Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9217034
Dongxu Wang, Jiawei Ren, Ying Cheng, F. Tao
For pursuing smart manufacturing, the industrial Internet platforms have got more and more attention. An industrial Internet platform can gather almost all information flows, manufacturing capacities and production tools in the form of services to achieve sharing and collaboration of resources, subjects and knowledge. The aggregation characteristic of the platform results a problem, namely the distributive services scheduling for the concurrently submitted manufacturing tasks, which hinders the further application of an industrial Internet platform. In this paper, it aims to propose an aggregated-tasks oriented manufacturing services scheduling approach toward industrial Internet platforms for improving their effectiveness and global performance. Firstly, the dual-aggregation of manufacturing services and tasks in the platform is analyzed. Then based on aggregated manufacturing services collaboration, a services-aggregation aware modeling for the aggregated tasks is presented to describe the dual-aggregation characteristic and decompose the aggregated tasks. Finally, a manufacturing services scheduling optimization model is established and solved by particle swarm optimization algorithm. The experimental result proves the effectiveness of the proposed scheduling approach for the dual-aggregation of manufacturing services and tasks on the platform.
{"title":"An aggregated-tasks oriented manufacturing services scheduling toward industrial Internet platforms","authors":"Dongxu Wang, Jiawei Ren, Ying Cheng, F. Tao","doi":"10.1109/CASE48305.2020.9217034","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9217034","url":null,"abstract":"For pursuing smart manufacturing, the industrial Internet platforms have got more and more attention. An industrial Internet platform can gather almost all information flows, manufacturing capacities and production tools in the form of services to achieve sharing and collaboration of resources, subjects and knowledge. The aggregation characteristic of the platform results a problem, namely the distributive services scheduling for the concurrently submitted manufacturing tasks, which hinders the further application of an industrial Internet platform. In this paper, it aims to propose an aggregated-tasks oriented manufacturing services scheduling approach toward industrial Internet platforms for improving their effectiveness and global performance. Firstly, the dual-aggregation of manufacturing services and tasks in the platform is analyzed. Then based on aggregated manufacturing services collaboration, a services-aggregation aware modeling for the aggregated tasks is presented to describe the dual-aggregation characteristic and decompose the aggregated tasks. Finally, a manufacturing services scheduling optimization model is established and solved by particle swarm optimization algorithm. The experimental result proves the effectiveness of the proposed scheduling approach for the dual-aggregation of manufacturing services and tasks on the platform.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131009078","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216964
David Hinwood, D. Herath, R. Goecke
Robots are fast becoming part of our daily lives, assisting us in a variety of applications. Rapid integration of autonomous agents into our routines has led to the exploration of novel research applications in robotics. One such area that has seen a recent resurgence is the manipulation of deformable objects such as textiles, an action which is simple to humans, but has been shown to be more challenging for robots. A simple fabric grasping action alone can be influenced by a multitude of parameters such as the end-effector utilised, the environment and the state of the grasping target. Previous research in designing end-effectors for deformable manipulation is discussed, arguing the need for approaching fabric manipulation from a human and hand-centric perspective to discover unique solutions. We then introduce a new approach of grasping deformable material through a novel robotic gripper design. A preliminary evaluation of the proposed end-effector’s design and ability to grasp material is presented and discussed, along with an outline of future research goals.
