Pub Date : 2016-08-01DOI: 10.1109/ICINFA.2016.7832004
Yongchao Wang, Guilin Yang, Liang Liu
A modular mobile manipulator system consists of standardized joint and wheel modules that can be assembled into a number of different robot configurations. This paper mainly focuses on the formulation of configuration-independent kinematics algorithms for modular mobile manipulators. Based on the design of various types of modules, a modified Assembly Incidence Matrix (AIM) is proposed to represent the modular mobile manipulators configurations. The local frame representation of POE (Product of Exponentials) formula is employed to automatically generate the kinematic models for a given mobile manipulator based on its AIM.
模块化移动机械手系统由标准化的关节和轮子模块组成，这些模块可以组装成许多不同的机器人结构。本文主要研究模块化移动机械臂的构型无关运动学算法。基于不同类型模块的设计，提出了一种改进的装配关联矩阵(AIM)来表示模块化移动机械臂的构型。采用POE (Product of exponals)公式的局部帧表示，基于给定移动机械臂的AIM自动生成运动模型。
{"title":"Configuration-independent kinematics for modular mobile manipulators","authors":"Yongchao Wang, Guilin Yang, Liang Liu","doi":"10.1109/ICINFA.2016.7832004","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7832004","url":null,"abstract":"A modular mobile manipulator system consists of standardized joint and wheel modules that can be assembled into a number of different robot configurations. This paper mainly focuses on the formulation of configuration-independent kinematics algorithms for modular mobile manipulators. Based on the design of various types of modules, a modified Assembly Incidence Matrix (AIM) is proposed to represent the modular mobile manipulators configurations. The local frame representation of POE (Product of Exponentials) formula is employed to automatically generate the kinematic models for a given mobile manipulator based on its AIM.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128873739","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}
In Artificial Intelligence, Loop Closing is a key issue of Simultaneous Localization and Mapping (SLAM) that helps SLAM work efficiently and robustly. To solve the problem of the quantity of scene matching increasing linearly with time when loop closing in SLAM for mobile robots, a laser range finder based method is proposed for classifying the geometric scene and determining the set of similar frames for indoor corridor environment. Firstly, based on the turning function, a new line segment extraction method is designed to swiftly obtain the segment feature of scenes. Secondly, the set of basically similar frames is constructed according to scene entropy, scan area and close scan area. Finally, the method describing geometric scenes with the sequences of turning angle is proposed based on the turning angle histogram. By using Longest Common Subsequence matching and Hu-moment-based contour matching, the compact set of similar frames and the best matched frames of query frame are found. The experiment proves that the compact set and the best matched frames can be obtained efficiently and accurately, and based on that, the quantity of scene matching could be greatly reduced.
{"title":"Active loop closing based on laser data in indoor environment","authors":"Xianshan Li, Maoyuan Sun, Zhenjun Liu, Fengda Zhao","doi":"10.1109/ICINFA.2016.7831930","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831930","url":null,"abstract":"In Artificial Intelligence, Loop Closing is a key issue of Simultaneous Localization and Mapping (SLAM) that helps SLAM work efficiently and robustly. To solve the problem of the quantity of scene matching increasing linearly with time when loop closing in SLAM for mobile robots, a laser range finder based method is proposed for classifying the geometric scene and determining the set of similar frames for indoor corridor environment. Firstly, based on the turning function, a new line segment extraction method is designed to swiftly obtain the segment feature of scenes. Secondly, the set of basically similar frames is constructed according to scene entropy, scan area and close scan area. Finally, the method describing geometric scenes with the sequences of turning angle is proposed based on the turning angle histogram. By using Longest Common Subsequence matching and Hu-moment-based contour matching, the compact set of similar frames and the best matched frames of query frame are found. The experiment proves that the compact set and the best matched frames can be obtained efficiently and accurately, and based on that, the quantity of scene matching could be greatly reduced.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125322172","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7832132
Xu-yang Chu, Huiqing Xu, G. Shao, W. Zheng
To meet the requirements of higher structural stiffness, higher vibration frequency, lower weight for the industrial robots, a method based on multi-objective topology optimization is presented. The method takes the deformation, vibration frequency, structure weight of the robot as the objective functions, and it optimizes the robot structure with topological method. Then, the method was applied to analyze and optimize a 3kg-load robot which has multi-function of assembly, transportation and so on. The results indicate that while the reduction of weight is 7.1%, the static deformation reduction is 22.4%, the first natural frequency is increased by 14.1%, the second natural frequency is increased by 14.2%, which fully verifies that the proposed method is available and effective.
