Pub Date : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994577
Meiling Chen, Jing Shao, Xiaoting Huang, Li Su, Shen He, Haitao Du
An important feature of 6G is to realize the integrated three-dimensional coverage of air, space, earth and sea areas, which requires the deep integration of ground network and air network on the basis of interconnection, so as to provide high-quality coverage and network services for all areas. The integration of terrestrial mobile network and non-terrestrial network will bring new security challenges. Based on the integrated architecture analysis of 3GPP, SAT5G and ETSI, this paper summarized architecture models and analyzed security risks and requirements for each model. According to the requirements, this paper proposes a protocol conversion module, an enhanced satellite access authentication algorithm, and a new wireless security negotiation mechanism to solve the security risks faced during the integration process, the analysis shows that these schemes have improved the security capability.
{"title":"Security Analysis and Improvement for Satellite and Mobile Network Integration","authors":"Meiling Chen, Jing Shao, Xiaoting Huang, Li Su, Shen He, Haitao Du","doi":"10.1109/COMNETSAT56033.2022.9994577","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994577","url":null,"abstract":"An important feature of 6G is to realize the integrated three-dimensional coverage of air, space, earth and sea areas, which requires the deep integration of ground network and air network on the basis of interconnection, so as to provide high-quality coverage and network services for all areas. The integration of terrestrial mobile network and non-terrestrial network will bring new security challenges. Based on the integrated architecture analysis of 3GPP, SAT5G and ETSI, this paper summarized architecture models and analyzed security risks and requirements for each model. According to the requirements, this paper proposes a protocol conversion module, an enhanced satellite access authentication algorithm, and a new wireless security negotiation mechanism to solve the security risks faced during the integration process, the analysis shows that these schemes have improved the security capability.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127950884","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994407
Nur Nafiiyah, C. Fatichah, D. Herumurti, E. Astuti, R. Putra, E. Prakasa
Gender identification and age estimation can use the mandible bone on panoramic radiographs. The identification process using the system requires a segmentation stage. Mandibular segmentation is research that has been done a lot to get an accurate object result. The purpose of this study was to segment the mandible on a panoramic radiograph using transfer learning CNN (MobileNetV2, ResNet18, ResNet50). The CNN method has been done before, so we tried to use the CNN method to produce clear and complete mandibular segmentation results on panoramic radiographs. The dataset used to train the model was taken from the Dental Hospital, Airlangga University, Surabaya. There are thousands of datasets, and based on the criteria of a radiologist, the data used are 38 images. The best result of mandibular segmentation on panoramic radiographs is the MobileNetV2 method because the highest Jaccard mean value is 0.9522.
{"title":"Mandibular segmentation on panoramic radiographs with CNN Transfer Learning","authors":"Nur Nafiiyah, C. Fatichah, D. Herumurti, E. Astuti, R. Putra, E. Prakasa","doi":"10.1109/COMNETSAT56033.2022.9994407","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994407","url":null,"abstract":"Gender identification and age estimation can use the mandible bone on panoramic radiographs. The identification process using the system requires a segmentation stage. Mandibular segmentation is research that has been done a lot to get an accurate object result. The purpose of this study was to segment the mandible on a panoramic radiograph using transfer learning CNN (MobileNetV2, ResNet18, ResNet50). The CNN method has been done before, so we tried to use the CNN method to produce clear and complete mandibular segmentation results on panoramic radiographs. The dataset used to train the model was taken from the Dental Hospital, Airlangga University, Surabaya. There are thousands of datasets, and based on the criteria of a radiologist, the data used are 38 images. The best result of mandibular segmentation on panoramic radiographs is the MobileNetV2 method because the highest Jaccard mean value is 0.9522.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"EM-25 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132791970","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}
Appliance classification using non-intrusive load monitoring (NILM) data is a growing research interest. Various studies in the field have used methods such as long short-term memory (LSTM), recurrent neural network (RNN), convolutional neural network (CNN), and deep neural network (DNN). However, there is a research opportunity to apply a gated recurrent unit (GRU), which is good for low-frequency data, with filtering mode (MF) for smoothing prediction results. This study proposes a novel GRU - MF method for classifying electricity appliances using power data from NILM. The first step in this research is to get NILM data. We use power data from the dishwasher, heater, refrigerator, and lighting. Then the first stage of data pre-processing consists of auto-correlation and time series-data transformation processes. The second stage of pre-processing data consists of normalization, standardization, label encoding, and one hot encoding process. The next stage is GRU training, where we compare the GRU with four benchmark methods: LSTM, CNN, DNN, and RNN. We tested the performance of our proposed model with Accuracy, Precision, and Recall. Finally, we implement MF to improve the performance of our appliance classification model. The test results show that our novel method is better than the LSTM, RNN, CNN, and DNN models. The GRU model itself has an Accuracy equal to 0.96 on test data. Once combined into GRU-MF, we achieve the Accuracy of 0.98 in real data.
