Pub Date : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689811
A. Z. Zadidul Karim, Md. Sazal Miah, G. R. Ahmed Jamal, Rafatul Alam Fahima, Muhammad Towhidur Rahman
In this research, we study the representation of remote photoplethysmography signals based on a low-cost RGB camera. Photoplethysmography etymologically is a compound term where the “plethysmo” stands for the “enlargement” in Greek. The remote photoplethysmography is recently utilized to evaluate heart rate through a camera that continuously monitors the blood volume pulse. It is a method of physiological parameters like heart rate, respiratory rate, and measuring the blood volume change in the tissue. Photoplethysmography-based approaches can be categorized into two groups: contact and non-contact photoplethysmography. The contact photoplethysmography approach is a fingertip pulse oximeter, broadly utilized in medical centers/hospitals. On the other hand, non-contact photoplethysmography changes the color around the face, which is specially used in cameras. A benchmark dataset that contains stationary and motion videos has been developed.
{"title":"Application of Chrominance Based rPPG in Estimation of Heart Rate from Video Signal","authors":"A. Z. Zadidul Karim, Md. Sazal Miah, G. R. Ahmed Jamal, Rafatul Alam Fahima, Muhammad Towhidur Rahman","doi":"10.1109/ICCIT54785.2021.9689811","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689811","url":null,"abstract":"In this research, we study the representation of remote photoplethysmography signals based on a low-cost RGB camera. Photoplethysmography etymologically is a compound term where the “plethysmo” stands for the “enlargement” in Greek. The remote photoplethysmography is recently utilized to evaluate heart rate through a camera that continuously monitors the blood volume pulse. It is a method of physiological parameters like heart rate, respiratory rate, and measuring the blood volume change in the tissue. Photoplethysmography-based approaches can be categorized into two groups: contact and non-contact photoplethysmography. The contact photoplethysmography approach is a fingertip pulse oximeter, broadly utilized in medical centers/hospitals. On the other hand, non-contact photoplethysmography changes the color around the face, which is specially used in cameras. A benchmark dataset that contains stationary and motion videos has been developed.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132561795","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689816
Bahauddin Taha, Fahmida Rahman Liza
Malaria has been a severe ailment spread by the plasmodium parasite, which is conveyed by the bite of an infected Anopheles mosquito. The conventional method of diagnosing malaria is to look for parasite-infected erythrocytes in human blood smears under a microscope by trained personnel. The outcome of this approach depends on the expertise of the persons performing the tests and sometimes they cannot maintain optimal proficiency. Deep learning can be a highly advantageous option as a means of clinical diagnostics. This paper presents two unique deep learning models for identifying malaria from blood cell images based on convolutional neural networks. Accuracy, recall and Matthews correlation coefficient were used to evaluate these models. Proposed method is more effective than the conventional approach of malaria detection which is time-consuming and will help physicians detect the disease more quickly and effortlessly.
{"title":"Automatic identification of malaria-infected cells using deep convolutional neural network","authors":"Bahauddin Taha, Fahmida Rahman Liza","doi":"10.1109/ICCIT54785.2021.9689816","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689816","url":null,"abstract":"Malaria has been a severe ailment spread by the plasmodium parasite, which is conveyed by the bite of an infected Anopheles mosquito. The conventional method of diagnosing malaria is to look for parasite-infected erythrocytes in human blood smears under a microscope by trained personnel. The outcome of this approach depends on the expertise of the persons performing the tests and sometimes they cannot maintain optimal proficiency. Deep learning can be a highly advantageous option as a means of clinical diagnostics. This paper presents two unique deep learning models for identifying malaria from blood cell images based on convolutional neural networks. Accuracy, recall and Matthews correlation coefficient were used to evaluate these models. Proposed method is more effective than the conventional approach of malaria detection which is time-consuming and will help physicians detect the disease more quickly and effortlessly.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132035773","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689884
Md. Ashfaqul Haque, Israt Jahan Dristy, Mohammad Tariqul Islam Tuhin, Ali Hossain Sagar, Jayed Mohammad Barek
Proper intent classification of web queries is significant in providing users with accurate search results. For STEM-related searches, the generalized search engine provides some discrete results, and it becomes challenging to find the desired ones. Here, in our work, we have used a semi-supervised process and compared it with supervising approaches. This process has been done on Java and C# Bing web queries. From the performance comparison, we have found that our semi-supervised model has performed better than others according to accuracy and f1-score. We have also analyzed the performance by changing training data size, doing error analysis on all models, and finished by presenting how this prediction can be used on a search data fetching process.
