Pub Date : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532572
Benjir Islam Alvee, Sadia Nasrin Tisha, Amitabha Chakrabarty
Involving machine learning in recognizing human activities is a widely discussed topic of this era. It has a noticeable growth of interest for implementing a wide range of applications such as health monitoring, indoor movements, navigation and location-based services. This paper compares the performance of various machine learning algorithms in the domain of human activity recognition. Data of different aged people is collected using a custom setup and custom hardware. The observed data are modeled using machine learning and neural network. As recorded human motions have variations and complexity, four dataset reduction techniques are used to manipulate the results. Best accuracy is obtained for SVM classifier with 99% accuracy and after applying PCA and SVD techniques the accuracy percentages increased to 100%. On the other hand, worst accuracy is obtained for Naive Bayes classifier before and after applying LDA technique for 100 components. The accuracy percentages are 77% and 98% respectively.
{"title":"Application of Machine Learning Classifiers for Predicting Human Activity","authors":"Benjir Islam Alvee, Sadia Nasrin Tisha, Amitabha Chakrabarty","doi":"10.1109/IAICT52856.2021.9532572","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532572","url":null,"abstract":"Involving machine learning in recognizing human activities is a widely discussed topic of this era. It has a noticeable growth of interest for implementing a wide range of applications such as health monitoring, indoor movements, navigation and location-based services. This paper compares the performance of various machine learning algorithms in the domain of human activity recognition. Data of different aged people is collected using a custom setup and custom hardware. The observed data are modeled using machine learning and neural network. As recorded human motions have variations and complexity, four dataset reduction techniques are used to manipulate the results. Best accuracy is obtained for SVM classifier with 99% accuracy and after applying PCA and SVD techniques the accuracy percentages increased to 100%. On the other hand, worst accuracy is obtained for Naive Bayes classifier before and after applying LDA technique for 100 components. The accuracy percentages are 77% and 98% respectively.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131544642","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532555
Aarati Medehal, Aniruddha Annaluru, Shalini Bandyopadhyay, T. Chandar
The neonatal period, first 28 days of life, is the most crucial and foundational period for a child's survival. Unfortunately, it is recorded that 2.6 million infants die each year during this period, owing to traditional manual monitoring coupled with problems such as alarm fatigue in neonatal intensive care units (NICU) which results in negligence during emergency situations. Moreover, most modern NICUs rely on heavily wired devices to track the vitals making it uncomfortable for the infant and difficult for the caregivers and parents to interact with them. The purpose of this research is to use the capabilities of Internet of Things (IoT) to automate the monitoring and controlling of neonatal vitals while making the process largely wireless and hence portable. The proposed study also pushes to solve the issue of alarm fatigue through an improvised alarm system.
{"title":"Portable Smart Neonatal Incubator with Improvised Alarm System","authors":"Aarati Medehal, Aniruddha Annaluru, Shalini Bandyopadhyay, T. Chandar","doi":"10.1109/IAICT52856.2021.9532555","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532555","url":null,"abstract":"The neonatal period, first 28 days of life, is the most crucial and foundational period for a child's survival. Unfortunately, it is recorded that 2.6 million infants die each year during this period, owing to traditional manual monitoring coupled with problems such as alarm fatigue in neonatal intensive care units (NICU) which results in negligence during emergency situations. Moreover, most modern NICUs rely on heavily wired devices to track the vitals making it uncomfortable for the infant and difficult for the caregivers and parents to interact with them. The purpose of this research is to use the capabilities of Internet of Things (IoT) to automate the monitoring and controlling of neonatal vitals while making the process largely wireless and hence portable. The proposed study also pushes to solve the issue of alarm fatigue through an improvised alarm system.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132101578","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532532
Andi Fatahillah Akbar, Hilman Fauzi, P. Aulia, Utari Nur Ramadhani Yora
Handwriting analysis, commonly referred to as Graphology, can reflect a person's personality because writing movements are controlled by the brain, which contains memories about various life experiences and stored in the subconscious. Currently, the process of identifying human personality through handwriting or Graphology is still performed manually. This process requires a reference book to analyze every aspect of a person's handwriting. As well as the baseline pattern of handwriting, still performed manually to decide whether it tends to be up, down, or straight. In this paper, the aspects studied were the primary writing lines to identify a person's personality traits and characteristics towards emotional individuals with optimistic and pessimistic characters. The test is carried out using the method classification of the ArcTan geometric formula to determine the angle of slanted of the line basic handwriting. System inputs were using handwriting samples obtained from 42 subjects, ranging from 19–27 years old. The system was designed to identify two classes of emotions, which are optimistic and pessimistic. Then three essential line aspects of handwriting, namely tend up, tend down, and straight, were classified according to the arctan geometric formula. The accuracy of this graphology system is 90.47%; it can be concluded that the system successfully identifies handwriting per 1 line or 1 page of HVS paper.