{"title":"GRU-MF: A Novel Appliance Classification Method for Non-Intrusive Load Monitoring Data","authors":"Aji Gautama Putrada, Nur Alamsyah, Syafrial Fachri Pane, Mohamad Nurkamal Fauzan","doi":"10.1109/COMNETSAT56033.2022.9994409","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994409","url":null,"abstract":"Appliance classification using non-intrusive load monitoring (NILM) data is a growing research interest. Various studies in the field have used methods such as long short-term memory (LSTM), recurrent neural network (RNN), convolutional neural network (CNN), and deep neural network (DNN). However, there is a research opportunity to apply a gated recurrent unit (GRU), which is good for low-frequency data, with filtering mode (MF) for smoothing prediction results. This study proposes a novel GRU - MF method for classifying electricity appliances using power data from NILM. The first step in this research is to get NILM data. We use power data from the dishwasher, heater, refrigerator, and lighting. Then the first stage of data pre-processing consists of auto-correlation and time series-data transformation processes. The second stage of pre-processing data consists of normalization, standardization, label encoding, and one hot encoding process. The next stage is GRU training, where we compare the GRU with four benchmark methods: LSTM, CNN, DNN, and RNN. We tested the performance of our proposed model with Accuracy, Precision, and Recall. Finally, we implement MF to improve the performance of our appliance classification model. The test results show that our novel method is better than the LSTM, RNN, CNN, and DNN models. The GRU model itself has an Accuracy equal to 0.96 on test data. Once combined into GRU-MF, we achieve the Accuracy of 0.98 in real data.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128295971","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994328
Melati Sabila Putri, B. S. Nugroho, Helni Mutiarsih Jumhur
Indonesia has started the deployment of 5G networks to continue to develop in terms of telecommunications. However, accelerating the deployment of a 5G network will take a long time because the cost of deploying infrastructure is not cheap, and getting permits to build infrastructure in an area isn't easy. In 5G, it has a new business model, namely micro operators. Micro operators are 5G service deployments outside the deployment and Mobile Network Operators (MNO). Implementing micro operators can accelerate the deployment of 5G networks and connectivity distribution. With this approach, an analysis of the implementation of micro operators in Jababeka using the mmwave 28 GHz is carried out. From the results, there is an increase in the population. Scenario 1 shows a negative trend and scenario 3 show a positive trend. That means Indonesia can adopt scenario 3 to implement micro operator for the booster 5G network. In terms of regulation, Law Number 36 of 1999, Government Regulation Number 52 of 2000, Law Number 11 of 2020, and Government Regulation Number 46 of 2021 are the basis for discussing the proposed micro operator regulation based on existing rules in Indonesia.
{"title":"Techno-Regulation Analysis of Micro Operator in Industrial Area","authors":"Melati Sabila Putri, B. S. Nugroho, Helni Mutiarsih Jumhur","doi":"10.1109/COMNETSAT56033.2022.9994328","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994328","url":null,"abstract":"Indonesia has started the deployment of 5G networks to continue to develop in terms of telecommunications. However, accelerating the deployment of a 5G network will take a long time because the cost of deploying infrastructure is not cheap, and getting permits to build infrastructure in an area isn't easy. In 5G, it has a new business model, namely micro operators. Micro operators are 5G service deployments outside the deployment and Mobile Network Operators (MNO). Implementing micro operators can accelerate the deployment of 5G networks and connectivity distribution. With this approach, an analysis of the implementation of micro operators in Jababeka using the mmwave 28 GHz is carried out. From the results, there is an increase in the population. Scenario 1 shows a negative trend and scenario 3 show a positive trend. That means Indonesia can adopt scenario 3 to implement micro operator for the booster 5G network. In terms of regulation, Law Number 36 of 1999, Government Regulation Number 52 of 2000, Law Number 11 of 2020, and Government Regulation Number 46 of 2021 are the basis for discussing the proposed micro operator regulation based on existing rules in Indonesia.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130275317","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994421
Mohammed Abdrabou, T. Gulliver
To overcome terrestrial network coverage limitations, low-earth orbit (LEO) satellites aim to provide worldwide connectivity for sixth generation (6G) networks. However, LEO satellites are vulnerable to spoofing attacks. To overcome this limitation, physical layer authentication (PLA) can be employed to provide effective satellite authentication by utilizing physical features. In this paper, an adaptive PLA scheme is proposed using a single-class classification support vector machine (SCC-SVM) with received power (RP) and Doppler frequency spread (DS) features. The proposed scheme is evaluated for on-the-pause satellite communication (OTPSC) systems. The results obtained show that using both RP and DS as features provides better authentication performance than when they are used individually.
