Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803938
Liangliang Gao, Chaoyi Dong, Xiaoyang Liu, Qifan Ye, Kang Zhang, Xiaoyan Chen
Laser slam usually needs to complete a back-end graph optimization at a fast speed in some specific scenes, such as sharp turns, fast motion, and limited calculation time. Aiming at these problems, this paper proposed a 2D laser slam back-end graph optimization combined with Cholesky decomposition to accelerate a linear solution process and further to achieve a purpose of accelerating graph optimization. In MATLAB simulation experiments, the rate of 2D laser slam back-end graph optimization combined with Cholesky decomposition increased 24%, compared to that of the traditional method without Cholesky decomposition. The result verified the effectiveness of the improved method.
{"title":"Improved 2D laser slam graph optimization based on Cholesky decomposition","authors":"Liangliang Gao, Chaoyi Dong, Xiaoyang Liu, Qifan Ye, Kang Zhang, Xiaoyan Chen","doi":"10.1109/CoDIT55151.2022.9803938","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803938","url":null,"abstract":"Laser slam usually needs to complete a back-end graph optimization at a fast speed in some specific scenes, such as sharp turns, fast motion, and limited calculation time. Aiming at these problems, this paper proposed a 2D laser slam back-end graph optimization combined with Cholesky decomposition to accelerate a linear solution process and further to achieve a purpose of accelerating graph optimization. In MATLAB simulation experiments, the rate of 2D laser slam back-end graph optimization combined with Cholesky decomposition increased 24%, compared to that of the traditional method without Cholesky decomposition. The result verified the effectiveness of the improved method.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116353353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804068
A. Meddour, N. Rizoug, A. Babin, C. Vagg, R. Burke
This paper investigates the impact of battery technology on the electric motor's optimization process for an electric vehicle application. Matlab and Ansys Electronics are used to conduct the simulations. The needed autonomy is estimated for the WLTC driving cycle using a dynamic vehicle model while considering the storage system mass calculated with a connected sizing algorithm. The Motor model is constructed using the finite element soft-ware Ansys electronics. The genetic algorithm will determine its geometrical parameters while considering the new power and torque demands, including the storage system weight. The comparison of the optimization results was carried out for four battery technologies that have promising characteristics for an automotive application. The results discussed active material cost and performances evaluated for the entire selected driving cycle.
{"title":"The influence of the battery technology choice on motor optimisation for electric vehicles","authors":"A. Meddour, N. Rizoug, A. Babin, C. Vagg, R. Burke","doi":"10.1109/CoDIT55151.2022.9804068","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804068","url":null,"abstract":"This paper investigates the impact of battery technology on the electric motor's optimization process for an electric vehicle application. Matlab and Ansys Electronics are used to conduct the simulations. The needed autonomy is estimated for the WLTC driving cycle using a dynamic vehicle model while considering the storage system mass calculated with a connected sizing algorithm. The Motor model is constructed using the finite element soft-ware Ansys electronics. The genetic algorithm will determine its geometrical parameters while considering the new power and torque demands, including the storage system weight. The comparison of the optimization results was carried out for four battery technologies that have promising characteristics for an automotive application. The results discussed active material cost and performances evaluated for the entire selected driving cycle.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121919504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804114
Wafa Ben Taleb, Ahmed Snoun, T. Bouchrika, O. Jemai
Alzheimer's disease is a chronic brain disease with multi-factorial causes that begins in the middle of life. It affects the patient in many ways, like the ability to perform daily life activities. In this paper, we proposed an assistance system for Alzheimer's patients to assist them in performing their activities of daily living autonomously. The developed system is based on a human activity recognition system and a prompt system to provide alerts to the patient in case of need. To detect the anomalies in the patient's behavior and provide assistance, we used a reinforcement learning (RL) module as a decision-making system. This module may be responsible for identifying and prompting the patient's wanted assistance based on his or her behavior. The efficiency of the proposed system was proven after testing using the Dem Care dataset.