{"title":"Multi-objective topology optimization for industrial robot","authors":"Xu-yang Chu, Huiqing Xu, G. Shao, W. Zheng","doi":"10.1109/ICINFA.2016.7832132","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7832132","url":null,"abstract":"To meet the requirements of higher structural stiffness, higher vibration frequency, lower weight for the industrial robots, a method based on multi-objective topology optimization is presented. The method takes the deformation, vibration frequency, structure weight of the robot as the objective functions, and it optimizes the robot structure with topological method. Then, the method was applied to analyze and optimize a 3kg-load robot which has multi-function of assembly, transportation and so on. The results indicate that while the reduction of weight is 7.1%, the static deformation reduction is 22.4%, the first natural frequency is increased by 14.1%, the second natural frequency is increased by 14.2%, which fully verifies that the proposed method is available and effective.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125439845","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7831838
Li Li, Kezhao Shi, D. Zeng
Cambered-plate moment limiter in tower crane is an over-load safety protection device. The cambered-plate deflection caused by its deformation can be used to represent the load moment of tower crane. However, inaccurate calculation of magnification exists in limiter design, which results in the moment deviation of the crane. This paper proposed an algorithm to improve the magnification accuracy. The analytical formula of magnification was derived based on mechanics analysis, and the parameters in the analytical formula were calculated. Meanwhile, software simulation was used to prove the validity of the analytical formula. The results have demonstrated that the magnification accuracy can be increased by the improved algorithm.
{"title":"An improved algorithm on magnification of cambered-plate moment limiter in tower crane","authors":"Li Li, Kezhao Shi, D. Zeng","doi":"10.1109/ICINFA.2016.7831838","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831838","url":null,"abstract":"Cambered-plate moment limiter in tower crane is an over-load safety protection device. The cambered-plate deflection caused by its deformation can be used to represent the load moment of tower crane. However, inaccurate calculation of magnification exists in limiter design, which results in the moment deviation of the crane. This paper proposed an algorithm to improve the magnification accuracy. The analytical formula of magnification was derived based on mechanics analysis, and the parameters in the analytical formula were calculated. Meanwhile, software simulation was used to prove the validity of the analytical formula. The results have demonstrated that the magnification accuracy can be increased by the improved algorithm.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126313359","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7831861
Changsheng Dai, Ning Zhang, Zhipeng Shen
Aiming at the uncertainty nonlinear model influenced by the external disturbances, an adaptive nonlinear iterative sliding mode controller based on adaptive heuristic critic algorithm is presented. The proposed controller uses nonlinear hyperbolic tangent function to design the system output sliding mode function. The stability of the proposed controller can be proved via the strict boundedness of the hyperbolic tangent function and the constraint of the system input. To improve the adaptive property of the controller, the sliding mode parameters are optimized through a fuzzy system. Moreover, by defining a chattering variable and an adaptive heuristic critic function, the parameters of the fuzzy system structure can be adjusted on-line, therefore, good performance in restraining controller output chattering is achieved. Furthermore, numerical simulations were carried out on the heading control of the sail-assisted ship. The simulation results show that the controller can achieve good performance and it is robust against the perturbation from the uncertain parameters and disturbances.
