Pub Date : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649680
Iqlima Bairat, A. A. Pramudita, Y. Wahyu
One of the 5G key features in improving energy efficiency is suitable for cognitive radio technology. Cognitive radio has the ability in sensing the operation situation and providing a certain response regarding the sensing result. The operation situation of electromagnetic propagation allows multipath and depolarization of antenna due to many obstacles. In this paper, polarization reconfigurable antenna was proposed to support cognitive radio technology in 3.5 GHz 5G system. The antenna has capability for reconfigure between linear polarization, right-hand circular polarization (RHCP), and left-hand circular polarization (LHCP) manually to mitigate the polarization loss during propagation. The results show that antenna has good performance in the perspective of matching impedance and axial ratio. It is shown in simulation that the S11 less than -10 dB for RHCP and LHCP with axial ratio 1.762 dB and 1.811 dB respectively. Whereas for linear polarization, the S11 of 3.5 GHz more than -10 dB and has optimum value at 3.1 GHz with an axial ratio of 40 dB.
{"title":"Polarization Reconfigurable Antenna for 5G Wireless Communication Systems On 3.5 GHz Frequency","authors":"Iqlima Bairat, A. A. Pramudita, Y. Wahyu","doi":"10.1109/ice3is54102.2021.9649680","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649680","url":null,"abstract":"One of the 5G key features in improving energy efficiency is suitable for cognitive radio technology. Cognitive radio has the ability in sensing the operation situation and providing a certain response regarding the sensing result. The operation situation of electromagnetic propagation allows multipath and depolarization of antenna due to many obstacles. In this paper, polarization reconfigurable antenna was proposed to support cognitive radio technology in 3.5 GHz 5G system. The antenna has capability for reconfigure between linear polarization, right-hand circular polarization (RHCP), and left-hand circular polarization (LHCP) manually to mitigate the polarization loss during propagation. The results show that antenna has good performance in the perspective of matching impedance and axial ratio. It is shown in simulation that the S11 less than -10 dB for RHCP and LHCP with axial ratio 1.762 dB and 1.811 dB respectively. Whereas for linear polarization, the S11 of 3.5 GHz more than -10 dB and has optimum value at 3.1 GHz with an axial ratio of 40 dB.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127101049","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649740
H. Fajrin, Kahfi Muhammad, Wisnu Kusuma Wardana
This study aims to monitor parameters such as chamber temperature, skin temperature, humidity, and noise from the incubator to prevent temperatures that are too hot, humidity that is too high or too low, and high noise levels that can damage baby's hearing by utilizing the internet system, so that with this tool medical personnel can monitor parameters on android smartphones. This study uses the ESP32 as the mainboard, the Ds18b20 sensor as the skin sensor, the SHT11 sensor as the chamber temperature and humidity sensor, and the analog sound level meter as the noise sensor of the device. From the test results, the largest error at chamber temperature is 0.97% at 36°C setting. In the noise test results, the largest error is 0.73 % at setting 55 dB. In testing the skin temperature on the incubator, a value that is close to linear is obtained where when the chamber temperature setting on the tool is increased, the value of the skin temperature on the incubator and tool will also increase. On the results of the humidity test at the setting of 32-37°C, the humidity value of the instrument and calibrator is 68-70%. In the data transmission test, the device can be monitored remotely on the android application as long as the device and smartphone are connected to the internet.