{"title":"Reinforcement Learning for assistance of Alzheimer's disease patients","authors":"Wafa Ben Taleb, Ahmed Snoun, T. Bouchrika, O. Jemai","doi":"10.1109/CoDIT55151.2022.9804114","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804114","url":null,"abstract":"Alzheimer's disease is a chronic brain disease with multi-factorial causes that begins in the middle of life. It affects the patient in many ways, like the ability to perform daily life activities. In this paper, we proposed an assistance system for Alzheimer's patients to assist them in performing their activities of daily living autonomously. The developed system is based on a human activity recognition system and a prompt system to provide alerts to the patient in case of need. To detect the anomalies in the patient's behavior and provide assistance, we used a reinforcement learning (RL) module as a decision-making system. This module may be responsible for identifying and prompting the patient's wanted assistance based on his or her behavior. The efficiency of the proposed system was proven after testing using the Dem Care dataset.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122067755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804061
Andrei Zhivitskii, O. Borisov, I. Dovgopolik
The problem addressed in the paper is twofold. First, the estimation of unknown robot parameters is carried out using three different approaches, namely the gradient descent method, extended Kalman filter, and dynamic regressor extension and mixing, to evaluate their performance as applied to the two-link planar elbow robot arm. Second, an indirect adaptive inverse dynamics controller based on the obtained estimates is designed to study performance achieved by the estimation methods in the control problem. The obtained results show advantages of the dynamic regressor extension and mixing in the both addressed problems.
{"title":"Parameter Estimation and Indirect Adaptive Control of a Robot Arm*","authors":"Andrei Zhivitskii, O. Borisov, I. Dovgopolik","doi":"10.1109/CoDIT55151.2022.9804061","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804061","url":null,"abstract":"The problem addressed in the paper is twofold. First, the estimation of unknown robot parameters is carried out using three different approaches, namely the gradient descent method, extended Kalman filter, and dynamic regressor extension and mixing, to evaluate their performance as applied to the two-link planar elbow robot arm. Second, an indirect adaptive inverse dynamics controller based on the obtained estimates is designed to study performance achieved by the estimation methods in the control problem. The obtained results show advantages of the dynamic regressor extension and mixing in the both addressed problems.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124016269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803911
Oleg Evstafev, Sergey V. Shavetov
The design and development of surface defect detection and recognition systems for optical non-destructive testing (NDT) tasks is a complex, important and pressing problem today. Detection and classification of surface defects using Computer Vision (CV) and Machine Learning (ML) algorithms serves as an effective tool for production process control, quality management and increasing the profitability of enterprises. In this paper, Deep Learning (DL) and Computer Vision (CV) techniques are used to solve the problem of surface defect detection. Using Convolutional Neural Network (CNN), detection and recognition of various defects is carried out to improve production standards and process efficiency. The outcome of this paper is a comparative analysis of DL models and the selection of an algorithm designed to find and classify defects online. The application of such CNN models could allow the creation of a tool that considerably facilitates human work.
{"title":"Surface Defect Detection and Recognition Based on CNN","authors":"Oleg Evstafev, Sergey V. Shavetov","doi":"10.1109/CoDIT55151.2022.9803911","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803911","url":null,"abstract":"The design and development of surface defect detection and recognition systems for optical non-destructive testing (NDT) tasks is a complex, important and pressing problem today. Detection and classification of surface defects using Computer Vision (CV) and Machine Learning (ML) algorithms serves as an effective tool for production process control, quality management and increasing the profitability of enterprises. In this paper, Deep Learning (DL) and Computer Vision (CV) techniques are used to solve the problem of surface defect detection. Using Convolutional Neural Network (CNN), detection and recognition of various defects is carried out to improve production standards and process efficiency. The outcome of this paper is a comparative analysis of DL models and the selection of an algorithm designed to find and classify defects online. The application of such CNN models could allow the creation of a tool that considerably facilitates human work.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128669828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803882
Mariem Ben Salem, Raouia Taktak
In this paper, we address a variant of the Two Edge Connected Problem (TECP), that is the TECP with color constraint on the edges, also known as the Labeled Two Edge Connected Problem (LTECP). Given a connected undirected graph $G$ whose edges are labeled (or colored), the LTECP consists in finding a two-edge connected spanning subgraph of $G$ with a minimum number of distinct labels (or colors). We distinguish two variants of the problem: the first one is when each edge is associated with exactly one label (i.e., the LTECP), and the second is when each edge may be associated with more than one label. This variant is called the Generalized Labeled Two Edge Connected Problem (i.e., the GLTECP). Both problems are relevant in some application fields such as telecommunication networks or transportation networks. We propose Integer Linear Programming formulations for the two variants, we identify a new class of valid inequalities, and present preliminary computational results.
