Pub Date : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668600
I. de Medeiros Esper, L. E. Cordova-Lopez, P. From, A. Mason
This paper presents work relating to the reconstruction of 3D point clouds taken from cameras placed arbitrarily in pairs on either side of an object (a pig carcass in this specific use-case). This poses a challenge for complete object reconstruction since the two sides or halves of the object have little or no overlap and high degree of symmetry. The investigation was part of a data collection inside slaughterhouses for a meat factory cell concept development, where the production line cannot be stopped to perform calibration of the cameras. In addition, the footprint should be small, and the cameras' lenses protected and easy to clean. This work presents the method, or pipeline, used to overcome this challenge along with the performance of the pipeline by comparing real-world and point cloud distance measurements.
{"title":"3D Registration of Multiple RGB-D Cameras on Arbitrary Position of a Symmetric Object with No Overlapping in a Meat Factory Environment","authors":"I. de Medeiros Esper, L. E. Cordova-Lopez, P. From, A. Mason","doi":"10.1109/CINTI53070.2021.9668600","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668600","url":null,"abstract":"This paper presents work relating to the reconstruction of 3D point clouds taken from cameras placed arbitrarily in pairs on either side of an object (a pig carcass in this specific use-case). This poses a challenge for complete object reconstruction since the two sides or halves of the object have little or no overlap and high degree of symmetry. The investigation was part of a data collection inside slaughterhouses for a meat factory cell concept development, where the production line cannot be stopped to perform calibration of the cameras. In addition, the footprint should be small, and the cameras' lenses protected and easy to clean. This work presents the method, or pipeline, used to overcome this challenge along with the performance of the pipeline by comparing real-world and point cloud distance measurements.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129923727","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668375
Abdallah Benhamida, Ghaith Slimani, M. Kucarov, Mera Abbassi, Eszter Koroknai, Anikó Szarvák, Melvin Ogbolu, Miklós Vincze, M. Kozlovszky
ECG graphs show the electrical activity of the heart in function of time. It helps doctors to better understand the actual heart activity of the patient. Before the use of computers in the medical field, the ECG was printed and analyzed on a paper format. Nowadays medical data is archived in digital format and many data formats for ECG data storage are available. The many formats present an important problem of interoperability and compatibility between different data representations. A new technique to solve the interoperability issue and furthermore to store even stream-like ECG data became a necessity to assure better service quality of hospitals and to ensure smooth transition between different formats. This paper proposes a new (working and tested) solution for ECG data conversion, using an intermediate JSON format designed especially for ECG data, from/to SCP-ECG, DICOM-ECG, and HL7 aECG.
{"title":"Effective ECG data conversion solution to solve ECG data interoperability problems","authors":"Abdallah Benhamida, Ghaith Slimani, M. Kucarov, Mera Abbassi, Eszter Koroknai, Anikó Szarvák, Melvin Ogbolu, Miklós Vincze, M. Kozlovszky","doi":"10.1109/CINTI53070.2021.9668375","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668375","url":null,"abstract":"ECG graphs show the electrical activity of the heart in function of time. It helps doctors to better understand the actual heart activity of the patient. Before the use of computers in the medical field, the ECG was printed and analyzed on a paper format. Nowadays medical data is archived in digital format and many data formats for ECG data storage are available. The many formats present an important problem of interoperability and compatibility between different data representations. A new technique to solve the interoperability issue and furthermore to store even stream-like ECG data became a necessity to assure better service quality of hospitals and to ensure smooth transition between different formats. This paper proposes a new (working and tested) solution for ECG data conversion, using an intermediate JSON format designed especially for ECG data, from/to SCP-ECG, DICOM-ECG, and HL7 aECG.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114722942","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668462
Mohammed Faeik Ruzaij AI-Okby, S. Neubert, T. Roddelkopf, K. Thurow
The occurrence of hazardous gases and toxic or harmful vapors in laboratories, factories, and chemical warehouses requires a fast detection of leakage accidents to avoid health impairments. In this paper, the integration and validation of two novel metal oxide gas sensors (MOX) for the application in an IoT-based air quality monitoring and the alarming system is proposed. The sensors are combined with WeMos D1 Mini IoT-based microcontroller for data processing and transmitting via Wi-Fi communication protocol. The system design takes into consideration the low-cost, light-weight, small-size, and low power consumption concepts to enable a portable compact system that can be operated stand-alone or easily be adapted to any stationary or mobile robotic platform. The system was tested with several volatile organic materials (VOCs). The acquired air quality data are transferred to an IoT cloud, where the data are stored in a database for further analysis and research. Further, the data can be directly monitored on a PC, tablet, and smartphone. The system testing results confirm that the system can be used efficiently in laboratory environments.
