Pub Date : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532560
M. Nugraha, M. I. Nashiruddin, Putri Rahmawati
Jakarta city is the capital and the economic center region for one of the largest countries in the world, Indonesia. The massive annual number of migrants that move to Jakarta city municipals; Thousand Islands, South Jakarta, East Jakarta, Central Jakarta, West Jakarta, and North Jakarta, pushed the traffic demand to be doubled or tripled every year. Therefore, it is crucial to prepared the latest cellular technology that could accommodate this considerable traffic. This research aims to use the 5G NR network planning with the frequency of 3.5 GHz and bandwidth 100 MHz to determine the required number of gNodeB for the capacity and coverage planning with user projection from 2021 until 2026 by engaging a case study in a dense urban area, Jakarta city that has a total area of 662.33 km2. The highest required number of gNodeB for both capacity and coverage planning among the municipals is located in East Jakarta. Capacity planning requires 203 gNodeB. In comparison, coverage planning requires 194 gNodeB. Meanwhile, the total required gNodeB and generated traffic demand forecast for all municipals in Jakarta city is 778 gNodeB and 17.68 Gbps/km2, respectively.
{"title":"An Assessment of 5G NR Network Planning for Dense Urban Scenario: Study Case of Jakarta City","authors":"M. Nugraha, M. I. Nashiruddin, Putri Rahmawati","doi":"10.1109/IAICT52856.2021.9532560","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532560","url":null,"abstract":"Jakarta city is the capital and the economic center region for one of the largest countries in the world, Indonesia. The massive annual number of migrants that move to Jakarta city municipals; Thousand Islands, South Jakarta, East Jakarta, Central Jakarta, West Jakarta, and North Jakarta, pushed the traffic demand to be doubled or tripled every year. Therefore, it is crucial to prepared the latest cellular technology that could accommodate this considerable traffic. This research aims to use the 5G NR network planning with the frequency of 3.5 GHz and bandwidth 100 MHz to determine the required number of gNodeB for the capacity and coverage planning with user projection from 2021 until 2026 by engaging a case study in a dense urban area, Jakarta city that has a total area of 662.33 km2. The highest required number of gNodeB for both capacity and coverage planning among the municipals is located in East Jakarta. Capacity planning requires 203 gNodeB. In comparison, coverage planning requires 194 gNodeB. Meanwhile, the total required gNodeB and generated traffic demand forecast for all municipals in Jakarta city is 778 gNodeB and 17.68 Gbps/km2, respectively.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122568183","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532524
Rahmatia Safitri, Denny Setiawan, A. C. Situmorang
The development of the telecommunication world nowadays gets innovative, as seen from the development of mobile wireless communication generation from 1G to 4G and the development towards 5G. In the era of the industrial revolution 4.0, 5G technology is considered to be very important because it has advantages in terms of data rate and latency, the massive of IoT connectivity, spectrum efficiency, mobility, and so on. Spectrum limitation in the deployment of 5G currently becomes a challenge in Indonesia. One of the spectrums that potentially for the early 5G deployment in Indonesia is the 3.4-3.7 GHz band known as the Ext. C-Band. This band is currently being utilized by 5 satellites. Therefore the reallocation process and the allocation of compensation carried out towards the satellite operator by assuming that 200 MHz bandwidth is used for 5G from 3.4 GHz-3.6 GHz frequency and 100 MHz guard band from 3.6 GHz-3.7 GHz frequency. Compensation calculation was conducted by using GHz band approach to find out what the techno-economics value of this method is and whether there is a solution to the problem if the model is applied in Indonesia. The obtained result of the research was the income compensation is 2 times greater than the cost compensation. The spectrum license fee value of 3.5 GHz frequency per 100 MHz is IDR 3.098 trillion. In the case of the NPV value business of each compensation for 10 years shows a positive value. This scenario can be a good solution for satellites operator and regulator as well as cellular operator because it can help improve the financial health of operator in the deployment of 5G. So the 5G technology can be implemented in the Ext. C-Band spectrum.
