Production Digital Twins (DTs) mirror and interact with the production lines that they model through the Industrial Internet of Things (IIoT) based bidirectional data flow pipelines. There is a need for interactive 3D visualization of DTs to unlock the promised capabilities for real time monitoring, optimization, reconfiguration, maintenance and control of the production process. DTs based on open source frameworks like SimPy lack an interactive 3D visualization frontend. This paper proposes a generic open source framework for the 3D visualization of any Discrete Event Simulation (DES) based production DT. As an example, an interactive 3D visualization of a SimPy based DT of a real Surface Mount Technology (SMT) Printed Circuit Board (PCB) line is presented. We visualize machine states, process flow, energy and throughput metrics of the DT and the real line in 3D. We believe that the proposed 3D visualization framework can help ease model validation efforts and can enable interactive “what if” analysis and control for optimization of the production process.
{"title":"An Open Simulator framework for 3D Visualization of Digital Twins","authors":"Ashish Joglekar, Gaurav Bhandari, Rajesh Sundaresan","doi":"10.1109/IoTaIS56727.2022.9975980","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975980","url":null,"abstract":"Production Digital Twins (DTs) mirror and interact with the production lines that they model through the Industrial Internet of Things (IIoT) based bidirectional data flow pipelines. There is a need for interactive 3D visualization of DTs to unlock the promised capabilities for real time monitoring, optimization, reconfiguration, maintenance and control of the production process. DTs based on open source frameworks like SimPy lack an interactive 3D visualization frontend. This paper proposes a generic open source framework for the 3D visualization of any Discrete Event Simulation (DES) based production DT. As an example, an interactive 3D visualization of a SimPy based DT of a real Surface Mount Technology (SMT) Printed Circuit Board (PCB) line is presented. We visualize machine states, process flow, energy and throughput metrics of the DT and the real line in 3D. We believe that the proposed 3D visualization framework can help ease model validation efforts and can enable interactive “what if” analysis and control for optimization of the production process.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134485804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975897
R. Avanzato, F. Beritelli, F. Raciti, Enrica Spataro
Lately, UAV-Femtocell systems have been representing an innovative solution to the problem of geolocalization of mobile terminals in civil protection scenarios (e.g. post-earthquake search for missing persons). This paper proposes a new approach to geolocalization of mobile terminals based on the use of game theory, in particular the introduction of new utility functions that guarantee the Nash equilibrium. Through a series of simulations aimed at validating the proposed method the paper presents a comparison of time and energy savings achieved by drones with methods previously introduced in the literature. The research results indicate that based on the density of mobile terminals, on average, the savings range between 30% and 50%.
{"title":"Energy Management optimization of UAV-Femtocell Geolocalization Systems based on Game Theory","authors":"R. Avanzato, F. Beritelli, F. Raciti, Enrica Spataro","doi":"10.1109/IoTaIS56727.2022.9975897","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975897","url":null,"abstract":"Lately, UAV-Femtocell systems have been representing an innovative solution to the problem of geolocalization of mobile terminals in civil protection scenarios (e.g. post-earthquake search for missing persons). This paper proposes a new approach to geolocalization of mobile terminals based on the use of game theory, in particular the introduction of new utility functions that guarantee the Nash equilibrium. Through a series of simulations aimed at validating the proposed method the paper presents a comparison of time and energy savings achieved by drones with methods previously introduced in the literature. The research results indicate that based on the density of mobile terminals, on average, the savings range between 30% and 50%.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133784127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9976013
Alireza Salimy, I. Mitiche, P. Boreham, A. Nesbitt, G. Morison
The experiments in this study propose a fault diagnosis method to incorporate in an internet-of-things (IoT) system for the condition monitoring of high-voltage generating stations. The approach is based on feature extraction with signal processing methods and a deep learning model to tackle fault classification in measured signals that contain one or more faults simultaneously. The proposed system implements feature extraction through the short-time Fourier transform (STFT) of 1-D electro-magnetic interference (EMI) fault signals obtained from online high-voltage (HV) assets. The produced feature maps are then used in parallel with label word embeddings to train and test a deep learning model consisting of, a graph convolutional network (GCN), implemented to learn inter-dependant fault label relationships from label co-occurrence matrices and label word embeddings, and a convolutional neural network (CNN) to extract relevant features from STFT data representations. The proposed system tackles the under-addressed EMI multi-label HV fault diagnosis problem and produces strong results in label classification even when implemented on a heavily imbalanced data set, to the author’s knowledge the system provides an unprecedented level of performance that is industrially acceptable in fault diagnosis and can be successfully implemented on a real-world IoT-based condition monitoring system. In addition, in theory the proposed system is scalable for the prediction of a higher quantity of fault labels present in data instances.