{"title":"The Labeled Two Edge Connected Subgraph Problem","authors":"Mariem Ben Salem, Raouia Taktak","doi":"10.1109/CoDIT55151.2022.9803882","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803882","url":null,"abstract":"In this paper, we address a variant of the Two Edge Connected Problem (TECP), that is the TECP with color constraint on the edges, also known as the Labeled Two Edge Connected Problem (LTECP). Given a connected undirected graph $G$ whose edges are labeled (or colored), the LTECP consists in finding a two-edge connected spanning subgraph of $G$ with a minimum number of distinct labels (or colors). We distinguish two variants of the problem: the first one is when each edge is associated with exactly one label (i.e., the LTECP), and the second is when each edge may be associated with more than one label. This variant is called the Generalized Labeled Two Edge Connected Problem (i.e., the GLTECP). Both problems are relevant in some application fields such as telecommunication networks or transportation networks. We propose Integer Linear Programming formulations for the two variants, we identify a new class of valid inequalities, and present preliminary computational results.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129676874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803974
Chaima Taieb, Takwa Tlili, I. Nouaouri, S. Krichen
In this paper, we present a charging station allocation model for electric vehicles. The goal is to assign each electric vehicle to the closest charging station with respect to capacity and charging time constraints. We assume that each vehicle's arrival time is provided by a GPS device and each charging station capacity as well as the required charging time are known in advance. We propose an integer programming model solved with CPLEX to efficiently deal with this combinatorial problem. The objective of Electric Vehicles Charging Stations Allocation (EVCSA) is to minimize the total required time from a start point to a destination going through a Charging Station (CS). To evaluate the performance of the proposed approach, computational experiments are conducted on large scale randomly generated instances simulating a real world scenario.
{"title":"Optimizing the charging stations allocation for efficient electric vehicles routing","authors":"Chaima Taieb, Takwa Tlili, I. Nouaouri, S. Krichen","doi":"10.1109/CoDIT55151.2022.9803974","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803974","url":null,"abstract":"In this paper, we present a charging station allocation model for electric vehicles. The goal is to assign each electric vehicle to the closest charging station with respect to capacity and charging time constraints. We assume that each vehicle's arrival time is provided by a GPS device and each charging station capacity as well as the required charging time are known in advance. We propose an integer programming model solved with CPLEX to efficiently deal with this combinatorial problem. The objective of Electric Vehicles Charging Stations Allocation (EVCSA) is to minimize the total required time from a start point to a destination going through a Charging Station (CS). To evaluate the performance of the proposed approach, computational experiments are conducted on large scale randomly generated instances simulating a real world scenario.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127403215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804088
Armin Mokhtarian, Bassam Alrifaee
Laboratories with model vehicles offer a middle ground between field tests and simulations. Thereby, the lab-oratories benefit from the advantages of more realistic setups and reduce acquisition and maintenance costs. However, the efficient use of a fixed laboratory presents further organizational hurdles. In addition, special hardware requirements, complex installation processes, and the cost and length of travel to the laboratories discourage users from getting involved. In this paper, we present the web app CPM Remote, which addresses these hurdles. The Cyber-Physical Mobility (CPM) Lab is an open source platform for networked and autonomous vehicles. Our online framework www.cpm-remote.de. provides a simulation environment and remote access to our CPM Lab (based in Aachen, Germany), making it accessible from anywhere in the world. The simulation environment is outsourced to our servers, reducing the hardware and software requirements of the users. CPM Remote aims to offer a user-friendly platform for making solutions to current research questions more transparent since results can be reproduced and extended quickly with little effort.
{"title":"CPM Remote: A Remote Access to the CPM Lab","authors":"Armin Mokhtarian, Bassam Alrifaee","doi":"10.1109/CoDIT55151.2022.9804088","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804088","url":null,"abstract":"Laboratories with model vehicles offer a middle ground between field tests and simulations. Thereby, the lab-oratories benefit from the advantages of more realistic setups and reduce acquisition and maintenance costs. However, the efficient use of a fixed laboratory presents further organizational hurdles. In addition, special hardware requirements, complex installation processes, and the cost and length of travel to the laboratories discourage users from getting involved. In this paper, we present the web app CPM Remote, which addresses these hurdles. The Cyber-Physical Mobility (CPM) Lab is an open source platform for networked and autonomous vehicles. Our online framework www.cpm-remote.de. provides a simulation environment and remote access to our CPM Lab (based in Aachen, Germany), making it accessible from anywhere in the world. The simulation environment is outsourced to our servers, reducing the hardware and software requirements of the users. CPM Remote aims to offer a user-friendly platform for making solutions to current research questions more transparent since results can be reproduced and extended quickly with little effort.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132025722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804064
Asma Channa, N. Popescu, Muhammad Faisal
Gait evaluation is important for apprehension and management of different neurocognitive disorders (NCD). The gait events are changing with the age factor and this variability is being incorrectly linked with people with NCD. So, there is a high need to analyze gait events correctly. The gait analysis is mostly performed on temporal and spectral feature extraction in which there is a high rate of missing important features. Apart from this, monitoring and quantification of Parkinson's disease patients raise many therapeutic challenges in terms of severity analysis of motor symptoms i.e. freezing of gait (FOG), bradykinesia and continuous remote monitoring of patients. The objective of this study is to use a smart insole dataset for the assessment of computational techniques focusing on gait evaluation. The objective of this research study is to use continuous wavelet transform to convert time series signals into an images instead of using more traditional techniques for dealing with time series based on e.g. recurrent architectures. The results evidence that the proposed system works efficiently with the accuracy of 96.5% in gait variability analyzing three cohorts i.e. adults, elderly, and patients with Parkinson's disease (PwPD) and 91% for analyzing the gait symptoms in different severity stages of PD patients.
