Pub Date : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454187
H. M. I. Salehin, Quazi Rubayet Anjum Joy, Fatima Tuz Zuhra Aparna, Ahnaf Tahmid Ridwan, R. Khan
Nowadays, people have a very busy and hectic life; thus, taking care of an infant constantly is tough. Especially for working parents, a modernized IoT-enabled baby management system will be beneficial. In these modern times, most children are taken care of by their grandparents, housemaids, or babysitters during the daytimes. In this work, we are using a very efficient and user-friendly technology to implement automatic swinging of the baby bassinet with sound detection of the baby crying using sound sensor and playing lullaby through speakers. The humidity sensor has been used to know the diaper's moisture level, and notifications have been sent to parents with certain conditions through mobile calls and text messages. A webpage using HTML and CSS has been developed, where parents/guardians can supervise the baby in real-time. Finally, the system will detect if the baby is in the cradle using the face recognition technique. This exciting feature is implemented by using a Raspberry Pi 4 (Model B), which is equipped with a Pi camera that will also offer the parents a live-stream option. The proposed baby monitoring system is believed to be an improved technology for new and working parents and colossal help and riddance of unrequired tensions.
{"title":"Development of an IoT based Smart Baby Monitoring System with Face Recognition","authors":"H. M. I. Salehin, Quazi Rubayet Anjum Joy, Fatima Tuz Zuhra Aparna, Ahnaf Tahmid Ridwan, R. Khan","doi":"10.1109/AIIoT52608.2021.9454187","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454187","url":null,"abstract":"Nowadays, people have a very busy and hectic life; thus, taking care of an infant constantly is tough. Especially for working parents, a modernized IoT-enabled baby management system will be beneficial. In these modern times, most children are taken care of by their grandparents, housemaids, or babysitters during the daytimes. In this work, we are using a very efficient and user-friendly technology to implement automatic swinging of the baby bassinet with sound detection of the baby crying using sound sensor and playing lullaby through speakers. The humidity sensor has been used to know the diaper's moisture level, and notifications have been sent to parents with certain conditions through mobile calls and text messages. A webpage using HTML and CSS has been developed, where parents/guardians can supervise the baby in real-time. Finally, the system will detect if the baby is in the cradle using the face recognition technique. This exciting feature is implemented by using a Raspberry Pi 4 (Model B), which is equipped with a Pi camera that will also offer the parents a live-stream option. The proposed baby monitoring system is believed to be an improved technology for new and working parents and colossal help and riddance of unrequired tensions.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122360227","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454190
Wesley Bevan Richardson, Johan Meyer, S. V. Solms
While predictive maintenance is a concept that has been around for several decades, it is only due to the relatively recent arrival and expeditious development of fourth industrial revolution technologies, such as the internet of things and machine learning, that it has become more of a reality. Rural communities face several challenges in their day to day lives and while several development projects have been enacted to address these problems, many have failed due to a multitude of factors. One of the contributing factors to these rural development projects failing is the lack of or insufficient maintenance. The aim of this study was to show how fault detection in data driven predictive maintenance in remote and rural locations could be achieved using the one-class support vector machines algorithm and low data rate (bandwidth) internet of things. The results of this study show how fault detection in predictive maintenance can be achieved using the one-class support vector machines algorithm and low bandwidth internet of things sensors, for rural applications. The outcome of this study provides a steppingstone to implementing data driven predictive maintenance in remote and rural locations.