{"title":"Monitoring of Incubator Parameters Using Android Applications","authors":"H. Fajrin, Kahfi Muhammad, Wisnu Kusuma Wardana","doi":"10.1109/ice3is54102.2021.9649740","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649740","url":null,"abstract":"This study aims to monitor parameters such as chamber temperature, skin temperature, humidity, and noise from the incubator to prevent temperatures that are too hot, humidity that is too high or too low, and high noise levels that can damage baby's hearing by utilizing the internet system, so that with this tool medical personnel can monitor parameters on android smartphones. This study uses the ESP32 as the mainboard, the Ds18b20 sensor as the skin sensor, the SHT11 sensor as the chamber temperature and humidity sensor, and the analog sound level meter as the noise sensor of the device. From the test results, the largest error at chamber temperature is 0.97% at 36°C setting. In the noise test results, the largest error is 0.73 % at setting 55 dB. In testing the skin temperature on the incubator, a value that is close to linear is obtained where when the chamber temperature setting on the tool is increased, the value of the skin temperature on the incubator and tool will also increase. On the results of the humidity test at the setting of 32-37°C, the humidity value of the instrument and calibrator is 68-70%. In the data transmission test, the device can be monitored remotely on the android application as long as the device and smartphone are connected to the internet.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127359286","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649707
Z. Abidin, Rohmat Indra Borman, Febri Bagus Ananda, Purwono Prasetyawan, Farli Rossi, Y. Jusman
Some people consider traditional snacks are out of date. Many of the traditional snacks were abandoned by the community and began to switch to more modern foods so that people sometimes do not recognize the traditional cakes in circulation. This study to develop model recognition traditional Indonesian snacks. As technology development, image recognition using the Convolutional Neural Network (CNN) method as classification method using the pre-trained MobilenetV2 model as the basic model can be used. From total dataset of 1545 images of traditional cakes consisting of 8 categories, they are divided into 80% train data and 20% test data. After going through the training and testing process, the accuracy results are 98.9% for train data and 90.5% for test data. Model testing performed on the new test data resulted in an accuracy of 92.5% where the model managed to classify 74 images from 80 images of traditional cakes according to their categories which were presented in the form of confusion matrix. Several experiments were also carried out to find the parameters that produce the model with the best accuracy, namely the effect of the number of epochs, the effect of the dataset distribution scenario, and the effect of the size of the learning rate.
{"title":"Classification of Indonesian Traditional Snacks Based on Image Using Convolutional Neural Network (CNN) Algorithm","authors":"Z. Abidin, Rohmat Indra Borman, Febri Bagus Ananda, Purwono Prasetyawan, Farli Rossi, Y. Jusman","doi":"10.1109/ice3is54102.2021.9649707","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649707","url":null,"abstract":"Some people consider traditional snacks are out of date. Many of the traditional snacks were abandoned by the community and began to switch to more modern foods so that people sometimes do not recognize the traditional cakes in circulation. This study to develop model recognition traditional Indonesian snacks. As technology development, image recognition using the Convolutional Neural Network (CNN) method as classification method using the pre-trained MobilenetV2 model as the basic model can be used. From total dataset of 1545 images of traditional cakes consisting of 8 categories, they are divided into 80% train data and 20% test data. After going through the training and testing process, the accuracy results are 98.9% for train data and 90.5% for test data. Model testing performed on the new test data resulted in an accuracy of 92.5% where the model managed to classify 74 images from 80 images of traditional cakes according to their categories which were presented in the form of confusion matrix. Several experiments were also carried out to find the parameters that produce the model with the best accuracy, namely the effect of the number of epochs, the effect of the dataset distribution scenario, and the effect of the size of the learning rate.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128466683","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649697
Sigit Widadi, Iswanto, Parwoto, H. Fajrin
The development of Village-Owned Enterprises requires careful planning and preparation from all stakeholders. This study seeks to develop Village-Owned Enterprises based on the information system (IS) development to obtain accounting business process standards agreed by stakeholders. The results can be used as the basis for developing an accounting information system (AIS). The research method used the ADM cycle from TOGAF combined with the accounting cycle. The activity began with the analysis of the preparation stage carried out by Village-Owned Enterprises to reach the maturity level in managing finances. Business process standards approved by Village-Owned Enterprises stakeholders become the basis for developing an accounting business process model oriented towards future business goals as a manifestation of lower-level architecture principles.
