Pub Date : 2022-11-03DOI: 10.1109/COMNETSAT56033.2022.9994490
Hasri Ainun Harris, Levy Olivia Nur, R. Anwar
This paper has proposed a design for an on-body textile antenna integrated with the vest along with a Wi-Fi module and a lithium battery for a tracking system. It is intended to operate at 2.4 GHz of the Industrial, Scientific, and Medical (ISM) frequency band. The substrate and radiating element of the antenna were chosen as nylon cloth and copper thread, respectively. Moreover, this study evaluated the system's ability represented by its coverage in the distance (meters) in non-line-of-sight (NLoS) and line-of-sight (LoS) conditions. The proposed wearable antenna design is discussed in detail. The prototype's experimental results have achieved the expected result. The free-space simulation has a VSWR value of 1,069, a bandwidth of 270 MHz, a gain value of 4,538 dBi, and a unidirectional radiation pattern. While in the measurement, the VSWR value obtained of 1,2 with a narrowing of the bandwidth of 70 MHz.
{"title":"Design and Implementation of On-Body Textile Antenna for Bird Tracking at 2.4 GHz","authors":"Hasri Ainun Harris, Levy Olivia Nur, R. Anwar","doi":"10.1109/COMNETSAT56033.2022.9994490","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994490","url":null,"abstract":"This paper has proposed a design for an on-body textile antenna integrated with the vest along with a Wi-Fi module and a lithium battery for a tracking system. It is intended to operate at 2.4 GHz of the Industrial, Scientific, and Medical (ISM) frequency band. The substrate and radiating element of the antenna were chosen as nylon cloth and copper thread, respectively. Moreover, this study evaluated the system's ability represented by its coverage in the distance (meters) in non-line-of-sight (NLoS) and line-of-sight (LoS) conditions. The proposed wearable antenna design is discussed in detail. The prototype's experimental results have achieved the expected result. The free-space simulation has a VSWR value of 1,069, a bandwidth of 270 MHz, a gain value of 4,538 dBi, and a unidirectional radiation pattern. While in the measurement, the VSWR value obtained of 1,2 with a narrowing of the bandwidth of 70 MHz.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"57 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":"116473077","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/COMNETSAT56033.2022.9994425
Vy-Hao Phan, Minh-Quan Ha, Trong-Hop Do
This paper deals with the problem of license plate reconstruction, which is a method used for enhancing the quality of images of vehicle license plates in parking lot management systems. More specifically, poorly capture images of vehicle license plates which are unrecognizable by both human eyes and computer will be reconstructed so that they can be perceptible. This paper proposes a two-stage deep learning based algorithm for this problem. In the first stage, the position of the license plate in the image is detected using a YOLOv4 based transfer learning model. In the second stage, the image area of the license plate detected in the previous stage is fed to Pix2Pix, which is a type of Generative Adversarial Networks for the reconstruction. The experiment results show that by applying the proposed algorithm, license plate images with blur and flare can be transformed in to clear images which can be read by human eyes or can be used as inputs for computer vision applications such as license plate recognition.
{"title":"A Novel License Plate Image Reconstruction System using Generative Adversarial Network","authors":"Vy-Hao Phan, Minh-Quan Ha, Trong-Hop Do","doi":"10.1109/COMNETSAT56033.2022.9994425","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994425","url":null,"abstract":"This paper deals with the problem of license plate reconstruction, which is a method used for enhancing the quality of images of vehicle license plates in parking lot management systems. More specifically, poorly capture images of vehicle license plates which are unrecognizable by both human eyes and computer will be reconstructed so that they can be perceptible. This paper proposes a two-stage deep learning based algorithm for this problem. In the first stage, the position of the license plate in the image is detected using a YOLOv4 based transfer learning model. In the second stage, the image area of the license plate detected in the previous stage is fed to Pix2Pix, which is a type of Generative Adversarial Networks for the reconstruction. The experiment results show that by applying the proposed algorithm, license plate images with blur and flare can be transformed in to clear images which can be read by human eyes or can be used as inputs for computer vision applications such as license plate recognition.","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":"128919510","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/COMNETSAT56033.2022.9994340
Bill Van Ricardo Zalukhu, Arie Wahyu Wijayanto, Muhammad Iqbal Habibie
Marine vessels or ships have been considered one of the primary vehicles used for sea transportation, which can also be used as an intermediary tool to serve numerous other marine-related activities. In tracking and monitoring the activities of these ships, automatic vessel object detection is undoubtedly challenging to extract the number and position of the vessels from complex seawater backgrounds. In this study, we build a one-stage network of YOLOv5x6 based deep learning model on ShipRSImageNet large-scale dataset. With 50 ship categories, our model obtained a promising performance with a mean average precision of 75.18%. Our findings are potentially beneficial to support maritime security enforcement policy including counter-measuring illegal fisheries and managing seawater traffic surveillance.