{"title":"Towards Machine Learning and Low Data Rate IoT for Fault Detection in Data Driven Predictive Maintenance","authors":"Wesley Bevan Richardson, Johan Meyer, S. V. Solms","doi":"10.1109/AIIoT52608.2021.9454190","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454190","url":null,"abstract":"While predictive maintenance is a concept that has been around for several decades, it is only due to the relatively recent arrival and expeditious development of fourth industrial revolution technologies, such as the internet of things and machine learning, that it has become more of a reality. Rural communities face several challenges in their day to day lives and while several development projects have been enacted to address these problems, many have failed due to a multitude of factors. One of the contributing factors to these rural development projects failing is the lack of or insufficient maintenance. The aim of this study was to show how fault detection in data driven predictive maintenance in remote and rural locations could be achieved using the one-class support vector machines algorithm and low data rate (bandwidth) internet of things. The results of this study show how fault detection in predictive maintenance can be achieved using the one-class support vector machines algorithm and low bandwidth internet of things sensors, for rural applications. The outcome of this study provides a steppingstone to implementing data driven predictive maintenance in remote and rural locations.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125189634","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454189
S. Sridhar, Sowmya Sanagavarapu
Stock markets have a centralized structure that has a number of intermediaries and operational trade policies contributing to high transaction times. Blockchain has the capability to optimize market transactions using automation with high security to create a peer-to-peer trading environment. It reduces operational risk by enabling transparency, certitude and interoperability in fragmented market systems to eliminate the need for third party regulators to a large extent. In this paper, a decentralized stock exchange system is implemented with Distributed Ledger Technology (DLT) on Ethereum for executing trades by separating concerns into three different smart contracts: buyer, seller and exchange. The self-enforcing smart contracts used are highly flexible and optimized for parallel operation due to functional abstraction. The multi-contract model is compared to a single contract model, which handles all three aspects within the same contract, by executing sample trading data from NASDAQ. Transaction fees for the miner at 161 Gwei is 27.96% lesser for the single-contract system and 98.75% lesser for the multi-contract system than the brokerage fees of traditional traders for the same transactions. Experimental results indicate that the separation of concern results in transaction costs being 98.26% lower and transaction time being 28.70% lower than having a single contract.
{"title":"Analysis of Smart Contract Abstraction in Decentralized Blockchain Based Stock Exchange","authors":"S. Sridhar, Sowmya Sanagavarapu","doi":"10.1109/AIIoT52608.2021.9454189","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454189","url":null,"abstract":"Stock markets have a centralized structure that has a number of intermediaries and operational trade policies contributing to high transaction times. Blockchain has the capability to optimize market transactions using automation with high security to create a peer-to-peer trading environment. It reduces operational risk by enabling transparency, certitude and interoperability in fragmented market systems to eliminate the need for third party regulators to a large extent. In this paper, a decentralized stock exchange system is implemented with Distributed Ledger Technology (DLT) on Ethereum for executing trades by separating concerns into three different smart contracts: buyer, seller and exchange. The self-enforcing smart contracts used are highly flexible and optimized for parallel operation due to functional abstraction. The multi-contract model is compared to a single contract model, which handles all three aspects within the same contract, by executing sample trading data from NASDAQ. Transaction fees for the miner at 161 Gwei is 27.96% lesser for the single-contract system and 98.75% lesser for the multi-contract system than the brokerage fees of traditional traders for the same transactions. Experimental results indicate that the separation of concern results in transaction costs being 98.26% lower and transaction time being 28.70% lower than having a single contract.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133291198","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454217
A. Voevoda, V. Shipagin, V. Filushov
When applying polynomial methods for the synthesis of multichannel controllers, there is a need for polynomial matrix calculus. However, when using this method, plants with the number of output channels equal to the number of input channels are mainly considered. This is necessary for the convenience of solving a system of linear algebraic equations in a matrix polynomial calculation. A fairly large number of real technical systems have an unequal number of input and output channels. At the same time, the issue of the synthesis of controllers by the polynomial method for multi-channel plants with an unequal number of input and output effects is not worked out in depth enough. In this paper, we consider an example of a linear model of an unstable plant consisting of three standard links with three channels for the input action and two channels for the output action. It is necessary to achieve certain quality indicators of the output vector value, while the control is carried out in the feedback of the system and is summed up with the input action. The plant feature is to limit the task to the second output, since it is essentially a derivative of the first output. The plant was represented as a left - hand polynomial matrix fractional description, and the controller was represented as a right-hand one. For the formation of the characteristic matrix of a closed system, with this variant of the plant and controller decomposition, some structural system transformations are demonstrated. The plant simplicity under consideration is related to the convenience of demonstrating a polynomial synthesis method for such a plants class.