{"title":"Can a deep learning based IoT fault diagnosis system identify more than one fault at a time?","authors":"Alireza Salimy, I. Mitiche, P. Boreham, A. Nesbitt, G. Morison","doi":"10.1109/IoTaIS56727.2022.9976013","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9976013","url":null,"abstract":"The experiments in this study propose a fault diagnosis method to incorporate in an internet-of-things (IoT) system for the condition monitoring of high-voltage generating stations. The approach is based on feature extraction with signal processing methods and a deep learning model to tackle fault classification in measured signals that contain one or more faults simultaneously. The proposed system implements feature extraction through the short-time Fourier transform (STFT) of 1-D electro-magnetic interference (EMI) fault signals obtained from online high-voltage (HV) assets. The produced feature maps are then used in parallel with label word embeddings to train and test a deep learning model consisting of, a graph convolutional network (GCN), implemented to learn inter-dependant fault label relationships from label co-occurrence matrices and label word embeddings, and a convolutional neural network (CNN) to extract relevant features from STFT data representations. The proposed system tackles the under-addressed EMI multi-label HV fault diagnosis problem and produces strong results in label classification even when implemented on a heavily imbalanced data set, to the author’s knowledge the system provides an unprecedented level of performance that is industrially acceptable in fault diagnosis and can be successfully implemented on a real-world IoT-based condition monitoring system. In addition, in theory the proposed system is scalable for the prediction of a higher quantity of fault labels present in data instances.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134110981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975927
M. H. A. Pratama, Willy Anugrah Cahyadi, Fiky Yosef Suratman
Image-based virtual try-on is a method that can let people try on clothes virtually. One of the challenges in image-based virtual try-on is segmentation. The segmentation needed in the virtual try-on implementation is the one that can divide humans into several objects based on their body parts such as hair, face, neck, hands, upper body, and lower body. This type of segmentation is called human parsing. There are several human parsing methods and datasets that have achieved great results. Unfortunately, some limitations make the method unsuitable in an image-based virtual try-on model. We proposed human parsing using the Pix2Pix model with the VITON dataset. Our model yields an average accuracy of 89.76%, an average F1-score of 86.80%, and an average IoU of 76.79%. These satisfactory results allow our model to be used in upcoming image-based virtual try-on research.
{"title":"Human Parsing for Image-Based Virtual Try-On Using Pix2Pix","authors":"M. H. A. Pratama, Willy Anugrah Cahyadi, Fiky Yosef Suratman","doi":"10.1109/IoTaIS56727.2022.9975927","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975927","url":null,"abstract":"Image-based virtual try-on is a method that can let people try on clothes virtually. One of the challenges in image-based virtual try-on is segmentation. The segmentation needed in the virtual try-on implementation is the one that can divide humans into several objects based on their body parts such as hair, face, neck, hands, upper body, and lower body. This type of segmentation is called human parsing. There are several human parsing methods and datasets that have achieved great results. Unfortunately, some limitations make the method unsuitable in an image-based virtual try-on model. We proposed human parsing using the Pix2Pix model with the VITON dataset. Our model yields an average accuracy of 89.76%, an average F1-score of 86.80%, and an average IoU of 76.79%. These satisfactory results allow our model to be used in upcoming image-based virtual try-on research.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133576314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975895
David Grenar, Milan Cucka, M. Filka, K. Slávicek, J. Vavra, M. Kyselak
Our research group deals with the utilization of light polarization and birefringent fiber optics for sensing purposes. This paper discusses the utilization of birefringent fiber (Panda type) as a tensile force sensor. Both theoretical analyses of the influence of tensile force on the geometry of the fiber optic line and the first laboratory experiments are documented in this paper. The first laboratory measurement approved the theory and showed the perspective utilization of birefringent finer for tensile detection..