{"title":"Techno-Economics Analysis of Ext. C-Band Frequency Reallocation in Indonesia","authors":"Rahmatia Safitri, Denny Setiawan, A. C. Situmorang","doi":"10.1109/IAICT52856.2021.9532524","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532524","url":null,"abstract":"The development of the telecommunication world nowadays gets innovative, as seen from the development of mobile wireless communication generation from 1G to 4G and the development towards 5G. In the era of the industrial revolution 4.0, 5G technology is considered to be very important because it has advantages in terms of data rate and latency, the massive of IoT connectivity, spectrum efficiency, mobility, and so on. Spectrum limitation in the deployment of 5G currently becomes a challenge in Indonesia. One of the spectrums that potentially for the early 5G deployment in Indonesia is the 3.4-3.7 GHz band known as the Ext. C-Band. This band is currently being utilized by 5 satellites. Therefore the reallocation process and the allocation of compensation carried out towards the satellite operator by assuming that 200 MHz bandwidth is used for 5G from 3.4 GHz-3.6 GHz frequency and 100 MHz guard band from 3.6 GHz-3.7 GHz frequency. Compensation calculation was conducted by using GHz band approach to find out what the techno-economics value of this method is and whether there is a solution to the problem if the model is applied in Indonesia. The obtained result of the research was the income compensation is 2 times greater than the cost compensation. The spectrum license fee value of 3.5 GHz frequency per 100 MHz is IDR 3.098 trillion. In the case of the NPV value business of each compensation for 10 years shows a positive value. This scenario can be a good solution for satellites operator and regulator as well as cellular operator because it can help improve the financial health of operator in the deployment of 5G. So the 5G technology can be implemented in the Ext. C-Band spectrum.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131165871","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532548
Hasmath Farhana Thariq Ahmed, Hafisoh Ahmad, S. K. Phang, Houda Harkat, Kulasekharan Narasingamurthi
Human sign language gesture recognition is an emerging application in the domain of Wi-Fi-based recognition. The recognition application utilizes the Channel State Information (CSI) of the Wi-Fi signal and captures the human gestures as signal amplitude and phase values. Most existing gesture recognition studies utilize only the amplitude values ignoring the phase information. Few works use both amplitude and phase information for recognition application. Besides, the existing studies adopt deep learning networks, especially Convolutional Neural Network (CNN), to improve recognition performance better. This motivates the present work to study the influence of using (i) amplitude values and (ii) amplitude and phase values together, using the Long Short-Term Memory (LSTM) network, as an alternate for CNN. Moreover, the proposed LSTM framework is fed with the CSI values without much pre-processing applied on it, except standardizing the data to make it more suitable for classification. This paper applies the proposed LSTM framework on a public sign language gesture dataset, SignFi with Adam and SGDM optimizer and analyses the performance with increasing hidden units. LSTM reported better recognition performance using Adam with 150 hidden units, and reported 99.8%, 99.5%, 99.4% and 78.0% for lab 276, home 276, lab+home 276 and lab 150 datasets, respectively.
人类手语手势识别是基于wi - fi识别领域的一项新兴应用。该识别应用程序利用Wi-Fi信号的信道状态信息(CSI)，以信号幅度和相位值捕获人类手势。现有的手势识别研究大多只利用振幅值，忽略了相位信息。很少有作品同时使用幅度和相位信息进行识别。此外，现有研究采用深度学习网络，特别是卷积神经网络(CNN)来更好地提高识别性能。这促使本研究使用长短期记忆(LSTM)网络作为CNN的替代品，研究(i)幅度值和(ii)幅度和相位值一起使用的影响。此外，所提出的LSTM框架除了对数据进行标准化处理以使其更适合分类外，没有进行过多的预处理。本文将提出的LSTM框架应用于公共手语手势数据集SignFi，并结合Adam和SGDM优化器，分析了增加隐藏单元的性能。LSTM报告了使用Adam的150个隐藏单元时更好的识别性能，在lab 276, home 276, lab+home 276和lab 150数据集上分别报告了99.8%，99.5%，99.4%和78.0%。
{"title":"Wi-Fi CSI Based Human Sign Language Recognition using LSTM Network","authors":"Hasmath Farhana Thariq Ahmed, Hafisoh Ahmad, S. K. Phang, Houda Harkat, Kulasekharan Narasingamurthi","doi":"10.1109/IAICT52856.2021.9532548","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532548","url":null,"abstract":"Human sign language gesture recognition is an emerging application in the domain of Wi-Fi-based recognition. The recognition application utilizes the Channel State Information (CSI) of the Wi-Fi signal and captures the human gestures as signal amplitude and phase values. Most existing gesture recognition studies utilize only the amplitude values ignoring the phase information. Few works use both amplitude and phase information for recognition application. Besides, the existing studies adopt deep learning networks, especially Convolutional Neural Network (CNN), to improve recognition performance better. This motivates the present work to study the influence of using (i) amplitude values and (ii) amplitude and phase values together, using the Long Short-Term Memory (LSTM) network, as an alternate for CNN. Moreover, the proposed LSTM framework is fed with the CSI values without much pre-processing applied on it, except standardizing the data to make it more suitable for classification. This paper applies the proposed LSTM framework on a public sign language gesture dataset, SignFi with Adam and SGDM optimizer and analyses the performance with increasing hidden units. LSTM reported better recognition performance using Adam with 150 hidden units, and reported 99.8%, 99.5%, 99.4% and 78.0% for lab 276, home 276, lab+home 276 and lab 150 datasets, respectively.