{"title":"Multichannel controller synthesis for the plant with three input and two output channels using polynomial matrix decomposition","authors":"A. Voevoda, V. Shipagin, V. Filushov","doi":"10.1109/AIIoT52608.2021.9454217","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454217","url":null,"abstract":"When applying polynomial methods for the synthesis of multichannel controllers, there is a need for polynomial matrix calculus. However, when using this method, plants with the number of output channels equal to the number of input channels are mainly considered. This is necessary for the convenience of solving a system of linear algebraic equations in a matrix polynomial calculation. A fairly large number of real technical systems have an unequal number of input and output channels. At the same time, the issue of the synthesis of controllers by the polynomial method for multi-channel plants with an unequal number of input and output effects is not worked out in depth enough. In this paper, we consider an example of a linear model of an unstable plant consisting of three standard links with three channels for the input action and two channels for the output action. It is necessary to achieve certain quality indicators of the output vector value, while the control is carried out in the feedback of the system and is summed up with the input action. The plant feature is to limit the task to the second output, since it is essentially a derivative of the first output. The plant was represented as a left - hand polynomial matrix fractional description, and the controller was represented as a right-hand one. For the formation of the characteristic matrix of a closed system, with this variant of the plant and controller decomposition, some structural system transformations are demonstrated. The plant simplicity under consideration is related to the convenience of demonstrating a polynomial synthesis method for such a plants class.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134266352","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454219
S. Chawathe
This paper addresses epidemiological spatiotemporal datasets such as those reporting the number of cases of infectious diseases over time and by geographical location. It studies methods for exploratory data analysis and for prediction of future cases based on prior data. It emphasizes methods that provide explainable predictions, such as those based on rules and decision trees. These methods are studied in the context of a recently published dataset of weekly Chickenpox cases in Hungarian counties over a 10-year period. As noted in prior work, this dataset exhibits several features, such as seasonality and heteroskedasticity, that make the prediction task especially challenging. This paper describes some results of an experimental study of both the exploratory and predictive aspects.
{"title":"Epidemiological Spatiotemporal Data Exploration and Prediction","authors":"S. Chawathe","doi":"10.1109/AIIoT52608.2021.9454219","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454219","url":null,"abstract":"This paper addresses epidemiological spatiotemporal datasets such as those reporting the number of cases of infectious diseases over time and by geographical location. It studies methods for exploratory data analysis and for prediction of future cases based on prior data. It emphasizes methods that provide explainable predictions, such as those based on rules and decision trees. These methods are studied in the context of a recently published dataset of weekly Chickenpox cases in Hungarian counties over a 10-year period. As noted in prior work, this dataset exhibits several features, such as seasonality and heteroskedasticity, that make the prediction task especially challenging. This paper describes some results of an experimental study of both the exploratory and predictive aspects.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125863350","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454204
Lahiru J. Ekanayake, Ruwan Dharshana Nawarathna, S. Kodituwakku, R. Yapa, A. Pinidiyaarachchi
The Internet of things (IoT), with its latest technologies, is one of the most trending areas in computer science and engineering. Many IoT applications require only a few bits to be sent to the cloud per iteration. Though there are load balancing and scheduling mechanisms available, every solution requires one or more centralized or edge devices to handle each request. The purpose of this study is to set up an independent device that can directly interact with relevant broker or server nodes in a scheduled manner after the initial communication with the server. This will reduce the server idle time, making the system get the maximum benefits from minimal resources. To achieve that, an algorithm is proposed to issue timestamps for devices of the IoT system without overlapping, where the timestamp is relative to each device but global to all devices. The time amount of 0.00106 seconds can be considered as the minimal time span with effective scheduling due to network communication delay. The proposed architecture and the algorithm can be efficiently applied for all IoT devices where “deep sleep” mode is used for energy saving. Also, it is possible to obtain a considerable increase in terms of optimization (2n) compared with the random deep sleep mode.