{"title":"Designing Individual Optimistic and Pessimistic Emotional Tendency Identification System Based on Digital Image Processing","authors":"Andi Fatahillah Akbar, Hilman Fauzi, P. Aulia, Utari Nur Ramadhani Yora","doi":"10.1109/IAICT52856.2021.9532532","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532532","url":null,"abstract":"Handwriting analysis, commonly referred to as Graphology, can reflect a person's personality because writing movements are controlled by the brain, which contains memories about various life experiences and stored in the subconscious. Currently, the process of identifying human personality through handwriting or Graphology is still performed manually. This process requires a reference book to analyze every aspect of a person's handwriting. As well as the baseline pattern of handwriting, still performed manually to decide whether it tends to be up, down, or straight. In this paper, the aspects studied were the primary writing lines to identify a person's personality traits and characteristics towards emotional individuals with optimistic and pessimistic characters. The test is carried out using the method classification of the ArcTan geometric formula to determine the angle of slanted of the line basic handwriting. System inputs were using handwriting samples obtained from 42 subjects, ranging from 19–27 years old. The system was designed to identify two classes of emotions, which are optimistic and pessimistic. Then three essential line aspects of handwriting, namely tend up, tend down, and straight, were classified according to the arctan geometric formula. The accuracy of this graphology system is 90.47%; it can be concluded that the system successfully identifies handwriting per 1 line or 1 page of HVS paper.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1031 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116462263","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532562
Cheng-Yun Kuo, Eric Jui-Lin Lu
Question answering system over linked data (QALD) has been a very important research field in natural language processing (NLP). And the process of detecting useful words and assigning them with right entity types is crucial to the performance of QALD systems. Although entity-type taggers achieved good results using probability graph models such as MEMM and CRF, the design and selection of features may pose limitations. Due to the popularity of deep learning architectures, many studies employed Recurrent Neural Network (RNN) framework and achieved state-of-art performances in NLP. Therefore, we choose to use BiLSTM-CRF in the design of entity-type tagger. It can be seen from the experimental results that the proposed BiLSTM-CRF model outperformed other probability graph models, which also lead to the best performance of overall Question Answering system than other competitor systems.
{"title":"A BiLSTM-CRF Entity Type Tagger for Question Answering System","authors":"Cheng-Yun Kuo, Eric Jui-Lin Lu","doi":"10.1109/IAICT52856.2021.9532562","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532562","url":null,"abstract":"Question answering system over linked data (QALD) has been a very important research field in natural language processing (NLP). And the process of detecting useful words and assigning them with right entity types is crucial to the performance of QALD systems. Although entity-type taggers achieved good results using probability graph models such as MEMM and CRF, the design and selection of features may pose limitations. Due to the popularity of deep learning architectures, many studies employed Recurrent Neural Network (RNN) framework and achieved state-of-art performances in NLP. Therefore, we choose to use BiLSTM-CRF in the design of entity-type tagger. It can be seen from the experimental results that the proposed BiLSTM-CRF model outperformed other probability graph models, which also lead to the best performance of overall Question Answering system than other competitor systems.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125170275","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532568
Irena Arvianda Wulan Utami, Hilman Fauzi, Y. Fuadah, Yolanda Sari Silaen, M. I. Shapiai
Stroke can be interpreted as a dysfunction of the nervous system that occurs suddenly and caused by blockage of blood vessels in the brain. Generally, the effort used to reduce stroke patients is the diagnostic method using Magnetic Resonance Imaging (MRI). However, the cost of examination using the MRI method is relatively expensive and not portable. One solution to overcome this problem is to use an Electroencephalograph (EEG) device to detect stroke signals in the brain that measure electrical activity detecting abnormalities in the brain. This action uses special sensors, namely electrodes attached to the head and connected to the computer. In previous research, EEG stroke signal processing was carried out using the Brain Symmetry Index and Hilbert Huang Transform (BSI-HHT) methods. However, this study did not specifically discuss channel selection in EEG stroke signals. Given these problems, in this study, the authors will process the EEG stroke signal using the modified Spatial Selection method using the Fast Fourier Transform (FFT) method through the active channel composition configuration so that it can be processed to obtain relevant results. Furthermore, the classification process is carried out using the k-Nearest Neighbor (k-NN) and Extreme Learning Machine (ELM) methods. Implementing the k-Nearest Neighbor (k-NN) classification shows that the spatial selection method can find the suitable channel composition with the same accuracy results as normal data in several areas. In contrast, the ELM classification can increase accuracy by 2% greater than normal data in the high mean area with a few channel compositions.