{"title":"LEO Satellite Authentication using Physical Layer Features with Support Vector Machine","authors":"Mohammed Abdrabou, T. Gulliver","doi":"10.1109/COMNETSAT56033.2022.9994421","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994421","url":null,"abstract":"To overcome terrestrial network coverage limitations, low-earth orbit (LEO) satellites aim to provide worldwide connectivity for sixth generation (6G) networks. However, LEO satellites are vulnerable to spoofing attacks. To overcome this limitation, physical layer authentication (PLA) can be employed to provide effective satellite authentication by utilizing physical features. In this paper, an adaptive PLA scheme is proposed using a single-class classification support vector machine (SCC-SVM) with received power (RP) and Doppler frequency spread (DS) features. The proposed scheme is evaluated for on-the-pause satellite communication (OTPSC) systems. The results obtained show that using both RP and DS as features provides better authentication performance than when they are used individually.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129524468","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994468
M. R. Perdana Kusuma Djaka, Fajar Aulia Rahman, Herry Tony Andhyka, C. Apriono
The government and The House of Representatives of Indonesia have decided to move the capital city from Jakarta to Nusantara. Nusantara is the world's superhub and the driver of Indonesia's new economy, following its vision to create 4.3 - 4.8 million new jobs. The relocation of the capital will mean moving around 1.9 million people to the Nusantara[3]. Thus, Nusantara requires high internet network connectivity with large bandwidth. This study proposes a fiber optic telecommunications network backbone design that connects the new capital Nusantara with Singapore and Jakarta via Pontianak. The proposed design for the connection from Nusantara to Pontianak is a land route, while from Pontianak to Singapore and Jakarta is a sea route. The design results show that the power loss and rise time values follow the standards, respectively 45 dB for power loss and 684 ps for the rise time. Therefore, the proposed network design is feasible to be implemented.
{"title":"Design and Analysis of Optical Fiber Network Jakarta - Singapore - Nusantara via Karimata Strait","authors":"M. R. Perdana Kusuma Djaka, Fajar Aulia Rahman, Herry Tony Andhyka, C. Apriono","doi":"10.1109/COMNETSAT56033.2022.9994468","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994468","url":null,"abstract":"The government and The House of Representatives of Indonesia have decided to move the capital city from Jakarta to Nusantara. Nusantara is the world's superhub and the driver of Indonesia's new economy, following its vision to create 4.3 - 4.8 million new jobs. The relocation of the capital will mean moving around 1.9 million people to the Nusantara[3]. Thus, Nusantara requires high internet network connectivity with large bandwidth. This study proposes a fiber optic telecommunications network backbone design that connects the new capital Nusantara with Singapore and Jakarta via Pontianak. The proposed design for the connection from Nusantara to Pontianak is a land route, while from Pontianak to Singapore and Jakarta is a sea route. The design results show that the power loss and rise time values follow the standards, respectively 45 dB for power loss and 684 ps for the rise time. Therefore, the proposed network design is feasible to be implemented.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130715497","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994547
Puput Dani Prasetyo Adi, Abdul Wahid, Agoestina Mappadang, Asworoningrum Yulindahwati, Yudi Prastiyono, Imam Tahyudin, La Sinaini, S. Sujak, N. Nurindah
One of the problem factors in transmitting LoRa data using a small bit rate (bytes) of a maximum of 125 kbps is the amount of packet loss. This is because many end nodes send data to the server simultaneously; transmitting data effectively needs to be done because this is a major thing. So one mechanism that can be done is to use the Adaptive Data Rate method on the LoRa module. This research discusses the Adaptive Data Rate shown explicitly by the way it works and the effect it gives if ADR is applied to transmitting LoRa data. And how much influence on packet Loss (bytes). Adaptive Data Rate on LoRa Transmission is essential for regulating power on LoRa in terms of battery power saving; LoRa runs in UHF, which is in the 300 MHz-3 GHz range; LoRa in this research works at 915 MHz-920 MHz depending on the type of devices used. LoRa works with power or supply voltage of 2.1-3.6 Volt DC, high sleep currents between 7.66 A up to 34 mA; in this research, LoRa is M2M between LoRa Transmitter and Receiver, which communicate alternately in sending sensor data with the delay method used for monitoring human health such as Pulse sensors, ECG sensors, and other sensors and these sensors' data is displayed in realtime using Thingspeak Application Server.