{"title":"Parkinson's Disease Gait Evaluation Leveraging Wearable Insoles and Deep Learning Approach*","authors":"Asma Channa, N. Popescu, Muhammad Faisal","doi":"10.1109/CoDIT55151.2022.9804064","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804064","url":null,"abstract":"Gait evaluation is important for apprehension and management of different neurocognitive disorders (NCD). The gait events are changing with the age factor and this variability is being incorrectly linked with people with NCD. So, there is a high need to analyze gait events correctly. The gait analysis is mostly performed on temporal and spectral feature extraction in which there is a high rate of missing important features. Apart from this, monitoring and quantification of Parkinson's disease patients raise many therapeutic challenges in terms of severity analysis of motor symptoms i.e. freezing of gait (FOG), bradykinesia and continuous remote monitoring of patients. The objective of this study is to use a smart insole dataset for the assessment of computational techniques focusing on gait evaluation. The objective of this research study is to use continuous wavelet transform to convert time series signals into an images instead of using more traditional techniques for dealing with time series based on e.g. recurrent architectures. The results evidence that the proposed system works efficiently with the accuracy of 96.5% in gait variability analyzing three cohorts i.e. adults, elderly, and patients with Parkinson's disease (PwPD) and 91% for analyzing the gait symptoms in different severity stages of PD patients.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130250544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804121
N. A. Othman, N. S. Damanhuri, Nabilah Md Ali, Belinda Chong Chiew Meng, A. Samat
Plant classification systems, in general, could be a beneficial tool in the agricultural industry, especially when it comes to recognising plant types in a systematic and manageable manner. Previously, plant growers used to rely on observation and experienced personnel to distinguish between plant varieties. However, some plants, such as leaves and branches, have nearly identical traits, making identification difficult. Hence, there is a need for a system capable of resolving this issue. Thus, the focus of this research is on classifying plant leaves using a convolutional neural network (CNN) technique. Coriander and parsley were chosen as test subjects for this study because their leaves have comparable structures. The input image was subjected to a number of filter layers using CNN. A total of 100 coriander and parsley leaf photos are collected for this research. These photos were filtered using kernels. These kernels have a set size and extract features from the input photos to create a feature map. These extracted features will then be used to classify plant leaves according to its classes type. With the use of the Graphical User Interface (GUI), the end user will be able to determine the type of leaf. Results show that, using the ReLu activation layer with 15 layers of network design and a 70–30 training-testing proportion, this plant leaf classification system was able to attain a coriander and parsley classification accuracy of 90% with an error rate of 0.1. In addition, due to its great accuracy, this system can be extended for additional uses such as recognising plant diseases and species.
{"title":"Plant Leaf Classification Using Convolutional Neural Network","authors":"N. A. Othman, N. S. Damanhuri, Nabilah Md Ali, Belinda Chong Chiew Meng, A. Samat","doi":"10.1109/CoDIT55151.2022.9804121","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804121","url":null,"abstract":"Plant classification systems, in general, could be a beneficial tool in the agricultural industry, especially when it comes to recognising plant types in a systematic and manageable manner. Previously, plant growers used to rely on observation and experienced personnel to distinguish between plant varieties. However, some plants, such as leaves and branches, have nearly identical traits, making identification difficult. Hence, there is a need for a system capable of resolving this issue. Thus, the focus of this research is on classifying plant leaves using a convolutional neural network (CNN) technique. Coriander and parsley were chosen as test subjects for this study because their leaves have comparable structures. The input image was subjected to a number of filter layers using CNN. A total of 100 coriander and parsley leaf photos are collected for this research. These photos were filtered using kernels. These kernels have a set size and extract features from the input photos to create a feature map. These extracted features will then be used to classify plant leaves according to its classes type. With the use of the Graphical User Interface (GUI), the end user will be able to determine the type of leaf. Results show that, using the ReLu activation layer with 15 layers of network design and a 70–30 training-testing proportion, this plant leaf classification system was able to attain a coriander and parsley classification accuracy of 90% with an error rate of 0.1. In addition, due to its great accuracy, this system can be extended for additional uses such as recognising plant diseases and species.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130252490","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：