{"title":"Marine Vessels Detection on Very High-Resolution Remote Sensing Optical Satellites using Object-Based Deep Learning","authors":"Bill Van Ricardo Zalukhu, Arie Wahyu Wijayanto, Muhammad Iqbal Habibie","doi":"10.1109/COMNETSAT56033.2022.9994340","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994340","url":null,"abstract":"Marine vessels or ships have been considered one of the primary vehicles used for sea transportation, which can also be used as an intermediary tool to serve numerous other marine-related activities. In tracking and monitoring the activities of these ships, automatic vessel object detection is undoubtedly challenging to extract the number and position of the vessels from complex seawater backgrounds. In this study, we build a one-stage network of YOLOv5x6 based deep learning model on ShipRSImageNet large-scale dataset. With 50 ship categories, our model obtained a promising performance with a mean average precision of 75.18%. Our findings are potentially beneficial to support maritime security enforcement policy including counter-measuring illegal fisheries and managing seawater traffic surveillance.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"40 1-8 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":"123378679","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/COMNETSAT56033.2022.9994316
Hans Geovani Andika, Michael The Hadinata, William Huang, Anderies, Irene Anindaputri Iswanto
The recommendation system is divided into collaborative filtering (CF), content-based (CB), and hybrid approaches. This paper focuses on the CF approach which has many algorithms such as K-Nearest Neighbor (KNN), K-Means, Singular Value Decomposition (SVD), etc. We used the systematic literature review approach to gather papers related to CF and 28 research papers were eventually considered for analysis in KNN, deep learning, and SVD. From the review results, most of the datasets used in CF were movie datasets to test the recommendation model, and most of the models produced a good result in recommending items. To achieve good results, the majority of existing works combine more than one method to overcome or reduce the impact of CF problems (cold-start, sparsity, shilling attacks, etc.) which can affect the recommendation performance.
{"title":"Systematic Literature Review: Comparison on Collaborative Filtering Algorithms for Recommendation Systems","authors":"Hans Geovani Andika, Michael The Hadinata, William Huang, Anderies, Irene Anindaputri Iswanto","doi":"10.1109/COMNETSAT56033.2022.9994316","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994316","url":null,"abstract":"The recommendation system is divided into collaborative filtering (CF), content-based (CB), and hybrid approaches. This paper focuses on the CF approach which has many algorithms such as K-Nearest Neighbor (KNN), K-Means, Singular Value Decomposition (SVD), etc. We used the systematic literature review approach to gather papers related to CF and 28 research papers were eventually considered for analysis in KNN, deep learning, and SVD. From the review results, most of the datasets used in CF were movie datasets to test the recommendation model, and most of the models produced a good result in recommending items. To achieve good results, the majority of existing works combine more than one method to overcome or reduce the impact of CF problems (cold-start, sparsity, shilling attacks, etc.) which can affect the recommendation performance.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"166 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":"134207378","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/COMNETSAT56033.2022.9994567
B. Kindhi, Sean John Rawlings
Clickbait has been widely circulated on social media and has become one of the ways used to increase reader traffic and website/website visitors, but this clickbait is often misused by website managers in increasing visitor traffic to get an income or profit by ignoring the satisfaction of news readers with how to display a trapping title and hyperbole and the information in the content does not match what is stated in the news title. Today's society is in an emergency for clickbait news, even on national news pages sometimes they still use the title clickbait. In this study, a clickbait news prediction system is proposed on the news circulating. A deep learning neural network method has been proposed, and the architecture we use is flexible feed forward, namely by providing classes with semantic or multiple-meaning languages. Our proposed deep learning architecture on the neural network is able to classify clickbait news with accuracy values of 80%. The purpose of this research is to provide intelligent education to the public to be able to sort out news easily.
