Pub Date : 2022-05-10DOI: 10.1109/airc56195.2022.9836455
Norah AlShaye, Lamia Almoajil, M. Abdullah-Al-Wadud
A gender recognition system (GRS) based on facial images can be embedded in different areas such as surveillance, human-robot interaction, targeted advertising, etc. Traditional facial feature-based recognition systems extract and analyze textures on a face. Although such approaches perform well under certain controlled situations, they may fail due to variations of faces in images, which is very common in real-life images. To overcome such problems, we need to have an effective combination of a feature descriptor, representation, and classifier providing better accuracy. Recently, many recognition problems are tackled by using the Deep Neural Network (DNN) such as Convolutional Neural Network (CNN). However, deep learning needs a large number of images, which is not usually available, to work as expected. We propose a model that combines handcrafted features with CNN to overcome the shortcomings including handling of variations in imaging, such as the illumination and pose variations, and the necessity of voluminous training sets. Experimental results also show that the proposed method performs better than the available gender recognition approaches.
{"title":"A Gender Recognition System Based on Facial Image","authors":"Norah AlShaye, Lamia Almoajil, M. Abdullah-Al-Wadud","doi":"10.1109/airc56195.2022.9836455","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836455","url":null,"abstract":"A gender recognition system (GRS) based on facial images can be embedded in different areas such as surveillance, human-robot interaction, targeted advertising, etc. Traditional facial feature-based recognition systems extract and analyze textures on a face. Although such approaches perform well under certain controlled situations, they may fail due to variations of faces in images, which is very common in real-life images. To overcome such problems, we need to have an effective combination of a feature descriptor, representation, and classifier providing better accuracy. Recently, many recognition problems are tackled by using the Deep Neural Network (DNN) such as Convolutional Neural Network (CNN). However, deep learning needs a large number of images, which is not usually available, to work as expected. We propose a model that combines handcrafted features with CNN to overcome the shortcomings including handling of variations in imaging, such as the illumination and pose variations, and the necessity of voluminous training sets. Experimental results also show that the proposed method performs better than the available gender recognition approaches.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115399794","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836986
F. Martinelli, Fabrizio Romanelli
In this paper we consider a Range Only (RO) SLAM problem for a unicycle like robot. The solution approach is based on a bearing reconstruction for each responding landmark obtained through a two dimensional EKF, which fuses odometry readings of the robot with the available range measurements to produce a range and bearing estimate of the considered landmark. These estimates, regarded as measurements with a proper covariance matrix, are used in an EKF SLAM algorithm. A resilient module is added to the algorithm to cope with the initial uncertainty characterizing the bearing estimates, but also to resist the effects of outliers and to detect possible abnormal situations. Simulation results show the effectiveness of the proposed approach which appears robust to several kinds of disturbances and provides estimation errors comparable to the case the bearing is directly available from the sensor and the range measurements have the same variance.
{"title":"A Resilient RO-SLAM Algorithm with Bearing Reconstruction of Detected Landmarks","authors":"F. Martinelli, Fabrizio Romanelli","doi":"10.1109/airc56195.2022.9836986","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836986","url":null,"abstract":"In this paper we consider a Range Only (RO) SLAM problem for a unicycle like robot. The solution approach is based on a bearing reconstruction for each responding landmark obtained through a two dimensional EKF, which fuses odometry readings of the robot with the available range measurements to produce a range and bearing estimate of the considered landmark. These estimates, regarded as measurements with a proper covariance matrix, are used in an EKF SLAM algorithm. A resilient module is added to the algorithm to cope with the initial uncertainty characterizing the bearing estimates, but also to resist the effects of outliers and to detect possible abnormal situations. Simulation results show the effectiveness of the proposed approach which appears robust to several kinds of disturbances and provides estimation errors comparable to the case the bearing is directly available from the sensor and the range measurements have the same variance.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116327979","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836454
E. S. Ghith, F. A. Tolba