{"title":"An adaptive nonlinear iterative sliding mode controller based on heuristic critic algorithm","authors":"Changsheng Dai, Ning Zhang, Zhipeng Shen","doi":"10.1109/ICINFA.2016.7831861","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831861","url":null,"abstract":"Aiming at the uncertainty nonlinear model influenced by the external disturbances, an adaptive nonlinear iterative sliding mode controller based on adaptive heuristic critic algorithm is presented. The proposed controller uses nonlinear hyperbolic tangent function to design the system output sliding mode function. The stability of the proposed controller can be proved via the strict boundedness of the hyperbolic tangent function and the constraint of the system input. To improve the adaptive property of the controller, the sliding mode parameters are optimized through a fuzzy system. Moreover, by defining a chattering variable and an adaptive heuristic critic function, the parameters of the fuzzy system structure can be adjusted on-line, therefore, good performance in restraining controller output chattering is achieved. Furthermore, numerical simulations were carried out on the heading control of the sail-assisted ship. The simulation results show that the controller can achieve good performance and it is robust against the perturbation from the uncertain parameters and disturbances.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114131515","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7832051
Ji Chen, Chuxiong Hu, Y. Zhu, Ze Wang
To meet the requirements of contouring accuracy, multi-axis coordination, and high productivity in the fields of machining tools, many researchers devote to exploring various strategies in terms of controller design, coordinate frame construction, and trajectory planning for high-performance multi-axis motion. In this paper, a generalized global task coordinate frame (GTCF) is constructed for complicated contours to make the calculation of contouring error equal to the first-order approximation of the actual contouring error at any position in the GTCF no matter how large the tracking error or contour curvature would be, which suggests that the contouring error of complicated curves can be directly controlled in the GTCF. Furthermore, an experimental investigation is conducted over an XY linear-motor-driven stage on the combination of a GTCF based learning adaptive robust controller (LARC) with a back and forward check (BFC) algorithm. The LARC scheme is designed in a serial structure of an adaptive robust control (ARC) term and an iterative learning control (ILC) term, which guarantees good parametric adaptation and excellent contouring accuracy. In addition, the BFC algorithm provides an efficient computation for minimum time feed-rate optimization. A Lissajous curve and flower-shape curves are used as case studies to demonstrate the efficacy of the generalized GTCF based LARC scheme with BFC. The proposed GTCF-LARC-BFC approach provides a high-performance and efficient contouring control framework as a guidance for applications in motion control on industrial XY systems such as precision laser engravers.
{"title":"High-performance motion control of an XY stage for complicated contours with BFC trajectory planning","authors":"Ji Chen, Chuxiong Hu, Y. Zhu, Ze Wang","doi":"10.1109/ICINFA.2016.7832051","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7832051","url":null,"abstract":"To meet the requirements of contouring accuracy, multi-axis coordination, and high productivity in the fields of machining tools, many researchers devote to exploring various strategies in terms of controller design, coordinate frame construction, and trajectory planning for high-performance multi-axis motion. In this paper, a generalized global task coordinate frame (GTCF) is constructed for complicated contours to make the calculation of contouring error equal to the first-order approximation of the actual contouring error at any position in the GTCF no matter how large the tracking error or contour curvature would be, which suggests that the contouring error of complicated curves can be directly controlled in the GTCF. Furthermore, an experimental investigation is conducted over an XY linear-motor-driven stage on the combination of a GTCF based learning adaptive robust controller (LARC) with a back and forward check (BFC) algorithm. The LARC scheme is designed in a serial structure of an adaptive robust control (ARC) term and an iterative learning control (ILC) term, which guarantees good parametric adaptation and excellent contouring accuracy. In addition, the BFC algorithm provides an efficient computation for minimum time feed-rate optimization. A Lissajous curve and flower-shape curves are used as case studies to demonstrate the efficacy of the generalized GTCF based LARC scheme with BFC. The proposed GTCF-LARC-BFC approach provides a high-performance and efficient contouring control framework as a guidance for applications in motion control on industrial XY systems such as precision laser engravers.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114151953","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7832119
Mingqiang Lin, Houde Dai
Humans have the capability to quickly prioritize external visual stimuli and localize their most interest in a scene. Inspired by this mechanism, we propose a robust object tracking algorithm based on visual attention. We fuse motion feature and color feature to estimate the target state under the guidance of saliency map. Principal Component Analysis method is used to compute saliency feature based on the dense appearance model generated from the background templates. Motion feature is extracted by using the method which is a Bayesian decision rule for classification of background and foreground. Numerous experiments demonstrate the proposed method performs well against state-of-the-art tracking methods when dealing with illumination change, pose variation, occlusion, and background clutter situations.