{"title":"Prediction on Intent Classification of Java and C# Web queries using Semi-supervision","authors":"Md. Ashfaqul Haque, Israt Jahan Dristy, Mohammad Tariqul Islam Tuhin, Ali Hossain Sagar, Jayed Mohammad Barek","doi":"10.1109/ICCIT54785.2021.9689884","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689884","url":null,"abstract":"Proper intent classification of web queries is significant in providing users with accurate search results. For STEM-related searches, the generalized search engine provides some discrete results, and it becomes challenging to find the desired ones. Here, in our work, we have used a semi-supervised process and compared it with supervising approaches. This process has been done on Java and C# Bing web queries. From the performance comparison, we have found that our semi-supervised model has performed better than others according to accuracy and f1-score. We have also analyzed the performance by changing training data size, doing error analysis on all models, and finished by presenting how this prediction can be used on a search data fetching process.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"779 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133039285","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689797
Mimun Barid, S. Hossain, Md. Mahmudur Rahman, M. Hasan
The study aims to employ sentiment analysis on Twitter data to determine the behavioral aspects of the ICC(International Cricket Council)’ s top-ranked ODI male all-rounders. The majority of the sportsmen share their thoughts and personal life events on social media platforms like Twitter. We identify some similarities and differences on several sentiment parameters. In addition, we present some insights into sentiments via some multidimensional analyses. Furthermore, the dispositions of those players are being studied and retained for future references, and a systematic way is being explored with a view to examining cricketers’ Twitter activities. This research includes a total of 56889 tweets from the verified Twitter account of 26 ODI all-rounders. We use the Big 5 personality attributes as one of the sentiment analysis methodologies that provide us with some pertinent findings of the pro-social sentiments of top-ranked all-rounders.
{"title":"Sentiment Analysis applying the Big 5 and Polarity on the ICC’s Top ODI All-Rounders based on Twitter","authors":"Mimun Barid, S. Hossain, Md. Mahmudur Rahman, M. Hasan","doi":"10.1109/ICCIT54785.2021.9689797","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689797","url":null,"abstract":"The study aims to employ sentiment analysis on Twitter data to determine the behavioral aspects of the ICC(International Cricket Council)’ s top-ranked ODI male all-rounders. The majority of the sportsmen share their thoughts and personal life events on social media platforms like Twitter. We identify some similarities and differences on several sentiment parameters. In addition, we present some insights into sentiments via some multidimensional analyses. Furthermore, the dispositions of those players are being studied and retained for future references, and a systematic way is being explored with a view to examining cricketers’ Twitter activities. This research includes a total of 56889 tweets from the verified Twitter account of 26 ODI all-rounders. We use the Big 5 personality attributes as one of the sentiment analysis methodologies that provide us with some pertinent findings of the pro-social sentiments of top-ranked all-rounders.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125972446","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689787
Rifat Rahman, Md. Abdul Masud, Raonak Jahan Mimi, Mst. Nusrat Sultana Dina
Opinion mining of consumers has become one of the undeniable approaches for finding gaps in businesses’ marketing strategies. For today’s gently growing film industry of Bangladesh, sentiment mining of viewers feedback on their specified work has become inevitably a dire need for the production company and also for the audiences to take decision about watching a film. With the availability of such a great extent of e-content on film reviews, it becomes handy to analyze the viewers’ sentiment on any film. Because of the lack of structured research work on Bengali movie review sentiment analysis, we are interested to focus this kind of research work. We collect 3000 Bengali movie reviews and extract TF-IDF features by using uni-gram, bi-gram, and tri-gram models. We use several machine learning classifiers for performing classification solutions on extracted TF-IDF features of the corpus. Experimental results show that the Multinomial Naïve Bayes classifier provides the highest accuracy, 86%, on uni-gram features of the validation data.