{"title":"Performance Evaluation of LoRa 915 MHz for Health Monitoring with Adaptive Data Rate","authors":"Puput Dani Prasetyo Adi, Abdul Wahid, Agoestina Mappadang, Asworoningrum Yulindahwati, Yudi Prastiyono, Imam Tahyudin, La Sinaini, S. Sujak, N. Nurindah","doi":"10.1109/COMNETSAT56033.2022.9994547","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994547","url":null,"abstract":"One of the problem factors in transmitting LoRa data using a small bit rate (bytes) of a maximum of 125 kbps is the amount of packet loss. This is because many end nodes send data to the server simultaneously; transmitting data effectively needs to be done because this is a major thing. So one mechanism that can be done is to use the Adaptive Data Rate method on the LoRa module. This research discusses the Adaptive Data Rate shown explicitly by the way it works and the effect it gives if ADR is applied to transmitting LoRa data. And how much influence on packet Loss (bytes). Adaptive Data Rate on LoRa Transmission is essential for regulating power on LoRa in terms of battery power saving; LoRa runs in UHF, which is in the 300 MHz-3 GHz range; LoRa in this research works at 915 MHz-920 MHz depending on the type of devices used. LoRa works with power or supply voltage of 2.1-3.6 Volt DC, high sleep currents between 7.66 A up to 34 mA; in this research, LoRa is M2M between LoRa Transmitter and Receiver, which communicate alternately in sending sensor data with the delay method used for monitoring human health such as Pulse sensors, ECG sensors, and other sensors and these sensors' data is displayed in realtime using Thingspeak Application Server.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132812193","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994387
Jimmy Tjen, Genrawan Hoendarto, Tony Darmanto
In this paper, a novel ensemble Principal Component Analysis (PCA) algorithm is proposed to detect the presence of damage by exploiting the structure's historical data. In particular, there are 2 main contributions highlighted in this paper: First, a sensor selection algorithm is derived from the distance correlation coefficient from the correlation analysis, to reduce the number of sensors without affecting the model accuracy and fault detection sensitivity. Next, a novel technique based on the combination of the distance correlation-based and the previously introduced entropy-based PCA, is derived, to generate the ensemble PCA algorithm, which can be used to detect structural damages and improves the robustness of the previous methods. The presented algorithms are validated on three different damage cases, providing evidence that the proposed ensemble PCA algorithm outperforms the previous approaches, in the sense that it improves the fault detection sensitivity and model prediction accuracy, while also offering information on the most sensitive subset of sensors in detecting faults.
{"title":"Ensemble of the Distance Correlation-Based and Entropy-Based Sensor Selection for Damage Detection","authors":"Jimmy Tjen, Genrawan Hoendarto, Tony Darmanto","doi":"10.1109/COMNETSAT56033.2022.9994387","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994387","url":null,"abstract":"In this paper, a novel ensemble Principal Component Analysis (PCA) algorithm is proposed to detect the presence of damage by exploiting the structure's historical data. In particular, there are 2 main contributions highlighted in this paper: First, a sensor selection algorithm is derived from the distance correlation coefficient from the correlation analysis, to reduce the number of sensors without affecting the model accuracy and fault detection sensitivity. Next, a novel technique based on the combination of the distance correlation-based and the previously introduced entropy-based PCA, is derived, to generate the ensemble PCA algorithm, which can be used to detect structural damages and improves the robustness of the previous methods. The presented algorithms are validated on three different damage cases, providing evidence that the proposed ensemble PCA algorithm outperforms the previous approaches, in the sense that it improves the fault detection sensitivity and model prediction accuracy, while also offering information on the most sensitive subset of sensors in detecting faults.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"68 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120892099","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994559
Rando, N. A. Setiawan, A. E. Permanasari, R. Rulaningtyas, A. B. Suksmono, I. S. Sitanggang
Cervical cancer is one of the deadliest diseases in women. One of the cervical cancer screening methods is pap smear method. However, using a pap smear method to detect cervical cancer takes a long time for a pathologist to diagnose. Hence, a rapid development of medical computerization for early detection to get the results quickly is needed. This paper proposes synthetic data augmentation by using Deep Convolutional Generative Adversarial Network (DCGAN) to increase number of pap smear samples in dataset. Gray Level Co-occurrence Matrix (GLCM) is employed to extract features from dataset. Classification of 3 classes which are Adenocarcinoma, High-Grade Squamous Intraepithelial Lesion (HSIL), and Squamous Cell Carcinoma (SCC) is conducted using Extreme Learning Machine (ELM). The result shows that the addition of synthetic data improves the performance of ELM with the accuracy of 90%. This accuracy is better than the accuracy of ELM using only the original dataset which is 85%.