{"title":"Optical sensor based on birefringent fiber type PANDA used for tensile detection","authors":"David Grenar, Milan Cucka, M. Filka, K. Slávicek, J. Vavra, M. Kyselak","doi":"10.1109/IoTaIS56727.2022.9975895","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975895","url":null,"abstract":"Our research group deals with the utilization of light polarization and birefringent fiber optics for sensing purposes. This paper discusses the utilization of birefringent fiber (Panda type) as a tensile force sensor. Both theoretical analyses of the influence of tensile force on the geometry of the fiber optic line and the first laboratory experiments are documented in this paper. The first laboratory measurement approved the theory and showed the perspective utilization of birefringent finer for tensile detection..","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132775722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975852
Inka Purnama Sari, Ahmad Qurthobi, S. Oktaviani, A. Suhendi, Sitti Amallia Suhandini
Feeding laying hens is one of the factors that affect the production of eggs. The appropriate feeding mass to achieve maximum egg production is 100 grams for each hen. To help out the feeding process, an automatic feed for hens system based on the feed mass will be designed. This system will be built by integrating the proximity sensor, relay, servo motor, and AC with a delay setup. The sensing of the proximity sensor is triggered by an object which is moved with the help of a servo motor with a certain delay that has been set up so it can sense the middle point of the stall fitly. The distance between stalls is 20 cm, when the sensor detects an object less than 20 cm, the relay will be off, and vice versa. The function of the relay is to connect and disconnect the current flow that affects the movement of the AC motor. Another servo motor was also installed in the feeding box to drop the feeds. To make the system able to drop the exact 100 grams of feeds for each hen, the delay for the servo motor has been set. In this system, the success parameters are the accuracy of the AC motor to stop right at the middle of each stall, the accuracy of feeds dropped by the system, and the accuracy of 180o servo motor opening. Based on the testing results, the error of the AC motor to stop is 3.5%, the average of dropped feed is 101,5 grams for each drop, and the error of 1800 servo motor opening is 1.5%. To compare the result of the feeding process by using the system and the manual process, three treatments of the experiment were also carried out, they are experimental feeding by weighing beforehand (PI), feeding with an estimated mass of feed (P2), and feeding using the built system (P3). Based on the experiments, the average weights of the egg production are 59.3 grams, 52.4 grams, and 60.6 grams by using the PI, P2, and P3 respectively. The comparison of egg production for 10 days can be seen in P2 and P3 which are 5.23 kg and 6.05 kg. The average feeding time for each treatment was also compared, the results are 34.4 seconds for PI, 9.73 seconds for P2, and 6.06 seconds for P3.
{"title":"Design of Chicken Feeding Tool Based on Feed Mass using a Microcontroller","authors":"Inka Purnama Sari, Ahmad Qurthobi, S. Oktaviani, A. Suhendi, Sitti Amallia Suhandini","doi":"10.1109/IoTaIS56727.2022.9975852","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975852","url":null,"abstract":"Feeding laying hens is one of the factors that affect the production of eggs. The appropriate feeding mass to achieve maximum egg production is 100 grams for each hen. To help out the feeding process, an automatic feed for hens system based on the feed mass will be designed. This system will be built by integrating the proximity sensor, relay, servo motor, and AC with a delay setup. The sensing of the proximity sensor is triggered by an object which is moved with the help of a servo motor with a certain delay that has been set up so it can sense the middle point of the stall fitly. The distance between stalls is 20 cm, when the sensor detects an object less than 20 cm, the relay will be off, and vice versa. The function of the relay is to connect and disconnect the current flow that affects the movement of the AC motor. Another servo motor was also installed in the feeding box to drop the feeds. To make the system able to drop the exact 100 grams of feeds for each hen, the delay for the servo motor has been set. In this system, the success parameters are the accuracy of the AC motor to stop right at the middle of each stall, the accuracy of feeds dropped by the system, and the accuracy of 180o servo motor opening. Based on the testing results, the error of the AC motor to stop is 3.5%, the average of dropped feed is 101,5 grams for each drop, and the error of 1800 servo motor opening is 1.5%. To compare the result of the feeding process by using the system and the manual process, three treatments of the experiment were also carried out, they are experimental feeding by weighing beforehand (PI), feeding with an estimated mass of feed (P2), and feeding using the built system (P3). Based on the experiments, the average weights of the egg production are 59.3 grams, 52.4 grams, and 60.6 grams by using the PI, P2, and P3 respectively. The comparison of egg production for 10 days can be seen in P2 and P3 which are 5.23 kg and 6.05 kg. The average feeding time for each treatment was also compared, the results are 34.4 seconds for PI, 9.73 seconds for P2, and 6.06 seconds for P3.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131650922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975929