{"title":"Towards the Design of a Human-Inspired Gripper for Textile Manipulation","authors":"David Hinwood, D. Herath, R. Goecke","doi":"10.1109/CASE48305.2020.9216964","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216964","url":null,"abstract":"Robots are fast becoming part of our daily lives, assisting us in a variety of applications. Rapid integration of autonomous agents into our routines has led to the exploration of novel research applications in robotics. One such area that has seen a recent resurgence is the manipulation of deformable objects such as textiles, an action which is simple to humans, but has been shown to be more challenging for robots. A simple fabric grasping action alone can be influenced by a multitude of parameters such as the end-effector utilised, the environment and the state of the grasping target. Previous research in designing end-effectors for deformable manipulation is discussed, arguing the need for approaching fabric manipulation from a human and hand-centric perspective to discover unique solutions. We then introduce a new approach of grasping deformable material through a novel robotic gripper design. A preliminary evaluation of the proposed end-effector’s design and ability to grasp material is presented and discussed, along with an outline of future research goals.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124425686","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216831
Y. Kao, Sheng-Jhe Chen, Feng-Jun Li
A robotic arm is an important equipment in an automated production line. The reducer in the robot arm is one of its important components but with the highest failure rate. The reducer is a complex system including input shaft, output shaft, gears and bearings, etc. When the reducer starts to be damaged, performance of the robotic arm will be affected, and even worse the system shut down and the production efficiency might be induced, to name only a few. Therefore, how to extend the useful life of the reducer has become an important issue. In general, the clamping jaws (grippers) are installed on the 6th axis in charge of the loading and unloading, which will inevitably higher the reducer failure rate than that of the other 5 axes. Therefore, this research aims at the useful life optimization of the 6th axis reducer. The machine learning algorithms were adopted to establish methodologies to find the key factors. In addition, since the movement path of the robot arm determines the life of the reducer, multiple paths with the same starting and ending position will be generated through the forward and reverse processing, and then the RMSF (Root Mean Squares of Features) values of various paths are calculated. The optimal path with the optimum useful life of the reducer will be the one with the minimum RMSF value. This study has successfully shown that significant differences exist among the various movement paths based on the healthy and abnormal data from the cooperated reducer manufacturing company. This means the developed methodology could be used as an helpful index to extend the useful life of the reducer and also to serve as the basis in futuristic predictive maintenance system.
{"title":"Study of the Usage Life for a Robotic Arm Based on Reducer Diagnosis","authors":"Y. Kao, Sheng-Jhe Chen, Feng-Jun Li","doi":"10.1109/CASE48305.2020.9216831","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216831","url":null,"abstract":"A robotic arm is an important equipment in an automated production line. The reducer in the robot arm is one of its important components but with the highest failure rate. The reducer is a complex system including input shaft, output shaft, gears and bearings, etc. When the reducer starts to be damaged, performance of the robotic arm will be affected, and even worse the system shut down and the production efficiency might be induced, to name only a few. Therefore, how to extend the useful life of the reducer has become an important issue. In general, the clamping jaws (grippers) are installed on the 6th axis in charge of the loading and unloading, which will inevitably higher the reducer failure rate than that of the other 5 axes. Therefore, this research aims at the useful life optimization of the 6th axis reducer. The machine learning algorithms were adopted to establish methodologies to find the key factors. In addition, since the movement path of the robot arm determines the life of the reducer, multiple paths with the same starting and ending position will be generated through the forward and reverse processing, and then the RMSF (Root Mean Squares of Features) values of various paths are calculated. The optimal path with the optimum useful life of the reducer will be the one with the minimum RMSF value. This study has successfully shown that significant differences exist among the various movement paths based on the healthy and abnormal data from the cooperated reducer manufacturing company. This means the developed methodology could be used as an helpful index to extend the useful life of the reducer and also to serve as the basis in futuristic predictive maintenance system.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125904464","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216791
Chen He, B. Dalmas, Xiaolan Xie
Unplanned readmissions to the emergency department (ED) have been identified as a key factor resulting in a negative effect on subjects’ health and healthcare resource scheduling. Often, the readmission prediction is modeled as a binary classification problem whose objective is to predict if a subject will be readmitted or not. Nevertheless, it ignores the uncertainty nature of readmission and usually results in poor prediction quality. In this paper, the problem is defined as a chance-constrained medical intervention rationing problem: at-risk subjects are targeted and given supplemental medical interventions, while the remaining subjects are treated as outpatients. The objective is to profile subjects, identify at-risk subjects, and select specific groups of subjects to which additional medical interventions are recommended, while addressing the unknown number of at-risk subjects and the unknown subjects’ readmission risks. We propose a white-box approach named Alternating Clustering and Bayesian Inference (ACBI) and investigate its efficiency on a real-life readmission data set. Results are promising and show the method could lead up to a 34.42% reduction in readmission rate.