{"title":"The Design of Stroke EEG Channel Selection System Using Spatial Selection Method","authors":"Irena Arvianda Wulan Utami, Hilman Fauzi, Y. Fuadah, Yolanda Sari Silaen, M. I. Shapiai","doi":"10.1109/IAICT52856.2021.9532568","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532568","url":null,"abstract":"Stroke can be interpreted as a dysfunction of the nervous system that occurs suddenly and caused by blockage of blood vessels in the brain. Generally, the effort used to reduce stroke patients is the diagnostic method using Magnetic Resonance Imaging (MRI). However, the cost of examination using the MRI method is relatively expensive and not portable. One solution to overcome this problem is to use an Electroencephalograph (EEG) device to detect stroke signals in the brain that measure electrical activity detecting abnormalities in the brain. This action uses special sensors, namely electrodes attached to the head and connected to the computer. In previous research, EEG stroke signal processing was carried out using the Brain Symmetry Index and Hilbert Huang Transform (BSI-HHT) methods. However, this study did not specifically discuss channel selection in EEG stroke signals. Given these problems, in this study, the authors will process the EEG stroke signal using the modified Spatial Selection method using the Fast Fourier Transform (FFT) method through the active channel composition configuration so that it can be processed to obtain relevant results. Furthermore, the classification process is carried out using the k-Nearest Neighbor (k-NN) and Extreme Learning Machine (ELM) methods. Implementing the k-Nearest Neighbor (k-NN) classification shows that the spatial selection method can find the suitable channel composition with the same accuracy results as normal data in several areas. In contrast, the ELM classification can increase accuracy by 2% greater than normal data in the high mean area with a few channel compositions.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121564451","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532552
Véronique Georlette, Juan Sánchez Melgarejo, S. Bette, Nicolas Point, V. Moeyaert
The popularisation of LED technology has enabled the development of new optical telecommunication technologies. The most popular in this sector is Visible Light Communication (VLC). It uses the visible part of the spectrum to send data and illuminate simultaneously. At the same time, as industries increasingly install mobile equipment on their assembly lines, there is a demand in this market for reliable and robust communication technology. The advantage of VLC compared to Radio Frequency (RF) technology in the industry is its immunity to electromagnetic interference as most industrial facilities are built in metal. This paper presents the foundations of an innovative solution to meet the needs of mobile assembly lines. In this example, the VLC system has the dual role of illuminating the operator or robot and communicating to and from a central controller. A two-way system, called Li-Fi that uses a downstream communication in visible light and the upstream in infrared, has been chosen. The work presented demonstrates, through the results of a simulator, that this technology can meet mobile assembly line requirements in terms of communication.
{"title":"Potential and challenges of visible light communication for industrial assembly lines with mobile workstations","authors":"Véronique Georlette, Juan Sánchez Melgarejo, S. Bette, Nicolas Point, V. Moeyaert","doi":"10.1109/IAICT52856.2021.9532552","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532552","url":null,"abstract":"The popularisation of LED technology has enabled the development of new optical telecommunication technologies. The most popular in this sector is Visible Light Communication (VLC). It uses the visible part of the spectrum to send data and illuminate simultaneously. At the same time, as industries increasingly install mobile equipment on their assembly lines, there is a demand in this market for reliable and robust communication technology. The advantage of VLC compared to Radio Frequency (RF) technology in the industry is its immunity to electromagnetic interference as most industrial facilities are built in metal. This paper presents the foundations of an innovative solution to meet the needs of mobile assembly lines. In this example, the VLC system has the dual role of illuminating the operator or robot and communicating to and from a central controller. A two-way system, called Li-Fi that uses a downstream communication in visible light and the upstream in infrared, has been chosen. The work presented demonstrates, through the results of a simulator, that this technology can meet mobile assembly line requirements in terms of communication.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131257680","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}
In the post-epidemic era, the digital transformation of offline stores is accelerating, and the application of new technologies promotes the customer value co-creation behavior to present new characteristics. Based on the service characteristics of offline stores, digital empowerment theory and value co-creation theory, this paper explores the influence mechanism of digital capability on customer value co-creation behavior. The empirical results show that connectivity capability has a positive impact on product service, a negative impact on perceived intrusiveness, and intelligence capability has a positive impact on product service. Product service has a positive impact on customer participation behavior and customer citizenship behavior, while perceived intrusiveness has a negative impact on them. Value co-creation elements play an important intermediary role in the relationship between digital capability and customer value co-creation behavior. When introducing technologies such as service robots, offline stores undergoing digital transformation should make proper choices, give full play to their positive role in product service, use them to reduce the perceived intrusiveness of customers, create a more harmonious and comfortable experience environment, and then stimulate customers' participation behavior and citizenship behavior.