{"title":"A Systematic Approach for Scheduling IoT Devices for Effective Load Balancing Based on Deep Sleep","authors":"Lahiru J. Ekanayake, Ruwan Dharshana Nawarathna, S. Kodituwakku, R. Yapa, A. Pinidiyaarachchi","doi":"10.1109/AIIoT52608.2021.9454204","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454204","url":null,"abstract":"The Internet of things (IoT), with its latest technologies, is one of the most trending areas in computer science and engineering. Many IoT applications require only a few bits to be sent to the cloud per iteration. Though there are load balancing and scheduling mechanisms available, every solution requires one or more centralized or edge devices to handle each request. The purpose of this study is to set up an independent device that can directly interact with relevant broker or server nodes in a scheduled manner after the initial communication with the server. This will reduce the server idle time, making the system get the maximum benefits from minimal resources. To achieve that, an algorithm is proposed to issue timestamps for devices of the IoT system without overlapping, where the timestamp is relative to each device but global to all devices. The time amount of 0.00106 seconds can be considered as the minimal time span with effective scheduling due to network communication delay. The proposed architecture and the algorithm can be efficiently applied for all IoT devices where “deep sleep” mode is used for energy saving. Also, it is possible to obtain a considerable increase in terms of optimization (2n) compared with the random deep sleep mode.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116367836","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454193
SK Adif Farhan, Md. Nasfikur R. Khan, Mostafizur Rahman Swaron, Ramendra Narayan Saha Shukhon, Md. Mofijul Islam, Md. Abdur Razzak
This paper shows the primary feedback of children with Autism Spectrum Disorder (ASD) interacting with Humanoid Robot NAO. Four autistic children from Society for the Welfare of Autistic Children (SWAC) is being picked based on their neurological and physical limitations which has been identified by specialist teachers, ASD specialist researchers, and faculty members. Their Intelligence Quotient depends on question-answer based Intelligence Test has been first carried out and they have undergone the autism diagnoses based on Autism Diagnostic Observation sessions by autism specialist teachers from Society for the Welfare of Autistic Children (SWAC). The four of Children with ASD will then involve in the Robot-based Interaction Program, which started from session 1 to session 4. The interaction between Children with ASD and Humanoid Robot NAO is being recorded with Android Phone Video Camera and one mini camera included on the middle of Humanoid Robot NAO for initial feedback analysis based on verbal and non-verbal communications. The interaction session between the children and robot has been developed by using the software named choreographe of Humanoid Robot NAO.
{"title":"Improvement of Verbal and Non-Verbal Communication Skills of Children with Autism Spectrum Disorder using Human Robot Interaction","authors":"SK Adif Farhan, Md. Nasfikur R. Khan, Mostafizur Rahman Swaron, Ramendra Narayan Saha Shukhon, Md. Mofijul Islam, Md. Abdur Razzak","doi":"10.1109/AIIoT52608.2021.9454193","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454193","url":null,"abstract":"This paper shows the primary feedback of children with Autism Spectrum Disorder (ASD) interacting with Humanoid Robot NAO. Four autistic children from Society for the Welfare of Autistic Children (SWAC) is being picked based on their neurological and physical limitations which has been identified by specialist teachers, ASD specialist researchers, and faculty members. Their Intelligence Quotient depends on question-answer based Intelligence Test has been first carried out and they have undergone the autism diagnoses based on Autism Diagnostic Observation sessions by autism specialist teachers from Society for the Welfare of Autistic Children (SWAC). The four of Children with ASD will then involve in the Robot-based Interaction Program, which started from session 1 to session 4. The interaction between Children with ASD and Humanoid Robot NAO is being recorded with Android Phone Video Camera and one mini camera included on the middle of Humanoid Robot NAO for initial feedback analysis based on verbal and non-verbal communications. The interaction session between the children and robot has been developed by using the software named choreographe of Humanoid Robot NAO.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132842607","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454212
Kevin Matthe Caramancion
This paper explores the relationship between a person's outlook on the issues of freedom of speech (IV1), fake news regulation (IV2), and the risk of him/her falling prey to Mis/Disinformation attacks (DV). Participants (n=162) were explicitly asked to choose a position among these issues and were subjected to the Fake News and deepfake test (15-item). The main data analysis tool employed for this study is factorial, two-way ANOVA. Important findings of the study include the revelation of the disparity in the performance of the subjects who are leaning to the government for information regulation against those who prefer the tech companies, among others. The intended target audience of this paper are policymakers and legal professionals possibly seeking for judicial references.
