Pub Date : 2018-06-25DOI: 10.1109/CoDIT.2018.8394881
A. Guel-Cortez, C. Méndez‐Barrios, Victor Manuel Ramírez, J. G. Romero, E. González-Galván, Jully Kado-Mercado
In this paper we present a simple procedure to design fractional-PD controllers for Single-Input-Single-Output-Linear Time Invariant (SISO-LTI) systems with constant time-delay. More precisely, based on a geometric approach, we present a methodology not only to design a stabilizing controller, but also to provide practical guidelines to design non-fragile PD controllers. Finally, in order to illustrate the simplicity of the proposed approach as well as the efficiency of the PD controller in a realistic scenario, we consider an experimental setup consisting of controlling a teleoperated system using two Phantom Omni haptic devices.
{"title":"Fractional—PD controllers design for LTI-systems with time-delay. A geometric approach","authors":"A. Guel-Cortez, C. Méndez‐Barrios, Victor Manuel Ramírez, J. G. Romero, E. González-Galván, Jully Kado-Mercado","doi":"10.1109/CoDIT.2018.8394881","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394881","url":null,"abstract":"In this paper we present a simple procedure to design fractional-PD controllers for Single-Input-Single-Output-Linear Time Invariant (SISO-LTI) systems with constant time-delay. More precisely, based on a geometric approach, we present a methodology not only to design a stabilizing controller, but also to provide practical guidelines to design non-fragile PD controllers. Finally, in order to illustrate the simplicity of the proposed approach as well as the efficiency of the PD controller in a realistic scenario, we consider an experimental setup consisting of controlling a teleoperated system using two Phantom Omni haptic devices.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130336691","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 : 2018-06-22DOI: 10.1109/CoDIT.2018.8394924
Sotiris Papatheodorou, M. Smyrnakis, H. Tembine, A. Tzes
The energy-efficient trip allocation of mobile robots employing differential drives for data retrieval from stationary sensor locations is the scope of this article. Given a team of robots and a set of targets (wireless sensor nodes), the planner computes all possible tours that each robot can make if it needs to visit a part of or the entire set of targets. Each segment of the tour relies on a minimum energy path planning algorithm. After the computation of all possible tour-segments, a utility function penalizing the overall energy consumption is formed. Rather than relying on the NP-hard Mobile Element Scheduling (MES) MILP problem, an approach using elements from game theory is employed. The suggested approach converges fast for most practical reasons thus allowing its utilization in near real time applications. Simulations are offered to highlight the efficiency of the developed algorithm.
{"title":"Path Planning and Task Assignment for Data Retrieval from Wireless Sensor Nodes Relying on Game-Theoretic Learning","authors":"Sotiris Papatheodorou, M. Smyrnakis, H. Tembine, A. Tzes","doi":"10.1109/CoDIT.2018.8394924","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394924","url":null,"abstract":"The energy-efficient trip allocation of mobile robots employing differential drives for data retrieval from stationary sensor locations is the scope of this article. Given a team of robots and a set of targets (wireless sensor nodes), the planner computes all possible tours that each robot can make if it needs to visit a part of or the entire set of targets. Each segment of the tour relies on a minimum energy path planning algorithm. After the computation of all possible tour-segments, a utility function penalizing the overall energy consumption is formed. Rather than relying on the NP-hard Mobile Element Scheduling (MES) MILP problem, an approach using elements from game theory is employed. The suggested approach converges fast for most practical reasons thus allowing its utilization in near real time applications. Simulations are offered to highlight the efficiency of the developed algorithm.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124745007","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 : 2018-06-22DOI: 10.1109/CoDIT.2018.8394776
Appolinaire C. Etoundi, J. Chong, A. Jafari
The process of designing bio-inspired knee joint for prosthetics/exoskeletons has been a challenging issue due to the complicated relationships between the performance criteria and the link lengths of the design space, or workspace in the case of manipulators. This paper address this issue by presenting numerical analysis and design methodology that have been used for mapping the design space of a bio-inspired knee joint. Four aspects of performance are modelled: peak mechanical advantage, RMS (root mean square) mechanical advantage, RMS sliding ratio, and range of movement. The performance of the joint is dependent on the shape of the condylar surfaces and the geometry of the four-bar mechanism. The results of the complete map for the design space are characterized by the mechanical advantage, sliding ratio and the range of movement that mimics the human knee joint with the movement of rolling and sliding between the condylar surfaces of the femur and tibia. Therefore, several design charts are proposed accordingly to facilitate the selection of designers of the optimal configuration adapted to their specific application. Based on our numerical analysis performed on the proposed bio-inspired knee joint model, the performance maps demonstrated that there is an estimated reduction of 30% for the actuator required force.