{"title":"Business Architecture Accounting Information System of Village-Owned Enterprises with TOGAF","authors":"Sigit Widadi, Iswanto, Parwoto, H. Fajrin","doi":"10.1109/ice3is54102.2021.9649697","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649697","url":null,"abstract":"The development of Village-Owned Enterprises requires careful planning and preparation from all stakeholders. This study seeks to develop Village-Owned Enterprises based on the information system (IS) development to obtain accounting business process standards agreed by stakeholders. The results can be used as the basis for developing an accounting information system (AIS). The research method used the ADM cycle from TOGAF combined with the accounting cycle. The activity began with the analysis of the preparation stage carried out by Village-Owned Enterprises to reach the maturity level in managing finances. Business process standards approved by Village-Owned Enterprises stakeholders become the basis for developing an accounting business process model oriented towards future business goals as a manifestation of lower-level architecture principles.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130084706","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649695
Iffah Zulaikha Saiful Bahri, S. Saon, A. Mahamad, Pratomo Budi Santosa
This paper proposes a study on U niversiti Tun Hussein Onn Malaysia (UTHM) shuttle bus services for the UTHM students to get to their desired destination in time. Hence, students refuse to ride the shuttle bus as sometimes the shuttle bus is late and not up to the schedule. Although the university has handed out the shuttle bus schedule through the UTHM KATSANA website, it is still inconsistent due to the traffic congestion. The proposed system required a student to request the services to the selected destination; thus, this application estimates the bus arrival time by locating the bus's live location, route, and bus number. Based on the estimated information, students can plan their rides. Additionally, this application allows the driver to minimise the path length taken to each pit stop by interacting with the students. It also enables them to react and decide before the bus's arrival or wait at the bus stop. Google's distance matrix; Application Programming Interface (API), helps coordinate the chosen bus location to the selected bus stop. There are a total of three development phases in this project. The first phase is database acquisition or collection of existing data related to this project. The second phase is the system's design which involves the Firebase Realtime Database, Google API and Android Studio application. Next, the third phase is the system's testing phase. As a result, the proposed system is simulated and tested in real applications. Finally, the driver's and student's information is recorded in Firebase Real-time Database.
{"title":"Shuttle Bus Service with Ride-Hailing Application","authors":"Iffah Zulaikha Saiful Bahri, S. Saon, A. Mahamad, Pratomo Budi Santosa","doi":"10.1109/ice3is54102.2021.9649695","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649695","url":null,"abstract":"This paper proposes a study on U niversiti Tun Hussein Onn Malaysia (UTHM) shuttle bus services for the UTHM students to get to their desired destination in time. Hence, students refuse to ride the shuttle bus as sometimes the shuttle bus is late and not up to the schedule. Although the university has handed out the shuttle bus schedule through the UTHM KATSANA website, it is still inconsistent due to the traffic congestion. The proposed system required a student to request the services to the selected destination; thus, this application estimates the bus arrival time by locating the bus's live location, route, and bus number. Based on the estimated information, students can plan their rides. Additionally, this application allows the driver to minimise the path length taken to each pit stop by interacting with the students. It also enables them to react and decide before the bus's arrival or wait at the bus stop. Google's distance matrix; Application Programming Interface (API), helps coordinate the chosen bus location to the selected bus stop. There are a total of three development phases in this project. The first phase is database acquisition or collection of existing data related to this project. The second phase is the system's design which involves the Firebase Realtime Database, Google API and Android Studio application. Next, the third phase is the system's testing phase. As a result, the proposed system is simulated and tested in real applications. Finally, the driver's and student's information is recorded in Firebase Real-time Database.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126513374","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649684
M. Hadi, S. Bhima Satria Rizki, Maulana Achmad As-Shidiqi, Maulana Ludfi Arrohman, Dyah Lestari, Mhd Irvan
Orchids are plants that are hard to live in and require extraordinary dealing with for the development cycle. In Indonesia, many kinds of orchids live stunningly in tropical woods like Kalimantan, and a few woodlands on the island of Java. Be that as it may, as the occasions advanced, Indonesia's environment became harmed, set apart by an extremely long dry season and a moderately short blustery season. On account of this issue, numerous wild orchids in the timberlands of Indonesia are compromised with annihilation. Orchids are hard to fill in sweltering and dry environments on the grounds that most orchids utilize their underlying foundations to discover food. The solution to this problem is a Smart greenhouse. It is a mini-greenhouse system that can maintain the temperature and humidity of the orchid following its natural ecosystem. The system is also equipped with Fuzzy-based automatic control. so that the system is able to work independently. The fuzzy system was tested to get the percentage of errors, where from the test results, the percentage of errors for the defuzzification process was 1.176%, which indicates that the system can run well.