{"title":"Clickbait Detection for Internet News Title with Deep Learning Feed Forward","authors":"B. Kindhi, Sean John Rawlings","doi":"10.1109/COMNETSAT56033.2022.9994567","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994567","url":null,"abstract":"Clickbait has been widely circulated on social media and has become one of the ways used to increase reader traffic and website/website visitors, but this clickbait is often misused by website managers in increasing visitor traffic to get an income or profit by ignoring the satisfaction of news readers with how to display a trapping title and hyperbole and the information in the content does not match what is stated in the news title. Today's society is in an emergency for clickbait news, even on national news pages sometimes they still use the title clickbait. In this study, a clickbait news prediction system is proposed on the news circulating. A deep learning neural network method has been proposed, and the architecture we use is flexible feed forward, namely by providing classes with semantic or multiple-meaning languages. Our proposed deep learning architecture on the neural network is able to classify clickbait news with accuracy values of 80%. The purpose of this research is to provide intelligent education to the public to be able to sort out news easily.","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":"114849110","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/COMNETSAT56033.2022.9994438
Handika Sawung Jaladara, Rizka Reza Pahlevi, H. Nuha
Kutoarjo Health Center still uses conventional methods to monitor the level of infusion fluids. monitoring by going around one by one to the patient's room. The purpose of this study is to design and analyze an Internet of Things-based infusion fluid level monitoring system. Using the ESP8266 module which is integrated with the Web and alarms. If the IV fluid level is below 50 mL an alarm will sound and the Web will display a “Dangerous” status. Analyzing the usefulness of the infusion fluid level monitoring system using the System Usability Scale method. The infusion monitoring system got a score of 54.3 which indicates that the system has not been able to improve the quality of public services. The low value of the usefulness of the infusion fluid level monitoring system is because this system is a new innovation that previously the Kutoarjo Health Center had never used it, so users need to adapt in using this system. although it has a fairly low value, the infusion fluid level monitoring system is running properly. We need to create manuals/user manuals and hold Technical Guidance/Workshops so that users can better understand and adapt quickly in using this system.
{"title":"System Usability Scale Analysis of Infusion Fluid Level Monitoring and Notification System Using IoT","authors":"Handika Sawung Jaladara, Rizka Reza Pahlevi, H. Nuha","doi":"10.1109/COMNETSAT56033.2022.9994438","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994438","url":null,"abstract":"Kutoarjo Health Center still uses conventional methods to monitor the level of infusion fluids. monitoring by going around one by one to the patient's room. The purpose of this study is to design and analyze an Internet of Things-based infusion fluid level monitoring system. Using the ESP8266 module which is integrated with the Web and alarms. If the IV fluid level is below 50 mL an alarm will sound and the Web will display a “Dangerous” status. Analyzing the usefulness of the infusion fluid level monitoring system using the System Usability Scale method. The infusion monitoring system got a score of 54.3 which indicates that the system has not been able to improve the quality of public services. The low value of the usefulness of the infusion fluid level monitoring system is because this system is a new innovation that previously the Kutoarjo Health Center had never used it, so users need to adapt in using this system. although it has a fairly low value, the infusion fluid level monitoring system is running properly. We need to create manuals/user manuals and hold Technical Guidance/Workshops so that users can better understand and adapt quickly in using this system.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"9 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":"117350064","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/COMNETSAT56033.2022.9994299
Long-An Doan, Phuong-Thao Nguyen, Thi-Oanh Phan, Trong-Hop Do
The omnipresence of online social media brings various positive and negative consequences for society. Besides benefits, social media can cause big problem caused by hate and offensive contents. Detecting and removing those toxic contents using machine learning is a major research topic in social network. Two of the challenges of this topic are that the volume of social media data is so big and that these data need to be processed in real-time. In this paper, we set out to develop system to detect hate speech in Vietnamese YouTube comments using machine learning and big data technology. The streaming data from Youtube is processed in real-time using Kafka, Spark, and machine learning technology. Finally, a dashboard powered by Streamlit will be used to display the results.