{"title":"Modelling of a Bio-Inspired Knee Joint and Design of an Energy Saving Exoskeleton Based on Performance Maps Optimisation for Condylar Knee Prosthetics","authors":"Appolinaire C. Etoundi, J. Chong, A. Jafari","doi":"10.1109/CoDIT.2018.8394776","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394776","url":null,"abstract":"The process of designing bio-inspired knee joint for prosthetics/exoskeletons has been a challenging issue due to the complicated relationships between the performance criteria and the link lengths of the design space, or workspace in the case of manipulators. This paper address this issue by presenting numerical analysis and design methodology that have been used for mapping the design space of a bio-inspired knee joint. Four aspects of performance are modelled: peak mechanical advantage, RMS (root mean square) mechanical advantage, RMS sliding ratio, and range of movement. The performance of the joint is dependent on the shape of the condylar surfaces and the geometry of the four-bar mechanism. The results of the complete map for the design space are characterized by the mechanical advantage, sliding ratio and the range of movement that mimics the human knee joint with the movement of rolling and sliding between the condylar surfaces of the femur and tibia. Therefore, several design charts are proposed accordingly to facilitate the selection of designers of the optimal configuration adapted to their specific application. Based on our numerical analysis performed on the proposed bio-inspired knee joint model, the performance maps demonstrated that there is an estimated reduction of 30% for the actuator required force.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121074504","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 : 2018-04-13DOI: 10.1109/CoDIT.2018.8394819
E. Jantunen, Jaime Campos, Pankaj Sharma, M. McKay
The current paper reviews existent data mining and big data analytics open source solutions. In the area of industrial maintenance engineering, the algorithms, which are part of these solutions, have started to be studied and introduced into the domain. In addition, the interest in big data and analytics have increased in several areas because of the increased amount of data produced as well as a remarkable speed attained and its variation, i.e. the so-called 3 V's (Volume, Velocity, and Variety). The companies and organizations have seen the need to optimize their decision-making processes with the support of data mining and big data analytics. The development of this kind of solutions might be a long process and for some companies something that is not within their reach for many reasons. It is, therefore, important to understand the characteristics of the open source solutions. Consequently, the authors use a framework to organize their findings. Thus, the framework used is called the knowledge discovery in databases (KDD) process for extracting useful knowledge from volumes of data. The authors suggest a modified KDD framework to be able to understand if the respective data mining/big data solutions are adequate and suitable to use in the domain of industrial maintenance engineering.