Zhenyu Ma, R. Rayhana, Zheng Liu, G. Xiao, Y. Ruan, J. Sangha
Smart agriculture is a new agricultural production mode and is considered a potential solution for food supply issues under current limited land space conditions. The application of the Internet of Things (IoT) in smart agriculture can effectively increase food production with relatively low labor costs by deploying various wireless communication sensors in the field to collect plant information during the agricultural process. This paper developed an extendable IoT based sensor system for smart agriculture applications. The proposed sensing system can acquire real-time plant information through its plant environment and plant phenotyping monitoring process. The plant environment monitoring process can collect real-time plant environmental data through multiple wireless environment measuring sensors. At the same time, the plant phenotyping monitoring process can achieve plant height monitoring with the root-mean-square error (RMSE) of 0.051 m and the mean absolute error (MAE) of 0.049 m through remote RGB-D (red, green, blue plus depth data) cameras and 3D reconstruction method. This study shows that the proposed system can provide valuable real-time plant information for farmers’ decision-making.
{"title":"Industrial Internet of Things (IoT) and 3D Reconstruction Empowered Smart Agriculture System","authors":"Zhenyu Ma, R. Rayhana, Zheng Liu, G. Xiao, Y. Ruan, J. Sangha","doi":"10.1109/IoTaIS56727.2022.9975929","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975929","url":null,"abstract":"Smart agriculture is a new agricultural production mode and is considered a potential solution for food supply issues under current limited land space conditions. The application of the Internet of Things (IoT) in smart agriculture can effectively increase food production with relatively low labor costs by deploying various wireless communication sensors in the field to collect plant information during the agricultural process. This paper developed an extendable IoT based sensor system for smart agriculture applications. The proposed sensing system can acquire real-time plant information through its plant environment and plant phenotyping monitoring process. The plant environment monitoring process can collect real-time plant environmental data through multiple wireless environment measuring sensors. At the same time, the plant phenotyping monitoring process can achieve plant height monitoring with the root-mean-square error (RMSE) of 0.051 m and the mean absolute error (MAE) of 0.049 m through remote RGB-D (red, green, blue plus depth data) cameras and 3D reconstruction method. This study shows that the proposed system can provide valuable real-time plant information for farmers’ decision-making.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126810211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975918
A. Aboulfotouh, Thiago Eustaquio Alves de Oliveira, Z. Fadlullah
Massive MIMO has provided immense improvement in the performance of wireless communication systems when it comes to spectral efficiency, which led to it becoming the main driving technology behind 5G. It is also expected to support Internet of Things (IoT) Connectivity [1] such as massive machine type communication (mMTC) and ultra-reliable low-latency communication (URLLC). For a massive MIMO system to perform well, an accurate estimate of the wireless channel response has to be acquired. The traditional approach for channel estimation makes use of empirical assumptions about the wireless channel statistics which is sufficient for deriving theoretical results. However, they can be inadequate for practical purposes. In this work, we propose a data-driven approach for channel estimation using the multilayer perceptron (MLP) neural network. Such an approach should be valid irrespective of the propagation environment. We demonstrate that this approach significantly outperforms the conventional Minimum-Mean-Square-Estimator (MMSE) except for the high signal-to-noise ratio (SNR) regime at which the performance of MLP estimator starts to saturate. To deal with this problem, we propose a heuristic algorithm which switches from the MLP estimator to the MMSE estimator at the high SNR regime.