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114251014","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532564
D. Suhartanto, T. Andrianto, N. Wibisono, Rivan Sutrisno
This paper aims to examine the roles of Virtual Reality (VR) system quality and VR content quality in affecting satisfaction and loyalty toward VR among Muslim tourists. The data were gathered from 282 Muslim tourists from various countries who visit tourist destinations in non-organization of Islamic Countries (OIC) countries via VR. The data were collected using Qualtrics Software and the M-Turk Survey application by generating self-administered questionnaires. Partial Least Square Modeling software was used to test the hypotheses. The results indicate that only the quality of VR content gives a direct impact on tourist loyalty. However, tourist satisfaction is influenced by the quality of both VR system and content. This study highlights the key role of VR system quality to enable delivering high content quality, providing satisfaction, and generating loyalty among Muslim tourists. It also deepens our knowledge of the role of the Muslim tourist experience in VR tourism and provides practitioners with insights to develop strategies in order to build and maintain Muslim tourist loyalty through VR.
{"title":"Virtual Reality in Halal Tourism: The Role of System Quality and Content Quality","authors":"D. Suhartanto, T. Andrianto, N. Wibisono, Rivan Sutrisno","doi":"10.1109/IAICT52856.2021.9532564","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532564","url":null,"abstract":"This paper aims to examine the roles of Virtual Reality (VR) system quality and VR content quality in affecting satisfaction and loyalty toward VR among Muslim tourists. The data were gathered from 282 Muslim tourists from various countries who visit tourist destinations in non-organization of Islamic Countries (OIC) countries via VR. The data were collected using Qualtrics Software and the M-Turk Survey application by generating self-administered questionnaires. Partial Least Square Modeling software was used to test the hypotheses. The results indicate that only the quality of VR content gives a direct impact on tourist loyalty. However, tourist satisfaction is influenced by the quality of both VR system and content. This study highlights the key role of VR system quality to enable delivering high content quality, providing satisfaction, and generating loyalty among Muslim tourists. It also deepens our knowledge of the role of the Muslim tourist experience in VR tourism and provides practitioners with insights to develop strategies in order to build and maintain Muslim tourist loyalty through VR.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125133159","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532515
Nabila Setya Utami, L. Novamizanti, Sofia Saidah, I. N. Apraz Ramatryana
Communication technology, multimedia, copyright protection, content data have gained attention in recent years. In addition, privacy and confidentiality are also major challenges in handling. A robust hybrid based on speeded-up robust features (SURF), discrete cosine transform (DCT), singular value decomposition or SVD, and chaotic (Arnold's Cat Map) scheme is proposed in this paper. The use of chaotic maps is for watermarking medical images, which can provide protection and security on medical images. In the watermark image, a method is applied that will increase the security of the watermark image, namely Arnold's Cat Maps. SVD method is used to decompose input data into three submatrices. To produce a watermarked image by combining the watermark image and the host image with the SURF-DCT-SVD method, the embedding stage is carried out. At the extraction stage, it will produce a watermark image from the watermarked image. Furthermore, various attacks were carried out against the proposed method. Experimental results show SVD can increase the robustness of DCT and SURF-based watermarking schemes. The proposed watermarking technique is resistant to JPEG compression attacks, noise addition, signal processing, and geometry attacks. In addition, the other state-of-the-art techniques are compared to the performance of the proposed method. Thus, the proposed watermarking scheme can protect ownership and medical records of medical images.