{"title":"Understanding the Association of Personal Outlook in Free Speech Regulation and the Risk of being Mis/Disinformed","authors":"Kevin Matthe Caramancion","doi":"10.1109/AIIoT52608.2021.9454212","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454212","url":null,"abstract":"This paper explores the relationship between a person's outlook on the issues of freedom of speech (IV1), fake news regulation (IV2), and the risk of him/her falling prey to Mis/Disinformation attacks (DV). Participants (n=162) were explicitly asked to choose a position among these issues and were subjected to the Fake News and deepfake test (15-item). The main data analysis tool employed for this study is factorial, two-way ANOVA. Important findings of the study include the revelation of the disparity in the performance of the subjects who are leaning to the government for information regulation against those who prefer the tech companies, among others. The intended target audience of this paper are policymakers and legal professionals possibly seeking for judicial references.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134415926","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454179
Breno Costa Dolabela Dias, H. J. Sadaei, P. C. de Lima e Silva, F. Guimarães
Sentiment analysis is an automatic technique to extract subjective information from texts, such as opinions and sentiments. For providing a time series forecasting using sentiment analysis, sentiment classifications of news and social media posts have to be aggregated into a single value to produce a time series with the same periodicity of the stock market prices, for example daily or hourly. In this paper, we adopt fuzzy linguistic values (and corresponding fuzzy sets) to represent prices and sentiments. Given the fuzzified sentiment index of each tweet, we proceed to an aggregation based on hesitant fuzzy sets, which aim to model the uncertainty caused by the hesitation that may arise in the attribution of degrees of membership of the elements to a fuzzy set. Having fuzzified the sentiment index and aggregated them within the same time period, we produce a fuzzified time series of sentiment data, which can be used as additional information for forecasting models. In this paper, we employ a multivariate fuzzy time series (FTS) method, namely Weighted Multivariate FTS (WMVFTS), as the machine learning model. For the experiments we collected tweets posted by Bloomberg and the closing prices of Standard & Poor's 500 Index and Nasdaq Composite Index. The main feature delivered by the proposed method is the capability of improving an FTS method by using hesitant information, such as the news posted on Twitter.
{"title":"Aggregation of Sentiment Analysis Index with Hesitant Fuzzy Sets for Financial Time Series Forecasting","authors":"Breno Costa Dolabela Dias, H. J. Sadaei, P. C. de Lima e Silva, F. Guimarães","doi":"10.1109/AIIoT52608.2021.9454179","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454179","url":null,"abstract":"Sentiment analysis is an automatic technique to extract subjective information from texts, such as opinions and sentiments. For providing a time series forecasting using sentiment analysis, sentiment classifications of news and social media posts have to be aggregated into a single value to produce a time series with the same periodicity of the stock market prices, for example daily or hourly. In this paper, we adopt fuzzy linguistic values (and corresponding fuzzy sets) to represent prices and sentiments. Given the fuzzified sentiment index of each tweet, we proceed to an aggregation based on hesitant fuzzy sets, which aim to model the uncertainty caused by the hesitation that may arise in the attribution of degrees of membership of the elements to a fuzzy set. Having fuzzified the sentiment index and aggregated them within the same time period, we produce a fuzzified time series of sentiment data, which can be used as additional information for forecasting models. In this paper, we employ a multivariate fuzzy time series (FTS) method, namely Weighted Multivariate FTS (WMVFTS), as the machine learning model. For the experiments we collected tweets posted by Bloomberg and the closing prices of Standard & Poor's 500 Index and Nasdaq Composite Index. The main feature delivered by the proposed method is the capability of improving an FTS method by using hesitant information, such as the news posted on Twitter.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126944905","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 : 2021-05-10DOI: 10.1109/AIIoT52608.2021.9454239
Erol Ozan
Machine learning (ML) application development constitutes a complex process that requires developers to have considerable amount of programming and specialized technical skills. There is still a substantial barrier for researchers who do not possess the programming and technical skills to develop ML models that meets the needs of their specific fields of study. The typical ML model development workflow entails the installation of a set of software elements and a certain amount of code development. This paper introduces a browser-based ML application development tool that is geared towards the needs of researchers who have limited knowledge in programming. The tool allows the users to create a customized image classifier model based on the image sets that they provide. The tool provides a no-code workflow that enables users to create and test their ML models on a browser without downloading any software modules.
{"title":"A Novel Browser-based No-code Machine Learning Application Development Tool","authors":"Erol Ozan","doi":"10.1109/AIIoT52608.2021.9454239","DOIUrl":"https://doi.org/10.1109/AIIoT52608.2021.9454239","url":null,"abstract":"Machine learning (ML) application development constitutes a complex process that requires developers to have considerable amount of programming and specialized technical skills. There is still a substantial barrier for researchers who do not possess the programming and technical skills to develop ML models that meets the needs of their specific fields of study. The typical ML model development workflow entails the installation of a set of software elements and a certain amount of code development. This paper introduces a browser-based ML application development tool that is geared towards the needs of researchers who have limited knowledge in programming. The tool allows the users to create a customized image classifier model based on the image sets that they provide. The tool provides a no-code workflow that enables users to create and test their ML models on a browser without downloading any software modules.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125781321","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：