{"title":"An Implementation of Large Scale Hate Speech Detection System for Streaming Social Media Data","authors":"Long-An Doan, Phuong-Thao Nguyen, Thi-Oanh Phan, Trong-Hop Do","doi":"10.1109/COMNETSAT56033.2022.9994299","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994299","url":null,"abstract":"The omnipresence of online social media brings various positive and negative consequences for society. Besides benefits, social media can cause big problem caused by hate and offensive contents. Detecting and removing those toxic contents using machine learning is a major research topic in social network. Two of the challenges of this topic are that the volume of social media data is so big and that these data need to be processed in real-time. In this paper, we set out to develop system to detect hate speech in Vietnamese YouTube comments using machine learning and big data technology. The streaming data from Youtube is processed in real-time using Kafka, Spark, and machine learning technology. Finally, a dashboard powered by Streamlit will be used to display the results.","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":"129752895","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/COMNETSAT56033.2022.9994461
A. Hendrawan, R. Gernowo, O. Nurhayati, B. Warsito, Adi Wibowo
Detecting objects using deep learning technology has the advantage of getting good accuracy. The accuracy obtained depends on the processing time of using deep learning technology. One object detection algorithm is called You Only Look Once (YOLO), which currently has its fifth version or Yolov5. This paper proposes the real-time object detection algorithm with a video dataset recorded on the highway using Yolov5. The increase of YOLOv5 started by adding augmentation data mosaic by the size of 480x480. We practiced the YOLOV5 - BottleNeckCSP model to detect objects and then got the object information divided into six classes. The results of using mosaic data augmentation are mAP@0.5 of 0.984, mAP@0.5-0.95 of 0.696 by the precision value of 0.95, and a recall value of 0.98. Our research framework can be applied effectively to improve the performance of object detection algorithms.
利用深度学习技术检测物体具有精度高的优点。所获得的精度取决于使用深度学习技术的处理时间。一种被称为You Only Look Once (YOLO)的目标检测算法，目前已经有了第五个版本，即Yolov5。本文利用Yolov5软件，提出了一种基于高速公路视频数据集的实时目标检测算法。YOLOv5的增加是从增加480 × 480大小的增强数据马赛克开始的。我们运用YOLOV5 - BottleNeckCSP模型对目标进行检测，并将目标信息划分为6类。采用马赛克数据增强的结果为mAP@0.5 = 0.984, mAP@0.5-0.95 = 0.696，精度值为0.95，召回率为0.98。我们的研究框架可以有效地应用于提高目标检测算法的性能。
{"title":"Improvement Object Detection Algorithm Based on YoloV5 with BottleneckCSP","authors":"A. Hendrawan, R. Gernowo, O. Nurhayati, B. Warsito, Adi Wibowo","doi":"10.1109/COMNETSAT56033.2022.9994461","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994461","url":null,"abstract":"Detecting objects using deep learning technology has the advantage of getting good accuracy. The accuracy obtained depends on the processing time of using deep learning technology. One object detection algorithm is called You Only Look Once (YOLO), which currently has its fifth version or Yolov5. This paper proposes the real-time object detection algorithm with a video dataset recorded on the highway using Yolov5. The increase of YOLOv5 started by adding augmentation data mosaic by the size of 480x480. We practiced the YOLOV5 - BottleNeckCSP model to detect objects and then got the object information divided into six classes. The results of using mosaic data augmentation are mAP@0.5 of 0.984, mAP@0.5-0.95 of 0.696 by the precision value of 0.95, and a recall value of 0.98. Our research framework can be applied effectively to improve the performance of object detection algorithms.","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":"129161304","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}
The use of high frequencies in the 5G system resulting in the sensitivity of the surrounding environment and attenuation such as human blockage. This study analyzed the performance of frame error rate (FER) based on polar code and without polar code on broadband channels that are affected by human blockage using a frequency of 2.3 GHz, bandwidth of 99 MHz, and the CP-OFDM technique. The purpose of this research is to determine the FER performances using polar codes and without polar codes on 5G network broadband channels that are affected by human blockage which has been validated with outage performances. Broadband channels on the 5G network are presented in a representative Power Delay Profile (PDP) with the influence of human blockage obtained as many as 41 paths with multiple delays of 10 ns on each path. This research was also used the scaling method on representative PDP because it could adjust the use of FFT of 128 blocks and the results of this scaling showed that there are 9 paths with multiple delays of 50 ns. This research evaluates the average FER of 10-3. FER performance without a polar code is affected by human blockage (R=1) and required a Signal to Noise (SNR) of 41 dB. However, by using a polar code R = 1/2 required an SNR of 20.1 dB. The results showed that the utilization of cyclic prefix (CP)-OFDM with channel coding helps the diversity effect of 5G transmissions to achievable.