{"title":"SVD on a Robust Medical Image Watermarking based on SURF and DCT","authors":"Nabila Setya Utami, L. Novamizanti, Sofia Saidah, I. N. Apraz Ramatryana","doi":"10.1109/IAICT52856.2021.9532515","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532515","url":null,"abstract":"Communication technology, multimedia, copyright protection, content data have gained attention in recent years. In addition, privacy and confidentiality are also major challenges in handling. A robust hybrid based on speeded-up robust features (SURF), discrete cosine transform (DCT), singular value decomposition or SVD, and chaotic (Arnold's Cat Map) scheme is proposed in this paper. The use of chaotic maps is for watermarking medical images, which can provide protection and security on medical images. In the watermark image, a method is applied that will increase the security of the watermark image, namely Arnold's Cat Maps. SVD method is used to decompose input data into three submatrices. To produce a watermarked image by combining the watermark image and the host image with the SURF-DCT-SVD method, the embedding stage is carried out. At the extraction stage, it will produce a watermark image from the watermarked image. Furthermore, various attacks were carried out against the proposed method. Experimental results show SVD can increase the robustness of DCT and SURF-based watermarking schemes. The proposed watermarking technique is resistant to JPEG compression attacks, noise addition, signal processing, and geometry attacks. In addition, the other state-of-the-art techniques are compared to the performance of the proposed method. Thus, the proposed watermarking scheme can protect ownership and medical records of medical images.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126414291","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532518
Rodrigo Carvalho, F. Al-Tam, N. Correia
LoRaWAN has emerged as one of the most popular technologies in the LPWAN industry due to its low cost and straightforward management. Despite its relatively simple architecture, LoRaWAN is able to optimize energy, data rate, and time on-air by means of an adaptive data rate mechanism. In this paper, a reinforcement learning agent is designed to contrast with the central ADR component. This new agent operates seamlessly to all end nodes while still reacting quickly to changes. A comparative analysis between the classic ADR and the proposed RL-based ADR agent is done using discrete event simulation. Results show that the new ADR mechanism can determine the best configuration and that the proposed reward function fits the intended learning process.
{"title":"Q-Learning ADR Agent for LoRaWAN Optimization","authors":"Rodrigo Carvalho, F. Al-Tam, N. Correia","doi":"10.1109/IAICT52856.2021.9532518","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532518","url":null,"abstract":"LoRaWAN has emerged as one of the most popular technologies in the LPWAN industry due to its low cost and straightforward management. Despite its relatively simple architecture, LoRaWAN is able to optimize energy, data rate, and time on-air by means of an adaptive data rate mechanism. In this paper, a reinforcement learning agent is designed to contrast with the central ADR component. This new agent operates seamlessly to all end nodes while still reacting quickly to changes. A comparative analysis between the classic ADR and the proposed RL-based ADR agent is done using discrete event simulation. Results show that the new ADR mechanism can determine the best configuration and that the proposed reward function fits the intended learning process.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133693533","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532521
Pavitra Mohandas, Sudesh Kumar Santhosh Kumar, Sandeep Pai Kulyadi, M. J. Shankar Raman, Vasan V S, B. Venkataswami
One of the many methods for identifying malware is to disassemble the malware files and obtain the opcodes from them. Since malware have predominantly been found to contain specific opcode sequences in them, the presence of the same sequences in any incoming file or network content can be taken up as a possible malware identification scheme. Malware detection systems help us to understand more about ways on how malware attack a system and how it can be prevented. The proposed method analyses malware executable files with the help of opcode information by converting the incoming executable files to assembly language thereby extracting opcode information (opcode count) from the same. The opcode count is then converted into opcode frequency which is stored in a CSV file format. The CSV file is passed to various machine learning algorithms like Decision Tree Classifier, Random Forest Classifier and Naive Bayes Classifier. Random Forest Classifier produced the highest accuracy and hence the same model was used to predict whether an incoming file contains a potential malware or not.