{"title":"Smart Greenhouse Control System For Orchid Growing Media Based On IoT And Fuzzy Logic Technology","authors":"M. Hadi, S. Bhima Satria Rizki, Maulana Achmad As-Shidiqi, Maulana Ludfi Arrohman, Dyah Lestari, Mhd Irvan","doi":"10.1109/ice3is54102.2021.9649684","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649684","url":null,"abstract":"Orchids are plants that are hard to live in and require extraordinary dealing with for the development cycle. In Indonesia, many kinds of orchids live stunningly in tropical woods like Kalimantan, and a few woodlands on the island of Java. Be that as it may, as the occasions advanced, Indonesia's environment became harmed, set apart by an extremely long dry season and a moderately short blustery season. On account of this issue, numerous wild orchids in the timberlands of Indonesia are compromised with annihilation. Orchids are hard to fill in sweltering and dry environments on the grounds that most orchids utilize their underlying foundations to discover food. The solution to this problem is a Smart greenhouse. It is a mini-greenhouse system that can maintain the temperature and humidity of the orchid following its natural ecosystem. The system is also equipped with Fuzzy-based automatic control. so that the system is able to work independently. The fuzzy system was tested to get the percentage of errors, where from the test results, the percentage of errors for the defuzzification process was 1.176%, which indicates that the system can run well.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121218126","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649676
Y. Jusman, Indah Monisa Firdiantika, S. Riyadi, Siti Nurul Aqmariah Mohd Kanafiah, R. Hassan, Z. Mohamed
Identification analysis of the malaria parasite cell infection, there is a possibility of human error factor done by paramedics because of the number of samples that must be analyzed. This case is because the human eye tends to be tired while working continuously, which can lead to misclassification and treatment that is not right. Therefore, it takes a computer-based system that facilitates medical expert or laboratory technician in identifying two types of parasite cells namely Plasmodium skizon and Plasmodium gametocytes to reduce instances of human error. This research will be conducted on computer-based identification by processing the image type of plasmodium malariae consists of two types, namely Plasmodium skizon and Plasmodium gametocytes levels using convolutional neural network with VGG-16 pre-trained model using 13 layers and 2 dense layers. This study applied 5-fold cross validation for datasets and the datasets are tested using 4 level epoch nodes. The results showed the success of the classification results which have highest training accuracy 90% as well as the results of the highest testing accuracy 100%• It showed the classification using CNN VGG-16 pre-trained model successfully classified the malaria type images.