在实验室、工厂和化学品仓库中发生危险气体和有毒或有害蒸气，需要快速检测泄漏事故，以避免对健康造成损害。本文提出了两种新型金属氧化物气体传感器(MOX)的集成和验证，用于基于物联网的空气质量监测和报警系统。传感器与WeMos D1 Mini iot微控制器相结合，通过Wi-Fi通信协议进行数据处理和传输。该系统设计考虑了低成本、轻重量、小尺寸和低功耗的概念，使便携式紧凑系统可以独立操作，也可以轻松适应任何固定或移动机器人平台。对该系统进行了几种挥发性有机物质(VOCs)的测试。获取的空气质量数据被传输到物联网云，数据存储在数据库中，供进一步分析和研究。此外，数据可以直接在PC、平板电脑和智能手机上进行监控。系统测试结果表明，该系统可以在实验室环境中高效使用。
{"title":"Integration and Testing of Novel MOX Gas Sensors for IoT-based Indoor Air Quality Monitoring","authors":"Mohammed Faeik Ruzaij AI-Okby, S. Neubert, T. Roddelkopf, K. Thurow","doi":"10.1109/CINTI53070.2021.9668462","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668462","url":null,"abstract":"The occurrence of hazardous gases and toxic or harmful vapors in laboratories, factories, and chemical warehouses requires a fast detection of leakage accidents to avoid health impairments. In this paper, the integration and validation of two novel metal oxide gas sensors (MOX) for the application in an IoT-based air quality monitoring and the alarming system is proposed. The sensors are combined with WeMos D1 Mini IoT-based microcontroller for data processing and transmitting via Wi-Fi communication protocol. The system design takes into consideration the low-cost, light-weight, small-size, and low power consumption concepts to enable a portable compact system that can be operated stand-alone or easily be adapted to any stationary or mobile robotic platform. The system was tested with several volatile organic materials (VOCs). The acquired air quality data are transferred to an IoT cloud, where the data are stored in a database for further analysis and research. Further, the data can be directly monitored on a PC, tablet, and smartphone. The system testing results confirm that the system can be used efficiently in laboratory environments.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130338462","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668550
Nguyen Huu Phuoc Dai, Lourdes Ruiz, Rajnai Zoltán
5G stands for the fifth and the latest generation in wireless networks. It offers three main technological advances compared to the previous standards: more speed network, reduced latency, and higher bandwidth. These improvements bring many applications in different industries such as manufacturing, healthcare, transportation, and more. However, it also faces various issues regarding spectrum, deployment, and security. This paper aims to provide an updated overview of this technology, the opportunities, and challenges to raise awareness and educate about the 5G revolution.
{"title":"5G revolution: Challenges and opportunities","authors":"Nguyen Huu Phuoc Dai, Lourdes Ruiz, Rajnai Zoltán","doi":"10.1109/CINTI53070.2021.9668550","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668550","url":null,"abstract":"5G stands for the fifth and the latest generation in wireless networks. It offers three main technological advances compared to the previous standards: more speed network, reduced latency, and higher bandwidth. These improvements bring many applications in different industries such as manufacturing, healthcare, transportation, and more. However, it also faces various issues regarding spectrum, deployment, and security. This paper aims to provide an updated overview of this technology, the opportunities, and challenges to raise awareness and educate about the 5G revolution.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126136129","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668584
F. Basçiftçi, L. M. Bokiye
Nowadays our life is becoming smart and simple with the help of smart and intelligent systems. The Internet of Things concept is enabling most digital devices to work cooperatively. In this article, we proposed a Library Management Automation system that is based on the Radio Frequency Identification (RFID) technology. The books and Students ID have RFID tags that are attached to them and hold information about books and students respectively. RFID readers used to read RFID tags attached to the books and students' IDs to do all tasks like the efficient and proper theft-controlled operation of libraries. This system will be connected to an RFID reader and printer. The main task of this system is to make work easy for users and librarians. Moreover, this system will be more user-friendly and easy. The proposed system reduces time and labor approximately from 70-80% after implementation.