This paper presents a new approach to control the position of the micro-robotics system with a proportional-integral-derivative (PID) controller. By using Marine Predator algorithm (MPA), the optimal PID controller indicators were obtained by applying a new objective function namely, integral square time multiplied square error (ISTES). The efficiency of the proposed MPA-based controller was verified by comparisons made with Grey Wolf Optimization (GWO) algorithm-based controllers in terms of time. Each control technique will be applied to the identified model using MATLAB Simulink and the experimental test facility was conducted using LABVIEW software. The simulation and experimental results show that the performance of MPA-PID controller based on ISTES cost function achieves the best performance among various techniques. Moreover, the MPA technique had the highest performance compared to GWO technique based on rising time, settling time and settling error. Thus, it is recommended to apply MPA for tuning the parameters of PID as it can enhance its performance in micro-robotic systems. It was found that the amount of error is reduced by 33.75% using MPA than other former experiments
{"title":"Real-Time Implementation of an Enhanced PID CONTROLLER based on Marine Predator Algorithm (MPA) for Micro-robotics System","authors":"E. S. Ghith, F. A. Tolba","doi":"10.1109/airc56195.2022.9836454","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836454","url":null,"abstract":"This paper presents a new approach to control the position of the micro-robotics system with a proportional-integral-derivative (PID) controller. By using Marine Predator algorithm (MPA), the optimal PID controller indicators were obtained by applying a new objective function namely, integral square time multiplied square error (ISTES). The efficiency of the proposed MPA-based controller was verified by comparisons made with Grey Wolf Optimization (GWO) algorithm-based controllers in terms of time. Each control technique will be applied to the identified model using MATLAB Simulink and the experimental test facility was conducted using LABVIEW software. The simulation and experimental results show that the performance of MPA-PID controller based on ISTES cost function achieves the best performance among various techniques. Moreover, the MPA technique had the highest performance compared to GWO technique based on rising time, settling time and settling error. Thus, it is recommended to apply MPA for tuning the parameters of PID as it can enhance its performance in micro-robotic systems. It was found that the amount of error is reduced by 33.75% using MPA than other former experiments","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116350114","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836987
Liping Zhou, Lin Wang, Xu Liu
The article constructed a general model for artificial intelligence to have the needs. The model believes that people or artificial intelligence must follow four basic assumptions to have needs, namely: the assumption that any kind of objective need is finite; the assumption that the sum of needs and satisfactions of the same type remains unchanged at the same time; the assumption that the degree of need can be directly compared and the assumption that subject's need system always tends to maintain equilibrium. By the mathod of giving the artificial intelligence vehicle a dual need system of power and mileage, it shows that this model can allow artificial intelligence to have different types of needs and form a need system. The construction of the dual needs system of artificial intelligence vehicle also proves that the general model is reasonable and feasible. This will provide a possible basis for artificial intelligence to make value judgments or affective computing.
{"title":"A General Model that Gives Artificial Intelligence Needs Based on the Perspective of Value Philosophy","authors":"Liping Zhou, Lin Wang, Xu Liu","doi":"10.1109/airc56195.2022.9836987","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836987","url":null,"abstract":"The article constructed a general model for artificial intelligence to have the needs. The model believes that people or artificial intelligence must follow four basic assumptions to have needs, namely: the assumption that any kind of objective need is finite; the assumption that the sum of needs and satisfactions of the same type remains unchanged at the same time; the assumption that the degree of need can be directly compared and the assumption that subject's need system always tends to maintain equilibrium. By the mathod of giving the artificial intelligence vehicle a dual need system of power and mileage, it shows that this model can allow artificial intelligence to have different types of needs and form a need system. The construction of the dual needs system of artificial intelligence vehicle also proves that the general model is reasonable and feasible. This will provide a possible basis for artificial intelligence to make value judgments or affective computing.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129246878","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836983
Bogdan Walek, Petr Fajmon
This article proposes a recommender system for recommending relevant products in e-shop using explanations. The proposed system consists of three recommender modules called VIEW, RATING, and PURCHASE. The recommender modules use a content-based filtering approach and a collaborative filtering approach. The proposed recommender system works with explanations that contain arguments why the system recommended the specific product. Based on these explanations the user sees why specific products are recommended by the system. The proposed system was experimentally verified and the results of the experimental verification are discussed.