{"title":"Classification of Plasmodium Skizon and Gametocytes Malaria Images Using Deep Learning","authors":"Y. Jusman, Indah Monisa Firdiantika, S. Riyadi, Siti Nurul Aqmariah Mohd Kanafiah, R. Hassan, Z. Mohamed","doi":"10.1109/ice3is54102.2021.9649676","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649676","url":null,"abstract":"Identification analysis of the malaria parasite cell infection, there is a possibility of human error factor done by paramedics because of the number of samples that must be analyzed. This case is because the human eye tends to be tired while working continuously, which can lead to misclassification and treatment that is not right. Therefore, it takes a computer-based system that facilitates medical expert or laboratory technician in identifying two types of parasite cells namely Plasmodium skizon and Plasmodium gametocytes to reduce instances of human error. This research will be conducted on computer-based identification by processing the image type of plasmodium malariae consists of two types, namely Plasmodium skizon and Plasmodium gametocytes levels using convolutional neural network with VGG-16 pre-trained model using 13 layers and 2 dense layers. This study applied 5-fold cross validation for datasets and the datasets are tested using 4 level epoch nodes. The results showed the success of the classification results which have highest training accuracy 90% as well as the results of the highest testing accuracy 100%• It showed the classification using CNN VGG-16 pre-trained model successfully classified the malaria type images.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116736734","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}
Early prevention of heart disease can be done by monitoring the condition of heart's health using an electrocardiograph (ECG). In order to make it easier for medical personnel to monitor heart signals, a media for storing results is needed when an examination is carried out. Storage media will be even more effective if it can be accessed remotely. The purpose of this study was to design a modified ECG to check the condition of the heart using a data logger system. The device is designed in simple and applicable which smartphone acts as the display in real-time and can store the readings. This problem is limited by the research device using one lead to monitor heart signals. This study uses AD8232 as a heart signal receiver from the body and Wemos Dl Mini as a link to WiFi to display data on a smartphone using a created application. The measurement and testing methods carried out are by comparing the heart rate (BPM) value with the Phantom ECG input read on a smartphone, comparing the readings of the human heart signal on smartphone and ECG, and testing the human BPM value on smartphone. The overall results of reading the BPM value in the design obtained the error value under 5%. Sending data from Wemos D1 Mini as a media hotspot programmed using Arduino IDE software works well. The results of the heart signal data that are read on the smartphone can be stored so that users can send or print them.
{"title":"Wireless Heart Signal Monitoring with Smartphone as Storage Media","authors":"Erika Loniza, Chairman Alfajar, Alya Izzaty Bika, Yuli Ermawati, W. Kartika","doi":"10.1109/ice3is54102.2021.9649669","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649669","url":null,"abstract":"Early prevention of heart disease can be done by monitoring the condition of heart's health using an electrocardiograph (ECG). In order to make it easier for medical personnel to monitor heart signals, a media for storing results is needed when an examination is carried out. Storage media will be even more effective if it can be accessed remotely. The purpose of this study was to design a modified ECG to check the condition of the heart using a data logger system. The device is designed in simple and applicable which smartphone acts as the display in real-time and can store the readings. This problem is limited by the research device using one lead to monitor heart signals. This study uses AD8232 as a heart signal receiver from the body and Wemos Dl Mini as a link to WiFi to display data on a smartphone using a created application. The measurement and testing methods carried out are by comparing the heart rate (BPM) value with the Phantom ECG input read on a smartphone, comparing the readings of the human heart signal on smartphone and ECG, and testing the human BPM value on smartphone. The overall results of reading the BPM value in the design obtained the error value under 5%. Sending data from Wemos D1 Mini as a media hotspot programmed using Arduino IDE software works well. The results of the heart signal data that are read on the smartphone can be stored so that users can send or print them.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121590976","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649763
Karisma Trinanda Putra, Prayitno, E. F. Cahyadi, Ardia Suttyawati Mamonto, S. S. Berutu, S. Muharom
PM2.5 is ultra-light micro-grained particles and dangerous air pollution that threatens public health. A real-time wireless sensor network (WSN) that measure air pollution is a solution to increase public awareness about the long-term impact of PM2.5 exposure. However, in a massive-scale WSN-based air pollution monitoring system, there are numerous noisy and low-concentration periods in the raw PM2.5 dataset, which may lead to unreliable causality predictions. This paper addresses the problem of optimizing sensor acquisition of a wireless sensor network to reconstruct and predict spatiotemporal PM concentrations data using ConvLSTM network. This prediction model is built by combining convolution network and long short-term memory network. The dataset is gathered from air quality WSN s that are already installed across Taiwan. Using the last 48-hour records, the next hour PM2.5 concentration is predicted. RMSE is used to evaluate the prediction accuracy. The results reveal that the ConvLSTM network achieves better performance than those using the LSTM network and regression analysis with RMSE of 1.31, 2.59, and 16.34, respectively.