{"title":"Channel Estimation in Cellular Massive MIMO: A Data-Driven Approach","authors":"A. Aboulfotouh, Thiago Eustaquio Alves de Oliveira, Z. Fadlullah","doi":"10.1109/IoTaIS56727.2022.9975918","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975918","url":null,"abstract":"Massive MIMO has provided immense improvement in the performance of wireless communication systems when it comes to spectral efficiency, which led to it becoming the main driving technology behind 5G. It is also expected to support Internet of Things (IoT) Connectivity [1] such as massive machine type communication (mMTC) and ultra-reliable low-latency communication (URLLC). For a massive MIMO system to perform well, an accurate estimate of the wireless channel response has to be acquired. The traditional approach for channel estimation makes use of empirical assumptions about the wireless channel statistics which is sufficient for deriving theoretical results. However, they can be inadequate for practical purposes. In this work, we propose a data-driven approach for channel estimation using the multilayer perceptron (MLP) neural network. Such an approach should be valid irrespective of the propagation environment. We demonstrate that this approach significantly outperforms the conventional Minimum-Mean-Square-Estimator (MMSE) except for the high signal-to-noise ratio (SNR) regime at which the performance of MLP estimator starts to saturate. To deal with this problem, we propose a heuristic algorithm which switches from the MLP estimator to the MMSE estimator at the high SNR regime.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115270141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975946
Benedictus Prabaswara, Wanda Safira, Kartika Purwandari, F. Kurniadi
Twitter is one of the social media that is currently a trend, where Twitter users can tweet as freely as possible about their opinions and even those opinions about airlines in Indonesia. Twitter sentiment analysis is a process to identify whether tweets on Twitter are included as positive tweets or negative tweets. In this research, the tweets will be divided into three categories: positive, neutral, and negative, using Lexicon and Long Short-Term Memory (LSTM). The data taken are tweets from Twitter in the form of text. One hundred positive, one hundred neutral, and one hundred negative tweets were taken. After going through the process using the Lexicon and LSTM method, the results obtained are 73% accuracy, where there are 130 positive tweets, 105 negative tweets, and 62 neutral tweets.
{"title":"Twitter Sentiment Analysis of Indonesian Airlines Using LSTM","authors":"Benedictus Prabaswara, Wanda Safira, Kartika Purwandari, F. Kurniadi","doi":"10.1109/IoTaIS56727.2022.9975946","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975946","url":null,"abstract":"Twitter is one of the social media that is currently a trend, where Twitter users can tweet as freely as possible about their opinions and even those opinions about airlines in Indonesia. Twitter sentiment analysis is a process to identify whether tweets on Twitter are included as positive tweets or negative tweets. In this research, the tweets will be divided into three categories: positive, neutral, and negative, using Lexicon and Long Short-Term Memory (LSTM). The data taken are tweets from Twitter in the form of text. One hundred positive, one hundred neutral, and one hundred negative tweets were taken. After going through the process using the Lexicon and LSTM method, the results obtained are 73% accuracy, where there are 130 positive tweets, 105 negative tweets, and 62 neutral tweets.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"2003 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116894227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975960
H. Harja, Heri Setiawan, Y. Erdani, Muhammad Zulfahmi Febriansyah
This paper proposed a virtual model configuration to build cyber-physical system of smart screw turbine for conducting performance monitoring functions and generating self-maintenance information of each machine component. The virtual model analyzes measurement data and reference data to evaluate a performance assessment and for resulting real-time machine condition information. The proposed model was verified experimentally and implemented in web-based dashboard software which was developed by Microsoft visual studio and SQL database. Dummy data are designed and published to validate the response of proposed model. Its data are the start-finish time of operation and measurement data values. According to the experiment result, the proposed model can function properly to respond and generate information about machine condition status, the value of efficiency power, and the remaining lifetime component.
{"title":"Development of Virtual Model for Cyber-Physical Screw Turbine","authors":"H. Harja, Heri Setiawan, Y. Erdani, Muhammad Zulfahmi Febriansyah","doi":"10.1109/IoTaIS56727.2022.9975960","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975960","url":null,"abstract":"This paper proposed a virtual model configuration to build cyber-physical system of smart screw turbine for conducting performance monitoring functions and generating self-maintenance information of each machine component. The virtual model analyzes measurement data and reference data to evaluate a performance assessment and for resulting real-time machine condition information. The proposed model was verified experimentally and implemented in web-based dashboard software which was developed by Microsoft visual studio and SQL database. Dummy data are designed and published to validate the response of proposed model. Its data are the start-finish time of operation and measurement data values. According to the experiment result, the proposed model can function properly to respond and generate information about machine condition status, the value of efficiency power, and the remaining lifetime component.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121801557","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：