{"title":"Sentiment Analysis on Bengali Movie Reviews using Multinomial Naïve Bayes","authors":"Rifat Rahman, Md. Abdul Masud, Raonak Jahan Mimi, Mst. Nusrat Sultana Dina","doi":"10.1109/ICCIT54785.2021.9689787","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689787","url":null,"abstract":"Opinion mining of consumers has become one of the undeniable approaches for finding gaps in businesses’ marketing strategies. For today’s gently growing film industry of Bangladesh, sentiment mining of viewers feedback on their specified work has become inevitably a dire need for the production company and also for the audiences to take decision about watching a film. With the availability of such a great extent of e-content on film reviews, it becomes handy to analyze the viewers’ sentiment on any film. Because of the lack of structured research work on Bengali movie review sentiment analysis, we are interested to focus this kind of research work. We collect 3000 Bengali movie reviews and extract TF-IDF features by using uni-gram, bi-gram, and tri-gram models. We use several machine learning classifiers for performing classification solutions on extracted TF-IDF features of the corpus. Experimental results show that the Multinomial Naïve Bayes classifier provides the highest accuracy, 86%, on uni-gram features of the validation data.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124917730","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 : 2021-12-18DOI: 10.1109/iccit54785.2021.9689818
{"title":"[Copyright notice]","authors":"","doi":"10.1109/iccit54785.2021.9689818","DOIUrl":"https://doi.org/10.1109/iccit54785.2021.9689818","url":null,"abstract":"","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125021709","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689878
M. Rahman, S. M. Mahbubur Rahman
The purpose of an avatar is to intensify the sense of reality in a simulated environment such as a virtual reality system. This is done by creating a replica of a real person in virtual reality, as intricately as possible. Implementation of 3D scanners (i.e., Microsoft Kinect) produced vast opportunities for creating 3D models of celebrities and other people who can afford them. These humanoid 3D models as well as fictional human avatars opened the door of perceiving a more realistic 3D system than before. However, a simplified approach of fully rigged 3D head avatar synthesis may help to expand the application of 3D avatars allowing anyone to feel a personalized experience of their own avatar. In this work, we propose a system of 3D head avatar synthesis at the user-end, using an easily accessible and low-cost sensor (smartphone camera). Our proposed methodology consists of data acquisition of the concerned person as video, feature extraction and matching, image registration, formation of structure form motion and post-processing. Without requiring any training data, our method provides a satisfactory performance based on the experimental results. Additionally, we release a public database for avatar synthesis from smartphone video and introduce a set of attributes to evaluate the synthesized 3D avatars.
{"title":"Synthesis of User-Level 3D Head Avatar from Smartphone Video for Virtual Reality","authors":"M. Rahman, S. M. Mahbubur Rahman","doi":"10.1109/ICCIT54785.2021.9689878","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689878","url":null,"abstract":"The purpose of an avatar is to intensify the sense of reality in a simulated environment such as a virtual reality system. This is done by creating a replica of a real person in virtual reality, as intricately as possible. Implementation of 3D scanners (i.e., Microsoft Kinect) produced vast opportunities for creating 3D models of celebrities and other people who can afford them. These humanoid 3D models as well as fictional human avatars opened the door of perceiving a more realistic 3D system than before. However, a simplified approach of fully rigged 3D head avatar synthesis may help to expand the application of 3D avatars allowing anyone to feel a personalized experience of their own avatar. In this work, we propose a system of 3D head avatar synthesis at the user-end, using an easily accessible and low-cost sensor (smartphone camera). Our proposed methodology consists of data acquisition of the concerned person as video, feature extraction and matching, image registration, formation of structure form motion and post-processing. Without requiring any training data, our method provides a satisfactory performance based on the experimental results. Additionally, we release a public database for avatar synthesis from smartphone video and introduce a set of attributes to evaluate the synthesized 3D avatars.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125174422","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689809
Sanzid Hossain Tayef, Md. Muhidur Rahman, Md. Abu Bakkar Sakib
The smart home is an advantageous home setup where all home appliances and gadgets can be specially built automatically from any connected web location in the world via smartphone or device. Many current systems are not available to most consumers due to high costs and maintenance difficulties. Furthermore, the existing systems are either locally or remotely operated. Last but not least is the lack of an easy-to-use GUI. To address these limitations, this project proposes a cost-effective and hybrid (local and remote) IoT-based home automation system that monitors and controls home appliances easily and efficiently through a user-friendly interface using smartphones and/or laptops. The goal of the project is to develop the design and production of an existing smart home prototype using IoT technology. In this project, A smart home has been designed and presented using MQTT (MQ Telemetry Transport) communication system in which included different smart objects used for home automation such as smart fans, smart lights, smart doors, fire sprinklers, etc. and different sensors. To governance these smart objects and sensors, we use the cayenne IOT platform that utilizes the MQTT system to publish or subscribe, i.e., receive data and an If This Than That (IFTTT) interface. As for the hardware section, we’ve to use NodeMCU- ESPS266 microcontroller in which has built-in Wi-Fi communication system NodeMCU is a widely used controller for its low cost and higher performance characteristics.