{"title":"the Influence of Digital Empowerment of Service Robot on Customer Value Co-creation Behavior","authors":"Cong Wang, Yunfeng Guo, Shenglan Yang, Xiongfei Yan, Yaowei Zhu","doi":"10.1109/IAICT52856.2021.9532578","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532578","url":null,"abstract":"In the post-epidemic era, the digital transformation of offline stores is accelerating, and the application of new technologies promotes the customer value co-creation behavior to present new characteristics. Based on the service characteristics of offline stores, digital empowerment theory and value co-creation theory, this paper explores the influence mechanism of digital capability on customer value co-creation behavior. The empirical results show that connectivity capability has a positive impact on product service, a negative impact on perceived intrusiveness, and intelligence capability has a positive impact on product service. Product service has a positive impact on customer participation behavior and customer citizenship behavior, while perceived intrusiveness has a negative impact on them. Value co-creation elements play an important intermediary role in the relationship between digital capability and customer value co-creation behavior. When introducing technologies such as service robots, offline stores undergoing digital transformation should make proper choices, give full play to their positive role in product service, use them to reduce the perceived intrusiveness of customers, create a more harmonious and comfortable experience environment, and then stimulate customers' participation behavior and citizenship behavior.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"333 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133507924","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532517
Samuel N. Huerta-Ruiz, Alberto Oliart-Ros, H. G. González-Hernández
When shining a light through a finger, some of it will be absorbed by oxygenated and unoxygenated hemoglobin. Measuring the absorbed light over time provides the photo-plethysmographic (PPG) waveform, which can represent the blood flow of a subject. One way of obtaining the PPG waveform is to use the camera and flash of a smartphone, placing them on the finger of a subject, and analyzing the variation of red color. The PPG can also be obtained using oximeter-like devices, which are non-invasive and safe. In contrast, to measure the blood glucose of a subject, a glucometer is used, which is a device that is typically invasive and expensive. Therefore, we propose the use of the following descriptors from Chaos theory to analyze the PPG signal: correlation dimension, maximum Lyapunov exponent and Hurst exponent. Then, these values are converted into a 3-dimensional vector that can be represented in a 3-dimensional space. Each vector has an associated glucose level that is used to train an algorithm which classifies all the vectors in three different ranges of blood glucose levels.