{"title":"ACBI: An Alternating Clustering and Bayesian Inference approach for optimizing medical intervention budget under chance constraints","authors":"Chen He, B. Dalmas, Xiaolan Xie","doi":"10.1109/CASE48305.2020.9216791","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216791","url":null,"abstract":"Unplanned readmissions to the emergency department (ED) have been identified as a key factor resulting in a negative effect on subjects’ health and healthcare resource scheduling. Often, the readmission prediction is modeled as a binary classification problem whose objective is to predict if a subject will be readmitted or not. Nevertheless, it ignores the uncertainty nature of readmission and usually results in poor prediction quality. In this paper, the problem is defined as a chance-constrained medical intervention rationing problem: at-risk subjects are targeted and given supplemental medical interventions, while the remaining subjects are treated as outpatients. The objective is to profile subjects, identify at-risk subjects, and select specific groups of subjects to which additional medical interventions are recommended, while addressing the unknown number of at-risk subjects and the unknown subjects’ readmission risks. We propose a white-box approach named Alternating Clustering and Bayesian Inference (ACBI) and investigate its efficiency on a real-life readmission data set. Results are promising and show the method could lead up to a 34.42% reduction in readmission rate.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114404137","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9217045
Asma Gasmi, V. Augusto, Paul-Antoine Beaudet, J. Faucheu, C. Morin, Xavier Serpaggi, F. Vassel
Analysis of sleep is important in order to detect health issues and try to prevent them. In particular, sleep dysfunctions may be the first signs of cognitive frailties for elderly persons. The polysomnography (PSG) is considered the golden standard to perform a comprehensive sleep analysis, as it is based on several sensors placements. However, for longitudinal study of sleep that is required to prevent frailty for elderly persons, such medical equipment is not suitable since it is very invasive. Recent technological advances in sensors allow to gather data with a good precision with less intrusive equipment. The main objective of this study consists in developing a new algorithmic approach to analyse sleep using data from low intrusive sensors. In this study we focus on sleep phase detection, i.e. wake, Non-Rapid Eye Movement (NREM) and Rapid Eye Movement (REM). We consider the following sources of data: heart beat rate, as well as user data such as gender, age, etc. The problem is considered as a supervised classification machine learning problem. We propose a benchmark of several machine learning algorithms and compare their performances against the medical gold standard, the PSG. To do so, we use a data-set collected from a published clinical trial. Support Vector Machine (SVM) algorithm globally outperforms all other methods with a 76.5% agreement with the PSG. As a direct perspective of this study, we plan to add other sources of data using custom sensors to improve the performance of the prediction.Sleep stages, machine learning, supervised classification, sleep architecture, polysomnography
{"title":"Sleep stages classification using cardio-respiratory variables","authors":"Asma Gasmi, V. Augusto, Paul-Antoine Beaudet, J. Faucheu, C. Morin, Xavier Serpaggi, F. Vassel","doi":"10.1109/CASE48305.2020.9217045","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9217045","url":null,"abstract":"Analysis of sleep is important in order to detect health issues and try to prevent them. In particular, sleep dysfunctions may be the first signs of cognitive frailties for elderly persons. The polysomnography (PSG) is considered the golden standard to perform a comprehensive sleep analysis, as it is based on several sensors placements. However, for longitudinal study of sleep that is required to prevent frailty for elderly persons, such medical equipment is not suitable since it is very invasive. Recent technological advances in sensors allow to gather data with a good precision with less intrusive equipment. The main objective of this study consists in developing a new algorithmic approach to analyse sleep using data from low intrusive sensors. In this study we focus on sleep phase detection, i.e. wake, Non-Rapid Eye Movement (NREM) and Rapid Eye Movement (REM). We consider the following sources of data: heart beat rate, as well as user data such as gender, age, etc. The problem is considered as a supervised classification machine learning problem. We propose a benchmark of several machine learning algorithms and compare their performances against the medical gold standard, the PSG. To do so, we use a data-set collected from a published clinical trial. Support Vector Machine (SVM) algorithm globally outperforms all other methods with a 76.5% agreement with the PSG. As a direct perspective of this study, we plan to add other sources of data using custom sensors to improve the performance of the prediction.Sleep stages, machine learning, supervised classification, sleep architecture, polysomnography","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126637888","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9217024
Liping Feng, Meng Zhou, Biao Hu
Motion planning with the multi-robot system is complex and challenging in a dynamic environment with unknown obstacles. This paper proposes a two-stage motion planning strategy to guarantee the formation of multi-robot when they pass through some obstacle areas. First, the multi-robot formation is constructed by a leader-follower strategy. Then a two-level algorithmic framework is introduced to optimize both global and local path planning. A Self-adaptive Dynamic Window Algorithm (SDWA) is proposed to dynamically search both global and local optimal path, which aims to balance the speed and safety of the multi-robot system. In SDWA, the weight parameter of the objective function is adaptively controlled based on the distance between the multi-robot system and obstacles. Finally, results of experiments demonstrate convincingly that the SDWA can avoid dynamic obstacles by switching between global path planning and local path planning modes, which makes the trajectory more reasonable in a complex environment, and ensure the smooth path and safety of multirobot formation.
