Pub Date : 2021-10-13DOI: 10.1109/QIR54354.2021.9716165
Amanda Nur Oktaviani, Marwah Zulfanny Alief, Lea Santiar, Prima Dewi Purnamasari, A. A. P. Ratna
This paper discusses the design for the development of an automatic essay grading system (SIMPLEO) using variations of the Convolutional Neural Network (CNN) and hybrid Convolutional Neural Network (CNN)-Long Short-term Memory (LSTM) for the assessment of the Japanese essay exam which is being developed by the Department of Electrical Engineering, University of Indonesia. Of the several variations tested, the most stable model is a model that has CNN-LSTM with kernel sizes of 5, the number of filters 64, pool size of 4, LSTM hidden units of 25, batch size of 50, repeated training of 50 epochs, and the SGD optimizer with a learning rate of 0.01 produces the highest prediction accuracy, which is 70.07%.
{"title":"Automatic Essay Grading System for Japanese Language Exam using CNN-LSTM","authors":"Amanda Nur Oktaviani, Marwah Zulfanny Alief, Lea Santiar, Prima Dewi Purnamasari, A. A. P. Ratna","doi":"10.1109/QIR54354.2021.9716165","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716165","url":null,"abstract":"This paper discusses the design for the development of an automatic essay grading system (SIMPLEO) using variations of the Convolutional Neural Network (CNN) and hybrid Convolutional Neural Network (CNN)-Long Short-term Memory (LSTM) for the assessment of the Japanese essay exam which is being developed by the Department of Electrical Engineering, University of Indonesia. Of the several variations tested, the most stable model is a model that has CNN-LSTM with kernel sizes of 5, the number of filters 64, pool size of 4, LSTM hidden units of 25, batch size of 50, repeated training of 50 epochs, and the SGD optimizer with a learning rate of 0.01 produces the highest prediction accuracy, which is 70.07%.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115461973","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716184
H. Samosir, Tegar Arifin Prasetyo, Sintong Lumbantobing, Diana Octaviana Naibaho, Christy Riris T Situmorang
Stasiun Mebel Jepara is a furniture store located in Medan, Indonesia. At the Stasiun Mebel Jepara store, there are problems regarding recording the results of transaction services, where the shop owner calculates the transaction results relying on a calculator and does not use a computer, product data collection also depends on recording on books so that employees have difficulty seeing product prices because they have to communicate again with the shop owner. Shop owners also find it challenging to record and collect data on products to be repaired and forged, so shop owners often seek back information obtained through private chats from customers. The author builds the Stasiun Mebel Jepara website using the Scrum method and the Laravel framework. The author uses the Scrum method because it is iterative, incremental, and can apply a continuous learning culture. The author decided to use Laravel because it has complete documentation and can be used freely and free of charge—the work on this final project resulted in the Stasiun Mebel Jepara Website. After building the Stasiun Mebel Jepara website, the author tested the website’s usability using the System Usability Scale. The results of testing on 169 respondents in using the System Usability Scale website showed that the average SUS score of respondents was 64.41 with an interpretation of the C grade category. Respondents assessed that the website created was OK (adjectives) and marginal (acceptability), and passive in terms of NPS.