{"title":"DCGAN-based Medical Image Augmentation to Improve ELM Classification Performance","authors":"Rando, N. A. Setiawan, A. E. Permanasari, R. Rulaningtyas, A. B. Suksmono, I. S. Sitanggang","doi":"10.1109/COMNETSAT56033.2022.9994559","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994559","url":null,"abstract":"Cervical cancer is one of the deadliest diseases in women. One of the cervical cancer screening methods is pap smear method. However, using a pap smear method to detect cervical cancer takes a long time for a pathologist to diagnose. Hence, a rapid development of medical computerization for early detection to get the results quickly is needed. This paper proposes synthetic data augmentation by using Deep Convolutional Generative Adversarial Network (DCGAN) to increase number of pap smear samples in dataset. Gray Level Co-occurrence Matrix (GLCM) is employed to extract features from dataset. Classification of 3 classes which are Adenocarcinoma, High-Grade Squamous Intraepithelial Lesion (HSIL), and Squamous Cell Carcinoma (SCC) is conducted using Extreme Learning Machine (ELM). The result shows that the addition of synthetic data improves the performance of ELM with the accuracy of 90%. This accuracy is better than the accuracy of ELM using only the original dataset which is 85%.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124830586","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 : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994385
I. Mustika, Fauza Khair, A. F. Isnawati, Tiara Apsari Dewi, D. Setyawan, Arrizky Ayu Faradila Purnama
Light fidelity (Li-Fi) technology emerged to over-come wireless technology problems in terms of increasing network capacity, efficiency, availability and security. However, the limitations of Li-Fi technology that can only be applied to line of sight (LOS) conditions, it is necessary to develop a multiplexing system on the Li-Fi technology to increase bandwidth efficiency, especially for indoor applications. Therefore, this study aims to design and analyze the proposed model of multiplexing indoor Li-Fi system using movable light emitting diode (LED) panel scheme. The modeling is carried out for 2 multiple input multiple output (MIMO) scenarios including 2x2 channels and 4x4 channels of multiplexing systems by varying the channel spacing value from 5 nm up to 25 nm. Observation of system model performance based on the parameter values of bit error rate (BER), Q-factor, signal to noise ratio (SNR), and optical received power. The results of the received power value on the receiving side shows that there is no significant difference values for either the 2x2 multiplexing system or the 4x4 multiplexing system. The increase in the channel spacing value affects the system performance improvement, where the 25 nm channel spacing scenario has the smallest BER value and the highest Q-factor value, especially on the fourth channel.
{"title":"Modeling of Multiplexing Indoor Light Fidelity (Li-Fi) Technology Using Movable LED Panel","authors":"I. Mustika, Fauza Khair, A. F. Isnawati, Tiara Apsari Dewi, D. Setyawan, Arrizky Ayu Faradila Purnama","doi":"10.1109/COMNETSAT56033.2022.9994385","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994385","url":null,"abstract":"Light fidelity (Li-Fi) technology emerged to over-come wireless technology problems in terms of increasing network capacity, efficiency, availability and security. However, the limitations of Li-Fi technology that can only be applied to line of sight (LOS) conditions, it is necessary to develop a multiplexing system on the Li-Fi technology to increase bandwidth efficiency, especially for indoor applications. Therefore, this study aims to design and analyze the proposed model of multiplexing indoor Li-Fi system using movable light emitting diode (LED) panel scheme. The modeling is carried out for 2 multiple input multiple output (MIMO) scenarios including 2x2 channels and 4x4 channels of multiplexing systems by varying the channel spacing value from 5 nm up to 25 nm. Observation of system model performance based on the parameter values of bit error rate (BER), Q-factor, signal to noise ratio (SNR), and optical received power. The results of the received power value on the receiving side shows that there is no significant difference values for either the 2x2 multiplexing system or the 4x4 multiplexing system. The increase in the channel spacing value affects the system performance improvement, where the 25 nm channel spacing scenario has the smallest BER value and the highest Q-factor value, especially on the fourth channel.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132229947","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：