhu, H. Tuan, Y. Fang
The paper considers the jointly 2D beamforming design for multi-user (MU) full-dimensional (3D) massive multiple-input multiple output (m-MIMO) systems to maximize the geometric mean of users’ rate (GM-rate), which yields not only users’ fairness in terms of their rate but also rational transmit powers at antennas. We develop a low-complex algorithms, which iterates closed-form expressions for computational solutions of the GM-rate maximization problem. The provided simulations confirm the viability of our development.
{"title":"2D Beamforming for 3D Full-Dimensional Massive MIMO","authors":"Wenbo Zhu, H. Tuan, Y. Fang","doi":"10.1109/ICCAIS56082.2022.9990535","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990535","url":null,"abstract":"The paper considers the jointly 2D beamforming design for multi-user (MU) full-dimensional (3D) massive multiple-input multiple output (m-MIMO) systems to maximize the geometric mean of users’ rate (GM-rate), which yields not only users’ fairness in terms of their rate but also rational transmit powers at antennas. We develop a low-complex algorithms, which iterates closed-form expressions for computational solutions of the GM-rate maximization problem. The provided simulations confirm the viability of our development.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133391315","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990527
C. Vorakulpipat, Ekkachan Rattanalerdnusorn, Sasakorn Pichetjamroen
The objective of this paper is to introduce a scheme of comprehensive-factor authentication in edge computing, focusing on a case study of time attendance in smart environments. This authentication scheme deploys all possible factors to maximize security while maintaining usability at a specific smart context. The factors used include three classic elements: something you know, something you have, and something you are, plus an additional location factor. The usability issue involves the ability to reduce time used and to minimize the human actions required throughout the authentication process. The results show that all factors should be authenticated at once in background, and a user can successfully complete the authentication process by performing one or two actions simultaneously. Since user role in a smart environment can be more complicated than roles in other smart offices, role classification at an early stage is highly recommended. The case study reveals that the same setting can require varying levels of security and usability for each user.
{"title":"Comprehensive-Factor Authentication in Edge Devices in Smart Environments: A Case Study","authors":"C. Vorakulpipat, Ekkachan Rattanalerdnusorn, Sasakorn Pichetjamroen","doi":"10.1109/ICCAIS56082.2022.9990527","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990527","url":null,"abstract":"The objective of this paper is to introduce a scheme of comprehensive-factor authentication in edge computing, focusing on a case study of time attendance in smart environments. This authentication scheme deploys all possible factors to maximize security while maintaining usability at a specific smart context. The factors used include three classic elements: something you know, something you have, and something you are, plus an additional location factor. The usability issue involves the ability to reduce time used and to minimize the human actions required throughout the authentication process. The results show that all factors should be authenticated at once in background, and a user can successfully complete the authentication process by performing one or two actions simultaneously. Since user role in a smart environment can be more complicated than roles in other smart offices, role classification at an early stage is highly recommended. The case study reveals that the same setting can require varying levels of security and usability for each user.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133464862","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990462
Linh Hoai Tran, Thanh Duc Nguyen
This paper will present a new solution for machine fault detection based on the vibration signals. The solution will used in improved fuzzy Gustaffson – Kessel clustering method to generate the classification data centers characteristic for different states of the machines. The Gustaffson – Kessel method offers a modified euclidian distance, which allows betters separation borders between data clusters. The model will be tested with the vibration signals collected from the standard CASE Bearing Data Sets to show the high accuracy of the results.