{"title":"A Recommender System for Recommending Suitable Products in E-shop Using Explanations","authors":"Bogdan Walek, Petr Fajmon","doi":"10.1109/airc56195.2022.9836983","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836983","url":null,"abstract":"This article proposes a recommender system for recommending relevant products in e-shop using explanations. The proposed system consists of three recommender modules called VIEW, RATING, and PURCHASE. The recommender modules use a content-based filtering approach and a collaborative filtering approach. The proposed recommender system works with explanations that contain arguments why the system recommended the specific product. Based on these explanations the user sees why specific products are recommended by the system. The proposed system was experimentally verified and the results of the experimental verification are discussed.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125633830","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836453
Jingjing Li, Qingda Li
With the rapid development of artificial intelligence, the library relies on the massive knowledge data to integrate the user behavior data, and continuously upgrade the library industry chain, the new form, the new service will bring the new experience for the user. The artificial intelligence technology based on machine learning and deep learning will promote the change of embedded service, upgrade the intelligence of embedded service physical scene in library, and advance the intelligence of information resources and virtual space. In the embedded service dimension, the artificial intelligence technology will promote the intelligent service supply of the library, the intelligent library will provide the “A I cloud processing” resource service for the user, the whole domain, the interactive scene service, the human-machine high-efficiency Coordinated Joint Service; In the dimension of user experience, artificial intelligence technology will bring a variety of user experience to the library. Taking the Library of Agricultural University as an example, this paper probes into the characteristics and modes of embedded service, puts forward the application of artificial intelligence in embedded service, and provides beneficial exploration for exerting the value of artificial intelligence in library service.
{"title":"Application and Research of Artificial Intelligence Embedded Service","authors":"Jingjing Li, Qingda Li","doi":"10.1109/airc56195.2022.9836453","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836453","url":null,"abstract":"With the rapid development of artificial intelligence, the library relies on the massive knowledge data to integrate the user behavior data, and continuously upgrade the library industry chain, the new form, the new service will bring the new experience for the user. The artificial intelligence technology based on machine learning and deep learning will promote the change of embedded service, upgrade the intelligence of embedded service physical scene in library, and advance the intelligence of information resources and virtual space. In the embedded service dimension, the artificial intelligence technology will promote the intelligent service supply of the library, the intelligent library will provide the “A I cloud processing” resource service for the user, the whole domain, the interactive scene service, the human-machine high-efficiency Coordinated Joint Service; In the dimension of user experience, artificial intelligence technology will bring a variety of user experience to the library. Taking the Library of Agricultural University as an example, this paper probes into the characteristics and modes of embedded service, puts forward the application of artificial intelligence in embedded service, and provides beneficial exploration for exerting the value of artificial intelligence in library service.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123498463","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836978
Hong Cu, T. Fujimoto
Japan has witnessed significant growth in the number of Vietnamese students and workers coming to this country. This phenomenon has led to the development of various educational programs to help Vietnamese workers and students prepare for their life in Japan. While there have been different applications invented to improve Vietnamese users' Japanese ability, hardly can we find a communication application that provides users with cultural knowledge. Therefore, we propose a Japanese - Vietnamese conversation application in this research, which can bridge the cultural gap between the two countries. The main purpose of this application is to help Vietnamese users in Japan have smoother communication with their Japanese counterparts.
{"title":"The Development of an Application to Bridge the Cultural Gap between Japan and Vietnam for Vietnamese Living in Japan","authors":"Hong Cu, T. Fujimoto","doi":"10.1109/airc56195.2022.9836978","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836978","url":null,"abstract":"Japan has witnessed significant growth in the number of Vietnamese students and workers coming to this country. This phenomenon has led to the development of various educational programs to help Vietnamese workers and students prepare for their life in Japan. While there have been different applications invented to improve Vietnamese users' Japanese ability, hardly can we find a communication application that provides users with cultural knowledge. Therefore, we propose a Japanese - Vietnamese conversation application in this research, which can bridge the cultural gap between the two countries. The main purpose of this application is to help Vietnamese users in Japan have smoother communication with their Japanese counterparts.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125421268","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836445
S. Adarsh, Jagajyoti Panda, S. Ray‐Chaudhuri
For control of seismic responses of structures, in contemporary research, either state feedback (i.e., displacement and velocity at each degree of freedom) or acceleration feedback is used. Even for full state feedback, the states of the system are generally estimated from homogeneous acceleration data as accelerometers do not require a local reference like displacement and velocity sensors. Like accelerometers, strain sensors (such as foil-type strain gauges) also do not require local references. This study considers the fusion of acceleration and strain data for H2 based seismic control of structural systems. A four-story lumped mass shear building model subjected to a seismic input is used to elucidate the efficacy of the proposed control scheme. It has been found that the proposed acceleration-strain feedback algorithm is highly effective for better control of seismic responses of structures.