{"title":"Object tracking based on visual attention","authors":"Mingqiang Lin, Houde Dai","doi":"10.1109/ICINFA.2016.7832119","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7832119","url":null,"abstract":"Humans have the capability to quickly prioritize external visual stimuli and localize their most interest in a scene. Inspired by this mechanism, we propose a robust object tracking algorithm based on visual attention. We fuse motion feature and color feature to estimate the target state under the guidance of saliency map. Principal Component Analysis method is used to compute saliency feature based on the dense appearance model generated from the background templates. Motion feature is extracted by using the method which is a Bayesian decision rule for classification of background and foreground. Numerous experiments demonstrate the proposed method performs well against state-of-the-art tracking methods when dealing with illumination change, pose variation, occlusion, and background clutter situations.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124918869","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7832110
Huan Chen, Xin Wang, Boru Xu
In view of old-fashioned digital display instrument of substation, an improved character recognition method for digital display instrument is proposed. It is a method mainly based on pulse coupled neural network which comes from study of cat's visual cortex neurons. Apart from synchronous oscillation that is one characteristic of pulse coupled neural network being used in image segmentation, the other characteristics for the constant peak of the corresponding time series are used in character recognition in this paper. The whole recognition process is as follows. Firstly, attention model is used with contour extraction to find digital display instrument's area, and then pulse coupled neural network is used for image segmentation. Some preprocessing algorithms of image processing like binarization, noise removing, corrosion and thinning are utilized for image preprocessing. And the methods for positioning and normalizing the character area are given through the horizontal vertical projection. And the algorithm based on pulse coupled neural network is used in the inspection robot for character recognition. Finally, tests show that the proposed recognition system is verified effectively.
{"title":"Study on digital display instrument recognition for substation based on pulse coupled neural network","authors":"Huan Chen, Xin Wang, Boru Xu","doi":"10.1109/ICINFA.2016.7832110","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7832110","url":null,"abstract":"In view of old-fashioned digital display instrument of substation, an improved character recognition method for digital display instrument is proposed. It is a method mainly based on pulse coupled neural network which comes from study of cat's visual cortex neurons. Apart from synchronous oscillation that is one characteristic of pulse coupled neural network being used in image segmentation, the other characteristics for the constant peak of the corresponding time series are used in character recognition in this paper. The whole recognition process is as follows. Firstly, attention model is used with contour extraction to find digital display instrument's area, and then pulse coupled neural network is used for image segmentation. Some preprocessing algorithms of image processing like binarization, noise removing, corrosion and thinning are utilized for image preprocessing. And the methods for positioning and normalizing the character area are given through the horizontal vertical projection. And the algorithm based on pulse coupled neural network is used in the inspection robot for character recognition. Finally, tests show that the proposed recognition system is verified effectively.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125163143","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}
This paper deals with the formation and obstacle avoidance of mobile robots in a cluttered environment. By combining an artificial potential field, a leader-follower method is presented to make the multi-robot system keep formation whilst avoiding obstacles. According to the pose and movement conditions of the designated leader, the follower would adjust its position so that the formation control could be achieved and so an artificial potential field has provided a significant improvement in the performance of obstacle avoidance for a multi-robot system. Moreover, considering trajectory dither of formation, a control law to limit the leader's angular velocity is designed to guarantee smooth formation motion trajectory. The simulation and experiential results indicate that the proposed method is efficient for robot formation control and enhances the robustness and stability of the multi-robot system.