{"title":"Forecasting Air Quality Using Massive-Scale WSN Based on Convolutional LSTM Network","authors":"Karisma Trinanda Putra, Prayitno, E. F. Cahyadi, Ardia Suttyawati Mamonto, S. S. Berutu, S. Muharom","doi":"10.1109/ice3is54102.2021.9649763","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649763","url":null,"abstract":"PM2.5 is ultra-light micro-grained particles and dangerous air pollution that threatens public health. A real-time wireless sensor network (WSN) that measure air pollution is a solution to increase public awareness about the long-term impact of PM2.5 exposure. However, in a massive-scale WSN-based air pollution monitoring system, there are numerous noisy and low-concentration periods in the raw PM2.5 dataset, which may lead to unreliable causality predictions. This paper addresses the problem of optimizing sensor acquisition of a wireless sensor network to reconstruct and predict spatiotemporal PM concentrations data using ConvLSTM network. This prediction model is built by combining convolution network and long short-term memory network. The dataset is gathered from air quality WSN s that are already installed across Taiwan. Using the last 48-hour records, the next hour PM2.5 concentration is predicted. RMSE is used to evaluate the prediction accuracy. The results reveal that the ConvLSTM network achieves better performance than those using the LSTM network and regression analysis with RMSE of 1.31, 2.59, and 16.34, respectively.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132728130","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 : 2021-10-15DOI: 10.1109/ice3is54102.2021.9649683
Y. Jusman, Ega Samudra, S. Riyadi, Siti Nurul Aqmariah Mohd Kanafiah, A. Faisal, R. Hassan, Z. Mohamed
Leukemia or often called blood cancer is one type of cancer caused by excessive white blood cells. Excessive white blood cells will cause disruption of normal function of other blood cells. To find out leukemia, we can do a physical examination in the form of a blood sample or can also use a spinal cord biopsy. In general, doctors take blood samples to see and look for abnormalities of the white blood cell count. To reduce human error in diagnosing leukemia, the study created two systems that can classify leukemia using the Hu moment invariant (HMI) and Support Vector Machine (SVM) methods and the Grey Level Co-occurance Matrix (GLCM) and SVM methods. Classification systems are used to classify acute and normal leukemia image classes using 10-fold cross validation in the sharing of its image data. The best classification results are the GLCM -SVM system with an accuracy value of 99% and the HMI-SVM system produces an accuracy value of 90%.
{"title":"Comparison of Texture and Shape Features Performance for Leukemia Cell Images using Support Vector Machine","authors":"Y. Jusman, Ega Samudra, S. Riyadi, Siti Nurul Aqmariah Mohd Kanafiah, A. Faisal, R. Hassan, Z. Mohamed","doi":"10.1109/ice3is54102.2021.9649683","DOIUrl":"https://doi.org/10.1109/ice3is54102.2021.9649683","url":null,"abstract":"Leukemia or often called blood cancer is one type of cancer caused by excessive white blood cells. Excessive white blood cells will cause disruption of normal function of other blood cells. To find out leukemia, we can do a physical examination in the form of a blood sample or can also use a spinal cord biopsy. In general, doctors take blood samples to see and look for abnormalities of the white blood cell count. To reduce human error in diagnosing leukemia, the study created two systems that can classify leukemia using the Hu moment invariant (HMI) and Support Vector Machine (SVM) methods and the Grey Level Co-occurance Matrix (GLCM) and SVM methods. Classification systems are used to classify acute and normal leukemia image classes using 10-fold cross validation in the sharing of its image data. The best classification results are the GLCM -SVM system with an accuracy value of 99% and the HMI-SVM system produces an accuracy value of 90%.","PeriodicalId":134945,"journal":{"name":"2021 1st International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114975610","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：