{"title":"Open Source Analytics Solutions for Maintenance","authors":"E. Jantunen, Jaime Campos, Pankaj Sharma, M. McKay","doi":"10.1109/CoDIT.2018.8394819","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394819","url":null,"abstract":"The current paper reviews existent data mining and big data analytics open source solutions. In the area of industrial maintenance engineering, the algorithms, which are part of these solutions, have started to be studied and introduced into the domain. In addition, the interest in big data and analytics have increased in several areas because of the increased amount of data produced as well as a remarkable speed attained and its variation, i.e. the so-called 3 V's (Volume, Velocity, and Variety). The companies and organizations have seen the need to optimize their decision-making processes with the support of data mining and big data analytics. The development of this kind of solutions might be a long process and for some companies something that is not within their reach for many reasons. It is, therefore, important to understand the characteristics of the open source solutions. Consequently, the authors use a framework to organize their findings. Thus, the framework used is called the knowledge discovery in databases (KDD) process for extracting useful knowledge from volumes of data. The authors suggest a modified KDD framework to be able to understand if the respective data mining/big data solutions are adequate and suitable to use in the domain of industrial maintenance engineering.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127882628","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 : 2018-04-10DOI: 10.1109/CoDIT.2018.8394926
Sharaf Eddine Kramti, Jaouher Ben Ali, L. Saidi, M. Sayadi, Eric Bechhoefer
Common mechanical failures in wind turbine generators (WTGs) result in unplanned downtime, loose of production and increase the maintenance cost. Statistical studies have shown that failures due to high-speed shaft bearing (HSSB) account for 64% of all drivetrain failures. Consequently, prognostic and health management (PHM) of WTGs aims to estimate the future state of health and predict the reaming useful life (RUL) of HSSB. This paper considers a new data-driven approach based on vibration signals. This approach extracts statistical time-domain features that reflect the behavior of the system and its degradation. Then, the extracted features are evaluated to select the most trendable condition indicators that will be considered as inputs for an Elman neural network (ENN). Moreover, this paper proposes a new ENN architecture for direct RUL estimation of HSSB validated by use of real measured data from a WTG drivetrain. The proposed method reveals accurate estimation capability even with noisy measurements and harsh conditions.
{"title":"Direct Wind Turbine Drivetrain Prognosis Approach Using Elman Neural Network","authors":"Sharaf Eddine Kramti, Jaouher Ben Ali, L. Saidi, M. Sayadi, Eric Bechhoefer","doi":"10.1109/CoDIT.2018.8394926","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394926","url":null,"abstract":"Common mechanical failures in wind turbine generators (WTGs) result in unplanned downtime, loose of production and increase the maintenance cost. Statistical studies have shown that failures due to high-speed shaft bearing (HSSB) account for 64% of all drivetrain failures. Consequently, prognostic and health management (PHM) of WTGs aims to estimate the future state of health and predict the reaming useful life (RUL) of HSSB. This paper considers a new data-driven approach based on vibration signals. This approach extracts statistical time-domain features that reflect the behavior of the system and its degradation. Then, the extracted features are evaluated to select the most trendable condition indicators that will be considered as inputs for an Elman neural network (ENN). Moreover, this paper proposes a new ENN architecture for direct RUL estimation of HSSB validated by use of real measured data from a WTG drivetrain. The proposed method reveals accurate estimation capability even with noisy measurements and harsh conditions.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114670465","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 : 2018-04-10DOI: 10.1109/CoDIT.2018.8394806
C. Cocianu, Alexandru Stan
The work reported in the paper addresses the problem of binary image registration. The proposed methodology is based on an evolution strategy (ES) developed to align two binary images. The fitness function is defined in terms of mutual information computed between the sensed image and the target image. We use various recombination schemes involving standard local/global convex and discrete crossover procedures as well as hybrid methods. The proposed hybridizations are developed based on some inner bond between the chromosome alleles. In the final stage we evaluate the similarity between the resulted image and the target using both quantitative and qualitative measures. Also, in order to experimentally establish the performances of our method, we compare it against one of the most commonly used procedures for image registration in case of rigid type perturbation, namely PAT registration. The experimental results together with some conclusive remarks regarding the quality of the proposed methodology are reported in the final part of the paper.