{"title":"H2 Based Acceleration-Strain Feedback Control of Structures Subjected to Seismic Input","authors":"S. Adarsh, Jagajyoti Panda, S. Ray‐Chaudhuri","doi":"10.1109/airc56195.2022.9836445","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836445","url":null,"abstract":"For control of seismic responses of structures, in contemporary research, either state feedback (i.e., displacement and velocity at each degree of freedom) or acceleration feedback is used. Even for full state feedback, the states of the system are generally estimated from homogeneous acceleration data as accelerometers do not require a local reference like displacement and velocity sensors. Like accelerometers, strain sensors (such as foil-type strain gauges) also do not require local references. This study considers the fusion of acceleration and strain data for H2 based seismic control of structural systems. A four-story lumped mass shear building model subjected to a seismic input is used to elucidate the efficacy of the proposed control scheme. It has been found that the proposed acceleration-strain feedback algorithm is highly effective for better control of seismic responses of structures.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116322696","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836443
Joseph Junior Rojas Vila, Jhon Stalin Figueroa Bados, J. Villanueva, Danitza Yalli Villa, Carlos Coaquira Rojo
The specific symptomatology of Covid-19 reveals discomfort with mild or moderate intensity depending on the body of each person. This article develops the design of an automatic device that encompasses an intelligent control and monitoring system for symptoms of covid-19, which allows determining and identifying an estimate of suspected cases of people who enter the Continental University - Peru, through a reading of patterns. The device was made covering three systems (mechanical, mechatronic and control), the integration of systems allowed an efficient design, dimensioned calculations in the mechanical, electrical, and electronic, and its integration of hardware-software for the graphical interface. The system presented allows real-time monitoring of parameters captured by sensors with IOT technology, which has made it possible to deepen and estimate suspected cases of covid by comparing measured values with the ranges of values established by the American Medical Association.
{"title":"Design of an Automatic System for the Control and Monitoring of Symptoms of Covid-19 through IoT Technology","authors":"Joseph Junior Rojas Vila, Jhon Stalin Figueroa Bados, J. Villanueva, Danitza Yalli Villa, Carlos Coaquira Rojo","doi":"10.1109/airc56195.2022.9836443","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836443","url":null,"abstract":"The specific symptomatology of Covid-19 reveals discomfort with mild or moderate intensity depending on the body of each person. This article develops the design of an automatic device that encompasses an intelligent control and monitoring system for symptoms of covid-19, which allows determining and identifying an estimate of suspected cases of people who enter the Continental University - Peru, through a reading of patterns. The device was made covering three systems (mechanical, mechatronic and control), the integration of systems allowed an efficient design, dimensioned calculations in the mechanical, electrical, and electronic, and its integration of hardware-software for the graphical interface. The system presented allows real-time monitoring of parameters captured by sensors with IOT technology, which has made it possible to deepen and estimate suspected cases of covid by comparing measured values with the ranges of values established by the American Medical Association.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114780903","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 : 2022-05-10DOI: 10.1109/airc56195.2022.9836981
Noor Khalifa, Maryam Alnasheet, Hasan Kadhem
Employees' Attrition has become a well-known concept among organizations in the recent years, and it is a problem that leads to many issues within organizations. Companies can use the enormous amount of data they have about their employees to help solve this problem. This paper focuses on examining the efficiency of different machine-learning techniques that can be used for predicting employees' attrition. The algorithms were chosen based on a detailed comparison between all Machine Learning algorithms provided in MATLAB which led to choosing the most suitable ones to later identify the top performing among them. The most suitable algorithms found are Logistic Regression, Support Vector Machine (Linear, Quadratic, and Kernel), and Boosted Trees. This paper's findings could make a notable impact on businesses' ability to prevent employee attrition.
{"title":"Evaluating Machine Learning Algorithms to Detect Employees' Attrition","authors":"Noor Khalifa, Maryam Alnasheet, Hasan Kadhem","doi":"10.1109/airc56195.2022.9836981","DOIUrl":"https://doi.org/10.1109/airc56195.2022.9836981","url":null,"abstract":"Employees' Attrition has become a well-known concept among organizations in the recent years, and it is a problem that leads to many issues within organizations. Companies can use the enormous amount of data they have about their employees to help solve this problem. This paper focuses on examining the efficiency of different machine-learning techniques that can be used for predicting employees' attrition. The algorithms were chosen based on a detailed comparison between all Machine Learning algorithms provided in MATLAB which led to choosing the most suitable ones to later identify the top performing among them. The most suitable algorithms found are Logistic Regression, Support Vector Machine (Linear, Quadratic, and Kernel), and Boosted Trees. This paper's findings could make a notable impact on businesses' ability to prevent employee attrition.","PeriodicalId":147463,"journal":{"name":"2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121838589","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：