{"title":"Detection of Malware using Machine Learning based on Operation Code Frequency","authors":"Pavitra Mohandas, Sudesh Kumar Santhosh Kumar, Sandeep Pai Kulyadi, M. J. Shankar Raman, Vasan V S, B. Venkataswami","doi":"10.1109/IAICT52856.2021.9532521","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532521","url":null,"abstract":"One of the many methods for identifying malware is to disassemble the malware files and obtain the opcodes from them. Since malware have predominantly been found to contain specific opcode sequences in them, the presence of the same sequences in any incoming file or network content can be taken up as a possible malware identification scheme. Malware detection systems help us to understand more about ways on how malware attack a system and how it can be prevented. The proposed method analyses malware executable files with the help of opcode information by converting the incoming executable files to assembly language thereby extracting opcode information (opcode count) from the same. The opcode count is then converted into opcode frequency which is stored in a CSV file format. The CSV file is passed to various machine learning algorithms like Decision Tree Classifier, Random Forest Classifier and Naive Bayes Classifier. Random Forest Classifier produced the highest accuracy and hence the same model was used to predict whether an incoming file contains a potential malware or not.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128687360","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532569
Charbel El Hachem, Gilles Perrot, Loïc Painvin, Jean-Baptiste Ernst-Desmulier, R. Couturier
Welding seam inspection is key process in the automotive industry and should guarantee the quality required by the client. Visual inspection is achieved by the operator who checks each part manually, making the reliability highly improvable. That's why automating the visual inspection is needed in today's production process. Collecting data from inside the plant may not provide a balanced number of images between good welding seams and bad welding seams. In this article, we will compare a standard deep learning algorithm applied on raw data with data augmentation approaches. Our target is to reach an accuracy of 97 % on the defected reference parts. This target is reached on some welds, while it remains a challenge on other welds.
{"title":"Welding Seam Classification in the Automotive Industry using Deep Learning Algorithms","authors":"Charbel El Hachem, Gilles Perrot, Loïc Painvin, Jean-Baptiste Ernst-Desmulier, R. Couturier","doi":"10.1109/IAICT52856.2021.9532569","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532569","url":null,"abstract":"Welding seam inspection is key process in the automotive industry and should guarantee the quality required by the client. Visual inspection is achieved by the operator who checks each part manually, making the reliability highly improvable. That's why automating the visual inspection is needed in today's production process. Collecting data from inside the plant may not provide a balanced number of images between good welding seams and bad welding seams. In this article, we will compare a standard deep learning algorithm applied on raw data with data augmentation approaches. Our target is to reach an accuracy of 97 % on the defected reference parts. This target is reached on some welds, while it remains a challenge on other welds.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127295573","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532514
Johnsymol Joy, Jinane Mounsef
Automated material takeoff (MTO) can significantly impact construction productivity of the projects control team. The takeoff work is often a repetitive and mundane routine since it involves a manual counting of a variety of items sprawled in all kinds of locations over a drawing layout. For larger projects, such takeoffs can be time-consuming and the results can be prone to counting errors. In order to automate the task, we propose the Smart Layout Analyzer (SLA) that uses computer vision capabilities to automatically detect and recognize the items in an electrical engineering drawing layout with the aim of producing an overall item count. The software trains a Faster R-CNN with a ResNet50 convolution neural network (CNN) on the different items and their respective labels in the layout legend to subsequently localize and count the items in the drawing layout. The proposed model is different from other commercial programs that automate the takeoff making during the design process, as it can efficiently learn to count the different elements by being directly trained on the drawing layout legend.