{"title":"A Hybrid Motion Planning Algorithm for Multi-robot Formation in a Dynamic Environment","authors":"Liping Feng, Meng Zhou, Biao Hu","doi":"10.1109/CASE48305.2020.9217024","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9217024","url":null,"abstract":"Motion planning with the multi-robot system is complex and challenging in a dynamic environment with unknown obstacles. This paper proposes a two-stage motion planning strategy to guarantee the formation of multi-robot when they pass through some obstacle areas. First, the multi-robot formation is constructed by a leader-follower strategy. Then a two-level algorithmic framework is introduced to optimize both global and local path planning. A Self-adaptive Dynamic Window Algorithm (SDWA) is proposed to dynamically search both global and local optimal path, which aims to balance the speed and safety of the multi-robot system. In SDWA, the weight parameter of the objective function is adaptively controlled based on the distance between the multi-robot system and obstacles. Finally, results of experiments demonstrate convincingly that the SDWA can avoid dynamic obstacles by switching between global path planning and local path planning modes, which makes the trajectory more reasonable in a complex environment, and ensure the smooth path and safety of multirobot formation.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127981454","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216805
Chenxi Hu, Hongxia Yuan, Jun Zhang, Jielu Yan, Tianlu Gao, Hang Zhao, Jieyu Lin, Peng Zhou
Considering that the economic indicators have a great impact on electricity consumption, social sensors are used to capture massive social signals and intelligent sensors are used to collect electricity data based on the cyber-physical-social system(CPSS) theoretical framework. In this paper, an economic-power cyber-physical-social system is built to integrate the data from different spaces. In cyberspace, the data will be fused, normalized before training, then a deep belief network(DBN) model is established to perform data mining and realize mid-long term electricity consumption forecasting. In the DBN training process, economic-power data from 31 provinces are used. DBN can achieve feature extraction automatically without variable selection steps and can achieve higher forecasting accuracy than traditional methods. The application of CPSS in electricity consumption forecasting has expanded the data border of physical power system researches and can provide a reference for subsequent multi-space data modeling.
{"title":"Mid-Long Term Electricity Consumption Forecasting Analysis Based on Cyber-Physical-Social System Architecture","authors":"Chenxi Hu, Hongxia Yuan, Jun Zhang, Jielu Yan, Tianlu Gao, Hang Zhao, Jieyu Lin, Peng Zhou","doi":"10.1109/CASE48305.2020.9216805","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216805","url":null,"abstract":"Considering that the economic indicators have a great impact on electricity consumption, social sensors are used to capture massive social signals and intelligent sensors are used to collect electricity data based on the cyber-physical-social system(CPSS) theoretical framework. In this paper, an economic-power cyber-physical-social system is built to integrate the data from different spaces. In cyberspace, the data will be fused, normalized before training, then a deep belief network(DBN) model is established to perform data mining and realize mid-long term electricity consumption forecasting. In the DBN training process, economic-power data from 31 provinces are used. DBN can achieve feature extraction automatically without variable selection steps and can achieve higher forecasting accuracy than traditional methods. The application of CPSS in electricity consumption forecasting has expanded the data border of physical power system researches and can provide a reference for subsequent multi-space data modeling.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115702070","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216997
Jinchao Fu, Chunrong Pan, Wenqing Xiong
With the trends of larger wafer diameters and smaller lot sizes, cluster tools are forced to work during long transient processes. In order to improve productivity, there has growing concern about the scheduling problem of cluster tools with concurrent processing of multiple wafer types. Since there is no intermediate buffer between process modules, the scheduling of cluster tools is more complicated than the traditional mixed assembly line. This paper reviews the modeling and scheduling of cluster tools with wafer residency time constraints, activity time variation, process module failure and multi-cluster tools. Then, in order to find the off-line and dynamic method to solve the scheduling problem of concurrent processing of multiple wafer types, intelligent search algorithm and reinforcement learning algorithm is the future research directions, respectively.