{"title":"Machine Fault Detection Using Vibration Signals and Improved Fuzzy Clustering Algorithm","authors":"Linh Hoai Tran, Thanh Duc Nguyen","doi":"10.1109/ICCAIS56082.2022.9990462","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990462","url":null,"abstract":"This paper will present a new solution for machine fault detection based on the vibration signals. The solution will used in improved fuzzy Gustaffson – Kessel clustering method to generate the classification data centers characteristic for different states of the machines. The Gustaffson – Kessel method offers a modified euclidian distance, which allows betters separation borders between data clusters. The model will be tested with the vibration signals collected from the standard CASE Bearing Data Sets to show the high accuracy of the results.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133339834","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990295
Jianguo Liu, Xiyuan Chen, Junwei Wang
This paper proposes an adaptively robust unscented Kalman filter (ARUKF) for the rotation micro-electro-mechanical system based strapdown inertial navigation system (MINS) to achieve fast in-motion initial alignment in the presence of large misalignment angles. First, UKF is utilized to address nonlinearity issues resulting from large misalignment angles. Second, the strong tracking strategy is implemented to robustly compensate for dynamic model errors during the transition phase. The variational Bayesian is then applied in the steady state to adaptively estimate the time-varying measurement noises. The proposed method speeds up convergence during the transition phase and improves convergence precision during the steady phase. In conclusion, the turntable experiments verify the validity of the proposed method.
{"title":"An Improved Adaptive and Robust Initial Alignment Method for Rotation MEMS-based SINS","authors":"Jianguo Liu, Xiyuan Chen, Junwei Wang","doi":"10.1109/ICCAIS56082.2022.9990295","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990295","url":null,"abstract":"This paper proposes an adaptively robust unscented Kalman filter (ARUKF) for the rotation micro-electro-mechanical system based strapdown inertial navigation system (MINS) to achieve fast in-motion initial alignment in the presence of large misalignment angles. First, UKF is utilized to address nonlinearity issues resulting from large misalignment angles. Second, the strong tracking strategy is implemented to robustly compensate for dynamic model errors during the transition phase. The variational Bayesian is then applied in the steady state to adaptively estimate the time-varying measurement noises. The proposed method speeds up convergence during the transition phase and improves convergence precision during the steady phase. In conclusion, the turntable experiments verify the validity of the proposed method.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125981568","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}
Pub Date : 2022-11-21DOI: 10.1109/ICCAIS56082.2022.9990092
Liwen Ma, Weifeng Liu
Keyphrase extraction aims to identify phrases in documents that contain core content. However, existing unsupervised keyphrase extraction models are limited to focusing on a single feature leading to biased results. In response to the above problems, it evaluates keyphrase scores through multiple features of semantic importance, topic diversity, and position features. Firstly, it masked the candidate keyphrase from a document and the Manhattan distance between the mask document and the original document is calculated as the semantic importance feature. Secondly, it calculated the topic-word distribution of candidate keyphrases as topic diversity, and the position features are calculated. Finally, the phrase importance score is calculated by integrating the three sub-models. Experiments are conducted on three academic datasets and compared with six state-of-the-art baseline models, outperforming existing methods. The results show that evaluating phrase importance from multiple features significantly improves the performance of extracting keyphrases.
{"title":"A Keyphrase Extraction Method Based on Multi-feature Evaluation and Mask Mechanism","authors":"Liwen Ma, Weifeng Liu","doi":"10.1109/ICCAIS56082.2022.9990092","DOIUrl":"https://doi.org/10.1109/ICCAIS56082.2022.9990092","url":null,"abstract":"Keyphrase extraction aims to identify phrases in documents that contain core content. However, existing unsupervised keyphrase extraction models are limited to focusing on a single feature leading to biased results. In response to the above problems, it evaluates keyphrase scores through multiple features of semantic importance, topic diversity, and position features. Firstly, it masked the candidate keyphrase from a document and the Manhattan distance between the mask document and the original document is calculated as the semantic importance feature. Secondly, it calculated the topic-word distribution of candidate keyphrases as topic diversity, and the position features are calculated. Finally, the phrase importance score is calculated by integrating the three sub-models. Experiments are conducted on three academic datasets and compared with six state-of-the-art baseline models, outperforming existing methods. The results show that evaluating phrase importance from multiple features significantly improves the performance of extracting keyphrases.","PeriodicalId":273404,"journal":{"name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125086495","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：