{"title":"FER Polar Codes Performances Using 5G Broadband Channel with CP-OFDM Techniques at 2.3 GHz Frequency","authors":"Reni Dyah Wahyuningrum, Khoirun Ni’amah, Solichah Larasati, Shinta Romadhona","doi":"10.1109/COMNETSAT56033.2022.9994329","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994329","url":null,"abstract":"The use of high frequencies in the 5G system resulting in the sensitivity of the surrounding environment and attenuation such as human blockage. This study analyzed the performance of frame error rate (FER) based on polar code and without polar code on broadband channels that are affected by human blockage using a frequency of 2.3 GHz, bandwidth of 99 MHz, and the CP-OFDM technique. The purpose of this research is to determine the FER performances using polar codes and without polar codes on 5G network broadband channels that are affected by human blockage which has been validated with outage performances. Broadband channels on the 5G network are presented in a representative Power Delay Profile (PDP) with the influence of human blockage obtained as many as 41 paths with multiple delays of 10 ns on each path. This research was also used the scaling method on representative PDP because it could adjust the use of FFT of 128 blocks and the results of this scaling showed that there are 9 paths with multiple delays of 50 ns. This research evaluates the average FER of 10-3. FER performance without a polar code is affected by human blockage (R=1) and required a Signal to Noise (SNR) of 41 dB. However, by using a polar code R = 1/2 required an SNR of 20.1 dB. The results showed that the utilization of cyclic prefix (CP)-OFDM with channel coding helps the diversity effect of 5G transmissions to achievable.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"18 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":"129176448","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/COMNETSAT56033.2022.9994555
Anindita Septiarini, H. Hamdani, Eko Junirianto, Mohammad Sofyan S. Thayf, Gandung Triyono, Henderi
Oil palm plant diseases typically manifest themselves on the leaves, resulting in reduced crop quality. It is necessary to solve this issue as the need for premium-quality palm oil keeps growing. Despite the fact that various automatic detection models for oil palm leaf disease have been developed, their performance was frequently inadequate due to the similarity of class characteristics. This work proposes a method that automatically detects the oil palm leaf disease on a natural background to distinguish between infected and healthy leaf classes. The method was developed using deep learning based on Convolution Neural Network (CNN) model. The private dataset consists of 600 oil palm leaf images (300 healthy and 300 infected) on a natural background. In order to decrease the computation time, pre-processing was carried out, which consists of resizing and normalizing the image, followed by augmentation. Augmentation was applied by rotation, flip, shear, and zooming techniques. Furthermore, the CNN model was employed to detect oil palm leaf disease using Tensorflow 2.5.0 framework with $224 times 224$ input data. The proposed method successfully achieved the highest performance, revealed by the accuracy value of 1.
{"title":"Oil Palm Leaf Disease Detection on Natural Background Using Convolutional Neural Networks","authors":"Anindita Septiarini, H. Hamdani, Eko Junirianto, Mohammad Sofyan S. Thayf, Gandung Triyono, Henderi","doi":"10.1109/COMNETSAT56033.2022.9994555","DOIUrl":"https://doi.org/10.1109/COMNETSAT56033.2022.9994555","url":null,"abstract":"Oil palm plant diseases typically manifest themselves on the leaves, resulting in reduced crop quality. It is necessary to solve this issue as the need for premium-quality palm oil keeps growing. Despite the fact that various automatic detection models for oil palm leaf disease have been developed, their performance was frequently inadequate due to the similarity of class characteristics. This work proposes a method that automatically detects the oil palm leaf disease on a natural background to distinguish between infected and healthy leaf classes. The method was developed using deep learning based on Convolution Neural Network (CNN) model. The private dataset consists of 600 oil palm leaf images (300 healthy and 300 infected) on a natural background. In order to decrease the computation time, pre-processing was carried out, which consists of resizing and normalizing the image, followed by augmentation. Augmentation was applied by rotation, flip, shear, and zooming techniques. Furthermore, the CNN model was employed to detect oil palm leaf disease using Tensorflow 2.5.0 framework with $224 times 224$ input data. The proposed method successfully achieved the highest performance, revealed by the accuracy value of 1.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"102 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":"128592125","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：