智能家居是一种有利的家庭设置，所有的家用电器和小工具都可以通过智能手机或设备从世界上任何连接的网络位置自动构建。由于成本高和维护困难，大多数消费者无法使用当前的许多系统。此外，现有的系统要么是本地操作，要么是远程操作。最后但并非最不重要的是缺乏易于使用的GUI。为了解决这些限制，该项目提出了一种具有成本效益的混合(本地和远程)基于物联网的家庭自动化系统，该系统通过使用智能手机和/或笔记本电脑的用户友好界面轻松有效地监控和控制家用电器。该项目的目标是利用物联网技术开发现有智能家居原型的设计和生产。在这个项目中，使用MQTT (MQ遥测传输)通信系统设计和展示了一个智能家居，其中包括用于家庭自动化的不同智能对象，如智能风扇，智能灯，智能门，消防喷头等和不同的传感器。为了管理这些智能对象和传感器，我们使用卡宴物联网平台，该平台利用MQTT系统发布或订阅，即接收数据和If This Than that (IFTTT)接口。在硬件部分，我们必须使用内置Wi-Fi通信系统的NodeMCU- ESPS266微控制器，NodeMCU以其低成本和高性能的特点被广泛使用。
{"title":"Design and Implementation of IoT based Smart Home Automation System","authors":"Sanzid Hossain Tayef, Md. Muhidur Rahman, Md. Abu Bakkar Sakib","doi":"10.1109/ICCIT54785.2021.9689809","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689809","url":null,"abstract":"The smart home is an advantageous home setup where all home appliances and gadgets can be specially built automatically from any connected web location in the world via smartphone or device. Many current systems are not available to most consumers due to high costs and maintenance difficulties. Furthermore, the existing systems are either locally or remotely operated. Last but not least is the lack of an easy-to-use GUI. To address these limitations, this project proposes a cost-effective and hybrid (local and remote) IoT-based home automation system that monitors and controls home appliances easily and efficiently through a user-friendly interface using smartphones and/or laptops. The goal of the project is to develop the design and production of an existing smart home prototype using IoT technology. In this project, A smart home has been designed and presented using MQTT (MQ Telemetry Transport) communication system in which included different smart objects used for home automation such as smart fans, smart lights, smart doors, fire sprinklers, etc. and different sensors. To governance these smart objects and sensors, we use the cayenne IOT platform that utilizes the MQTT system to publish or subscribe, i.e., receive data and an If This Than That (IFTTT) interface. As for the hardware section, we’ve to use NodeMCU- ESPS266 microcontroller in which has built-in Wi-Fi communication system NodeMCU is a widely used controller for its low cost and higher performance characteristics.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127411737","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689776
T. Rani, T. K. Roy
In this work, to maintain proper power in DC microgrids, a robust integral-sliding mode controller is designed by considering the continuous function-based fast power reaching law. In a DC microgrid to ensure the power balance, a constant and stable DC-bus is considered as a key indicator. Hence, controlling the DC microgrid’s different components’ output power is necessary to keep the DC bus voltage constant. To meet this control requirement, each microgrid component is interfaced to the DC-bus with a respective power electronic converter. The proposed DC microgrid compromises with a solar photovoltaic (SPV) system, a battery, and DC loads. Hence, the SPV is interfaced with a DC-DC boost converter to match its output voltage with the DC-bus voltage. On the other hand, a DC-DC buck-boost converter is used with the battery for controlling its discharging and charging current. The controller is designed for all of these components i.e., SPV and battery to control their corresponding output power while keeping a constant value of the DC-bus voltage. Afterward, to prove the overall stability of the system, the Lyapunov theory is used. Finally, a simulation study under different operating scenarios is conducted to validate the usefulness of the designed controller and it compares with the existing controller to confirm its superiority.