{"title":"Intelligent Scheduling Methods for Challenges of Cluster Tools with Concurrent Processing of Multiple Wafer Types*","authors":"Jinchao Fu, Chunrong Pan, Wenqing Xiong","doi":"10.1109/CASE48305.2020.9216997","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216997","url":null,"abstract":"With the trends of larger wafer diameters and smaller lot sizes, cluster tools are forced to work during long transient processes. In order to improve productivity, there has growing concern about the scheduling problem of cluster tools with concurrent processing of multiple wafer types. Since there is no intermediate buffer between process modules, the scheduling of cluster tools is more complicated than the traditional mixed assembly line. This paper reviews the modeling and scheduling of cluster tools with wafer residency time constraints, activity time variation, process module failure and multi-cluster tools. Then, in order to find the off-line and dynamic method to solve the scheduling problem of concurrent processing of multiple wafer types, intelligent search algorithm and reinforcement learning algorithm is the future research directions, respectively.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115610648","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216853
Qianyi Zhang, Lei Zhou, Yingli Zhao, Rui Cao, Jingtai Liu
How to plan a path in big and complex environments has always been a key issue. In this paper, we proposed Global Sampling and Local Search Trees(GSLST), a parallel planning algorithm. It uses Connect-RRT to grow two global sampling trees in the entire map while using Closed-Operation and Jump Point Search(JPS) to extract narrow paths and create Local Dynamic Link Trees. GSLST shows both the fastness of the sampling-based algorithm for planning in a wide range of environment and the completeness of the search based algorithm for planning in complex environment with narrow paths. The simulations demonstrate that GSLST is faster than that of sampling-based and search-based algorithms in big complex environments.
{"title":"A Parallel Algorithm Combining Improved-Connect-RRT and JPS with Closed-operation","authors":"Qianyi Zhang, Lei Zhou, Yingli Zhao, Rui Cao, Jingtai Liu","doi":"10.1109/CASE48305.2020.9216853","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216853","url":null,"abstract":"How to plan a path in big and complex environments has always been a key issue. In this paper, we proposed Global Sampling and Local Search Trees(GSLST), a parallel planning algorithm. It uses Connect-RRT to grow two global sampling trees in the entire map while using Closed-Operation and Jump Point Search(JPS) to extract narrow paths and create Local Dynamic Link Trees. GSLST shows both the fastness of the sampling-based algorithm for planning in a wide range of environment and the completeness of the search based algorithm for planning in complex environment with narrow paths. The simulations demonstrate that GSLST is faster than that of sampling-based and search-based algorithms in big complex environments.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127242731","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 : 2020-08-01DOI: 10.1109/CASE48305.2020.9216873
Tarik Yigit, Feng Han, E. Rankins, J. Yi, K. McKeever, K. Malinowski
Objective, automated early lameness detection plays an important role for animal well-being. The work in this paper uses horse locomotion data collected by wearable inertial measurement units, extracts gait cycle routines and constructs a multi-layer classifier for horse lameness detection, identification, and evaluation. Multi-layer classifier (MLC) is based on support vector machine and K-Nearest-Neighbors methods. Each layer is independently designed and works as a binary classifier. Horse gait classification and limb lameness detection and evaluation are then handled by each layer successively. Experiment results show that the MLC achieves 94 % detection accuracy and also generates superior performance than a deep convolutional neural network-based multiclass classifier in terms of various assessment criteria.
{"title":"Wearable IMU-based Early Limb Lameness Detection for Horses using Multi-Layer Classifiers","authors":"Tarik Yigit, Feng Han, E. Rankins, J. Yi, K. McKeever, K. Malinowski","doi":"10.1109/CASE48305.2020.9216873","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216873","url":null,"abstract":"Objective, automated early lameness detection plays an important role for animal well-being. The work in this paper uses horse locomotion data collected by wearable inertial measurement units, extracts gait cycle routines and constructs a multi-layer classifier for horse lameness detection, identification, and evaluation. Multi-layer classifier (MLC) is based on support vector machine and K-Nearest-Neighbors methods. Each layer is independently designed and works as a binary classifier. Horse gait classification and limb lameness detection and evaluation are then handled by each layer successively. Experiment results show that the MLC achieves 94 % detection accuracy and also generates superior performance than a deep convolutional neural network-based multiclass classifier in terms of various assessment criteria.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127582674","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：