{"title":"Website Development with Laravel and Scrum Method: A Study case of Stasiun Mebel Jepara Store Case","authors":"H. Samosir, Tegar Arifin Prasetyo, Sintong Lumbantobing, Diana Octaviana Naibaho, Christy Riris T Situmorang","doi":"10.1109/QIR54354.2021.9716184","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716184","url":null,"abstract":"Stasiun Mebel Jepara is a furniture store located in Medan, Indonesia. At the Stasiun Mebel Jepara store, there are problems regarding recording the results of transaction services, where the shop owner calculates the transaction results relying on a calculator and does not use a computer, product data collection also depends on recording on books so that employees have difficulty seeing product prices because they have to communicate again with the shop owner. Shop owners also find it challenging to record and collect data on products to be repaired and forged, so shop owners often seek back information obtained through private chats from customers. The author builds the Stasiun Mebel Jepara website using the Scrum method and the Laravel framework. The author uses the Scrum method because it is iterative, incremental, and can apply a continuous learning culture. The author decided to use Laravel because it has complete documentation and can be used freely and free of charge—the work on this final project resulted in the Stasiun Mebel Jepara Website. After building the Stasiun Mebel Jepara website, the author tested the website’s usability using the System Usability Scale. The results of testing on 169 respondents in using the System Usability Scale website showed that the average SUS score of respondents was 64.41 with an interpretation of the C grade category. Respondents assessed that the website created was OK (adjectives) and marginal (acceptability), and passive in terms of NPS.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130305413","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716161
Gunawan Aji, Teuku Salman Farizi, Muhammad Farhan, R. F. Sari
Short Message Service (SMS) is one of the most common communication media for mobile devices. Although there are many alternatives to mobile text communication such as Whatsapp or LINE based online, SMS is still very commonly used because it only requires mobile number information and mobile signals available. Because of the ease of disseminating information with this SMS media, many people use SMS to send unimportant or even harmful messages to mobile device users. This unimportant SMS is referred to as SPAM. The number of SPAM messages that enter a person’s mobile phone filled the inbox with non-essential information, covered important information, wasted user time, and hindered communication. Therefore, a system that can automatically classify SPAM is required. Data obtained from this classification system may contain sensitive user information such as mobile numbers. Therefore, a SPAM SMS classification storage system with a blockchain platform is created. In this work, we use Hyperledger Composer to create our blockchain. Blockchain technology is used because it is an immutable and secure data storage system that can maintain the confidentiality of sensitive information that may be contained in SPAM messages.
{"title":"Machine Learning Based SPAM Message Classification System using Blockchain Technology","authors":"Gunawan Aji, Teuku Salman Farizi, Muhammad Farhan, R. F. Sari","doi":"10.1109/QIR54354.2021.9716161","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716161","url":null,"abstract":"Short Message Service (SMS) is one of the most common communication media for mobile devices. Although there are many alternatives to mobile text communication such as Whatsapp or LINE based online, SMS is still very commonly used because it only requires mobile number information and mobile signals available. Because of the ease of disseminating information with this SMS media, many people use SMS to send unimportant or even harmful messages to mobile device users. This unimportant SMS is referred to as SPAM. The number of SPAM messages that enter a person’s mobile phone filled the inbox with non-essential information, covered important information, wasted user time, and hindered communication. Therefore, a system that can automatically classify SPAM is required. Data obtained from this classification system may contain sensitive user information such as mobile numbers. Therefore, a SPAM SMS classification storage system with a blockchain platform is created. In this work, we use Hyperledger Composer to create our blockchain. Blockchain technology is used because it is an immutable and secure data storage system that can maintain the confidentiality of sensitive information that may be contained in SPAM messages.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128201812","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716204
D. Sudiana, M. Rizkinia, Nathanael Tristan
The need for renewable energy has increased recently, along with the shortage of non-renewable energy sources such as petroleum, coal, uranium, crude oil, and others. One of the renewable energies whose technology has recently been developing is wind power; however, it still suffers from a drawback due to the fluctuations in energy production. Increasing wind energy potential requires a wind power prediction method that can predict the intermittent patterns of the prediction result from the generated wind power. In dealing with the frequent intermittent patterns that fluctuate frequently and have many variations, the Triple Exponential Smoothing Multiplicative LSTM (TES-MLSTM) model can read them and then predict with a short term few steps ahead. In this paper, LSTM Bayesian Network as another deep learning method is proposed and compared with the TES-MLSTM. This method uses the same LSTM base, enhanced with its hyperparameter tuning and run in a Bayesian Network. The model parameters are learned from the training data, and hyperparameters are tuned to get the best fit. The tuned hyperparameter will be processed using Bayesian Network. In the experiment, we used the 2013 dataset of Pandansimo wind power plant (PLTB) in Indonesia as the input data. The average wind power prediction errors (MSE) using the TES-MLSTM and LSTM Bayesian Network are 0.891 and 0.644, respectively. It can be concluded that the proposed LSTM Bayesian Network method is more accurate in predicting the wind power potential of a wind turbine than the TES-MLSTM method.