{"title":"Design of a Robust Integral Sliding Mode Controller Considering Continuous Function-Based Fast Power Reaching Law for DC Microgrids","authors":"T. Rani, T. K. Roy","doi":"10.1109/ICCIT54785.2021.9689776","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689776","url":null,"abstract":"In this work, to maintain proper power in DC microgrids, a robust integral-sliding mode controller is designed by considering the continuous function-based fast power reaching law. In a DC microgrid to ensure the power balance, a constant and stable DC-bus is considered as a key indicator. Hence, controlling the DC microgrid’s different components’ output power is necessary to keep the DC bus voltage constant. To meet this control requirement, each microgrid component is interfaced to the DC-bus with a respective power electronic converter. The proposed DC microgrid compromises with a solar photovoltaic (SPV) system, a battery, and DC loads. Hence, the SPV is interfaced with a DC-DC boost converter to match its output voltage with the DC-bus voltage. On the other hand, a DC-DC buck-boost converter is used with the battery for controlling its discharging and charging current. The controller is designed for all of these components i.e., SPV and battery to control their corresponding output power while keeping a constant value of the DC-bus voltage. Afterward, to prove the overall stability of the system, the Lyapunov theory is used. Finally, a simulation study under different operating scenarios is conducted to validate the usefulness of the designed controller and it compares with the existing controller to confirm its superiority.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124102738","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689810
Rezwana Mahfuza, R. Uddin, Yeaminur Rahman, Md. Abdul Hai
A superstore is an extensive store offering a diverse variety of everyday commodities under one roof, saving customers the trouble of shopping at different locations. The market industry is rapidly expanding, and to maximize profit utilizing customer behaviour, superstores need to constantly monitor their client’s purchasing patterns and take appropriate measures to keep their loyalty while pushing them to spend more and bring in more new clients. The research presents a suitable framework for segmenting superstore consumers based on their attributes and assessing customer value through profit analysis applying appropriate segmentation and clustering techniques. An extensive comparison of the recency, frequency, monetary value (RFM) and length, recency, frequency, monetary value (LRFM) models employing three clustering algorithms: K-means Clustering, Agglomerative Clustering, and Fuzzy C-means Clustering is experimented to obtain the optimal framework. According to the findings, the LRFM model with the K-means algorithm produces the most promising output. It consists of 7 clusters where cluster 3 is the most crucial cluster as its customers hold the most customer value and generate the most profit for the superstore. As a result, superstore owners have a better understanding of their customers’ needs and wants, allowing them to implement effective marketing strategies for the relevant sector.
{"title":"A Comprehensive Framework for Superstore Business with Employing Effective Clustering Techniques","authors":"Rezwana Mahfuza, R. Uddin, Yeaminur Rahman, Md. Abdul Hai","doi":"10.1109/ICCIT54785.2021.9689810","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689810","url":null,"abstract":"A superstore is an extensive store offering a diverse variety of everyday commodities under one roof, saving customers the trouble of shopping at different locations. The market industry is rapidly expanding, and to maximize profit utilizing customer behaviour, superstores need to constantly monitor their client’s purchasing patterns and take appropriate measures to keep their loyalty while pushing them to spend more and bring in more new clients. The research presents a suitable framework for segmenting superstore consumers based on their attributes and assessing customer value through profit analysis applying appropriate segmentation and clustering techniques. An extensive comparison of the recency, frequency, monetary value (RFM) and length, recency, frequency, monetary value (LRFM) models employing three clustering algorithms: K-means Clustering, Agglomerative Clustering, and Fuzzy C-means Clustering is experimented to obtain the optimal framework. According to the findings, the LRFM model with the K-means algorithm produces the most promising output. It consists of 7 clusters where cluster 3 is the most crucial cluster as its customers hold the most customer value and generate the most profit for the superstore. As a result, superstore owners have a better understanding of their customers’ needs and wants, allowing them to implement effective marketing strategies for the relevant sector.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127225054","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：