{"title":"A strategy of multi-robot formation and obstacle avoidance in unknown environment","authors":"Ting Chi, Cheng-jin Zhang, Yong Song, Jinglun Feng","doi":"10.1109/ICINFA.2016.7832048","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7832048","url":null,"abstract":"This paper deals with the formation and obstacle avoidance of mobile robots in a cluttered environment. By combining an artificial potential field, a leader-follower method is presented to make the multi-robot system keep formation whilst avoiding obstacles. According to the pose and movement conditions of the designated leader, the follower would adjust its position so that the formation control could be achieved and so an artificial potential field has provided a significant improvement in the performance of obstacle avoidance for a multi-robot system. Moreover, considering trajectory dither of formation, a control law to limit the leader's angular velocity is designed to guarantee smooth formation motion trajectory. The simulation and experiential results indicate that the proposed method is efficient for robot formation control and enhances the robustness and stability of the multi-robot system.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122459921","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 : 2016-08-01DOI: 10.1109/ICINFA.2016.7831966
Hai-qing Yang, Yang-yang Wang
Fast measurement of soil organic matter is essential for site-specific application of fertilizer into farmlands. Total 100 soil samples were collected from several rice rehabilitation fields on the outskirts of Hangzhou City, China. Using a portable 350–2500nm spectrometer, absorbance spectra of the samples were recorded for the study. The spectra were separated into a calibration set (70%) and a prediction set (30%). The spectra were firstly transformed by several preprocessing methods for the purpose of removing noise and bias. Then, the original spectra and the various transformed spectra of calibration set were subjected to a partial least squares regression (PLSR) algorithm for obtaining PLSR calibration models. Finally, the PLSR models were applied to measure soil organic matter with the unknown samples in prediction set. The results show that the PLSR model developed for the original spectra can obtain good prediction accuracy with coefficient of determination (R2) of 0.83 and residual prediction deviation (RPD) of 2.49. The PLSR models developed by various transformed spectra achieved better prediction performance. The spectra transformed by the 1st derivative preprocessing method produced the best PLSR model which achieved highest prediction accuracy with R2 of 0.93 and RPD of 3.77. The study suggests that (1) soil organic matter of rice rehabilitation fields can be accurately measured by a spectrometer, and (2) prediction performance of a PLSR model could be improved if the original absorbance spectra are transformed by appropriate preprocessing methods such as the 1st derivative transformation used in the study.
{"title":"Fast measurement of soil organic matter of rice rehabilitation fields based on vis-near-infrared spectroscopy (350–2500nm)","authors":"Hai-qing Yang, Yang-yang Wang","doi":"10.1109/ICINFA.2016.7831966","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831966","url":null,"abstract":"Fast measurement of soil organic matter is essential for site-specific application of fertilizer into farmlands. Total 100 soil samples were collected from several rice rehabilitation fields on the outskirts of Hangzhou City, China. Using a portable 350–2500nm spectrometer, absorbance spectra of the samples were recorded for the study. The spectra were separated into a calibration set (70%) and a prediction set (30%). The spectra were firstly transformed by several preprocessing methods for the purpose of removing noise and bias. Then, the original spectra and the various transformed spectra of calibration set were subjected to a partial least squares regression (PLSR) algorithm for obtaining PLSR calibration models. Finally, the PLSR models were applied to measure soil organic matter with the unknown samples in prediction set. The results show that the PLSR model developed for the original spectra can obtain good prediction accuracy with coefficient of determination (R2) of 0.83 and residual prediction deviation (RPD) of 2.49. The PLSR models developed by various transformed spectra achieved better prediction performance. The spectra transformed by the 1st derivative preprocessing method produced the best PLSR model which achieved highest prediction accuracy with R2 of 0.93 and RPD of 3.77. The study suggests that (1) soil organic matter of rice rehabilitation fields can be accurately measured by a spectrometer, and (2) prediction performance of a PLSR model could be improved if the original absorbance spectra are transformed by appropriate preprocessing methods such as the 1st derivative transformation used in the study.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121858486","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：