{"title":"Development of Long Short-Term Memory (LSTM) Bayesian Network Method for Predicting Wind Power Potential in a Wind Power Plant in Indonesia","authors":"D. Sudiana, M. Rizkinia, Nathanael Tristan","doi":"10.1109/QIR54354.2021.9716204","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716204","url":null,"abstract":"The need for renewable energy has increased recently, along with the shortage of non-renewable energy sources such as petroleum, coal, uranium, crude oil, and others. One of the renewable energies whose technology has recently been developing is wind power; however, it still suffers from a drawback due to the fluctuations in energy production. Increasing wind energy potential requires a wind power prediction method that can predict the intermittent patterns of the prediction result from the generated wind power. In dealing with the frequent intermittent patterns that fluctuate frequently and have many variations, the Triple Exponential Smoothing Multiplicative LSTM (TES-MLSTM) model can read them and then predict with a short term few steps ahead. In this paper, LSTM Bayesian Network as another deep learning method is proposed and compared with the TES-MLSTM. This method uses the same LSTM base, enhanced with its hyperparameter tuning and run in a Bayesian Network. The model parameters are learned from the training data, and hyperparameters are tuned to get the best fit. The tuned hyperparameter will be processed using Bayesian Network. In the experiment, we used the 2013 dataset of Pandansimo wind power plant (PLTB) in Indonesia as the input data. The average wind power prediction errors (MSE) using the TES-MLSTM and LSTM Bayesian Network are 0.891 and 0.644, respectively. It can be concluded that the proposed LSTM Bayesian Network method is more accurate in predicting the wind power potential of a wind turbine than the TES-MLSTM method.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129966737","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716201
H. Elfira Febriani, R. Fitriana, Cendana Lestari Faturrahman
This study aims to transactions analysis from a coffee shop transaction in six months to define consumer purchases pattern with the development of a model of association rules. One of the coffee shops in Jakarta, the 8th Bean Cafe, was used as a study case in this study. The problems that occurred when deciding not based on data analysis, so they lost for 3 sales periods. This cafe has 80 menus that keep changing every time according to the owner’s wishes without knowing the favorite menu, the most frequently purchased menu, and so on. They never analyze what menu that consumers are interested in buying. Based on the results found 3 association rules, namely {CLASSIC $Rightarrow$ SIGNATURE}, {FRIED RICE AND PASTA $Rightarrow$ LIGHT BITES}, {LIGHT BITES FRIED RICE AND PASTA} from sales transaction data mining. The rules provide information that two types of 2-itemset combinations tend to buy together.
本研究旨在通过对某咖啡店6个月的交易进行分析，通过建立关联规则模型来定义消费者的购买模式。在本研究中，雅加达的一家咖啡店，第八豆咖啡馆，被用作研究案例。在决策时出现的问题不是基于数据分析，所以他们输了3个销售周期。这家咖啡馆有80个菜单，每次都根据主人的意愿不断改变，不知道最喜欢的菜单，最常购买的菜单等等。他们从不分析消费者对什么菜单感兴趣。基于结果从销售交易数据挖掘中发现了3条关联规则，即{CLASSIC $Rightarrow$ SIGNATURE}、{FRIED RICE AND PASTA $Rightarrow$ LIGHT BITES}、{LIGHT BITES FRIED RICE AND PASTA}。规则提供了两种类型的2-itemset组合倾向于一起购买的信息。
{"title":"Applying Data Mining of Association Rules as Decision Making In Coffee-Shop: a Case Study","authors":"H. Elfira Febriani, R. Fitriana, Cendana Lestari Faturrahman","doi":"10.1109/QIR54354.2021.9716201","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716201","url":null,"abstract":"This study aims to transactions analysis from a coffee shop transaction in six months to define consumer purchases pattern with the development of a model of association rules. One of the coffee shops in Jakarta, the 8th Bean Cafe, was used as a study case in this study. The problems that occurred when deciding not based on data analysis, so they lost for 3 sales periods. This cafe has 80 menus that keep changing every time according to the owner’s wishes without knowing the favorite menu, the most frequently purchased menu, and so on. They never analyze what menu that consumers are interested in buying. Based on the results found 3 association rules, namely {CLASSIC $Rightarrow$ SIGNATURE}, {FRIED RICE AND PASTA $Rightarrow$ LIGHT BITES}, {LIGHT BITES FRIED RICE AND PASTA} from sales transaction data mining. The rules provide information that two types of 2-itemset combinations tend to buy together.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123159694","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716168
Rosza Madina, F. Zulkifli
The rapid development of AIS (Automatic Identification System) data usage applications, makes AIS began to be applied in satellites to obtain a larger coverage area. Indonesia through the Indonesian National Aeronautics and Space Agency (LAPAN) has two micro satellites with the AIS mission, namely LAPAN-A2/LAPAN-ORARI and LAPAN-A3/LAPAN-IPB. LAPAN will also build another micro satellite that carries AIS in order to get near real-time data. AIS based satellite has problems with large VHF antenna dimensions and data collisions in high traffic areas. The final dimension of the purposed antenna is 133.00 x 88.00 x 1.52 mm3, therefore this antenna can be applied in micro satellite. The simulation results show that the antenna works at a frequency 160.93-164.04 MHz with gain 1.654 dB. Miniaturization with meander-line and metamaterial structure technique has succeeded in reducing dimensions by 42%. This antenna has an omnidirectional radiation pattern with a beamwidth of 88.26°, and when this VHF antenna is installed on a satellite, the projection of the antenna on the earth’s surface is reduced by 50% from existing antenna. Hence this antenna can be used to reduce data collision of the satellite.