{"title":"Relationship between PPG Signals and Glucose levels through Chaotic Descriptors and Support Vector Machines","authors":"Samuel N. Huerta-Ruiz, Alberto Oliart-Ros, H. G. González-Hernández","doi":"10.1109/IAICT52856.2021.9532517","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532517","url":null,"abstract":"When shining a light through a finger, some of it will be absorbed by oxygenated and unoxygenated hemoglobin. Measuring the absorbed light over time provides the photo-plethysmographic (PPG) waveform, which can represent the blood flow of a subject. One way of obtaining the PPG waveform is to use the camera and flash of a smartphone, placing them on the finger of a subject, and analyzing the variation of red color. The PPG can also be obtained using oximeter-like devices, which are non-invasive and safe. In contrast, to measure the blood glucose of a subject, a glucometer is used, which is a device that is typically invasive and expensive. Therefore, we propose the use of the following descriptors from Chaos theory to analyze the PPG signal: correlation dimension, maximum Lyapunov exponent and Hurst exponent. Then, these values are converted into a 3-dimensional vector that can be represented in a 3-dimensional space. Each vector has an associated glucose level that is used to train an algorithm which classifies all the vectors in three different ranges of blood glucose levels.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133851558","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532541
Jose Maria C. Ibardaloza, Juan Antonio G. Mapua, Wilson M. Tan
Voice-user interfaces (VUIs) have gained popularity in recent years since these provide ease of access to users. The problem with current VUIs, however, is that they become unusable once Internet connection is cut off since processes such as speech-to-text decoding of commands and Internet of Things (IoT) management are implemented on cloud servers. This, however, does not necessarily have to be the case since there are commands, such as managing IoT devices like smart lights, smart thermostats, and smart locks, which do not need Internet connection for it to be executed. In this work, a proposal for a VUI which can determine when Internet connection is cut off and locally execute tasks which do not need information retrieval from the Internet, is presented. The proposed VUI runs 2 systems: the full system and the offline system. The full system is used when there is Internet connection while the offline system is used when Internet connection is cut off. Through experiments, the difference in performance between the two systems, along with the amount of time that should be given to the VUI as leeway in order for it to process all incoming voice inputs once it switches from the full system to the offline system and vice versa, were quantified.
{"title":"Modifying Voice-User Interfaces for Resiliency and Offline Management of IoT Devices","authors":"Jose Maria C. Ibardaloza, Juan Antonio G. Mapua, Wilson M. Tan","doi":"10.1109/IAICT52856.2021.9532541","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532541","url":null,"abstract":"Voice-user interfaces (VUIs) have gained popularity in recent years since these provide ease of access to users. The problem with current VUIs, however, is that they become unusable once Internet connection is cut off since processes such as speech-to-text decoding of commands and Internet of Things (IoT) management are implemented on cloud servers. This, however, does not necessarily have to be the case since there are commands, such as managing IoT devices like smart lights, smart thermostats, and smart locks, which do not need Internet connection for it to be executed. In this work, a proposal for a VUI which can determine when Internet connection is cut off and locally execute tasks which do not need information retrieval from the Internet, is presented. The proposed VUI runs 2 systems: the full system and the offline system. The full system is used when there is Internet connection while the offline system is used when Internet connection is cut off. Through experiments, the difference in performance between the two systems, along with the amount of time that should be given to the VUI as leeway in order for it to process all incoming voice inputs once it switches from the full system to the offline system and vice versa, were quantified.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121928537","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532513
Nidhal Hadj Abdallah, Raouf Brahim, Y. Bouslimani, M. Ghribi, A. Kaddouri
In modern sports training, collection, acquisition, and analysis of data concerning the athlete's activities are a necessity to improve trainings. This paper presents a new wearable IoT device, capable of monitoring athletes' movements in real time. The collected data are of a great importance for training sessions and improvement of athlete's performances. The proposed wearable device located on the athletes' wrist is an inertial sensing module that connects to Wi-Fi and sends information about Athlete activities. This paper presents also an electrical design proposed for such connected device using an inertial measurement unit (IMU) as a sensor. Furthermore, this article investigates different IoT communication technologies and protocol used for securing data transmission. An application was developed for data visualization and for activities classification. The application allows to remotely view the athletes' movement corresponding signals and detect the associated activity. The experimental results of this research show that the developed system is able to identify several activities of players during their training with a high success rate.
{"title":"IoT device for Athlete's movements recognition using inertial measurement unit (IMU)","authors":"Nidhal Hadj Abdallah, Raouf Brahim, Y. Bouslimani, M. Ghribi, A. Kaddouri","doi":"10.1109/IAICT52856.2021.9532513","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532513","url":null,"abstract":"In modern sports training, collection, acquisition, and analysis of data concerning the athlete's activities are a necessity to improve trainings. This paper presents a new wearable IoT device, capable of monitoring athletes' movements in real time. The collected data are of a great importance for training sessions and improvement of athlete's performances. The proposed wearable device located on the athletes' wrist is an inertial sensing module that connects to Wi-Fi and sends information about Athlete activities. This paper presents also an electrical design proposed for such connected device using an inertial measurement unit (IMU) as a sensor. Furthermore, this article investigates different IoT communication technologies and protocol used for securing data transmission. An application was developed for data visualization and for activities classification. The application allows to remotely view the athletes' movement corresponding signals and detect the associated activity. The experimental results of this research show that the developed system is able to identify several activities of players during their training with a high success rate.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126800780","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：