{"title":"IoT Based Library Management Automation System Using RFID","authors":"F. Basçiftçi, L. M. Bokiye","doi":"10.1109/CINTI53070.2021.9668584","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668584","url":null,"abstract":"Nowadays our life is becoming smart and simple with the help of smart and intelligent systems. The Internet of Things concept is enabling most digital devices to work cooperatively. In this article, we proposed a Library Management Automation system that is based on the Radio Frequency Identification (RFID) technology. The books and Students ID have RFID tags that are attached to them and hold information about books and students respectively. RFID readers used to read RFID tags attached to the books and students' IDs to do all tasks like the efficient and proper theft-controlled operation of libraries. This system will be connected to an RFID reader and printer. The main task of this system is to make work easy for users and librarians. Moreover, this system will be more user-friendly and easy. The proposed system reduces time and labor approximately from 70-80% after implementation.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130109799","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668314
Viera Anderková, F. Babič
The road safety management system aims to ensure a safe transport system for all road users. Analyses of data about traffic accidents can provide important knowledge to support relevant decision-makers or processes. This fact motivated our case study covering the analytical process over publicly available data about traffic accidents in England, Scotland, and Wales. Based on our previous experience with this dataset, we aimed not on the prediction models and their accuracy, but on their explanations for the end-users with limited knowledge from data mining, machine learning, or artificial intelligence. For this purpose, we improved the generated decision models with selected explainable methods like The Local Interpretable Model-Agnostic Explanation (LIME) and SHap Additive exPlanations (SHAP) values. The final visualizations show which attributes and to what extent they contribute to each type of accident.
{"title":"Better understandability of prediction models: a case study for data-based road safety management system","authors":"Viera Anderková, F. Babič","doi":"10.1109/CINTI53070.2021.9668314","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668314","url":null,"abstract":"The road safety management system aims to ensure a safe transport system for all road users. Analyses of data about traffic accidents can provide important knowledge to support relevant decision-makers or processes. This fact motivated our case study covering the analytical process over publicly available data about traffic accidents in England, Scotland, and Wales. Based on our previous experience with this dataset, we aimed not on the prediction models and their accuracy, but on their explanations for the end-users with limited knowledge from data mining, machine learning, or artificial intelligence. For this purpose, we improved the generated decision models with selected explainable methods like The Local Interpretable Model-Agnostic Explanation (LIME) and SHap Additive exPlanations (SHAP) values. The final visualizations show which attributes and to what extent they contribute to each type of accident.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125569112","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668488
S. Karakatič, D. Fister, Ömer Faruk Beyca, Iztok Fister
The paper proposes an innovative approach in solving the fault detection problem of sewerage treatment plant machinery. The proposed approach treats the fault detection data with the class decomposition problem, ensuring that a classification algorithm overlooks no disjunct instances. As the class decomposition technique requires heavy customization to each class of instances in every data set, Grey Wolf Optimizer is used to determine the appropriate clustering method with the appropriate setting for each class of instances. The proposed approach is tested on real-life sensor data from a sewerage treatment plant, and the results show that here proposed approach overshadows several manually proposed class decomposition methods.
本文提出了一种解决污水处理厂机械故障检测问题的创新方法。该方法利用类分解问题处理故障检测数据，保证了分类算法不会忽略不相交的实例。由于类分解技术需要对每个数据集中的每一类实例进行大量定制，因此使用Grey Wolf Optimizer为每一类实例确定具有适当设置的适当聚类方法。在污水处理厂的真实传感器数据上对所提出的方法进行了测试，结果表明所提出的方法掩盖了几种人工提出的分类分解方法。
{"title":"Optimized Class Decomposition for Fault Detection","authors":"S. Karakatič, D. Fister, Ömer Faruk Beyca, Iztok Fister","doi":"10.1109/CINTI53070.2021.9668488","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668488","url":null,"abstract":"The paper proposes an innovative approach in solving the fault detection problem of sewerage treatment plant machinery. The proposed approach treats the fault detection data with the class decomposition problem, ensuring that a classification algorithm overlooks no disjunct instances. As the class decomposition technique requires heavy customization to each class of instances in every data set, Grey Wolf Optimizer is used to determine the appropriate clustering method with the appropriate setting for each class of instances. The proposed approach is tested on real-life sensor data from a sewerage treatment plant, and the results show that here proposed approach overshadows several manually proposed class decomposition methods.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116862080","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668551
Zoltán Vízvári, Nina Gyorfi, Mihály Klincsik, Zoltan Sári, Attila Tóth, P. Odry
Our research group examines a new aspect of the implementation of the Electrical Impedance Tomography (EIT) inverse problem solving method. As a result, the investigated material, which can be considered a continuum, is modeled as a linear network with concentrated parameters. In this article we managed to generalize the mathematical model that it also takes into account the dielectric constant of the material (the pair of concentrated parameters, i.e. the capacity). Thus, despite a significant increase in the number of unknowns in the model, we created an opportunity to apply a multi-frequency approach, as a result of which the optimized system of equations always remains overdetermined. After defining the mathematical model, for its validation, we created a physical model in order to reconstruct the resistance and capacitor values placed on the branches of the graph within their tolerance.