AIS(自动识别系统)数据使用应用的迅速发展，使得AIS开始在卫星上应用，以获得更大的覆盖范围。印度尼西亚通过印度尼西亚国家航空和航天局(LAPAN)有两颗微型卫星执行AIS任务，即LAPAN- a2 /LAPAN- orari和LAPAN- a3 /LAPAN- ipb。LAPAN还将建造另一颗携带AIS系统的微型卫星，以便获得接近实时的数据。基于AIS的卫星在高流量区域存在甚高频天线尺寸大、数据冲突等问题。最终天线尺寸为133.00 x 88.00 x 1.52 mm3，可应用于微型卫星。仿真结果表明，该天线工作频率为160.93 ~ 164.04 MHz，增益为1.654 dB。采用弯曲线和超材料结构技术的微型化成功地将尺寸缩小了42%。该天线具有全向辐射方向图，波束宽度为88.26°，当该甚高频天线安装在卫星上时，该天线在地球表面的投影比现有天线减少50%。因此，该天线可用于减少卫星数据碰撞。
{"title":"Meander line Antenna with Metamaterial Structure for AIS (Automatic Identification System) Micro Satellite","authors":"Rosza Madina, F. Zulkifli","doi":"10.1109/QIR54354.2021.9716168","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716168","url":null,"abstract":"The rapid development of AIS (Automatic Identification System) data usage applications, makes AIS began to be applied in satellites to obtain a larger coverage area. Indonesia through the Indonesian National Aeronautics and Space Agency (LAPAN) has two micro satellites with the AIS mission, namely LAPAN-A2/LAPAN-ORARI and LAPAN-A3/LAPAN-IPB. LAPAN will also build another micro satellite that carries AIS in order to get near real-time data. AIS based satellite has problems with large VHF antenna dimensions and data collisions in high traffic areas. The final dimension of the purposed antenna is 133.00 x 88.00 x 1.52 mm3, therefore this antenna can be applied in micro satellite. The simulation results show that the antenna works at a frequency 160.93-164.04 MHz with gain 1.654 dB. Miniaturization with meander-line and metamaterial structure technique has succeeded in reducing dimensions by 42%. This antenna has an omnidirectional radiation pattern with a beamwidth of 88.26°, and when this VHF antenna is installed on a satellite, the projection of the antenna on the earth’s surface is reduced by 50% from existing antenna. Hence this antenna can be used to reduce data collision of the satellite.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131681793","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716188
Nanda Aulia Ilmatus Sakdiyah, M. Asvial
The resource scheduling scheme is essential because it selects an accurate time and frequency domain, distributes radio resources and determines channel conditions and working range for the 5.5G new radio technology. Determining the appropriate packet traffic scheduling method is vital in improving the quality of service on the 5.5G multi-user OFDM (MU-OFDM) cellular network. A Greedy power allocation round robin scheduling algorithm is proposed in this paper. Complexity is reduced by performing subcarrier and power allocation steps with a proportional rate limit for the MUOFDM 5.5G system. The simulation results show that the capacity can be increased using the proposed algorithm. The 86 Mbps and 1972 users per cell can be achieved compared to the conventional algorithm.