{"title":"New Attempts in Binary Image Registration","authors":"C. Cocianu, Alexandru Stan","doi":"10.1109/CoDIT.2018.8394806","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394806","url":null,"abstract":"The work reported in the paper addresses the problem of binary image registration. The proposed methodology is based on an evolution strategy (ES) developed to align two binary images. The fitness function is defined in terms of mutual information computed between the sensed image and the target image. We use various recombination schemes involving standard local/global convex and discrete crossover procedures as well as hybrid methods. The proposed hybridizations are developed based on some inner bond between the chromosome alleles. In the final stage we evaluate the similarity between the resulted image and the target using both quantitative and qualitative measures. Also, in order to experimentally establish the performances of our method, we compare it against one of the most commonly used procedures for image registration in case of rigid type perturbation, namely PAT registration. The experimental results together with some conclusive remarks regarding the quality of the proposed methodology are reported in the final part of the paper.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117264469","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 : 2018-04-10DOI: 10.1109/CoDIT.2018.8394804
S. Dehghan, M. Khojasteh, M. Marzband, G. Lightbody
Operators of micro-grid as privately-owned sectors try to optimally determine their energy supply strategy aiming at maximizing their profits. Smart grid infrastructures enable residential consumers to modify their electricity consumption in response to energy prices. Clearly, increasing energy tariffs have positive impacts on the operator's profit. Additionally, sensitivity of consumption to selling prices leads to demand reduction by increasing energy tariffs. Therefore, operators of micro-grids retain a tradeoff between energy tariffs and demand. This paper presents a game theoretical approach for operators of micro-grids to supply the required energy of price-sensitive clients. Additionally, the information-gap decision theory (IGDT) is used to handle the financial risk arising from the uncertain wholesale prices. Simulation results justify the performance of the proposed approach.
{"title":"Optimal Energy Providing Strategy of Micro-Grid's Operator Based on a Game Theoretical Approach","authors":"S. Dehghan, M. Khojasteh, M. Marzband, G. Lightbody","doi":"10.1109/CoDIT.2018.8394804","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394804","url":null,"abstract":"Operators of micro-grid as privately-owned sectors try to optimally determine their energy supply strategy aiming at maximizing their profits. Smart grid infrastructures enable residential consumers to modify their electricity consumption in response to energy prices. Clearly, increasing energy tariffs have positive impacts on the operator's profit. Additionally, sensitivity of consumption to selling prices leads to demand reduction by increasing energy tariffs. Therefore, operators of micro-grids retain a tradeoff between energy tariffs and demand. This paper presents a game theoretical approach for operators of micro-grids to supply the required energy of price-sensitive clients. Additionally, the information-gap decision theory (IGDT) is used to handle the financial risk arising from the uncertain wholesale prices. Simulation results justify the performance of the proposed approach.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116549148","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 : 2018-04-10DOI: 10.1109/CoDIT.2018.8394868
Qiuyu Li, Jun Yu, T. Kurihara, Shu Zhan
Micro-expression is a kind of brief facial movements which could not be controlled by nervous system. Micro-expression indicates that a person is hiding his truly emotion consciously. Micro-expression analysis has various potential applications in public security and clinical medicine. Researches are focused on the automatic micro-expression recognition, because it is hard to recognize the micro-expression by the naked eye. This research proposes a novel algorithm for automatic micro-expression analysis which combines a deep multi-task convolutional network for detecting the facial landmarks and a fused deep convolutional network for estimating the optical flow features of the micro-expression. Firstly, the deep multi-task convolutional network is employed to detect facial landmarks with the manifold related tasks for dividing the facial region. Furthermore, a fused convolutional network is applied for extracting the optical flow features from the facial regions which contain the muscle changes when the micro-expression presents. Finally, a revised optical flow feature is applied for refining the information of the features and a Support Vector Machine classifier is adopted for recognizing and detecting the micro-expression. The result of experiments on two spontaneous micro-expression database proves that our method achieved competitive performance in micro-expression recognition and detection.