{"title":"Automation of Material Takeoff using Computer Vision","authors":"Johnsymol Joy, Jinane Mounsef","doi":"10.1109/IAICT52856.2021.9532514","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532514","url":null,"abstract":"Automated material takeoff (MTO) can significantly impact construction productivity of the projects control team. The takeoff work is often a repetitive and mundane routine since it involves a manual counting of a variety of items sprawled in all kinds of locations over a drawing layout. For larger projects, such takeoffs can be time-consuming and the results can be prone to counting errors. In order to automate the task, we propose the Smart Layout Analyzer (SLA) that uses computer vision capabilities to automatically detect and recognize the items in an electrical engineering drawing layout with the aim of producing an overall item count. The software trains a Faster R-CNN with a ResNet50 convolution neural network (CNN) on the different items and their respective labels in the layout legend to subsequently localize and count the items in the drawing layout. The proposed model is different from other commercial programs that automate the takeoff making during the design process, as it can efficiently learn to count the different elements by being directly trained on the drawing layout legend.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124253180","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 : 2021-07-27DOI: 10.1109/IAICT52856.2021.9532550
Eza Yolanda Fitria, M. A. Murti, C. Setianingsih
Hydroponics is the future of agricultural cultivation because it uses water as its growing medium. Therefore, several conditions need to be considered, namely the pH value of the water, the value of the nutrient solution, and the circulating water pump. Manually controlling water and environmental conditions will consume a lot of time and energy and is susceptible to human measurement errors. So it is necessary to design an integrated control system on hydroponic plants, including a water pH control system and a nutrient solution control system. This system uses several components, including a pH sensor, EC (Electrical Conductivity) sensor, Mega 2560 Pro as a microcontroller, a 4V 5 channel relay, and a peristaltic pump as an actuator that will move to remove pH-up, pH-down, and AB-mix nutrients. This system is also based on the Internet of Things (IoT), where data obtained from pH sensors and EC sensors will be processed by a microcontroller and then sent to the IoT Antares platform via the available communication modules. Data is stored on Antares's cloud server to be displayed in a User Interface to the user. Based on the test results, the monitoring and integrated control systems for hydroponic plants have been successfully created and run well. The accuracy of the pH sensor is 99.99%, and the EC sensor is 99.93%. From the response time characteristics of the pH control system, the rise time is 2.5 minutes, the peak time is 5 minutes, the maximum overshoot is 131.53%, the settling time is 16 minutes, and the steady-state error value is 109.90%. Whereas the characteristic response time of the nutrient solution control system is obtained a rise time of 1.2 s, a peak time of 2 s, a maximum overshoot of 159.55%, a settling time of 14 s, and a steady-state error value amounted to 1.29%.
{"title":"Design of Integrated Control System Based On IoT With Context Aware Method In Hydroponic Plants","authors":"Eza Yolanda Fitria, M. A. Murti, C. Setianingsih","doi":"10.1109/IAICT52856.2021.9532550","DOIUrl":"https://doi.org/10.1109/IAICT52856.2021.9532550","url":null,"abstract":"Hydroponics is the future of agricultural cultivation because it uses water as its growing medium. Therefore, several conditions need to be considered, namely the pH value of the water, the value of the nutrient solution, and the circulating water pump. Manually controlling water and environmental conditions will consume a lot of time and energy and is susceptible to human measurement errors. So it is necessary to design an integrated control system on hydroponic plants, including a water pH control system and a nutrient solution control system. This system uses several components, including a pH sensor, EC (Electrical Conductivity) sensor, Mega 2560 Pro as a microcontroller, a 4V 5 channel relay, and a peristaltic pump as an actuator that will move to remove pH-up, pH-down, and AB-mix nutrients. This system is also based on the Internet of Things (IoT), where data obtained from pH sensors and EC sensors will be processed by a microcontroller and then sent to the IoT Antares platform via the available communication modules. Data is stored on Antares's cloud server to be displayed in a User Interface to the user. Based on the test results, the monitoring and integrated control systems for hydroponic plants have been successfully created and run well. The accuracy of the pH sensor is 99.99%, and the EC sensor is 99.93%. From the response time characteristics of the pH control system, the rise time is 2.5 minutes, the peak time is 5 minutes, the maximum overshoot is 131.53%, the settling time is 16 minutes, and the steady-state error value is 109.90%. Whereas the characteristic response time of the nutrient solution control system is obtained a rise time of 1.2 s, a peak time of 2 s, a maximum overshoot of 159.55%, a settling time of 14 s, and a steady-state error value amounted to 1.29%.","PeriodicalId":416542,"journal":{"name":"2021 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115821020","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：