{"title":"Development of Greedy Power Allocation Round Robin Scheduling for 5.5G Traffic Management","authors":"Nanda Aulia Ilmatus Sakdiyah, M. Asvial","doi":"10.1109/QIR54354.2021.9716188","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716188","url":null,"abstract":"The resource scheduling scheme is essential because it selects an accurate time and frequency domain, distributes radio resources and determines channel conditions and working range for the 5.5G new radio technology. Determining the appropriate packet traffic scheduling method is vital in improving the quality of service on the 5.5G multi-user OFDM (MU-OFDM) cellular network. A Greedy power allocation round robin scheduling algorithm is proposed in this paper. Complexity is reduced by performing subcarrier and power allocation steps with a proportional rate limit for the MUOFDM 5.5G system. The simulation results show that the capacity can be increased using the proposed algorithm. The 86 Mbps and 1972 users per cell can be achieved compared to the conventional algorithm.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116173564","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716164
Ernia Susana, K. Ramli
The emergence of photoplethysmography for the non-invasive estimation of blood glucose levels in diabetes management offers an alternative solution to the limitations of invasive methods. The application of artificial intelligence technology to PPG signals for non-invasive measurement of monitoring blood glucose level (BGL) using either a machine learning (ML) or deep learning (DL) approach is proven to improve the resulting performance. This review is presented to provide concise information about current and proposed technologies developments of non-invasive blood glucose level monitoring methods using photoplethysmography. The study focuses on the opportunities and constraints in developing research on this topic.
{"title":"Review of Non-Invasive Blood Glucose Level Estimation based on Photoplethysmography and Artificial Intelligent Technology","authors":"Ernia Susana, K. Ramli","doi":"10.1109/QIR54354.2021.9716164","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716164","url":null,"abstract":"The emergence of photoplethysmography for the non-invasive estimation of blood glucose levels in diabetes management offers an alternative solution to the limitations of invasive methods. The application of artificial intelligence technology to PPG signals for non-invasive measurement of monitoring blood glucose level (BGL) using either a machine learning (ML) or deep learning (DL) approach is proven to improve the resulting performance. This review is presented to provide concise information about current and proposed technologies developments of non-invasive blood glucose level monitoring methods using photoplethysmography. The study focuses on the opportunities and constraints in developing research on this topic.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121093600","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716185
Y. Rahayu, Inesti Lailatul Qodriyah, Meilita Kurniati, Anhar, H. Masdar, M. Savira
Bacteria found in food are very harmful to the health of the human body. This will cause various kinds of diseases. Therefore, food that is clean from bacteria is very important to maintain. Various solutions have been developed by researchers to provide a fast, sensitive, and cost-effective way to detect pathogens such as bacteria. The use of electrochemical biosensor devices is very commonly used to detect bacteria, viruses, fungi, and others. This approach is to identify infections quickly and accurately. In this study, the antenna biosensor was designed to detect bacteria. The antenna is designed to operate at a working frequency of 2.45 GHz (2.4 – 2.5 GHz) using a proximity coupled feed. The antenna is printed using Roger 3010 as a substrate material which has a thickness of 1.28 mm. Antenna biosensor testing was carried out using three (3) liquid samples, namely pure water (Aquadest), fresh milk, and Yakult. From the test results of the antenna without using a liquid sample, it was found that the antenna was able to work at an average frequency of 2.496 GHz with the best reflection coefficient at -16 dB. There is a shift in frequency compared to the frequency in the simulation. Tests using distilled water showed that there was no frequency shift, but testing with milk showed a decrease in frequency to an average frequency of 2.417 GHz. As for testing with Yakult, the frequency is on average at 2.491 GHz. As an initial hypothesis, the bacteria found in Yakult caused a slight shift in frequency from the original frequency. This is because fermentation in Yakult caused by bacteria results the viscosity to decrease compared to the viscosity of fresh milk.