{"title":"Micro-expression Analysis by Fusing Deep Convolutional Neural Network and Optical Flow","authors":"Qiuyu Li, Jun Yu, T. Kurihara, Shu Zhan","doi":"10.1109/CoDIT.2018.8394868","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394868","url":null,"abstract":"Micro-expression is a kind of brief facial movements which could not be controlled by nervous system. Micro-expression indicates that a person is hiding his truly emotion consciously. Micro-expression analysis has various potential applications in public security and clinical medicine. Researches are focused on the automatic micro-expression recognition, because it is hard to recognize the micro-expression by the naked eye. This research proposes a novel algorithm for automatic micro-expression analysis which combines a deep multi-task convolutional network for detecting the facial landmarks and a fused deep convolutional network for estimating the optical flow features of the micro-expression. Firstly, the deep multi-task convolutional network is employed to detect facial landmarks with the manifold related tasks for dividing the facial region. Furthermore, a fused convolutional network is applied for extracting the optical flow features from the facial regions which contain the muscle changes when the micro-expression presents. Finally, a revised optical flow feature is applied for refining the information of the features and a Support Vector Machine classifier is adopted for recognizing and detecting the micro-expression. The result of experiments on two spontaneous micro-expression database proves that our method achieved competitive performance in micro-expression recognition and detection.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"15 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122690715","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 : 2018-04-10DOI: 10.1109/CoDIT.2018.8394954
I. Alaridh, A. Aitouche, A. Zemouche, B. Boulkroune
This paper proposes an actuator fault detection based on unknown input observer for simultaneously state estimation and fault estimation applied to lateral vehicle dynamics. The lateral dynamics is modeled by a linear parameter varying model where the longitudinal velocity is considered as parameter varying. The observers gains are based on the resolution of linear matrix inequalities. The observers convergence is analyzed by using the Lyapunov theory. The proposed fault detection system is finally applied to the detection and estimation of steering angle fault and the estimation of the yaw velocity, yaw angle and the trajectory of the vehicle. Simulation study verifies the effectiveness of the proposed approach.
{"title":"Actuator Fault Detection for Vehicle Lateral Dynamics","authors":"I. Alaridh, A. Aitouche, A. Zemouche, B. Boulkroune","doi":"10.1109/CoDIT.2018.8394954","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394954","url":null,"abstract":"This paper proposes an actuator fault detection based on unknown input observer for simultaneously state estimation and fault estimation applied to lateral vehicle dynamics. The lateral dynamics is modeled by a linear parameter varying model where the longitudinal velocity is considered as parameter varying. The observers gains are based on the resolution of linear matrix inequalities. The observers convergence is analyzed by using the Lyapunov theory. The proposed fault detection system is finally applied to the detection and estimation of steering angle fault and the estimation of the yaw velocity, yaw angle and the trajectory of the vehicle. Simulation study verifies the effectiveness of the proposed approach.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128774774","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 : 2018-04-10DOI: 10.1109/CoDIT.2018.8394791
Senyue Zhang, Wenan Tan, Yibo Li
Online sequential extreme learning machine (OS-ELM) can learn the data one-by-one or chunk-by-chunk with the fixed or varying chunk size. It was proposed by Liang et al. is a faster and more accurate algorithm as compared to other online learning algorithms. However, besides the advantages of OS-ELM machine, the original OS-ELM algorithm also introced some issues; first, the improved OS-ELM algorithms need to be network structure adjustment to improve learning promance; second, OS-ELM algorithm learning with stability will affect its generalization ability. For such reasons, in this paper we propose a survey of OS-ELM algorithm with the development of history and the latest results of researching which can hopefully support researchers in the furture.
{"title":"A Survey of Online Sequential Extreme Learning Machine","authors":"Senyue Zhang, Wenan Tan, Yibo Li","doi":"10.1109/CoDIT.2018.8394791","DOIUrl":"https://doi.org/10.1109/CoDIT.2018.8394791","url":null,"abstract":"Online sequential extreme learning machine (OS-ELM) can learn the data one-by-one or chunk-by-chunk with the fixed or varying chunk size. It was proposed by Liang et al. is a faster and more accurate algorithm as compared to other online learning algorithms. However, besides the advantages of OS-ELM machine, the original OS-ELM algorithm also introced some issues; first, the improved OS-ELM algorithms need to be network structure adjustment to improve learning promance; second, OS-ELM algorithm learning with stability will affect its generalization ability. For such reasons, in this paper we propose a survey of OS-ELM algorithm with the development of history and the latest results of researching which can hopefully support researchers in the furture.","PeriodicalId":128011,"journal":{"name":"2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"237 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121161342","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：