{"title":"Validation of a Self-developed Algorithm for Solving Inverse Problems on Impedance Networks","authors":"Zoltán Vízvári, Nina Gyorfi, Mihály Klincsik, Zoltan Sári, Attila Tóth, P. Odry","doi":"10.1109/CINTI53070.2021.9668551","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668551","url":null,"abstract":"Our research group examines a new aspect of the implementation of the Electrical Impedance Tomography (EIT) inverse problem solving method. As a result, the investigated material, which can be considered a continuum, is modeled as a linear network with concentrated parameters. In this article we managed to generalize the mathematical model that it also takes into account the dielectric constant of the material (the pair of concentrated parameters, i.e. the capacity). Thus, despite a significant increase in the number of unknowns in the model, we created an opportunity to apply a multi-frequency approach, as a result of which the optimized system of equations always remains overdetermined. After defining the mathematical model, for its validation, we created a physical model in order to reconstruct the resistance and capacitor values placed on the branches of the graph within their tolerance.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115891280","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668337
Ferenc Tolner, M. Takács, G. Eigner, Balázs Barta
Textual data provides a new perspective and a huge potential with additional information in analysing and segmenting business organisations. Statistical “hard data” is often too general or even misleading and might be affected by several exogenous and endogenous factors while questionnaire or survey related “soft data” is hardly available or can be biased by the interviewees position in the organisation or by its own personal orientation. On the other hand, besides the aforementioned information sources business organisations, education- and research institutions etc. provide many times textual data on themselves as well, that can further contribute to the understanding of the investigated population. In this paper a topic modeling of 51 Central European business-, educational- and research organisation has been performed by Latent Dirichlet Allocation (LDA). The investigated organisations were partakers of an online survey where their textual organisational descriptions were collected together with basic geographical and industry related data. Based on the result a grouping of the stakeholders has been implemented and an LDA based methodology has been tested in order to further support cluster-forming efforts of business- and other type of organisations within the Central European region.
{"title":"Clustering of Business Organisations based on Textual Data - An LDA Topic Modeling Approach","authors":"Ferenc Tolner, M. Takács, G. Eigner, Balázs Barta","doi":"10.1109/CINTI53070.2021.9668337","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668337","url":null,"abstract":"Textual data provides a new perspective and a huge potential with additional information in analysing and segmenting business organisations. Statistical “hard data” is often too general or even misleading and might be affected by several exogenous and endogenous factors while questionnaire or survey related “soft data” is hardly available or can be biased by the interviewees position in the organisation or by its own personal orientation. On the other hand, besides the aforementioned information sources business organisations, education- and research institutions etc. provide many times textual data on themselves as well, that can further contribute to the understanding of the investigated population. In this paper a topic modeling of 51 Central European business-, educational- and research organisation has been performed by Latent Dirichlet Allocation (LDA). The investigated organisations were partakers of an online survey where their textual organisational descriptions were collected together with basic geographical and industry related data. Based on the result a grouping of the stakeholders has been implemented and an LDA based methodology has been tested in order to further support cluster-forming efforts of business- and other type of organisations within the Central European region.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"55 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113938705","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 : 2021-11-18DOI: 10.1109/CINTI53070.2021.9668426
Bálint Tamás Rozgonyi, Natabara Máté Gyöngyössy, Beáta Korcsok, J. Botzheim
With the advancement of social artificial agents the need for correct understanding of sentiment is growing. In this paper we propose a method for building a context-less word-level emotional model of words in the Hungarian language based on Russell's Circumpex model of affect. By utilizing Bacterial Evo-lutionary Algorithm for feature selection, a method for efficient web-based annotation is proposed. Using the latent information of word embeddings multi-layer perceptron networks are trained to realize an interpolative function of two-dimensional emotion vectors over the embedding space. Dimensionality reduction via correlation analysis is also discussed.
{"title":"Bacterial Evolutionary Algorithm-based Feature Selection for Word Sentiment Interpolation in Hungarian Language","authors":"Bálint Tamás Rozgonyi, Natabara Máté Gyöngyössy, Beáta Korcsok, J. Botzheim","doi":"10.1109/CINTI53070.2021.9668426","DOIUrl":"https://doi.org/10.1109/CINTI53070.2021.9668426","url":null,"abstract":"With the advancement of social artificial agents the need for correct understanding of sentiment is growing. In this paper we propose a method for building a context-less word-level emotional model of words in the Hungarian language based on Russell's Circumpex model of affect. By utilizing Bacterial Evo-lutionary Algorithm for feature selection, a method for efficient web-based annotation is proposed. Using the latent information of word embeddings multi-layer perceptron networks are trained to realize an interpolative function of two-dimensional emotion vectors over the embedding space. Dimensionality reduction via correlation analysis is also discussed.","PeriodicalId":340545,"journal":{"name":"2021 IEEE 21st International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133455173","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：