{"title":"Biosensor Microstrip Antenna Design at 2.45 GHz for Bacteria Detection","authors":"Y. Rahayu, Inesti Lailatul Qodriyah, Meilita Kurniati, Anhar, H. Masdar, M. Savira","doi":"10.1109/QIR54354.2021.9716185","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716185","url":null,"abstract":"Bacteria found in food are very harmful to the health of the human body. This will cause various kinds of diseases. Therefore, food that is clean from bacteria is very important to maintain. Various solutions have been developed by researchers to provide a fast, sensitive, and cost-effective way to detect pathogens such as bacteria. The use of electrochemical biosensor devices is very commonly used to detect bacteria, viruses, fungi, and others. This approach is to identify infections quickly and accurately. In this study, the antenna biosensor was designed to detect bacteria. The antenna is designed to operate at a working frequency of 2.45 GHz (2.4 – 2.5 GHz) using a proximity coupled feed. The antenna is printed using Roger 3010 as a substrate material which has a thickness of 1.28 mm. Antenna biosensor testing was carried out using three (3) liquid samples, namely pure water (Aquadest), fresh milk, and Yakult. From the test results of the antenna without using a liquid sample, it was found that the antenna was able to work at an average frequency of 2.496 GHz with the best reflection coefficient at -16 dB. There is a shift in frequency compared to the frequency in the simulation. Tests using distilled water showed that there was no frequency shift, but testing with milk showed a decrease in frequency to an average frequency of 2.417 GHz. As for testing with Yakult, the frequency is on average at 2.491 GHz. As an initial hypothesis, the bacteria found in Yakult caused a slight shift in frequency from the original frequency. This is because fermentation in Yakult caused by bacteria results the viscosity to decrease compared to the viscosity of fresh milk.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127310532","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 : 2021-10-13DOI: 10.1109/QIR54354.2021.9716181
Alif M. Hafizh, T. Abuzairi, Ahli Irfan
Fever has a sensitivity of 54% and specificity of 67% against SARS-CoV-2 so it can be used to determine whether a person is infected with COVID-19. To prevent the spread of the virus in public places, a body temperature screening process using an infrared thermometer is required. The two sensors that are commonly used as infrared thermometers are the MLX90614 and AMG8833 because of their high temperature range and good accuracy. However, the measurement results can be affected by the measuring distance, room temperature, and physical activity in the human body. Therefore, an infrared thermometer with two sensors arranged in overlay was designed to evaluate the performance of infrared thermal sensors based on measuring distances (15, 30, 40, and 60 cm), 2 rooms (26.4 °C and 30 °C), and physical activity on the object. The results in the 30 °C room at 15 – 40 cm show measured temperature above 36 °C for both sensors, while in the 26.4 °C room it decreased up to 35.32 °C. At 15 cm in a 26.4 °C room, the measured temperature results are the closest to the reference values with a difference of less than 0.3 °C for the MLX90614 sensor, while at 60 cm, the results are the furthest from the reference values also it has larger difference value, which is 0.21 °C for the MLX90614 and 1.01 °C for the AMG8833. In conclusion, the MLX90614 sensor is better than the AMG8833 sensor because its outputs are closer to the reference values.
{"title":"Performance Evaluation of Infrared Thermal Sensors based on Distance, Room Temperature, and Physical Activity on Objects","authors":"Alif M. Hafizh, T. Abuzairi, Ahli Irfan","doi":"10.1109/QIR54354.2021.9716181","DOIUrl":"https://doi.org/10.1109/QIR54354.2021.9716181","url":null,"abstract":"Fever has a sensitivity of 54% and specificity of 67% against SARS-CoV-2 so it can be used to determine whether a person is infected with COVID-19. To prevent the spread of the virus in public places, a body temperature screening process using an infrared thermometer is required. The two sensors that are commonly used as infrared thermometers are the MLX90614 and AMG8833 because of their high temperature range and good accuracy. However, the measurement results can be affected by the measuring distance, room temperature, and physical activity in the human body. Therefore, an infrared thermometer with two sensors arranged in overlay was designed to evaluate the performance of infrared thermal sensors based on measuring distances (15, 30, 40, and 60 cm), 2 rooms (26.4 °C and 30 °C), and physical activity on the object. The results in the 30 °C room at 15 – 40 cm show measured temperature above 36 °C for both sensors, while in the 26.4 °C room it decreased up to 35.32 °C. At 15 cm in a 26.4 °C room, the measured temperature results are the closest to the reference values with a difference of less than 0.3 °C for the MLX90614 sensor, while at 60 cm, the results are the furthest from the reference values also it has larger difference value, which is 0.21 °C for the MLX90614 and 1.01 °C for the AMG8833. In conclusion, the MLX90614 sensor is better than the AMG8833 sensor because its outputs are closer to the reference values.","PeriodicalId":446396,"journal":{"name":"2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132485922","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：